[WIP][RISCV][InsertVSETVLI] Allow promotion of TA to TU and MA to MU

[reames]

Summary

This is not a final patch - I need to properly plumb through MRI among other things. I'm posting for discussion. What do we think of the idea of eliminating vsetvli transitions by expanding the region which is mu and/or tu? I think this is generally reasonable, but are there any cases we need to be careful about?

[reames]

llvm/test/CodeGen/RISCV/fold-vector-cmp.ll

16

FYI, D135794 is somewhat of an alternate patch to this test change. If we land that, this becomes less impactful, and vice versa.

[craig.topper]

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-bitcast.ll

527

So now we can't execute this instruction until the previous writer of vmv.v.x completes? At least on a renamed microarchitecture.

[reames]

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-bitcast.ll

527

For the instruction "vmv.v.x v8, a1", there's now a false dependence on the prior value of v8. Previously, the hardware could ignore this dependence as the input value could be ignored, and the high lanes unconditionally set to -1. After the change to TU, the hardware must wait for the dependency to be resolved.

[craig.topper]

llvm/test/CodeGen/RISCV/rvv/vmacc.ll

1572

If this were in a loop and a load misses the cache, the later iterations couldn't speculatively start loading until the earlier cache miss is resolved. That doesn't seem ideal.

[reames]

llvm/test/CodeGen/RISCV/rvv/vmacc.ll

1572

Depends on how the hardware handles this, and I don't really know what's realistic. In theory, the load can be issued, and only the merge is bottlenecked by the false dependency . Not sure if that's a realistic hardware expectation or not.

Note that the vmacc has the same loop carried false dependency issue in either case. So we're really just talking about the issue to overlap the loads.

But yes, unless the hardware is pretty uniformly smart about this - as sketched above - this would seem to be a fatal flaw for this patch.

[craig.topper]

llvm/test/CodeGen/RISCV/rvv/vmacc.ll

1572

I guess on most of the loop iterations of the loop you would be using vlmax so there isn't a tail. So maybe only the last iteration would be affected.

[reames]

Chatted w/ Craig about this offline. As pointed out in review comments, there are some cases where switching from agnostic to undisturbed can have significant runtime cost - mostly by preventing otherwise legal speculative reordering. We could maybe refine this into a patch which only exploits the possible state conversion for cheap instructions, but that's a bunch of infrastructure we don't have right now. At the moment, we don't have a strong motivation to push this. In some quick glancing at vector code, we're down to a small handful of tu or mu cases, and some extra toggles probably aren't worth aggressively optimizing. We'll revisit when we have motivating examples.

llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp

 static bool isMaskRegOp(const MachineInstr &MI) {
   if (!RISCVII::hasSEWOp(MI.getDesc().TSFlags))
     return false;
   const unsigned Log2SEW = MI.getOperand(getSEWOpNum(MI)).getImm();
   // A Log2SEW of 0 is an operation on mask registers only.
   return Log2SEW == 0;
 }
 
+/// Returns pair of {is-tail-agnostic, is-mask-agnostic).
+std::pair<bool, bool> getPolicyFlags(const MachineInstr &MI,
+                                     const MachineRegisterInfo *MRI = nullptr) {
+  const unsigned TSFlags = MI.getDesc().TSFlags;
+  bool TailAgnostic, MaskAgnostic;
+  unsigned UseOpIdx;
+  if (MI.isRegTiedToUseOperand(0, &UseOpIdx)) {
+    // Start with undisturbed.
+    TailAgnostic = false;
+    MaskAgnostic = false;
+
+    // If there is a policy operand, use it.
+    if (RISCVII::hasVecPolicyOp(TSFlags)) {
+      const MachineOperand &Op = MI.getOperand(MI.getNumExplicitOperands() - 1);
+      uint64_t Policy = Op.getImm();
+      assert(Policy <= (RISCVII::TAIL_AGNOSTIC | RISCVII::MASK_AGNOSTIC) &&
+             "Invalid Policy Value");
+      TailAgnostic = Policy & RISCVII::TAIL_AGNOSTIC;
+      MaskAgnostic = Policy & RISCVII::MASK_AGNOSTIC;
+    }
+
+    // If the tied operand is an IMPLICIT_DEF we can use TailAgnostic and
+    // MaskAgnostic.
+    const MachineOperand &UseMO = MI.getOperand(UseOpIdx);
+    if (MRI) {
+      MachineInstr *UseMI = MRI->getVRegDef(UseMO.getReg());
+      if (UseMI && UseMI->isImplicitDef()) {
+        TailAgnostic = true;
+        MaskAgnostic = true;
+      }
+    }
+    // Some pseudo instructions force a tail agnostic policy despite having a
+    // tied def.
+    if (RISCVII::doesForceTailAgnostic(TSFlags))
+      TailAgnostic = true;
+
+    if (!RISCVII::usesMaskPolicy(TSFlags))
+      MaskAgnostic = true;
+  } else {
+    // If there is no tied operand,, there shouldn't be a policy operand.
+    assert(!RISCVII::hasVecPolicyOp(TSFlags) && "Unexpected policy operand");
+    // No tied operand use agnostic policies.
+    TailAgnostic = true;
+    MaskAgnostic = true;
+  }
+
+  return {TailAgnostic, MaskAgnostic};
+}
+
 /// Which subfields of VL or VTYPE have values we need to preserve?
 struct DemandedFields {
   bool VL = false;
   bool SEW = false;
   bool LMUL = false;
   bool SEWLMULRatio = false;
   bool TailPolicy = false;
   bool MaskPolicy = false;
static DemandedFields getDemanded(const MachineInstr &MI) {
   if (RISCVII::hasSEWOp(TSFlags)) {
     Res.demandVTYPE();
     if (RISCVII::hasVLOp(TSFlags))
       Res.VL = true;
 
     // Behavior is independent of mask policy.
     if (!RISCVII::usesMaskPolicy(TSFlags))
       Res.MaskPolicy = false;
+
+    auto [TA, MA] = getPolicyFlags(MI);
+    if (TA)
+      Res.TailPolicy = false;
+    if (MA)
+      Res.MaskPolicy = false;
   }
 
   // Loads and stores with implicit EEW do not demand SEW or LMUL directly.
   // They instead demand the ratio of the two which is used in computing
   // EMUL, but which allows us the flexibility to change SEW and LMUL
   // provided we don't change the ratio.
   // Note: We assume that the instructions initial SEW is the EEW encoded
   // in the opcode.  This is asserted when constructing the VSETVLIInfo.

 
 INITIALIZE_PASS(RISCVInsertVSETVLI, DEBUG_TYPE, RISCV_INSERT_VSETVLI_NAME,
                 false, false)
 
 static VSETVLIInfo computeInfoForInstr(const MachineInstr &MI, uint64_t TSFlags,
                                        const MachineRegisterInfo *MRI) {
   VSETVLIInfo InstrInfo;
 
-  bool TailAgnostic, MaskAgnostic;
-  unsigned UseOpIdx;
-  if (MI.isRegTiedToUseOperand(0, &UseOpIdx)) {
-    // Start with undisturbed.
-    TailAgnostic = false;
-    MaskAgnostic = false;
-
-    // If there is a policy operand, use it.
-    if (RISCVII::hasVecPolicyOp(TSFlags)) {
-      const MachineOperand &Op = MI.getOperand(MI.getNumExplicitOperands() - 1);
-      uint64_t Policy = Op.getImm();
-      assert(Policy <= (RISCVII::TAIL_AGNOSTIC | RISCVII::MASK_AGNOSTIC) &&
-             "Invalid Policy Value");
-      TailAgnostic = Policy & RISCVII::TAIL_AGNOSTIC;
-      MaskAgnostic = Policy & RISCVII::MASK_AGNOSTIC;
-    }
-
-    // If the tied operand is an IMPLICIT_DEF we can use TailAgnostic and
-    // MaskAgnostic.
-    const MachineOperand &UseMO = MI.getOperand(UseOpIdx);
-    MachineInstr *UseMI = MRI->getVRegDef(UseMO.getReg());
-    if (UseMI && UseMI->isImplicitDef()) {
-      TailAgnostic = true;
-      MaskAgnostic = true;
-    }
-    // Some pseudo instructions force a tail agnostic policy despite having a
-    // tied def.
-    if (RISCVII::doesForceTailAgnostic(TSFlags))
-      TailAgnostic = true;
-
-    if (!RISCVII::usesMaskPolicy(TSFlags))
-      MaskAgnostic = true;
-  } else {
-    // If there is no tied operand,, there shouldn't be a policy operand.
-    assert(!RISCVII::hasVecPolicyOp(TSFlags) && "Unexpected policy operand");
-    // No tied operand use agnostic policies.
-    TailAgnostic = true;
-    MaskAgnostic = true;
-  }
-
+  auto [TailAgnostic, MaskAgnostic] = getPolicyFlags(MI, MRI);
   RISCVII::VLMUL VLMul = RISCVII::getLMul(TSFlags);
 
   unsigned Log2SEW = MI.getOperand(getSEWOpNum(MI)).getImm();
   // A Log2SEW of 0 is an operation on mask registers only.
   unsigned SEW = Log2SEW ? 1 << Log2SEW : 8;
   assert(RISCVVType::isValidSEW(SEW) && "Unexpected SEW");
 
   if (RISCVII::hasVLOp(TSFlags)) {

llvm/test/CodeGen/RISCV/fold-vector-cmp.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -start-after codegenprepare -mtriple=riscv64 -mattr=-v -o - %s | FileCheck --check-prefix=CHECK-NOV %s
 ; RUN: llc -start-after codegenprepare -mtriple=riscv64 -mattr=+v -o - %s | FileCheck --check-prefix=CHECK-V %s
 
 ; Reproducer for https://github.com/llvm/llvm-project/issues/55168.
 ; We should always return 1 (and not -1).
 define i32 @test(i32 %call.i) {
 ; CHECK-NOV-LABEL: test:
 ; CHECK-NOV:       # %bb.0:
 ; CHECK-NOV-NEXT:    li a0, 1
 ; CHECK-NOV-NEXT:    ret
 ;
 ; CHECK-V-LABEL: test:
 ; CHECK-V:       # %bb.0:
 ; CHECK-V-NEXT:    lui a1, 524288
-; CHECK-V-NEXT:    vsetivli zero, 2, e32, mf2, ta, ma
+; CHECK-V-NEXT:    vsetivli zero, 2, e32, mf2, tu, ma
 ; CHECK-V-NEXT:    vmv.v.x v8, a1
-; CHECK-V-NEXT:    vsetvli zero, zero, e32, mf2, tu, ma
 ; CHECK-V-NEXT:    vmv.s.x v8, a0
 ; CHECK-V-NEXT:    addiw a0, a1, 2
-; CHECK-V-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
 ; CHECK-V-NEXT:    vmslt.vx v0, v8, a0
 ; CHECK-V-NEXT:    vmv.v.i v8, 0
 ; CHECK-V-NEXT:    vmerge.vim v8, v8, 1, v0
 ; CHECK-V-NEXT:    vsetivli zero, 1, e32, mf2, ta, ma
 ; CHECK-V-NEXT:    vslidedown.vi v8, v8, 1
 ; CHECK-V-NEXT:    vmv.x.s a0, v8
 ; CHECK-V-NEXT:    ret
   %t2 = insertelement <2 x i32> <i32 poison, i32 -2147483648>, i32 %call.i, i64 0
   %t3 = icmp slt <2 x i32> %t2, <i32 -2147483646, i32 -2147483646>
   %t4 = zext <2 x i1> %t3 to <2 x i32>
   %t6 = extractelement <2 x i32> %t4, i64 1
   ret i32 %t6
 }

llvm/test/CodeGen/RISCV/fpclamptosat_vec.ll

 ; CHECK-V-NEXT:    vslideup.vi v10, v8, 2
 ; CHECK-V-NEXT:    addi a0, sp, 8
 ; CHECK-V-NEXT:    vsetivli zero, 1, e64, m1, ta, ma
 ; CHECK-V-NEXT:    vle64.v v8, (a0)
 ; CHECK-V-NEXT:    vsetivli zero, 4, e64, m2, tu, ma
 ; CHECK-V-NEXT:    vslideup.vi v10, v8, 3
 ; CHECK-V-NEXT:    lui a0, 524288
 ; CHECK-V-NEXT:    addiw a1, a0, -1
-; CHECK-V-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
 ; CHECK-V-NEXT:    vmin.vx v8, v10, a1
 ; CHECK-V-NEXT:    vmax.vx v10, v8, a0
 ; CHECK-V-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-V-NEXT:    vnsrl.wi v8, v10, 0
 ; CHECK-V-NEXT:    ld ra, 56(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s0, 48(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s1, 40(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s2, 32(sp) # 8-byte Folded Reload

 ; CHECK-V-NEXT:    vslideup.vi v10, v8, 2
 ; CHECK-V-NEXT:    addi a0, sp, 8
 ; CHECK-V-NEXT:    vsetivli zero, 1, e64, m1, ta, ma
 ; CHECK-V-NEXT:    vle64.v v8, (a0)
 ; CHECK-V-NEXT:    vsetivli zero, 4, e64, m2, tu, ma
 ; CHECK-V-NEXT:    vslideup.vi v10, v8, 3
 ; CHECK-V-NEXT:    li a0, -1
 ; CHECK-V-NEXT:    srli a0, a0, 32
-; CHECK-V-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
 ; CHECK-V-NEXT:    vminu.vx v10, v10, a0
 ; CHECK-V-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-V-NEXT:    vnsrl.wi v8, v10, 0
 ; CHECK-V-NEXT:    ld ra, 56(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s0, 48(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s1, 40(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s2, 32(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    addi sp, sp, 64

 ; CHECK-V-NEXT:    vslideup.vi v10, v8, 2
 ; CHECK-V-NEXT:    addi a0, sp, 8
 ; CHECK-V-NEXT:    vsetivli zero, 1, e64, m1, ta, ma
 ; CHECK-V-NEXT:    vle64.v v8, (a0)
 ; CHECK-V-NEXT:    vsetivli zero, 4, e64, m2, tu, ma
 ; CHECK-V-NEXT:    vslideup.vi v10, v8, 3
 ; CHECK-V-NEXT:    li a0, -1
 ; CHECK-V-NEXT:    srli a0, a0, 32
-; CHECK-V-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
 ; CHECK-V-NEXT:    vmin.vx v8, v10, a0
 ; CHECK-V-NEXT:    vmax.vx v10, v8, zero
 ; CHECK-V-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-V-NEXT:    vnsrl.wi v8, v10, 0
 ; CHECK-V-NEXT:    ld ra, 56(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s0, 48(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s1, 40(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s2, 32(sp) # 8-byte Folded Reload

 ; CHECK-V-NEXT:    vslideup.vi v8, v10, 6
 ; CHECK-V-NEXT:    addi a0, sp, 4
 ; CHECK-V-NEXT:    vsetivli zero, 1, e32, mf2, ta, ma
 ; CHECK-V-NEXT:    vle32.v v10, (a0)
 ; CHECK-V-NEXT:    vsetivli zero, 8, e32, m2, tu, ma
 ; CHECK-V-NEXT:    vslideup.vi v8, v10, 7
 ; CHECK-V-NEXT:    lui a0, 8
 ; CHECK-V-NEXT:    addiw a0, a0, -1
-; CHECK-V-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
 ; CHECK-V-NEXT:    vmin.vx v8, v8, a0
 ; CHECK-V-NEXT:    lui a0, 1048568
 ; CHECK-V-NEXT:    vmax.vx v10, v8, a0
 ; CHECK-V-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
 ; CHECK-V-NEXT:    vnsrl.wi v8, v10, 0
 ; CHECK-V-NEXT:    ld ra, 88(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s0, 80(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s1, 72(sp) # 8-byte Folded Reload

 ; CHECK-V-NEXT:    vslideup.vi v8, v10, 6
 ; CHECK-V-NEXT:    addi a0, sp, 4
 ; CHECK-V-NEXT:    vsetivli zero, 1, e32, mf2, ta, ma
 ; CHECK-V-NEXT:    vle32.v v10, (a0)
 ; CHECK-V-NEXT:    vsetivli zero, 8, e32, m2, tu, ma
 ; CHECK-V-NEXT:    vslideup.vi v8, v10, 7
 ; CHECK-V-NEXT:    lui a0, 16
 ; CHECK-V-NEXT:    addiw a0, a0, -1
-; CHECK-V-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
 ; CHECK-V-NEXT:    vminu.vx v10, v8, a0
 ; CHECK-V-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
 ; CHECK-V-NEXT:    vnsrl.wi v8, v10, 0
 ; CHECK-V-NEXT:    ld ra, 88(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s0, 80(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s1, 72(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s2, 64(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s3, 56(sp) # 8-byte Folded Reload

 ; CHECK-V-NEXT:    vslideup.vi v8, v10, 6
 ; CHECK-V-NEXT:    addi a0, sp, 4
 ; CHECK-V-NEXT:    vsetivli zero, 1, e32, mf2, ta, ma
 ; CHECK-V-NEXT:    vle32.v v10, (a0)
 ; CHECK-V-NEXT:    vsetivli zero, 8, e32, m2, tu, ma
 ; CHECK-V-NEXT:    vslideup.vi v8, v10, 7
 ; CHECK-V-NEXT:    lui a0, 16
 ; CHECK-V-NEXT:    addiw a0, a0, -1
-; CHECK-V-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
 ; CHECK-V-NEXT:    vmin.vx v8, v8, a0
 ; CHECK-V-NEXT:    vmax.vx v10, v8, zero
 ; CHECK-V-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
 ; CHECK-V-NEXT:    vnsrl.wi v8, v10, 0
 ; CHECK-V-NEXT:    ld ra, 88(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s0, 80(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s1, 72(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s2, 64(sp) # 8-byte Folded Reload

 ; CHECK-V-NEXT:    vslideup.vi v10, v8, 2
 ; CHECK-V-NEXT:    addi a0, sp, 8
 ; CHECK-V-NEXT:    vsetivli zero, 1, e64, m1, ta, ma
 ; CHECK-V-NEXT:    vle64.v v8, (a0)
 ; CHECK-V-NEXT:    vsetivli zero, 4, e64, m2, tu, ma
 ; CHECK-V-NEXT:    vslideup.vi v10, v8, 3
 ; CHECK-V-NEXT:    lui a0, 524288
 ; CHECK-V-NEXT:    addiw a1, a0, -1
-; CHECK-V-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
 ; CHECK-V-NEXT:    vmin.vx v8, v10, a1
 ; CHECK-V-NEXT:    vmax.vx v10, v8, a0
 ; CHECK-V-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-V-NEXT:    vnsrl.wi v8, v10, 0
 ; CHECK-V-NEXT:    ld ra, 56(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s0, 48(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s1, 40(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s2, 32(sp) # 8-byte Folded Reload

 ; CHECK-V-NEXT:    vslideup.vi v10, v8, 2
 ; CHECK-V-NEXT:    addi a0, sp, 8
 ; CHECK-V-NEXT:    vsetivli zero, 1, e64, m1, ta, ma
 ; CHECK-V-NEXT:    vle64.v v8, (a0)
 ; CHECK-V-NEXT:    vsetivli zero, 4, e64, m2, tu, ma
 ; CHECK-V-NEXT:    vslideup.vi v10, v8, 3
 ; CHECK-V-NEXT:    li a0, -1
 ; CHECK-V-NEXT:    srli a0, a0, 32
-; CHECK-V-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
 ; CHECK-V-NEXT:    vminu.vx v10, v10, a0
 ; CHECK-V-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-V-NEXT:    vnsrl.wi v8, v10, 0
 ; CHECK-V-NEXT:    ld ra, 56(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s0, 48(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s1, 40(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s2, 32(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    addi sp, sp, 64

 ; CHECK-V-NEXT:    vslideup.vi v10, v8, 2
 ; CHECK-V-NEXT:    addi a0, sp, 8
 ; CHECK-V-NEXT:    vsetivli zero, 1, e64, m1, ta, ma
 ; CHECK-V-NEXT:    vle64.v v8, (a0)
 ; CHECK-V-NEXT:    vsetivli zero, 4, e64, m2, tu, ma
 ; CHECK-V-NEXT:    vslideup.vi v10, v8, 3
 ; CHECK-V-NEXT:    li a0, -1
 ; CHECK-V-NEXT:    srli a0, a0, 32
-; CHECK-V-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
 ; CHECK-V-NEXT:    vmin.vx v8, v10, a0
 ; CHECK-V-NEXT:    vmax.vx v10, v8, zero
 ; CHECK-V-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-V-NEXT:    vnsrl.wi v8, v10, 0
 ; CHECK-V-NEXT:    ld ra, 56(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s0, 48(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s1, 40(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s2, 32(sp) # 8-byte Folded Reload

 ; CHECK-V-NEXT:    vslideup.vi v8, v10, 6
 ; CHECK-V-NEXT:    addi a0, sp, 4
 ; CHECK-V-NEXT:    vsetivli zero, 1, e32, mf2, ta, ma
 ; CHECK-V-NEXT:    vle32.v v10, (a0)
 ; CHECK-V-NEXT:    vsetivli zero, 8, e32, m2, tu, ma
 ; CHECK-V-NEXT:    vslideup.vi v8, v10, 7
 ; CHECK-V-NEXT:    lui a0, 8
 ; CHECK-V-NEXT:    addiw a0, a0, -1
-; CHECK-V-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
 ; CHECK-V-NEXT:    vmin.vx v8, v8, a0
 ; CHECK-V-NEXT:    lui a0, 1048568
 ; CHECK-V-NEXT:    vmax.vx v10, v8, a0
 ; CHECK-V-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
 ; CHECK-V-NEXT:    vnsrl.wi v8, v10, 0
 ; CHECK-V-NEXT:    ld ra, 88(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s0, 80(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s1, 72(sp) # 8-byte Folded Reload

 ; CHECK-V-NEXT:    vslideup.vi v8, v10, 6
 ; CHECK-V-NEXT:    addi a0, sp, 4
 ; CHECK-V-NEXT:    vsetivli zero, 1, e32, mf2, ta, ma
 ; CHECK-V-NEXT:    vle32.v v10, (a0)
 ; CHECK-V-NEXT:    vsetivli zero, 8, e32, m2, tu, ma
 ; CHECK-V-NEXT:    vslideup.vi v8, v10, 7
 ; CHECK-V-NEXT:    lui a0, 16
 ; CHECK-V-NEXT:    addiw a0, a0, -1
-; CHECK-V-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
 ; CHECK-V-NEXT:    vminu.vx v10, v8, a0
 ; CHECK-V-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
 ; CHECK-V-NEXT:    vnsrl.wi v8, v10, 0
 ; CHECK-V-NEXT:    ld ra, 88(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s0, 80(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s1, 72(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s2, 64(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s3, 56(sp) # 8-byte Folded Reload

 ; CHECK-V-NEXT:    vslideup.vi v8, v10, 6
 ; CHECK-V-NEXT:    addi a0, sp, 4
 ; CHECK-V-NEXT:    vsetivli zero, 1, e32, mf2, ta, ma
 ; CHECK-V-NEXT:    vle32.v v10, (a0)
 ; CHECK-V-NEXT:    vsetivli zero, 8, e32, m2, tu, ma
 ; CHECK-V-NEXT:    vslideup.vi v8, v10, 7
 ; CHECK-V-NEXT:    lui a0, 16
 ; CHECK-V-NEXT:    addiw a0, a0, -1
-; CHECK-V-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
 ; CHECK-V-NEXT:    vmin.vx v8, v8, a0
 ; CHECK-V-NEXT:    vmax.vx v10, v8, zero
 ; CHECK-V-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
 ; CHECK-V-NEXT:    vnsrl.wi v8, v10, 0
 ; CHECK-V-NEXT:    ld ra, 88(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s0, 80(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s1, 72(sp) # 8-byte Folded Reload
 ; CHECK-V-NEXT:    ld s2, 64(sp) # 8-byte Folded Reload

llvm/test/CodeGen/RISCV/rvv/ceil-vp.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=ilp32d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=lp64d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 
 declare <vscale x 1 x half> @llvm.vp.ceil.nxv1f16(<vscale x 1 x half>, <vscale x 1 x i1>, i32)
 
 define <vscale x 1 x half> @vp_ceil_vv_nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv1f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI0_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI0_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 1 x half> @llvm.vp.ceil.nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x half> %v
 }
 
 define <vscale x 1 x half> @vp_ceil_vv_nxv1f16_unmasked(<vscale x 1 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv1f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI1_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI1_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
   %v = call <vscale x 1 x half> @llvm.vp.ceil.nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x half> %v
 }
 
 declare <vscale x 2 x half> @llvm.vp.ceil.nxv2f16(<vscale x 2 x half>, <vscale x 2 x i1>, i32)
 
 define <vscale x 2 x half> @vp_ceil_vv_nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv2f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI2_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI2_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 2 x half> @llvm.vp.ceil.nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x half> %v
 }
 
 define <vscale x 2 x half> @vp_ceil_vv_nxv2f16_unmasked(<vscale x 2 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv2f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI3_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI3_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
   %v = call <vscale x 2 x half> @llvm.vp.ceil.nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x half> %v
 }
 
 declare <vscale x 4 x half> @llvm.vp.ceil.nxv4f16(<vscale x 4 x half>, <vscale x 4 x i1>, i32)
 
 define <vscale x 4 x half> @vp_ceil_vv_nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv4f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI4_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI4_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 4 x half> @llvm.vp.ceil.nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x half> %v
 }
 
 define <vscale x 4 x half> @vp_ceil_vv_nxv4f16_unmasked(<vscale x 4 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv4f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI5_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI5_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
   %v = call <vscale x 4 x half> @llvm.vp.ceil.nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x half> %v
 }
 
 declare <vscale x 8 x half> @llvm.vp.ceil.nxv8f16(<vscale x 8 x half>, <vscale x 8 x i1>, i32)
 
 define <vscale x 8 x half> @vp_ceil_vv_nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv8f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI6_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI6_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 8 x half> @llvm.vp.ceil.nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x half> %v
 }
 
 define <vscale x 8 x half> @vp_ceil_vv_nxv8f16_unmasked(<vscale x 8 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv8f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI7_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI7_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
   %v = call <vscale x 8 x half> @llvm.vp.ceil.nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x half> %v
 }
 
 declare <vscale x 16 x half> @llvm.vp.ceil.nxv16f16(<vscale x 16 x half>, <vscale x 16 x i1>, i32)
 
 define <vscale x 16 x half> @vp_ceil_vv_nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv16f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI8_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI8_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 16 x half> @llvm.vp.ceil.nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x half> %v
 }
 
 define <vscale x 16 x half> @vp_ceil_vv_nxv16f16_unmasked(<vscale x 16 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv16f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI9_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI9_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
   %v = call <vscale x 16 x half> @llvm.vp.ceil.nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x half> %v
 }
 
 declare <vscale x 32 x half> @llvm.vp.ceil.nxv32f16(<vscale x 32 x half>, <vscale x 32 x i1>, i32)
 
 define <vscale x 32 x half> @vp_ceil_vv_nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv32f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI10_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI10_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 32 x half> @llvm.vp.ceil.nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x i1> %m, i32 %evl)
   ret <vscale x 32 x half> %v
 }
 
 define <vscale x 32 x half> @vp_ceil_vv_nxv32f16_unmasked(<vscale x 32 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv32f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI11_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI11_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 32 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 32 x i1> %head, <vscale x 32 x i1> poison, <vscale x 32 x i32> zeroinitializer
   %v = call <vscale x 32 x half> @llvm.vp.ceil.nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x i1> %m, i32 %evl)
   ret <vscale x 32 x half> %v
 }
 
 declare <vscale x 1 x float> @llvm.vp.ceil.nxv1f32(<vscale x 1 x float>, <vscale x 1 x i1>, i32)
 
 define <vscale x 1 x float> @vp_ceil_vv_nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv1f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI12_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI12_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 1 x float> @llvm.vp.ceil.nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x float> %v
 }
 
 define <vscale x 1 x float> @vp_ceil_vv_nxv1f32_unmasked(<vscale x 1 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv1f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI13_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI13_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
   %v = call <vscale x 1 x float> @llvm.vp.ceil.nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x float> %v
 }
 
 declare <vscale x 2 x float> @llvm.vp.ceil.nxv2f32(<vscale x 2 x float>, <vscale x 2 x i1>, i32)
 
 define <vscale x 2 x float> @vp_ceil_vv_nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv2f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI14_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI14_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 2 x float> @llvm.vp.ceil.nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x float> %v
 }
 
 define <vscale x 2 x float> @vp_ceil_vv_nxv2f32_unmasked(<vscale x 2 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv2f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI15_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI15_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
   %v = call <vscale x 2 x float> @llvm.vp.ceil.nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x float> %v
 }
 
 declare <vscale x 4 x float> @llvm.vp.ceil.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, i32)
 
 define <vscale x 4 x float> @vp_ceil_vv_nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv4f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI16_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI16_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 4 x float> @llvm.vp.ceil.nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x float> %v
 }
 
 define <vscale x 4 x float> @vp_ceil_vv_nxv4f32_unmasked(<vscale x 4 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv4f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI17_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI17_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
   %v = call <vscale x 4 x float> @llvm.vp.ceil.nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x float> %v
 }
 
 declare <vscale x 8 x float> @llvm.vp.ceil.nxv8f32(<vscale x 8 x float>, <vscale x 8 x i1>, i32)
 
 define <vscale x 8 x float> @vp_ceil_vv_nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv8f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI18_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI18_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 8 x float> @llvm.vp.ceil.nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x float> %v
 }
 
 define <vscale x 8 x float> @vp_ceil_vv_nxv8f32_unmasked(<vscale x 8 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv8f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI19_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI19_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
   %v = call <vscale x 8 x float> @llvm.vp.ceil.nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x float> %v
 }
 
 declare <vscale x 16 x float> @llvm.vp.ceil.nxv16f32(<vscale x 16 x float>, <vscale x 16 x i1>, i32)
 
 define <vscale x 16 x float> @vp_ceil_vv_nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv16f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI20_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI20_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 16 x float> @llvm.vp.ceil.nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x float> %v
 }
 
 define <vscale x 16 x float> @vp_ceil_vv_nxv16f32_unmasked(<vscale x 16 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv16f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI21_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI21_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
   %v = call <vscale x 16 x float> @llvm.vp.ceil.nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x float> %v
 }
 
 declare <vscale x 1 x double> @llvm.vp.ceil.nxv1f64(<vscale x 1 x double>, <vscale x 1 x i1>, i32)
 
 define <vscale x 1 x double> @vp_ceil_vv_nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv1f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI22_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI22_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 1 x double> @llvm.vp.ceil.nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x double> %v
 }
 
 define <vscale x 1 x double> @vp_ceil_vv_nxv1f64_unmasked(<vscale x 1 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv1f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI23_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI23_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
   %v = call <vscale x 1 x double> @llvm.vp.ceil.nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x double> %v
 }
 
 declare <vscale x 2 x double> @llvm.vp.ceil.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, i32)
 
 define <vscale x 2 x double> @vp_ceil_vv_nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv2f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI24_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI24_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 2 x double> @llvm.vp.ceil.nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x double> %v
 }
 
 define <vscale x 2 x double> @vp_ceil_vv_nxv2f64_unmasked(<vscale x 2 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv2f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI25_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI25_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
   %v = call <vscale x 2 x double> @llvm.vp.ceil.nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x double> %v
 }
 
 declare <vscale x 4 x double> @llvm.vp.ceil.nxv4f64(<vscale x 4 x double>, <vscale x 4 x i1>, i32)
 
 define <vscale x 4 x double> @vp_ceil_vv_nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv4f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI26_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI26_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 4 x double> @llvm.vp.ceil.nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x double> %v
 }
 
 define <vscale x 4 x double> @vp_ceil_vv_nxv4f64_unmasked(<vscale x 4 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv4f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI27_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI27_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
   %v = call <vscale x 4 x double> @llvm.vp.ceil.nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x double> %v
 }
 
 declare <vscale x 7 x double> @llvm.vp.ceil.nxv7f64(<vscale x 7 x double>, <vscale x 7 x i1>, i32)
 
 define <vscale x 7 x double> @vp_ceil_vv_nxv7f64(<vscale x 7 x double> %va, <vscale x 7 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv7f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI28_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI28_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 7 x double> @llvm.vp.ceil.nxv7f64(<vscale x 7 x double> %va, <vscale x 7 x i1> %m, i32 %evl)
   ret <vscale x 7 x double> %v
 }
 
 define <vscale x 7 x double> @vp_ceil_vv_nxv7f64_unmasked(<vscale x 7 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv7f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI29_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI29_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 7 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 7 x i1> %head, <vscale x 7 x i1> poison, <vscale x 7 x i32> zeroinitializer
   %v = call <vscale x 7 x double> @llvm.vp.ceil.nxv7f64(<vscale x 7 x double> %va, <vscale x 7 x i1> %m, i32 %evl)
   ret <vscale x 7 x double> %v
 }
 
 declare <vscale x 8 x double> @llvm.vp.ceil.nxv8f64(<vscale x 8 x double>, <vscale x 8 x i1>, i32)
 
 define <vscale x 8 x double> @vp_ceil_vv_nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv8f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI30_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI30_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 8 x double> @llvm.vp.ceil.nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x double> %v
 }
 
 define <vscale x 8 x double> @vp_ceil_vv_nxv8f64_unmasked(<vscale x 8 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv8f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI31_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI31_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
   %v = call <vscale x 8 x double> @llvm.vp.ceil.nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x double> %v
 }
 
 ; Test splitting.
 declare <vscale x 16 x double> @llvm.vp.ceil.nxv16f64(<vscale x 16 x double>, <vscale x 16 x i1>, i32)
 
 define <vscale x 16 x double> @vp_ceil_vv_nxv16f64(<vscale x 16 x double> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv16f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    slli a1, a1, 4
-; CHECK-NEXT:    sub sp, sp, a1
-; CHECK-NEXT:    vmv1r.v v24, v0
-; CHECK-NEXT:    addi a1, sp, 16
-; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT:    vmv1r.v v1, v0
 ; CHECK-NEXT:    li a2, 0
 ; CHECK-NEXT:    csrr a1, vlenb
 ; CHECK-NEXT:    srli a4, a1, 3
 ; CHECK-NEXT:    vsetvli a3, zero, e8, mf4, ta, ma
 ; CHECK-NEXT:    sub a3, a0, a1
-; CHECK-NEXT:    vslidedown.vx v25, v0, a4
+; CHECK-NEXT:    vslidedown.vx v2, v0, a4
 ; CHECK-NEXT:    bltu a0, a3, .LBB32_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    mv a2, a3
 ; CHECK-NEXT:  .LBB32_2:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a3, vlenb
+; CHECK-NEXT:    slli a3, a3, 3
+; CHECK-NEXT:    sub sp, sp, a3
 ; CHECK-NEXT:    lui a3, %hi(.LCPI32_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI32_0)(a3)
-; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfabs.v v8, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v25, v8, ft0, v0.t
+; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfabs.v v24, v16, v0.t
+; CHECK-NEXT:    vmflt.vf v2, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a2, 3
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfcvt.x.f.v v8, v16, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
+; CHECK-NEXT:    addi a3, sp, 16
+; CHECK-NEXT:    vs8r.v v24, (a3) # Unknown-size Folded Spill
 ; CHECK-NEXT:    fsrm a2
-; CHECK-NEXT:    vfcvt.f.x.v v8, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vfsgnj.vv v16, v8, v16, v0.t
-; CHECK-NEXT:    csrr a2, vlenb
-; CHECK-NEXT:    slli a2, a2, 3
-; CHECK-NEXT:    add a2, sp, a2
-; CHECK-NEXT:    addi a2, a2, 16
+; CHECK-NEXT:    addi a2, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a2) # Unknown-size Folded Reload
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
+; CHECK-NEXT:    addi a2, sp, 16
 ; CHECK-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
 ; CHECK-NEXT:    bltu a0, a1, .LBB32_4
 ; CHECK-NEXT:  # %bb.3:
 ; CHECK-NEXT:    mv a0, a1
 ; CHECK-NEXT:  .LBB32_4:
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vl8re8.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v24, v16, ft0, v0.t
+; CHECK-NEXT:    vmflt.vf v1, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
+; CHECK-NEXT:    vmv1r.v v0, v1
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    add a0, sp, a0
-; CHECK-NEXT:    addi a0, a0, 16
+; CHECK-NEXT:    addi a0, sp, 16
 ; CHECK-NEXT:    vl8re8.v v16, (a0) # Unknown-size Folded Reload
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 4
+; CHECK-NEXT:    slli a0, a0, 3
 ; CHECK-NEXT:    add sp, sp, a0
 ; CHECK-NEXT:    addi sp, sp, 16
 ; CHECK-NEXT:    ret
   %v = call <vscale x 16 x double> @llvm.vp.ceil.nxv16f64(<vscale x 16 x double> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x double> %v
 }
 
 define <vscale x 16 x double> @vp_ceil_vv_nxv16f64_unmasked(<vscale x 16 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_vv_nxv16f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    csrr a1, vlenb
 ; CHECK-NEXT:    mv a2, a0
 ; CHECK-NEXT:    bltu a0, a1, .LBB33_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    mv a2, a1
 ; CHECK-NEXT:  .LBB33_2:
 ; CHECK-NEXT:    lui a3, %hi(.LCPI33_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI33_0)(a3)
 ; CHECK-NEXT:    li a3, 0
-; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8
 ; CHECK-NEXT:    vmflt.vf v0, v24, ft0
 ; CHECK-NEXT:    fsrmi a2, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a2
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    sub a1, a0, a1
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    bltu a0, a1, .LBB33_4
 ; CHECK-NEXT:  # %bb.3:
 ; CHECK-NEXT:    mv a3, a1
 ; CHECK-NEXT:  .LBB33_4:
-; CHECK-NEXT:    vsetvli zero, a3, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a3, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v16
 ; CHECK-NEXT:    vmflt.vf v0, v24, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
   %v = call <vscale x 16 x double> @llvm.vp.ceil.nxv16f64(<vscale x 16 x double> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x double> %v
 }

llvm/test/CodeGen/RISCV/rvv/fceil-sdnode.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=ilp32d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=lp64d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 
 define <vscale x 1 x half> @ceil_nxv1f16(<vscale x 1 x half> %x) {
 ; CHECK-LABEL: ceil_nxv1f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI0_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI0_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 1 x half> @llvm.ceil.nxv1f16(<vscale x 1 x half> %x)
   ret <vscale x 1 x half> %a
 }
 declare <vscale x 1 x half> @llvm.ceil.nxv1f16(<vscale x 1 x half>)
 
 define <vscale x 2 x half> @ceil_nxv2f16(<vscale x 2 x half> %x) {
 ; CHECK-LABEL: ceil_nxv2f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI1_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI1_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 2 x half> @llvm.ceil.nxv2f16(<vscale x 2 x half> %x)
   ret <vscale x 2 x half> %a
 }
 declare <vscale x 2 x half> @llvm.ceil.nxv2f16(<vscale x 2 x half>)
 
 define <vscale x 4 x half> @ceil_nxv4f16(<vscale x 4 x half> %x) {
 ; CHECK-LABEL: ceil_nxv4f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI2_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI2_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 4 x half> @llvm.ceil.nxv4f16(<vscale x 4 x half> %x)
   ret <vscale x 4 x half> %a
 }
 declare <vscale x 4 x half> @llvm.ceil.nxv4f16(<vscale x 4 x half>)
 
 define <vscale x 8 x half> @ceil_nxv8f16(<vscale x 8 x half> %x) {
 ; CHECK-LABEL: ceil_nxv8f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI3_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI3_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, m2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 8 x half> @llvm.ceil.nxv8f16(<vscale x 8 x half> %x)
   ret <vscale x 8 x half> %a
 }
 declare <vscale x 8 x half> @llvm.ceil.nxv8f16(<vscale x 8 x half>)
 
 define <vscale x 16 x half> @ceil_nxv16f16(<vscale x 16 x half> %x) {
 ; CHECK-LABEL: ceil_nxv16f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI4_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI4_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, m4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 16 x half> @llvm.ceil.nxv16f16(<vscale x 16 x half> %x)
   ret <vscale x 16 x half> %a
 }
 declare <vscale x 16 x half> @llvm.ceil.nxv16f16(<vscale x 16 x half>)
 
 define <vscale x 32 x half> @ceil_nxv32f16(<vscale x 32 x half> %x) {
 ; CHECK-LABEL: ceil_nxv32f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI5_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI5_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, m8, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 32 x half> @llvm.ceil.nxv32f16(<vscale x 32 x half> %x)
   ret <vscale x 32 x half> %a
 }
 declare <vscale x 32 x half> @llvm.ceil.nxv32f16(<vscale x 32 x half>)
 
 define <vscale x 1 x float> @ceil_nxv1f32(<vscale x 1 x float> %x) {
 ; CHECK-LABEL: ceil_nxv1f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI6_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI6_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 1 x float> @llvm.ceil.nxv1f32(<vscale x 1 x float> %x)
   ret <vscale x 1 x float> %a
 }
 declare <vscale x 1 x float> @llvm.ceil.nxv1f32(<vscale x 1 x float>)
 
 define <vscale x 2 x float> @ceil_nxv2f32(<vscale x 2 x float> %x) {
 ; CHECK-LABEL: ceil_nxv2f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI7_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI7_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 2 x float> @llvm.ceil.nxv2f32(<vscale x 2 x float> %x)
   ret <vscale x 2 x float> %a
 }
 declare <vscale x 2 x float> @llvm.ceil.nxv2f32(<vscale x 2 x float>)
 
 define <vscale x 4 x float> @ceil_nxv4f32(<vscale x 4 x float> %x) {
 ; CHECK-LABEL: ceil_nxv4f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI8_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI8_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 4 x float> @llvm.ceil.nxv4f32(<vscale x 4 x float> %x)
   ret <vscale x 4 x float> %a
 }
 declare <vscale x 4 x float> @llvm.ceil.nxv4f32(<vscale x 4 x float>)
 
 define <vscale x 8 x float> @ceil_nxv8f32(<vscale x 8 x float> %x) {
 ; CHECK-LABEL: ceil_nxv8f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI9_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI9_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 8 x float> @llvm.ceil.nxv8f32(<vscale x 8 x float> %x)
   ret <vscale x 8 x float> %a
 }
 declare <vscale x 8 x float> @llvm.ceil.nxv8f32(<vscale x 8 x float>)
 
 define <vscale x 16 x float> @ceil_nxv16f32(<vscale x 16 x float> %x) {
 ; CHECK-LABEL: ceil_nxv16f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI10_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI10_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m8, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 16 x float> @llvm.ceil.nxv16f32(<vscale x 16 x float> %x)
   ret <vscale x 16 x float> %a
 }
 declare <vscale x 16 x float> @llvm.ceil.nxv16f32(<vscale x 16 x float>)
 
 define <vscale x 1 x double> @ceil_nxv1f64(<vscale x 1 x double> %x) {
 ; CHECK-LABEL: ceil_nxv1f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI11_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI11_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 1 x double> @llvm.ceil.nxv1f64(<vscale x 1 x double> %x)
   ret <vscale x 1 x double> %a
 }
 declare <vscale x 1 x double> @llvm.ceil.nxv1f64(<vscale x 1 x double>)
 
 define <vscale x 2 x double> @ceil_nxv2f64(<vscale x 2 x double> %x) {
 ; CHECK-LABEL: ceil_nxv2f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI12_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI12_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e64, m2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 2 x double> @llvm.ceil.nxv2f64(<vscale x 2 x double> %x)
   ret <vscale x 2 x double> %a
 }
 declare <vscale x 2 x double> @llvm.ceil.nxv2f64(<vscale x 2 x double>)
 
 define <vscale x 4 x double> @ceil_nxv4f64(<vscale x 4 x double> %x) {
 ; CHECK-LABEL: ceil_nxv4f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI13_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI13_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e64, m4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 4 x double> @llvm.ceil.nxv4f64(<vscale x 4 x double> %x)
   ret <vscale x 4 x double> %a
 }
 declare <vscale x 4 x double> @llvm.ceil.nxv4f64(<vscale x 4 x double>)
 
 define <vscale x 8 x double> @ceil_nxv8f64(<vscale x 8 x double> %x) {
 ; CHECK-LABEL: ceil_nxv8f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI14_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI14_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 8 x double> @llvm.ceil.nxv8f64(<vscale x 8 x double> %x)
   ret <vscale x 8 x double> %a
 }
 declare <vscale x 8 x double> @llvm.ceil.nxv8f64(<vscale x 8 x double>)

llvm/test/CodeGen/RISCV/rvv/ffloor-sdnode.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=ilp32d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=lp64d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 
 define <vscale x 1 x half> @floor_nxv1f16(<vscale x 1 x half> %x) {
 ; CHECK-LABEL: floor_nxv1f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI0_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI0_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 1 x half> @llvm.floor.nxv1f16(<vscale x 1 x half> %x)
   ret <vscale x 1 x half> %a
 }
 declare <vscale x 1 x half> @llvm.floor.nxv1f16(<vscale x 1 x half>)
 
 define <vscale x 2 x half> @floor_nxv2f16(<vscale x 2 x half> %x) {
 ; CHECK-LABEL: floor_nxv2f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI1_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI1_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 2 x half> @llvm.floor.nxv2f16(<vscale x 2 x half> %x)
   ret <vscale x 2 x half> %a
 }
 declare <vscale x 2 x half> @llvm.floor.nxv2f16(<vscale x 2 x half>)
 
 define <vscale x 4 x half> @floor_nxv4f16(<vscale x 4 x half> %x) {
 ; CHECK-LABEL: floor_nxv4f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI2_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI2_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 4 x half> @llvm.floor.nxv4f16(<vscale x 4 x half> %x)
   ret <vscale x 4 x half> %a
 }
 declare <vscale x 4 x half> @llvm.floor.nxv4f16(<vscale x 4 x half>)
 
 define <vscale x 8 x half> @floor_nxv8f16(<vscale x 8 x half> %x) {
 ; CHECK-LABEL: floor_nxv8f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI3_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI3_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, m2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 8 x half> @llvm.floor.nxv8f16(<vscale x 8 x half> %x)
   ret <vscale x 8 x half> %a
 }
 declare <vscale x 8 x half> @llvm.floor.nxv8f16(<vscale x 8 x half>)
 
 define <vscale x 16 x half> @floor_nxv16f16(<vscale x 16 x half> %x) {
 ; CHECK-LABEL: floor_nxv16f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI4_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI4_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, m4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 16 x half> @llvm.floor.nxv16f16(<vscale x 16 x half> %x)
   ret <vscale x 16 x half> %a
 }
 declare <vscale x 16 x half> @llvm.floor.nxv16f16(<vscale x 16 x half>)
 
 define <vscale x 32 x half> @floor_nxv32f16(<vscale x 32 x half> %x) {
 ; CHECK-LABEL: floor_nxv32f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI5_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI5_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, m8, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 32 x half> @llvm.floor.nxv32f16(<vscale x 32 x half> %x)
   ret <vscale x 32 x half> %a
 }
 declare <vscale x 32 x half> @llvm.floor.nxv32f16(<vscale x 32 x half>)
 
 define <vscale x 1 x float> @floor_nxv1f32(<vscale x 1 x float> %x) {
 ; CHECK-LABEL: floor_nxv1f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI6_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI6_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 1 x float> @llvm.floor.nxv1f32(<vscale x 1 x float> %x)
   ret <vscale x 1 x float> %a
 }
 declare <vscale x 1 x float> @llvm.floor.nxv1f32(<vscale x 1 x float>)
 
 define <vscale x 2 x float> @floor_nxv2f32(<vscale x 2 x float> %x) {
 ; CHECK-LABEL: floor_nxv2f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI7_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI7_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 2 x float> @llvm.floor.nxv2f32(<vscale x 2 x float> %x)
   ret <vscale x 2 x float> %a
 }
 declare <vscale x 2 x float> @llvm.floor.nxv2f32(<vscale x 2 x float>)
 
 define <vscale x 4 x float> @floor_nxv4f32(<vscale x 4 x float> %x) {
 ; CHECK-LABEL: floor_nxv4f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI8_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI8_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 4 x float> @llvm.floor.nxv4f32(<vscale x 4 x float> %x)
   ret <vscale x 4 x float> %a
 }
 declare <vscale x 4 x float> @llvm.floor.nxv4f32(<vscale x 4 x float>)
 
 define <vscale x 8 x float> @floor_nxv8f32(<vscale x 8 x float> %x) {
 ; CHECK-LABEL: floor_nxv8f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI9_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI9_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 8 x float> @llvm.floor.nxv8f32(<vscale x 8 x float> %x)
   ret <vscale x 8 x float> %a
 }
 declare <vscale x 8 x float> @llvm.floor.nxv8f32(<vscale x 8 x float>)
 
 define <vscale x 16 x float> @floor_nxv16f32(<vscale x 16 x float> %x) {
 ; CHECK-LABEL: floor_nxv16f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI10_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI10_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m8, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 16 x float> @llvm.floor.nxv16f32(<vscale x 16 x float> %x)
   ret <vscale x 16 x float> %a
 }
 declare <vscale x 16 x float> @llvm.floor.nxv16f32(<vscale x 16 x float>)
 
 define <vscale x 1 x double> @floor_nxv1f64(<vscale x 1 x double> %x) {
 ; CHECK-LABEL: floor_nxv1f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI11_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI11_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 1 x double> @llvm.floor.nxv1f64(<vscale x 1 x double> %x)
   ret <vscale x 1 x double> %a
 }
 declare <vscale x 1 x double> @llvm.floor.nxv1f64(<vscale x 1 x double>)
 
 define <vscale x 2 x double> @floor_nxv2f64(<vscale x 2 x double> %x) {
 ; CHECK-LABEL: floor_nxv2f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI12_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI12_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e64, m2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 2 x double> @llvm.floor.nxv2f64(<vscale x 2 x double> %x)
   ret <vscale x 2 x double> %a
 }
 declare <vscale x 2 x double> @llvm.floor.nxv2f64(<vscale x 2 x double>)
 
 define <vscale x 4 x double> @floor_nxv4f64(<vscale x 4 x double> %x) {
 ; CHECK-LABEL: floor_nxv4f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI13_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI13_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e64, m4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 4 x double> @llvm.floor.nxv4f64(<vscale x 4 x double> %x)
   ret <vscale x 4 x double> %a
 }
 declare <vscale x 4 x double> @llvm.floor.nxv4f64(<vscale x 4 x double>)
 
 define <vscale x 8 x double> @floor_nxv8f64(<vscale x 8 x double> %x) {
 ; CHECK-LABEL: floor_nxv8f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI14_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI14_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 8 x double> @llvm.floor.nxv8f64(<vscale x 8 x double> %x)
   ret <vscale x 8 x double> %a
 }
 declare <vscale x 8 x double> @llvm.floor.nxv8f64(<vscale x 8 x double>)

llvm/test/CodeGen/RISCV/rvv/fixed-vector-shuffle-reverse.ll

 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
 ; CHECK-NEXT:    vmv.v.i v8, 0
 ; CHECK-NEXT:    vmerge.vim v8, v8, 1, v0
 ; CHECK-NEXT:    vsetivli zero, 1, e8, mf8, ta, ma
 ; CHECK-NEXT:    vslidedown.vi v9, v8, 1
 ; CHECK-NEXT:    vmv.x.s a0, v9
 ; CHECK-NEXT:    vmv.x.s a1, v8
-; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
+; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, tu, ma
 ; CHECK-NEXT:    vmv.v.x v8, a1
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, tu, ma
 ; CHECK-NEXT:    vmv.s.x v8, a0
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, ta, ma
 ; CHECK-NEXT:    vand.vi v8, v8, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %res = call <2 x i1> @llvm.experimental.vector.reverse.v2i1(<2 x i1> %a)
   ret <2 x i1> %res
 }
 
 define <4 x i1> @reverse_v4i1(<4 x i1> %a) {

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-bitcast.ll

 ; RV64-LABEL: bitcast_i64_v4i16:
 ; RV64:       # %bb.0:
 ; RV64-NEXT:    vsetivli zero, 1, e64, m1, ta, ma
 ; RV64-NEXT:    vmv.s.x v8, a0
 ; RV64-NEXT:    ret
 ;
 ; RV32ELEN32-LABEL: bitcast_i64_v4i16:
 ; RV32ELEN32:       # %bb.0:
-; RV32ELEN32-NEXT:    vsetivli zero, 2, e32, m1, ta, ma
+; RV32ELEN32-NEXT:    vsetivli zero, 2, e32, m1, tu, ma
 ; RV32ELEN32-NEXT:    vmv.v.x v8, a1
-; RV32ELEN32-NEXT:    vsetvli zero, zero, e32, m1, tu, ma
 ; RV32ELEN32-NEXT:    vmv.s.x v8, a0
 ; RV32ELEN32-NEXT:    ret
 ;
 ; RV64ELEN32-LABEL: bitcast_i64_v4i16:
 ; RV64ELEN32:       # %bb.0:
 ; RV64ELEN32-NEXT:    addi sp, sp, -16
 ; RV64ELEN32-NEXT:    .cfi_def_cfa_offset 16
 ; RV64ELEN32-NEXT:    sd a0, 8(sp)

 ; RV64-LABEL: bitcast_i64_v2i32:
 ; RV64:       # %bb.0:
 ; RV64-NEXT:    vsetivli zero, 1, e64, m1, ta, ma
 ; RV64-NEXT:    vmv.s.x v8, a0
 ; RV64-NEXT:    ret
 ;
 ; RV32ELEN32-LABEL: bitcast_i64_v2i32:
 ; RV32ELEN32:       # %bb.0:
-; RV32ELEN32-NEXT:    vsetivli zero, 2, e32, m1, ta, ma
+; RV32ELEN32-NEXT:    vsetivli zero, 2, e32, m1, tu, ma
 ; RV32ELEN32-NEXT:    vmv.v.x v8, a1
-; RV32ELEN32-NEXT:    vsetvli zero, zero, e32, m1, tu, ma
 ; RV32ELEN32-NEXT:    vmv.s.x v8, a0
 ; RV32ELEN32-NEXT:    ret
 ;
 ; RV64ELEN32-LABEL: bitcast_i64_v2i32:
 ; RV64ELEN32:       # %bb.0:
 ; RV64ELEN32-NEXT:    addi sp, sp, -16
 ; RV64ELEN32-NEXT:    .cfi_def_cfa_offset 16
 ; RV64ELEN32-NEXT:    sd a0, 8(sp)

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-ceil-vp.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=ilp32d -riscv-v-vector-bits-min=128 \
 ; RUN:   -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=lp64d -riscv-v-vector-bits-min=128 \
 ; RUN:   -verify-machineinstrs < %s | FileCheck %s
 
 declare <2 x half> @llvm.vp.ceil.v2f16(<2 x half>, <2 x i1>, i32)
 
 define <2 x half> @vp_ceil_v2f16(<2 x half> %va, <2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v2f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI0_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI0_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <2 x half> @llvm.vp.ceil.v2f16(<2 x half> %va, <2 x i1> %m, i32 %evl)
   ret <2 x half> %v
 }
 
 define <2 x half> @vp_ceil_v2f16_unmasked(<2 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v2f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI1_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI1_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <2 x i1> poison, i1 true, i32 0
   %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
   %v = call <2 x half> @llvm.vp.ceil.v2f16(<2 x half> %va, <2 x i1> %m, i32 %evl)
   ret <2 x half> %v
 }
 
 declare <4 x half> @llvm.vp.ceil.v4f16(<4 x half>, <4 x i1>, i32)
 
 define <4 x half> @vp_ceil_v4f16(<4 x half> %va, <4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v4f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI2_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI2_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <4 x half> @llvm.vp.ceil.v4f16(<4 x half> %va, <4 x i1> %m, i32 %evl)
   ret <4 x half> %v
 }
 
 define <4 x half> @vp_ceil_v4f16_unmasked(<4 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v4f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI3_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI3_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <4 x i1> poison, i1 true, i32 0
   %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
   %v = call <4 x half> @llvm.vp.ceil.v4f16(<4 x half> %va, <4 x i1> %m, i32 %evl)
   ret <4 x half> %v
 }
 
 declare <8 x half> @llvm.vp.ceil.v8f16(<8 x half>, <8 x i1>, i32)
 
 define <8 x half> @vp_ceil_v8f16(<8 x half> %va, <8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v8f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI4_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI4_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <8 x half> @llvm.vp.ceil.v8f16(<8 x half> %va, <8 x i1> %m, i32 %evl)
   ret <8 x half> %v
 }
 
 define <8 x half> @vp_ceil_v8f16_unmasked(<8 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v8f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI5_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI5_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <8 x i1> poison, i1 true, i32 0
   %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
   %v = call <8 x half> @llvm.vp.ceil.v8f16(<8 x half> %va, <8 x i1> %m, i32 %evl)
   ret <8 x half> %v
 }
 
 declare <16 x half> @llvm.vp.ceil.v16f16(<16 x half>, <16 x i1>, i32)
 
 define <16 x half> @vp_ceil_v16f16(<16 x half> %va, <16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v16f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI6_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI6_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <16 x half> @llvm.vp.ceil.v16f16(<16 x half> %va, <16 x i1> %m, i32 %evl)
   ret <16 x half> %v
 }
 
 define <16 x half> @vp_ceil_v16f16_unmasked(<16 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v16f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI7_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI7_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vmset.m v10
-; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <16 x i1> poison, i1 true, i32 0
   %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
   %v = call <16 x half> @llvm.vp.ceil.v16f16(<16 x half> %va, <16 x i1> %m, i32 %evl)
   ret <16 x half> %v
 }
 
 declare <2 x float> @llvm.vp.ceil.v2f32(<2 x float>, <2 x i1>, i32)
 
 define <2 x float> @vp_ceil_v2f32(<2 x float> %va, <2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v2f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI8_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI8_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <2 x float> @llvm.vp.ceil.v2f32(<2 x float> %va, <2 x i1> %m, i32 %evl)
   ret <2 x float> %v
 }
 
 define <2 x float> @vp_ceil_v2f32_unmasked(<2 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v2f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI9_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI9_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <2 x i1> poison, i1 true, i32 0
   %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
   %v = call <2 x float> @llvm.vp.ceil.v2f32(<2 x float> %va, <2 x i1> %m, i32 %evl)
   ret <2 x float> %v
 }
 
 declare <4 x float> @llvm.vp.ceil.v4f32(<4 x float>, <4 x i1>, i32)
 
 define <4 x float> @vp_ceil_v4f32(<4 x float> %va, <4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v4f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI10_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI10_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <4 x float> @llvm.vp.ceil.v4f32(<4 x float> %va, <4 x i1> %m, i32 %evl)
   ret <4 x float> %v
 }
 
 define <4 x float> @vp_ceil_v4f32_unmasked(<4 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v4f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI11_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI11_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <4 x i1> poison, i1 true, i32 0
   %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
   %v = call <4 x float> @llvm.vp.ceil.v4f32(<4 x float> %va, <4 x i1> %m, i32 %evl)
   ret <4 x float> %v
 }
 
 declare <8 x float> @llvm.vp.ceil.v8f32(<8 x float>, <8 x i1>, i32)
 
 define <8 x float> @vp_ceil_v8f32(<8 x float> %va, <8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v8f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI12_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI12_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <8 x float> @llvm.vp.ceil.v8f32(<8 x float> %va, <8 x i1> %m, i32 %evl)
   ret <8 x float> %v
 }
 
 define <8 x float> @vp_ceil_v8f32_unmasked(<8 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v8f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI13_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI13_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
 ; CHECK-NEXT:    vmset.m v10
-; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <8 x i1> poison, i1 true, i32 0
   %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
   %v = call <8 x float> @llvm.vp.ceil.v8f32(<8 x float> %va, <8 x i1> %m, i32 %evl)
   ret <8 x float> %v
 }
 
 declare <16 x float> @llvm.vp.ceil.v16f32(<16 x float>, <16 x i1>, i32)
 
 define <16 x float> @vp_ceil_v16f32(<16 x float> %va, <16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v16f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI14_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI14_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <16 x float> @llvm.vp.ceil.v16f32(<16 x float> %va, <16 x i1> %m, i32 %evl)
   ret <16 x float> %v
 }
 
 define <16 x float> @vp_ceil_v16f32_unmasked(<16 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v16f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI15_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI15_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vmset.m v12
-; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <16 x i1> poison, i1 true, i32 0
   %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
   %v = call <16 x float> @llvm.vp.ceil.v16f32(<16 x float> %va, <16 x i1> %m, i32 %evl)
   ret <16 x float> %v
 }
 
 declare <2 x double> @llvm.vp.ceil.v2f64(<2 x double>, <2 x i1>, i32)
 
 define <2 x double> @vp_ceil_v2f64(<2 x double> %va, <2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v2f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI16_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI16_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <2 x double> @llvm.vp.ceil.v2f64(<2 x double> %va, <2 x i1> %m, i32 %evl)
   ret <2 x double> %v
 }
 
 define <2 x double> @vp_ceil_v2f64_unmasked(<2 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v2f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI17_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI17_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <2 x i1> poison, i1 true, i32 0
   %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
   %v = call <2 x double> @llvm.vp.ceil.v2f64(<2 x double> %va, <2 x i1> %m, i32 %evl)
   ret <2 x double> %v
 }
 
 declare <4 x double> @llvm.vp.ceil.v4f64(<4 x double>, <4 x i1>, i32)
 
 define <4 x double> @vp_ceil_v4f64(<4 x double> %va, <4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v4f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI18_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI18_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <4 x double> @llvm.vp.ceil.v4f64(<4 x double> %va, <4 x i1> %m, i32 %evl)
   ret <4 x double> %v
 }
 
 define <4 x double> @vp_ceil_v4f64_unmasked(<4 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v4f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI19_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI19_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
 ; CHECK-NEXT:    vmset.m v10
-; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <4 x i1> poison, i1 true, i32 0
   %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
   %v = call <4 x double> @llvm.vp.ceil.v4f64(<4 x double> %va, <4 x i1> %m, i32 %evl)
   ret <4 x double> %v
 }
 
 declare <8 x double> @llvm.vp.ceil.v8f64(<8 x double>, <8 x i1>, i32)
 
 define <8 x double> @vp_ceil_v8f64(<8 x double> %va, <8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v8f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI20_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI20_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <8 x double> @llvm.vp.ceil.v8f64(<8 x double> %va, <8 x i1> %m, i32 %evl)
   ret <8 x double> %v
 }
 
 define <8 x double> @vp_ceil_v8f64_unmasked(<8 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v8f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI21_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI21_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
 ; CHECK-NEXT:    vmset.m v12
-; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <8 x i1> poison, i1 true, i32 0
   %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
   %v = call <8 x double> @llvm.vp.ceil.v8f64(<8 x double> %va, <8 x i1> %m, i32 %evl)
   ret <8 x double> %v
 }
 
 declare <15 x double> @llvm.vp.ceil.v15f64(<15 x double>, <15 x i1>, i32)
 
 define <15 x double> @vp_ceil_v15f64(<15 x double> %va, <15 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v15f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI22_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI22_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <15 x double> @llvm.vp.ceil.v15f64(<15 x double> %va, <15 x i1> %m, i32 %evl)
   ret <15 x double> %v
 }
 
 define <15 x double> @vp_ceil_v15f64_unmasked(<15 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v15f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI23_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI23_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vmset.m v16
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <15 x i1> poison, i1 true, i32 0
   %m = shufflevector <15 x i1> %head, <15 x i1> poison, <15 x i32> zeroinitializer
   %v = call <15 x double> @llvm.vp.ceil.v15f64(<15 x double> %va, <15 x i1> %m, i32 %evl)
   ret <15 x double> %v
 }
 
 declare <16 x double> @llvm.vp.ceil.v16f64(<16 x double>, <16 x i1>, i32)
 
 define <16 x double> @vp_ceil_v16f64(<16 x double> %va, <16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v16f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI24_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI24_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <16 x double> @llvm.vp.ceil.v16f64(<16 x double> %va, <16 x i1> %m, i32 %evl)
   ret <16 x double> %v
 }
 
 define <16 x double> @vp_ceil_v16f64_unmasked(<16 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v16f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI25_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI25_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vmset.m v16
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <16 x i1> poison, i1 true, i32 0
   %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
   %v = call <16 x double> @llvm.vp.ceil.v16f64(<16 x double> %va, <16 x i1> %m, i32 %evl)
   ret <16 x double> %v
 }
 
 declare <32 x double> @llvm.vp.ceil.v32f64(<32 x double>, <32 x i1>, i32)
 
 define <32 x double> @vp_ceil_v32f64(<32 x double> %va, <32 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v32f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    slli a1, a1, 4
-; CHECK-NEXT:    sub sp, sp, a1
-; CHECK-NEXT:    vmv1r.v v24, v0
-; CHECK-NEXT:    addi a1, sp, 16
-; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT:    vmv1r.v v1, v0
 ; CHECK-NEXT:    li a1, 0
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf4, ta, ma
 ; CHECK-NEXT:    addi a2, a0, -16
-; CHECK-NEXT:    vslidedown.vi v25, v0, 2
+; CHECK-NEXT:    vslidedown.vi v2, v0, 2
 ; CHECK-NEXT:    bltu a0, a2, .LBB26_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    mv a1, a2
 ; CHECK-NEXT:  .LBB26_2:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a2, vlenb
+; CHECK-NEXT:    slli a2, a2, 3
+; CHECK-NEXT:    sub sp, sp, a2
 ; CHECK-NEXT:    lui a2, %hi(.LCPI26_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI26_0)(a2)
-; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfabs.v v8, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v25, v8, ft0, v0.t
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfabs.v v24, v16, v0.t
+; CHECK-NEXT:    vmflt.vf v2, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a1, 3
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfcvt.x.f.v v8, v16, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
 ; CHECK-NEXT:    fsrm a1
-; CHECK-NEXT:    vfcvt.f.x.v v8, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    addi a1, sp, 16
+; CHECK-NEXT:    vs8r.v v24, (a1) # Unknown-size Folded Spill
 ; CHECK-NEXT:    li a1, 16
-; CHECK-NEXT:    vfsgnj.vv v16, v8, v16, v0.t
-; CHECK-NEXT:    csrr a2, vlenb
-; CHECK-NEXT:    slli a2, a2, 3
-; CHECK-NEXT:    add a2, sp, a2
-; CHECK-NEXT:    addi a2, a2, 16
+; CHECK-NEXT:    addi a2, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a2) # Unknown-size Folded Reload
+; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
+; CHECK-NEXT:    addi a2, sp, 16
 ; CHECK-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
 ; CHECK-NEXT:    bltu a0, a1, .LBB26_4
 ; CHECK-NEXT:  # %bb.3:
 ; CHECK-NEXT:    li a0, 16
 ; CHECK-NEXT:  .LBB26_4:
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vl8re8.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v24, v16, ft0, v0.t
+; CHECK-NEXT:    vmflt.vf v1, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
+; CHECK-NEXT:    vmv1r.v v0, v1
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    add a0, sp, a0
-; CHECK-NEXT:    addi a0, a0, 16
+; CHECK-NEXT:    addi a0, sp, 16
 ; CHECK-NEXT:    vl8re8.v v16, (a0) # Unknown-size Folded Reload
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 4
+; CHECK-NEXT:    slli a0, a0, 3
 ; CHECK-NEXT:    add sp, sp, a0
 ; CHECK-NEXT:    addi sp, sp, 16
 ; CHECK-NEXT:    ret
   %v = call <32 x double> @llvm.vp.ceil.v32f64(<32 x double> %va, <32 x i1> %m, i32 %evl)
   ret <32 x double> %v
 }
 
 define <32 x double> @vp_ceil_v32f64_unmasked(<32 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_ceil_v32f64_unmasked:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    slli a1, a1, 4
-; CHECK-NEXT:    sub sp, sp, a1
-; CHECK-NEXT:    addi a1, sp, 16
-; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
 ; CHECK-NEXT:    li a1, 0
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    addi a2, a0, -16
-; CHECK-NEXT:    vmset.m v24
+; CHECK-NEXT:    vmset.m v1
 ; CHECK-NEXT:    bltu a0, a2, .LBB27_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    mv a1, a2
 ; CHECK-NEXT:  .LBB27_2:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a2, vlenb
+; CHECK-NEXT:    slli a2, a2, 3
+; CHECK-NEXT:    sub sp, sp, a2
 ; CHECK-NEXT:    lui a2, %hi(.LCPI27_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI27_0)(a2)
-; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    vfabs.v v8, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmv1r.v v25, v24
-; CHECK-NEXT:    vmflt.vf v25, v8, ft0, v0.t
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    vfabs.v v24, v16, v0.t
+; CHECK-NEXT:    vmv1r.v v2, v1
+; CHECK-NEXT:    vmflt.vf v2, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a1, 3
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfcvt.x.f.v v8, v16, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
 ; CHECK-NEXT:    fsrm a1
-; CHECK-NEXT:    vfcvt.f.x.v v8, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    addi a1, sp, 16
+; CHECK-NEXT:    vs8r.v v24, (a1) # Unknown-size Folded Spill
 ; CHECK-NEXT:    li a1, 16
-; CHECK-NEXT:    vfsgnj.vv v16, v8, v16, v0.t
+; CHECK-NEXT:    addi a2, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a2) # Unknown-size Folded Reload
+; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
 ; CHECK-NEXT:    csrr a2, vlenb
 ; CHECK-NEXT:    slli a2, a2, 3
-; CHECK-NEXT:    add a2, sp, a2
-; CHECK-NEXT:    addi a2, a2, 16
-; CHECK-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
+; CHECK-NEXT:    add sp, sp, a2
+; CHECK-NEXT:    addi sp, sp, 16
 ; CHECK-NEXT:    bltu a0, a1, .LBB27_4
 ; CHECK-NEXT:  # %bb.3:
 ; CHECK-NEXT:    li a0, 16
 ; CHECK-NEXT:  .LBB27_4:
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vl8re8.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v24, v16, ft0, v0.t
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    vfabs.v v24, v8, v0.t
+; CHECK-NEXT:    vmflt.vf v1, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
-; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    add a0, sp, a0
-; CHECK-NEXT:    addi a0, a0, 16
-; CHECK-NEXT:    vl8re8.v v16, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 4
-; CHECK-NEXT:    add sp, sp, a0
-; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <32 x i1> poison, i1 true, i32 0
   %m = shufflevector <32 x i1> %head, <32 x i1> poison, <32 x i32> zeroinitializer
   %v = call <32 x double> @llvm.vp.ceil.v32f64(<32 x double> %va, <32 x i1> %m, i32 %evl)
   ret <32 x double> %v
 }

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-extract.ll

 ; RV32NOM-LABEL: extractelt_sdiv_v4i32:
 ; RV32NOM:       # %bb.0:
 ; RV32NOM-NEXT:    li a0, -1
 ; RV32NOM-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
 ; RV32NOM-NEXT:    vmv.s.x v9, a0
 ; RV32NOM-NEXT:    vmv.v.i v10, 0
 ; RV32NOM-NEXT:    vsetvli zero, zero, e32, m1, tu, ma
 ; RV32NOM-NEXT:    vslideup.vi v10, v9, 3
-; RV32NOM-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; RV32NOM-NEXT:    lui a0, %hi(.LCPI38_0)
 ; RV32NOM-NEXT:    addi a0, a0, %lo(.LCPI38_0)
 ; RV32NOM-NEXT:    vle32.v v9, (a0)
 ; RV32NOM-NEXT:    lui a0, %hi(.LCPI38_1)
 ; RV32NOM-NEXT:    addi a0, a0, %lo(.LCPI38_1)
 ; RV32NOM-NEXT:    vle32.v v11, (a0)
 ; RV32NOM-NEXT:    vand.vv v10, v8, v10
 ; RV32NOM-NEXT:    vmulh.vv v8, v8, v9

 ; RV64-LABEL: extractelt_sdiv_v4i32:
 ; RV64:       # %bb.0:
 ; RV64-NEXT:    li a0, -1
 ; RV64-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
 ; RV64-NEXT:    vmv.s.x v9, a0
 ; RV64-NEXT:    vmv.v.i v10, 0
 ; RV64-NEXT:    vsetvli zero, zero, e32, m1, tu, ma
 ; RV64-NEXT:    vslideup.vi v10, v9, 3
-; RV64-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; RV64-NEXT:    lui a0, %hi(.LCPI38_0)
 ; RV64-NEXT:    addi a0, a0, %lo(.LCPI38_0)
 ; RV64-NEXT:    vle32.v v9, (a0)
 ; RV64-NEXT:    lui a0, %hi(.LCPI38_1)
 ; RV64-NEXT:    addi a0, a0, %lo(.LCPI38_1)
 ; RV64-NEXT:    vle32.v v11, (a0)
 ; RV64-NEXT:    vand.vv v10, v8, v10
 ; RV64-NEXT:    vmulh.vv v8, v8, v9

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-floor-vp.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=ilp32d -riscv-v-vector-bits-min=128 \
 ; RUN:   -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=lp64d -riscv-v-vector-bits-min=128 \
 ; RUN:   -verify-machineinstrs < %s | FileCheck %s
 
 declare <2 x half> @llvm.vp.floor.v2f16(<2 x half>, <2 x i1>, i32)
 
 define <2 x half> @vp_floor_v2f16(<2 x half> %va, <2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v2f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI0_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI0_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <2 x half> @llvm.vp.floor.v2f16(<2 x half> %va, <2 x i1> %m, i32 %evl)
   ret <2 x half> %v
 }
 
 define <2 x half> @vp_floor_v2f16_unmasked(<2 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v2f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI1_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI1_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <2 x i1> poison, i1 true, i32 0
   %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
   %v = call <2 x half> @llvm.vp.floor.v2f16(<2 x half> %va, <2 x i1> %m, i32 %evl)
   ret <2 x half> %v
 }
 
 declare <4 x half> @llvm.vp.floor.v4f16(<4 x half>, <4 x i1>, i32)
 
 define <4 x half> @vp_floor_v4f16(<4 x half> %va, <4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v4f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI2_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI2_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <4 x half> @llvm.vp.floor.v4f16(<4 x half> %va, <4 x i1> %m, i32 %evl)
   ret <4 x half> %v
 }
 
 define <4 x half> @vp_floor_v4f16_unmasked(<4 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v4f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI3_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI3_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <4 x i1> poison, i1 true, i32 0
   %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
   %v = call <4 x half> @llvm.vp.floor.v4f16(<4 x half> %va, <4 x i1> %m, i32 %evl)
   ret <4 x half> %v
 }
 
 declare <8 x half> @llvm.vp.floor.v8f16(<8 x half>, <8 x i1>, i32)
 
 define <8 x half> @vp_floor_v8f16(<8 x half> %va, <8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v8f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI4_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI4_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <8 x half> @llvm.vp.floor.v8f16(<8 x half> %va, <8 x i1> %m, i32 %evl)
   ret <8 x half> %v
 }
 
 define <8 x half> @vp_floor_v8f16_unmasked(<8 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v8f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI5_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI5_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <8 x i1> poison, i1 true, i32 0
   %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
   %v = call <8 x half> @llvm.vp.floor.v8f16(<8 x half> %va, <8 x i1> %m, i32 %evl)
   ret <8 x half> %v
 }
 
 declare <16 x half> @llvm.vp.floor.v16f16(<16 x half>, <16 x i1>, i32)
 
 define <16 x half> @vp_floor_v16f16(<16 x half> %va, <16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v16f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI6_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI6_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <16 x half> @llvm.vp.floor.v16f16(<16 x half> %va, <16 x i1> %m, i32 %evl)
   ret <16 x half> %v
 }
 
 define <16 x half> @vp_floor_v16f16_unmasked(<16 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v16f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI7_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI7_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vmset.m v10
-; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <16 x i1> poison, i1 true, i32 0
   %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
   %v = call <16 x half> @llvm.vp.floor.v16f16(<16 x half> %va, <16 x i1> %m, i32 %evl)
   ret <16 x half> %v
 }
 
 declare <2 x float> @llvm.vp.floor.v2f32(<2 x float>, <2 x i1>, i32)
 
 define <2 x float> @vp_floor_v2f32(<2 x float> %va, <2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v2f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI8_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI8_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <2 x float> @llvm.vp.floor.v2f32(<2 x float> %va, <2 x i1> %m, i32 %evl)
   ret <2 x float> %v
 }
 
 define <2 x float> @vp_floor_v2f32_unmasked(<2 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v2f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI9_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI9_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <2 x i1> poison, i1 true, i32 0
   %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
   %v = call <2 x float> @llvm.vp.floor.v2f32(<2 x float> %va, <2 x i1> %m, i32 %evl)
   ret <2 x float> %v
 }
 
 declare <4 x float> @llvm.vp.floor.v4f32(<4 x float>, <4 x i1>, i32)
 
 define <4 x float> @vp_floor_v4f32(<4 x float> %va, <4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v4f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI10_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI10_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <4 x float> @llvm.vp.floor.v4f32(<4 x float> %va, <4 x i1> %m, i32 %evl)
   ret <4 x float> %v
 }
 
 define <4 x float> @vp_floor_v4f32_unmasked(<4 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v4f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI11_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI11_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <4 x i1> poison, i1 true, i32 0
   %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
   %v = call <4 x float> @llvm.vp.floor.v4f32(<4 x float> %va, <4 x i1> %m, i32 %evl)
   ret <4 x float> %v
 }
 
 declare <8 x float> @llvm.vp.floor.v8f32(<8 x float>, <8 x i1>, i32)
 
 define <8 x float> @vp_floor_v8f32(<8 x float> %va, <8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v8f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI12_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI12_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <8 x float> @llvm.vp.floor.v8f32(<8 x float> %va, <8 x i1> %m, i32 %evl)
   ret <8 x float> %v
 }
 
 define <8 x float> @vp_floor_v8f32_unmasked(<8 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v8f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI13_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI13_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
 ; CHECK-NEXT:    vmset.m v10
-; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <8 x i1> poison, i1 true, i32 0
   %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
   %v = call <8 x float> @llvm.vp.floor.v8f32(<8 x float> %va, <8 x i1> %m, i32 %evl)
   ret <8 x float> %v
 }
 
 declare <16 x float> @llvm.vp.floor.v16f32(<16 x float>, <16 x i1>, i32)
 
 define <16 x float> @vp_floor_v16f32(<16 x float> %va, <16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v16f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI14_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI14_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <16 x float> @llvm.vp.floor.v16f32(<16 x float> %va, <16 x i1> %m, i32 %evl)
   ret <16 x float> %v
 }
 
 define <16 x float> @vp_floor_v16f32_unmasked(<16 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v16f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI15_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI15_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vmset.m v12
-; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <16 x i1> poison, i1 true, i32 0
   %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
   %v = call <16 x float> @llvm.vp.floor.v16f32(<16 x float> %va, <16 x i1> %m, i32 %evl)
   ret <16 x float> %v
 }
 
 declare <2 x double> @llvm.vp.floor.v2f64(<2 x double>, <2 x i1>, i32)
 
 define <2 x double> @vp_floor_v2f64(<2 x double> %va, <2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v2f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI16_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI16_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <2 x double> @llvm.vp.floor.v2f64(<2 x double> %va, <2 x i1> %m, i32 %evl)
   ret <2 x double> %v
 }
 
 define <2 x double> @vp_floor_v2f64_unmasked(<2 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v2f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI17_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI17_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <2 x i1> poison, i1 true, i32 0
   %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
   %v = call <2 x double> @llvm.vp.floor.v2f64(<2 x double> %va, <2 x i1> %m, i32 %evl)
   ret <2 x double> %v
 }
 
 declare <4 x double> @llvm.vp.floor.v4f64(<4 x double>, <4 x i1>, i32)
 
 define <4 x double> @vp_floor_v4f64(<4 x double> %va, <4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v4f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI18_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI18_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <4 x double> @llvm.vp.floor.v4f64(<4 x double> %va, <4 x i1> %m, i32 %evl)
   ret <4 x double> %v
 }
 
 define <4 x double> @vp_floor_v4f64_unmasked(<4 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v4f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI19_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI19_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
 ; CHECK-NEXT:    vmset.m v10
-; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <4 x i1> poison, i1 true, i32 0
   %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
   %v = call <4 x double> @llvm.vp.floor.v4f64(<4 x double> %va, <4 x i1> %m, i32 %evl)
   ret <4 x double> %v
 }
 
 declare <8 x double> @llvm.vp.floor.v8f64(<8 x double>, <8 x i1>, i32)
 
 define <8 x double> @vp_floor_v8f64(<8 x double> %va, <8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v8f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI20_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI20_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <8 x double> @llvm.vp.floor.v8f64(<8 x double> %va, <8 x i1> %m, i32 %evl)
   ret <8 x double> %v
 }
 
 define <8 x double> @vp_floor_v8f64_unmasked(<8 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v8f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI21_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI21_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
 ; CHECK-NEXT:    vmset.m v12
-; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <8 x i1> poison, i1 true, i32 0
   %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
   %v = call <8 x double> @llvm.vp.floor.v8f64(<8 x double> %va, <8 x i1> %m, i32 %evl)
   ret <8 x double> %v
 }
 
 declare <15 x double> @llvm.vp.floor.v15f64(<15 x double>, <15 x i1>, i32)
 
 define <15 x double> @vp_floor_v15f64(<15 x double> %va, <15 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v15f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI22_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI22_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <15 x double> @llvm.vp.floor.v15f64(<15 x double> %va, <15 x i1> %m, i32 %evl)
   ret <15 x double> %v
 }
 
 define <15 x double> @vp_floor_v15f64_unmasked(<15 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v15f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI23_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI23_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vmset.m v16
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <15 x i1> poison, i1 true, i32 0
   %m = shufflevector <15 x i1> %head, <15 x i1> poison, <15 x i32> zeroinitializer
   %v = call <15 x double> @llvm.vp.floor.v15f64(<15 x double> %va, <15 x i1> %m, i32 %evl)
   ret <15 x double> %v
 }
 
 declare <16 x double> @llvm.vp.floor.v16f64(<16 x double>, <16 x i1>, i32)
 
 define <16 x double> @vp_floor_v16f64(<16 x double> %va, <16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v16f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI24_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI24_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <16 x double> @llvm.vp.floor.v16f64(<16 x double> %va, <16 x i1> %m, i32 %evl)
   ret <16 x double> %v
 }
 
 define <16 x double> @vp_floor_v16f64_unmasked(<16 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v16f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI25_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI25_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vmset.m v16
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <16 x i1> poison, i1 true, i32 0
   %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
   %v = call <16 x double> @llvm.vp.floor.v16f64(<16 x double> %va, <16 x i1> %m, i32 %evl)
   ret <16 x double> %v
 }
 
 declare <32 x double> @llvm.vp.floor.v32f64(<32 x double>, <32 x i1>, i32)
 
 define <32 x double> @vp_floor_v32f64(<32 x double> %va, <32 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v32f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    slli a1, a1, 4
-; CHECK-NEXT:    sub sp, sp, a1
-; CHECK-NEXT:    vmv1r.v v24, v0
-; CHECK-NEXT:    addi a1, sp, 16
-; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT:    vmv1r.v v1, v0
 ; CHECK-NEXT:    li a1, 0
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf4, ta, ma
 ; CHECK-NEXT:    addi a2, a0, -16
-; CHECK-NEXT:    vslidedown.vi v25, v0, 2
+; CHECK-NEXT:    vslidedown.vi v2, v0, 2
 ; CHECK-NEXT:    bltu a0, a2, .LBB26_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    mv a1, a2
 ; CHECK-NEXT:  .LBB26_2:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a2, vlenb
+; CHECK-NEXT:    slli a2, a2, 3
+; CHECK-NEXT:    sub sp, sp, a2
 ; CHECK-NEXT:    lui a2, %hi(.LCPI26_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI26_0)(a2)
-; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfabs.v v8, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v25, v8, ft0, v0.t
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfabs.v v24, v16, v0.t
+; CHECK-NEXT:    vmflt.vf v2, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a1, 2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfcvt.x.f.v v8, v16, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
 ; CHECK-NEXT:    fsrm a1
-; CHECK-NEXT:    vfcvt.f.x.v v8, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    addi a1, sp, 16
+; CHECK-NEXT:    vs8r.v v24, (a1) # Unknown-size Folded Spill
 ; CHECK-NEXT:    li a1, 16
-; CHECK-NEXT:    vfsgnj.vv v16, v8, v16, v0.t
-; CHECK-NEXT:    csrr a2, vlenb
-; CHECK-NEXT:    slli a2, a2, 3
-; CHECK-NEXT:    add a2, sp, a2
-; CHECK-NEXT:    addi a2, a2, 16
+; CHECK-NEXT:    addi a2, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a2) # Unknown-size Folded Reload
+; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
+; CHECK-NEXT:    addi a2, sp, 16
 ; CHECK-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
 ; CHECK-NEXT:    bltu a0, a1, .LBB26_4
 ; CHECK-NEXT:  # %bb.3:
 ; CHECK-NEXT:    li a0, 16
 ; CHECK-NEXT:  .LBB26_4:
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vl8re8.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v24, v16, ft0, v0.t
+; CHECK-NEXT:    vmflt.vf v1, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
+; CHECK-NEXT:    vmv1r.v v0, v1
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    add a0, sp, a0
-; CHECK-NEXT:    addi a0, a0, 16
+; CHECK-NEXT:    addi a0, sp, 16
 ; CHECK-NEXT:    vl8re8.v v16, (a0) # Unknown-size Folded Reload
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 4
+; CHECK-NEXT:    slli a0, a0, 3
 ; CHECK-NEXT:    add sp, sp, a0
 ; CHECK-NEXT:    addi sp, sp, 16
 ; CHECK-NEXT:    ret
   %v = call <32 x double> @llvm.vp.floor.v32f64(<32 x double> %va, <32 x i1> %m, i32 %evl)
   ret <32 x double> %v
 }
 
 define <32 x double> @vp_floor_v32f64_unmasked(<32 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_v32f64_unmasked:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    slli a1, a1, 4
-; CHECK-NEXT:    sub sp, sp, a1
-; CHECK-NEXT:    addi a1, sp, 16
-; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
 ; CHECK-NEXT:    li a1, 0
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    addi a2, a0, -16
-; CHECK-NEXT:    vmset.m v24
+; CHECK-NEXT:    vmset.m v1
 ; CHECK-NEXT:    bltu a0, a2, .LBB27_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    mv a1, a2
 ; CHECK-NEXT:  .LBB27_2:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a2, vlenb
+; CHECK-NEXT:    slli a2, a2, 3
+; CHECK-NEXT:    sub sp, sp, a2
 ; CHECK-NEXT:    lui a2, %hi(.LCPI27_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI27_0)(a2)
-; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    vfabs.v v8, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmv1r.v v25, v24
-; CHECK-NEXT:    vmflt.vf v25, v8, ft0, v0.t
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    vfabs.v v24, v16, v0.t
+; CHECK-NEXT:    vmv1r.v v2, v1
+; CHECK-NEXT:    vmflt.vf v2, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a1, 2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfcvt.x.f.v v8, v16, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
 ; CHECK-NEXT:    fsrm a1
-; CHECK-NEXT:    vfcvt.f.x.v v8, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    addi a1, sp, 16
+; CHECK-NEXT:    vs8r.v v24, (a1) # Unknown-size Folded Spill
 ; CHECK-NEXT:    li a1, 16
-; CHECK-NEXT:    vfsgnj.vv v16, v8, v16, v0.t
+; CHECK-NEXT:    addi a2, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a2) # Unknown-size Folded Reload
+; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
 ; CHECK-NEXT:    csrr a2, vlenb
 ; CHECK-NEXT:    slli a2, a2, 3
-; CHECK-NEXT:    add a2, sp, a2
-; CHECK-NEXT:    addi a2, a2, 16
-; CHECK-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
+; CHECK-NEXT:    add sp, sp, a2
+; CHECK-NEXT:    addi sp, sp, 16
 ; CHECK-NEXT:    bltu a0, a1, .LBB27_4
 ; CHECK-NEXT:  # %bb.3:
 ; CHECK-NEXT:    li a0, 16
 ; CHECK-NEXT:  .LBB27_4:
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vl8re8.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v24, v16, ft0, v0.t
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    vfabs.v v24, v8, v0.t
+; CHECK-NEXT:    vmflt.vf v1, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
-; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    add a0, sp, a0
-; CHECK-NEXT:    addi a0, a0, 16
-; CHECK-NEXT:    vl8re8.v v16, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 4
-; CHECK-NEXT:    add sp, sp, a0
-; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <32 x i1> poison, i1 true, i32 0
   %m = shufflevector <32 x i1> %head, <32 x i1> poison, <32 x i32> zeroinitializer
   %v = call <32 x double> @llvm.vp.floor.v32f64(<32 x double> %va, <32 x i1> %m, i32 %evl)
   ret <32 x double> %v
 }

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp.ll

; CHECK-NEXT:    ret
   %e = call <2 x double> @llvm.fma.v2f64(<2 x double> %neg, <2 x double> %a, <2 x double> %neg2)
   store <2 x double> %e, <2 x double>* %x
   ret void
 }
 
 define void @trunc_v8f16(<8 x half>* %x) {
 ; CHECK-LABEL: trunc_v8f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
 ; CHECK-NEXT:    vle16.v v8, (a0)
 ; CHECK-NEXT:    lui a1, %hi(.LCPI91_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI91_0)(a1)
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    vfcvt.rtz.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    vse16.v v8, (a0)
 ; CHECK-NEXT:    ret
   %a = load <8 x half>, <8 x half>* %x
   %b = call <8 x half> @llvm.trunc.v8f16(<8 x half> %a)
   store <8 x half> %b, <8 x half>* %x
   ret void
 }
 declare <8 x half> @llvm.trunc.v8f16(<8 x half>)
 
 define void @trunc_v4f32(<4 x float>* %x) {
 ; CHECK-LABEL: trunc_v4f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
 ; CHECK-NEXT:    vle32.v v8, (a0)
 ; CHECK-NEXT:    lui a1, %hi(.LCPI92_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI92_0)(a1)
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    vfcvt.rtz.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    vse32.v v8, (a0)
 ; CHECK-NEXT:    ret
   %a = load <4 x float>, <4 x float>* %x
   %b = call <4 x float> @llvm.trunc.v4f32(<4 x float> %a)
   store <4 x float> %b, <4 x float>* %x
   ret void
 }
 declare <4 x float> @llvm.trunc.v4f32(<4 x float>)
 
 define void @trunc_v2f64(<2 x double>* %x) {
 ; CHECK-LABEL: trunc_v2f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 2, e64, m1, ta, mu
 ; CHECK-NEXT:    vle64.v v8, (a0)
 ; CHECK-NEXT:    lui a1, %hi(.LCPI93_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI93_0)(a1)
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    vfcvt.rtz.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    vse64.v v8, (a0)
 ; CHECK-NEXT:    ret
   %a = load <2 x double>, <2 x double>* %x
   %b = call <2 x double> @llvm.trunc.v2f64(<2 x double> %a)
   store <2 x double> %b, <2 x double>* %x
   ret void
 }
 declare <2 x double> @llvm.trunc.v2f64(<2 x double>)
 
 define void @ceil_v8f16(<8 x half>* %x) {
 ; CHECK-LABEL: ceil_v8f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
 ; CHECK-NEXT:    vle16.v v8, (a0)
 ; CHECK-NEXT:    lui a1, %hi(.LCPI94_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI94_0)(a1)
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a1, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a1
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    vse16.v v8, (a0)
 ; CHECK-NEXT:    ret
   %a = load <8 x half>, <8 x half>* %x
   %b = call <8 x half> @llvm.ceil.v8f16(<8 x half> %a)
   store <8 x half> %b, <8 x half>* %x
   ret void
 }
 declare <8 x half> @llvm.ceil.v8f16(<8 x half>)
 
 define void @ceil_v4f32(<4 x float>* %x) {
 ; CHECK-LABEL: ceil_v4f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
 ; CHECK-NEXT:    vle32.v v8, (a0)
 ; CHECK-NEXT:    lui a1, %hi(.LCPI95_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI95_0)(a1)
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a1, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a1
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    vse32.v v8, (a0)
 ; CHECK-NEXT:    ret
   %a = load <4 x float>, <4 x float>* %x
   %b = call <4 x float> @llvm.ceil.v4f32(<4 x float> %a)
   store <4 x float> %b, <4 x float>* %x
   ret void
 }
 declare <4 x float> @llvm.ceil.v4f32(<4 x float>)
 
 define void @ceil_v2f64(<2 x double>* %x) {
 ; CHECK-LABEL: ceil_v2f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 2, e64, m1, ta, mu
 ; CHECK-NEXT:    vle64.v v8, (a0)
 ; CHECK-NEXT:    lui a1, %hi(.LCPI96_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI96_0)(a1)
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a1, 3
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a1
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    vse64.v v8, (a0)
 ; CHECK-NEXT:    ret
   %a = load <2 x double>, <2 x double>* %x
   %b = call <2 x double> @llvm.ceil.v2f64(<2 x double> %a)
   store <2 x double> %b, <2 x double>* %x
   ret void
 }
 declare <2 x double> @llvm.ceil.v2f64(<2 x double>)
 
 define void @floor_v8f16(<8 x half>* %x) {
 ; CHECK-LABEL: floor_v8f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
 ; CHECK-NEXT:    vle16.v v8, (a0)
 ; CHECK-NEXT:    lui a1, %hi(.LCPI97_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI97_0)(a1)
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a1, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a1
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    vse16.v v8, (a0)
 ; CHECK-NEXT:    ret
   %a = load <8 x half>, <8 x half>* %x
   %b = call <8 x half> @llvm.floor.v8f16(<8 x half> %a)
   store <8 x half> %b, <8 x half>* %x
   ret void
 }
 declare <8 x half> @llvm.floor.v8f16(<8 x half>)
 
 define void @floor_v4f32(<4 x float>* %x) {
 ; CHECK-LABEL: floor_v4f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
 ; CHECK-NEXT:    vle32.v v8, (a0)
 ; CHECK-NEXT:    lui a1, %hi(.LCPI98_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI98_0)(a1)
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a1, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a1
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    vse32.v v8, (a0)
 ; CHECK-NEXT:    ret
   %a = load <4 x float>, <4 x float>* %x
   %b = call <4 x float> @llvm.floor.v4f32(<4 x float> %a)
   store <4 x float> %b, <4 x float>* %x
   ret void
 }
 declare <4 x float> @llvm.floor.v4f32(<4 x float>)
 
 define void @floor_v2f64(<2 x double>* %x) {
 ; CHECK-LABEL: floor_v2f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 2, e64, m1, ta, mu
 ; CHECK-NEXT:    vle64.v v8, (a0)
 ; CHECK-NEXT:    lui a1, %hi(.LCPI99_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI99_0)(a1)
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a1, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a1
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    vse64.v v8, (a0)
 ; CHECK-NEXT:    ret
   %a = load <2 x double>, <2 x double>* %x
   %b = call <2 x double> @llvm.floor.v2f64(<2 x double> %a)
   store <2 x double> %b, <2 x double>* %x
   ret void
 }
 declare <2 x double> @llvm.floor.v2f64(<2 x double>)
 
 define void @round_v8f16(<8 x half>* %x) {
 ; CHECK-LABEL: round_v8f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
 ; CHECK-NEXT:    vle16.v v8, (a0)
 ; CHECK-NEXT:    lui a1, %hi(.LCPI100_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI100_0)(a1)
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a1, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a1
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    vse16.v v8, (a0)
 ; CHECK-NEXT:    ret
   %a = load <8 x half>, <8 x half>* %x
   %b = call <8 x half> @llvm.round.v8f16(<8 x half> %a)
   store <8 x half> %b, <8 x half>* %x
   ret void
 }
 declare <8 x half> @llvm.round.v8f16(<8 x half>)
 
 define void @round_v4f32(<4 x float>* %x) {
 ; CHECK-LABEL: round_v4f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
 ; CHECK-NEXT:    vle32.v v8, (a0)
 ; CHECK-NEXT:    lui a1, %hi(.LCPI101_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI101_0)(a1)
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a1, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a1
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    vse32.v v8, (a0)
 ; CHECK-NEXT:    ret
   %a = load <4 x float>, <4 x float>* %x
   %b = call <4 x float> @llvm.round.v4f32(<4 x float> %a)
   store <4 x float> %b, <4 x float>* %x
   ret void
 }
 declare <4 x float> @llvm.round.v4f32(<4 x float>)
 
 define void @round_v2f64(<2 x double>* %x) {
 ; CHECK-LABEL: round_v2f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 2, e64, m1, ta, mu
 ; CHECK-NEXT:    vle64.v v8, (a0)
 ; CHECK-NEXT:    lui a1, %hi(.LCPI102_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI102_0)(a1)
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a1, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a1
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    vse64.v v8, (a0)
 ; CHECK-NEXT:    ret
   %a = load <2 x double>, <2 x double>* %x
   %b = call <2 x double> @llvm.round.v2f64(<2 x double> %a)
   store <2 x double> %b, <2 x double>* %x
   ret void
 }

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp2i-sat.ll

 ; RV32-NEXT:    fmin.d ft1, ft1, ft0
 ; RV32-NEXT:    fcvt.wu.d a0, ft1, rtz
 ; RV32-NEXT:    vsetivli zero, 1, e64, m1, ta, ma
 ; RV32-NEXT:    vslidedown.vi v8, v8, 1
 ; RV32-NEXT:    vfmv.f.s ft1, v8
 ; RV32-NEXT:    fmax.d ft1, ft1, ft2
 ; RV32-NEXT:    fmin.d ft0, ft1, ft0
 ; RV32-NEXT:    fcvt.wu.d a2, ft0, rtz
-; RV32-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
+; RV32-NEXT:    vsetivli zero, 2, e8, mf8, tu, ma
 ; RV32-NEXT:    vmv.v.x v8, a2
-; RV32-NEXT:    vsetvli zero, zero, e8, mf8, tu, ma
 ; RV32-NEXT:    vmv.s.x v8, a0
 ; RV32-NEXT:    vse8.v v8, (a1)
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: fp2ui_v2f64_v2i8:
 ; RV64:       # %bb.0:
 ; RV64-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
 ; RV64-NEXT:    vle64.v v8, (a0)
 ; RV64-NEXT:    lui a0, %hi(.LCPI11_0)
 ; RV64-NEXT:    fld ft0, %lo(.LCPI11_0)(a0)
 ; RV64-NEXT:    vfmv.f.s ft1, v8
 ; RV64-NEXT:    fmv.d.x ft2, zero
 ; RV64-NEXT:    fmax.d ft1, ft1, ft2
 ; RV64-NEXT:    fmin.d ft1, ft1, ft0
 ; RV64-NEXT:    fcvt.lu.d a0, ft1, rtz
 ; RV64-NEXT:    vsetivli zero, 1, e64, m1, ta, ma
 ; RV64-NEXT:    vslidedown.vi v8, v8, 1
 ; RV64-NEXT:    vfmv.f.s ft1, v8
 ; RV64-NEXT:    fmax.d ft1, ft1, ft2
 ; RV64-NEXT:    fmin.d ft0, ft1, ft0
 ; RV64-NEXT:    fcvt.lu.d a2, ft0, rtz
-; RV64-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
+; RV64-NEXT:    vsetivli zero, 2, e8, mf8, tu, ma
 ; RV64-NEXT:    vmv.v.x v8, a2
-; RV64-NEXT:    vsetvli zero, zero, e8, mf8, tu, ma
 ; RV64-NEXT:    vmv.s.x v8, a0
 ; RV64-NEXT:    vse8.v v8, (a1)
 ; RV64-NEXT:    ret
   %a = load <2 x double>, <2 x double>* %x
   %d = call <2 x i8> @llvm.fptoui.sat.v2i8.v2f64(<2 x double> %a)
   store <2 x i8> %d, <2 x i8>* %y
   ret void
 }

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp2i.ll

 ; LMULMAX1-NEXT:    vfncvt.rtz.x.f.w v10, v9
 ; LMULMAX1-NEXT:    vand.vi v9, v10, 1
 ; LMULMAX1-NEXT:    vmsne.vi v0, v9, 0
 ; LMULMAX1-NEXT:    vsetvli zero, zero, e8, mf4, ta, ma
 ; LMULMAX1-NEXT:    vmv.v.i v9, 0
 ; LMULMAX1-NEXT:    vmerge.vim v9, v9, 1, v0
 ; LMULMAX1-NEXT:    vsetivli zero, 8, e8, mf2, tu, ma
 ; LMULMAX1-NEXT:    vslideup.vi v8, v9, 4
-; LMULMAX1-NEXT:    vsetvli zero, zero, e8, mf2, ta, ma
 ; LMULMAX1-NEXT:    vmsne.vi v0, v8, 0
 ; LMULMAX1-NEXT:    ret
   %z = fptosi <8 x float> %x to <8 x i1>
   ret <8 x i1> %z
 }
 
 define <8 x i1> @fp2ui_v8f32_v8i1(<8 x float> %x) {
 ; LMULMAX8-LABEL: fp2ui_v8f32_v8i1:

 ; LMULMAX1-NEXT:    vfncvt.rtz.xu.f.w v10, v9
 ; LMULMAX1-NEXT:    vand.vi v9, v10, 1
 ; LMULMAX1-NEXT:    vmsne.vi v0, v9, 0
 ; LMULMAX1-NEXT:    vsetvli zero, zero, e8, mf4, ta, ma
 ; LMULMAX1-NEXT:    vmv.v.i v9, 0
 ; LMULMAX1-NEXT:    vmerge.vim v9, v9, 1, v0
 ; LMULMAX1-NEXT:    vsetivli zero, 8, e8, mf2, tu, ma
 ; LMULMAX1-NEXT:    vslideup.vi v8, v9, 4
-; LMULMAX1-NEXT:    vsetvli zero, zero, e8, mf2, ta, ma
 ; LMULMAX1-NEXT:    vmsne.vi v0, v8, 0
 ; LMULMAX1-NEXT:    ret
   %z = fptoui <8 x float> %x to <8 x i1>
   ret <8 x i1> %z
 }
 
 define void @fp2si_v2f32_v2i64(<2 x float>* %x, <2 x i64>* %y) {
 ; CHECK-LABEL: fp2si_v2f32_v2i64:

 ; LMULMAX1-NEXT:    vsetivli zero, 2, e32, mf2, ta, ma
 ; LMULMAX1-NEXT:    vfncvt.rtz.x.f.w v10, v11
 ; LMULMAX1-NEXT:    vand.vi v10, v10, 1
 ; LMULMAX1-NEXT:    vmsne.vi v0, v10, 0
 ; LMULMAX1-NEXT:    vsetvli zero, zero, e8, mf8, ta, ma
 ; LMULMAX1-NEXT:    vmerge.vim v9, v9, 1, v0
 ; LMULMAX1-NEXT:    vsetivli zero, 8, e8, mf2, tu, ma
 ; LMULMAX1-NEXT:    vslideup.vi v8, v9, 6
-; LMULMAX1-NEXT:    vsetvli zero, zero, e8, mf2, ta, ma
 ; LMULMAX1-NEXT:    vmsne.vi v0, v8, 0
 ; LMULMAX1-NEXT:    ret
   %z = fptosi <8 x double> %x to <8 x i1>
   ret <8 x i1> %z
 }
 
 define <8 x i1> @fp2ui_v8f64_v8i1(<8 x double> %x) {
 ; LMULMAX8-LABEL: fp2ui_v8f64_v8i1:

 ; LMULMAX1-NEXT:    vsetivli zero, 2, e32, mf2, ta, ma
 ; LMULMAX1-NEXT:    vfncvt.rtz.xu.f.w v10, v11
 ; LMULMAX1-NEXT:    vand.vi v10, v10, 1
 ; LMULMAX1-NEXT:    vmsne.vi v0, v10, 0
 ; LMULMAX1-NEXT:    vsetvli zero, zero, e8, mf8, ta, ma
 ; LMULMAX1-NEXT:    vmerge.vim v9, v9, 1, v0
 ; LMULMAX1-NEXT:    vsetivli zero, 8, e8, mf2, tu, ma
 ; LMULMAX1-NEXT:    vslideup.vi v8, v9, 6
-; LMULMAX1-NEXT:    vsetvli zero, zero, e8, mf2, ta, ma
 ; LMULMAX1-NEXT:    vmsne.vi v0, v8, 0
 ; LMULMAX1-NEXT:    ret
   %z = fptoui <8 x double> %x to <8 x i1>
   ret <8 x i1> %z
 }

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fround.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=ilp32d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=lp64d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 
 ; This file tests the code generation for `llvm.round.*` on fixed vector type.
 
 define <1 x half> @round_v1f16(<1 x half> %x) {
 ; CHECK-LABEL: round_v1f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI0_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI0_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 1, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetivli zero, 1, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <1 x half> @llvm.round.v1f16(<1 x half> %x)
   ret <1 x half> %a
 }
 declare <1 x half> @llvm.round.v1f16(<1 x half>)
 
 define <2 x half> @round_v2f16(<2 x half> %x) {
 ; CHECK-LABEL: round_v2f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI1_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI1_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 2, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetivli zero, 2, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <2 x half> @llvm.round.v2f16(<2 x half> %x)
   ret <2 x half> %a
 }
 declare <2 x half> @llvm.round.v2f16(<2 x half>)
 
 define <4 x half> @round_v4f16(<4 x half> %x) {
 ; CHECK-LABEL: round_v4f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI2_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI2_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <4 x half> @llvm.round.v4f16(<4 x half> %x)
   ret <4 x half> %a
 }
 declare <4 x half> @llvm.round.v4f16(<4 x half>)
 
 define <8 x half> @round_v8f16(<8 x half> %x) {
 ; CHECK-LABEL: round_v8f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI3_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI3_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <8 x half> @llvm.round.v8f16(<8 x half> %x)
   ret <8 x half> %a
 }
 declare <8 x half> @llvm.round.v8f16(<8 x half>)
 
 define <16 x half> @round_v16f16(<16 x half> %x) {
 ; CHECK-LABEL: round_v16f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI4_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI4_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 16, e16, m2, ta, ma
+; CHECK-NEXT:    vsetivli zero, 16, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <16 x half> @llvm.round.v16f16(<16 x half> %x)
   ret <16 x half> %a
 }
 declare <16 x half> @llvm.round.v16f16(<16 x half>)
 
 define <32 x half> @round_v32f16(<32 x half> %x) {
 ; CHECK-LABEL: round_v32f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI5_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI5_0)(a0)
 ; CHECK-NEXT:    li a0, 32
-; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <32 x half> @llvm.round.v32f16(<32 x half> %x)
   ret <32 x half> %a
 }
 declare <32 x half> @llvm.round.v32f16(<32 x half>)
 
 define <1 x float> @round_v1f32(<1 x float> %x) {
 ; CHECK-LABEL: round_v1f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI6_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI6_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 1, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetivli zero, 1, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <1 x float> @llvm.round.v1f32(<1 x float> %x)
   ret <1 x float> %a
 }
 declare <1 x float> @llvm.round.v1f32(<1 x float>)
 
 define <2 x float> @round_v2f32(<2 x float> %x) {
 ; CHECK-LABEL: round_v2f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI7_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI7_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <2 x float> @llvm.round.v2f32(<2 x float> %x)
   ret <2 x float> %a
 }
 declare <2 x float> @llvm.round.v2f32(<2 x float>)
 
 define <4 x float> @round_v4f32(<4 x float> %x) {
 ; CHECK-LABEL: round_v4f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI8_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI8_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <4 x float> @llvm.round.v4f32(<4 x float> %x)
   ret <4 x float> %a
 }
 declare <4 x float> @llvm.round.v4f32(<4 x float>)
 
 define <8 x float> @round_v8f32(<8 x float> %x) {
 ; CHECK-LABEL: round_v8f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI9_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI9_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 8, e32, m2, ta, ma
+; CHECK-NEXT:    vsetivli zero, 8, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <8 x float> @llvm.round.v8f32(<8 x float> %x)
   ret <8 x float> %a
 }
 declare <8 x float> @llvm.round.v8f32(<8 x float>)
 
 define <16 x float> @round_v16f32(<16 x float> %x) {
 ; CHECK-LABEL: round_v16f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI10_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI10_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 16, e32, m4, ta, ma
+; CHECK-NEXT:    vsetivli zero, 16, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <16 x float> @llvm.round.v16f32(<16 x float> %x)
   ret <16 x float> %a
 }
 declare <16 x float> @llvm.round.v16f32(<16 x float>)
 
 define <1 x double> @round_v1f64(<1 x double> %x) {
 ; CHECK-LABEL: round_v1f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI11_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI11_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 1, e64, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 1, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <1 x double> @llvm.round.v1f64(<1 x double> %x)
   ret <1 x double> %a
 }
 declare <1 x double> @llvm.round.v1f64(<1 x double>)
 
 define <2 x double> @round_v2f64(<2 x double> %x) {
 ; CHECK-LABEL: round_v2f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI12_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI12_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 2, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <2 x double> @llvm.round.v2f64(<2 x double> %x)
   ret <2 x double> %a
 }
 declare <2 x double> @llvm.round.v2f64(<2 x double>)
 
 define <4 x double> @round_v4f64(<4 x double> %x) {
 ; CHECK-LABEL: round_v4f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI13_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI13_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 4, e64, m2, ta, ma
+; CHECK-NEXT:    vsetivli zero, 4, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <4 x double> @llvm.round.v4f64(<4 x double> %x)
   ret <4 x double> %a
 }
 declare <4 x double> @llvm.round.v4f64(<4 x double>)
 
 define <8 x double> @round_v8f64(<8 x double> %x) {
 ; CHECK-LABEL: round_v8f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI14_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI14_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 8, e64, m4, ta, ma
+; CHECK-NEXT:    vsetivli zero, 8, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <8 x double> @llvm.round.v8f64(<8 x double> %x)
   ret <8 x double> %a
 }
 declare <8 x double> @llvm.round.v8f64(<8 x double>)

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-froundeven.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=ilp32d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=lp64d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 
 ; This file tests the code generation for `llvm.roundeven.*` on fixed vector type.
 
 define <1 x half> @roundeven_v1f16(<1 x half> %x) {
 ; CHECK-LABEL: roundeven_v1f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI0_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI0_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 1, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetivli zero, 1, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <1 x half> @llvm.roundeven.v1f16(<1 x half> %x)
   ret <1 x half> %a
 }
 declare <1 x half> @llvm.roundeven.v1f16(<1 x half>)
 
 define <2 x half> @roundeven_v2f16(<2 x half> %x) {
 ; CHECK-LABEL: roundeven_v2f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI1_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI1_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 2, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetivli zero, 2, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <2 x half> @llvm.roundeven.v2f16(<2 x half> %x)
   ret <2 x half> %a
 }
 declare <2 x half> @llvm.roundeven.v2f16(<2 x half>)
 
 define <4 x half> @roundeven_v4f16(<4 x half> %x) {
 ; CHECK-LABEL: roundeven_v4f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI2_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI2_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <4 x half> @llvm.roundeven.v4f16(<4 x half> %x)
   ret <4 x half> %a
 }
 declare <4 x half> @llvm.roundeven.v4f16(<4 x half>)
 
 define <8 x half> @roundeven_v8f16(<8 x half> %x) {
 ; CHECK-LABEL: roundeven_v8f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI3_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI3_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <8 x half> @llvm.roundeven.v8f16(<8 x half> %x)
   ret <8 x half> %a
 }
 declare <8 x half> @llvm.roundeven.v8f16(<8 x half>)
 
 define <16 x half> @roundeven_v16f16(<16 x half> %x) {
 ; CHECK-LABEL: roundeven_v16f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI4_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI4_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 16, e16, m2, ta, ma
+; CHECK-NEXT:    vsetivli zero, 16, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <16 x half> @llvm.roundeven.v16f16(<16 x half> %x)
   ret <16 x half> %a
 }
 declare <16 x half> @llvm.roundeven.v16f16(<16 x half>)
 
 define <32 x half> @roundeven_v32f16(<32 x half> %x) {
 ; CHECK-LABEL: roundeven_v32f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI5_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI5_0)(a0)
 ; CHECK-NEXT:    li a0, 32
-; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <32 x half> @llvm.roundeven.v32f16(<32 x half> %x)
   ret <32 x half> %a
 }
 declare <32 x half> @llvm.roundeven.v32f16(<32 x half>)
 
 define <1 x float> @roundeven_v1f32(<1 x float> %x) {
 ; CHECK-LABEL: roundeven_v1f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI6_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI6_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 1, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetivli zero, 1, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <1 x float> @llvm.roundeven.v1f32(<1 x float> %x)
   ret <1 x float> %a
 }
 declare <1 x float> @llvm.roundeven.v1f32(<1 x float>)
 
 define <2 x float> @roundeven_v2f32(<2 x float> %x) {
 ; CHECK-LABEL: roundeven_v2f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI7_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI7_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <2 x float> @llvm.roundeven.v2f32(<2 x float> %x)
   ret <2 x float> %a
 }
 declare <2 x float> @llvm.roundeven.v2f32(<2 x float>)
 
 define <4 x float> @roundeven_v4f32(<4 x float> %x) {
 ; CHECK-LABEL: roundeven_v4f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI8_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI8_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <4 x float> @llvm.roundeven.v4f32(<4 x float> %x)
   ret <4 x float> %a
 }
 declare <4 x float> @llvm.roundeven.v4f32(<4 x float>)
 
 define <8 x float> @roundeven_v8f32(<8 x float> %x) {
 ; CHECK-LABEL: roundeven_v8f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI9_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI9_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 8, e32, m2, ta, ma
+; CHECK-NEXT:    vsetivli zero, 8, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <8 x float> @llvm.roundeven.v8f32(<8 x float> %x)
   ret <8 x float> %a
 }
 declare <8 x float> @llvm.roundeven.v8f32(<8 x float>)
 
 define <16 x float> @roundeven_v16f32(<16 x float> %x) {
 ; CHECK-LABEL: roundeven_v16f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI10_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI10_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 16, e32, m4, ta, ma
+; CHECK-NEXT:    vsetivli zero, 16, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <16 x float> @llvm.roundeven.v16f32(<16 x float> %x)
   ret <16 x float> %a
 }
 declare <16 x float> @llvm.roundeven.v16f32(<16 x float>)
 
 define <1 x double> @roundeven_v1f64(<1 x double> %x) {
 ; CHECK-LABEL: roundeven_v1f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI11_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI11_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 1, e64, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 1, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <1 x double> @llvm.roundeven.v1f64(<1 x double> %x)
   ret <1 x double> %a
 }
 declare <1 x double> @llvm.roundeven.v1f64(<1 x double>)
 
 define <2 x double> @roundeven_v2f64(<2 x double> %x) {
 ; CHECK-LABEL: roundeven_v2f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI12_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI12_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 2, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <2 x double> @llvm.roundeven.v2f64(<2 x double> %x)
   ret <2 x double> %a
 }
 declare <2 x double> @llvm.roundeven.v2f64(<2 x double>)
 
 define <4 x double> @roundeven_v4f64(<4 x double> %x) {
 ; CHECK-LABEL: roundeven_v4f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI13_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI13_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 4, e64, m2, ta, ma
+; CHECK-NEXT:    vsetivli zero, 4, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <4 x double> @llvm.roundeven.v4f64(<4 x double> %x)
   ret <4 x double> %a
 }
 declare <4 x double> @llvm.roundeven.v4f64(<4 x double>)
 
 define <8 x double> @roundeven_v8f64(<8 x double> %x) {
 ; CHECK-LABEL: roundeven_v8f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI14_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI14_0)(a0)
-; CHECK-NEXT:    vsetivli zero, 8, e64, m4, ta, ma
+; CHECK-NEXT:    vsetivli zero, 8, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <8 x double> @llvm.roundeven.v8f64(<8 x double> %x)
   ret <8 x double> %a
 }
 declare <8 x double> @llvm.roundeven.v8f64(<8 x double>)

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-insert-i1.ll

 ; CHECK-LABEL: insertelt_v2i1:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
 ; CHECK-NEXT:    vmv.s.x v8, a0
 ; CHECK-NEXT:    vmv.v.i v9, 0
 ; CHECK-NEXT:    vmerge.vim v9, v9, 1, v0
 ; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, tu, ma
 ; CHECK-NEXT:    vslideup.vi v9, v8, 1
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, ta, ma
 ; CHECK-NEXT:    vand.vi v8, v9, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %y = insertelement <2 x i1> %x, i1 %elt, i64 1
   ret <2 x i1> %y
 }
 
 define <2 x i1> @insertelt_idx_v2i1(<2 x i1> %x, i1 %elt, i32 zeroext %idx) nounwind {

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-insert-subvector.ll

; CHECK-NEXT:    ret
   ret void
 }
 
 define void @insert_v4i32_v2i32_2(<4 x i32>* %vp, <2 x i32>* %svp) {
 ; CHECK-LABEL: insert_v4i32_v2i32_2:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, ma
 ; CHECK-NEXT:    vle32.v v8, (a1)
-; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, tu, ma
 ; CHECK-NEXT:    vle32.v v9, (a0)
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, tu, ma
 ; CHECK-NEXT:    vslideup.vi v9, v8, 2
 ; CHECK-NEXT:    vse32.v v9, (a0)
 ; CHECK-NEXT:    ret
   %sv = load <2 x i32>, <2 x i32>* %svp
   %vec = load <4 x i32>, <4 x i32>* %vp
   %v = call <4 x i32> @llvm.vector.insert.v2i32.v4i32(<4 x i32> %vec, <2 x i32> %sv, i64 2)
   store <4 x i32> %v, <4 x i32>* %vp
   ret void

 ; LMULMAX2-NEXT:    vsetivli zero, 8, e32, m2, ta, ma
 ; LMULMAX2-NEXT:    vse32.v v10, (a0)
 ; LMULMAX2-NEXT:    ret
 ;
 ; LMULMAX1-LABEL: insert_v8i32_v2i32_2:
 ; LMULMAX1:       # %bb.0:
 ; LMULMAX1-NEXT:    vsetivli zero, 2, e32, mf2, ta, ma
 ; LMULMAX1-NEXT:    vle32.v v8, (a1)
-; LMULMAX1-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; LMULMAX1-NEXT:    vsetivli zero, 4, e32, m1, tu, ma
 ; LMULMAX1-NEXT:    vle32.v v9, (a0)
-; LMULMAX1-NEXT:    vsetvli zero, zero, e32, m1, tu, ma
 ; LMULMAX1-NEXT:    vslideup.vi v9, v8, 2
 ; LMULMAX1-NEXT:    vse32.v v9, (a0)
 ; LMULMAX1-NEXT:    ret
   %sv = load <2 x i32>, <2 x i32>* %svp
   %vec = load <8 x i32>, <8 x i32>* %vp
   %v = call <8 x i32> @llvm.vector.insert.v2i32.v8i32(<8 x i32> %vec, <2 x i32> %sv, i64 2)
   store <8 x i32> %v, <8 x i32>* %vp
   ret void
 }
 
 define void @insert_v8i32_v2i32_6(<8 x i32>* %vp, <2 x i32>* %svp) {
 ; LMULMAX2-LABEL: insert_v8i32_v2i32_6:
 ; LMULMAX2:       # %bb.0:
 ; LMULMAX2-NEXT:    vsetivli zero, 2, e32, mf2, ta, ma
 ; LMULMAX2-NEXT:    vle32.v v8, (a1)
-; LMULMAX2-NEXT:    vsetivli zero, 8, e32, m2, ta, ma
+; LMULMAX2-NEXT:    vsetivli zero, 8, e32, m2, tu, ma
 ; LMULMAX2-NEXT:    vle32.v v10, (a0)
-; LMULMAX2-NEXT:    vsetvli zero, zero, e32, m2, tu, ma
 ; LMULMAX2-NEXT:    vslideup.vi v10, v8, 6
 ; LMULMAX2-NEXT:    vse32.v v10, (a0)
 ; LMULMAX2-NEXT:    ret
 ;
 ; LMULMAX1-LABEL: insert_v8i32_v2i32_6:
 ; LMULMAX1:       # %bb.0:
 ; LMULMAX1-NEXT:    vsetivli zero, 2, e32, mf2, ta, ma
 ; LMULMAX1-NEXT:    vle32.v v8, (a1)
 ; LMULMAX1-NEXT:    addi a0, a0, 16
-; LMULMAX1-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; LMULMAX1-NEXT:    vsetivli zero, 4, e32, m1, tu, ma
 ; LMULMAX1-NEXT:    vle32.v v9, (a0)
-; LMULMAX1-NEXT:    vsetvli zero, zero, e32, m1, tu, ma
 ; LMULMAX1-NEXT:    vslideup.vi v9, v8, 2
 ; LMULMAX1-NEXT:    vse32.v v9, (a0)
 ; LMULMAX1-NEXT:    ret
   %sv = load <2 x i32>, <2 x i32>* %svp
   %vec = load <8 x i32>, <8 x i32>* %vp
   %v = call <8 x i32> @llvm.vector.insert.v2i32.v8i32(<8 x i32> %vec, <2 x i32> %sv, i64 6)
   store <8 x i32> %v, <8 x i32>* %vp
   ret void

 ; CHECK-NEXT:    vmv.v.i v9, 0
 ; CHECK-NEXT:    vmerge.vim v9, v9, 1, v0
 ; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
 ; CHECK-NEXT:    vmv.v.i v10, 0
 ; CHECK-NEXT:    vmv1r.v v0, v8
 ; CHECK-NEXT:    vmerge.vim v8, v10, 1, v0
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, tu, ma
 ; CHECK-NEXT:    vslideup.vi v9, v8, 4
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf2, ta, ma
 ; CHECK-NEXT:    vmsne.vi v8, v9, 0
 ; CHECK-NEXT:    vsm.v v8, (a0)
 ; CHECK-NEXT:    ret
   %v = load <8 x i1>, <8 x i1>* %vp
   %sv = load <4 x i1>, <4 x i1>* %svp
   %c = call <8 x i1> @llvm.vector.insert.v4i1.v8i1(<8 x i1> %v, <4 x i1> %sv, i64 4)
   store <8 x i1> %c, <8 x i1>* %vp
   ret void

 define <vscale x 2 x i1> @insert_nxv2i1_v4i1_0(<vscale x 2 x i1> %v, <4 x i1>* %svp) {
 ; CHECK-LABEL: insert_nxv2i1_v4i1_0:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
 ; CHECK-NEXT:    vlm.v v8, (a0)
 ; CHECK-NEXT:    vsetvli a0, zero, e8, mf4, ta, ma
 ; CHECK-NEXT:    vmv.v.i v9, 0
 ; CHECK-NEXT:    vmerge.vim v9, v9, 1, v0
-; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
+; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, tu, ma
 ; CHECK-NEXT:    vmv.v.i v10, 0
 ; CHECK-NEXT:    vmv1r.v v0, v8
 ; CHECK-NEXT:    vmerge.vim v8, v10, 1, v0
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf4, tu, ma
 ; CHECK-NEXT:    vslideup.vi v9, v8, 0
 ; CHECK-NEXT:    vsetvli a0, zero, e8, mf4, ta, ma
 ; CHECK-NEXT:    vmsne.vi v0, v9, 0
 ; CHECK-NEXT:    ret
   %sv = load <4 x i1>, <4 x i1>* %svp
   %c = call <vscale x 2 x i1> @llvm.vector.insert.v4i1.nxv2i1(<vscale x 2 x i1> %v, <4 x i1> %sv, i64 0)
   ret <vscale x 2 x i1> %c
 }

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-insert.ll

 ; this test was written.
 define void @insertelt_v3i64(<3 x i64>* %x, i64 %y) {
 ; RV32-LABEL: insertelt_v3i64:
 ; RV32:       # %bb.0:
 ; RV32-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
 ; RV32-NEXT:    vle64.v v8, (a0)
 ; RV32-NEXT:    lw a3, 16(a0)
 ; RV32-NEXT:    addi a4, a0, 20
-; RV32-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; RV32-NEXT:    vsetivli zero, 4, e32, m1, tu, ma
 ; RV32-NEXT:    vlse32.v v10, (a4), zero
-; RV32-NEXT:    vsetvli zero, zero, e32, m1, tu, ma
 ; RV32-NEXT:    vmv.s.x v10, a3
 ; RV32-NEXT:    vsetvli zero, zero, e64, m2, tu, ma
 ; RV32-NEXT:    vslideup.vi v8, v10, 2
 ; RV32-NEXT:    vsetivli zero, 2, e32, m2, ta, ma
 ; RV32-NEXT:    vmv.v.i v10, 0
 ; RV32-NEXT:    vslide1up.vx v12, v10, a2
 ; RV32-NEXT:    vslide1up.vx v10, v12, a1
 ; RV32-NEXT:    vsetivli zero, 3, e64, m2, tu, ma
; RV64-NEXT:    ret
   %b = insertelement <8 x float> %a, float %y, i32 %idx
   store <8 x float> %b, <8 x float>* %x
   ret void
 }
 
 define void @insertelt_v8i64_0(<8 x i64>* %x) {
 ; CHECK-LABEL: insertelt_v8i64_0:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 8, e64, m4, ta, ma
+; CHECK-NEXT:    vsetivli zero, 8, e64, m4, tu, ma
 ; CHECK-NEXT:    vle64.v v8, (a0)
 ; CHECK-NEXT:    li a1, -1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, tu, ma
 ; CHECK-NEXT:    vmv.s.x v8, a1
 ; CHECK-NEXT:    vse64.v v8, (a0)
 ; CHECK-NEXT:    ret
   %a = load <8 x i64>, <8 x i64>* %x
   %b = insertelement <8 x i64> %a, i64 -1, i32 0
   store <8 x i64> %b, <8 x i64>* %x
   ret void
 }
; RV64-NEXT:    ret
   %b = insertelement <8 x i64> %a, i64 -1, i32 %idx
   store <8 x i64> %b, <8 x i64>* %x
   ret void
 }
 
 define void @insertelt_c6_v8i64_0(<8 x i64>* %x) {
 ; CHECK-LABEL: insertelt_c6_v8i64_0:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 8, e64, m4, ta, ma
+; CHECK-NEXT:    vsetivli zero, 8, e64, m4, tu, ma
 ; CHECK-NEXT:    vle64.v v8, (a0)
 ; CHECK-NEXT:    li a1, 6
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, tu, ma
 ; CHECK-NEXT:    vmv.s.x v8, a1
 ; CHECK-NEXT:    vse64.v v8, (a0)
 ; CHECK-NEXT:    ret
   %a = load <8 x i64>, <8 x i64>* %x
   %b = insertelement <8 x i64> %a, i64 6, i32 0
   store <8 x i64> %b, <8 x i64>* %x
   ret void
 }
; RV64-NEXT:    ret
   ret void
 }
 
 ; Test that using a insertelement at element 0 by a later operation doesn't
 ; crash the compiler.
 define void @insertelt_c6_v8i64_0_add(<8 x i64>* %x, <8 x i64>* %y) {
 ; CHECK-LABEL: insertelt_c6_v8i64_0_add:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 8, e64, m4, ta, ma
+; CHECK-NEXT:    vsetivli zero, 8, e64, m4, tu, ma
 ; CHECK-NEXT:    vle64.v v8, (a0)
-; CHECK-NEXT:    li a2, 6
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, tu, ma
-; CHECK-NEXT:    vmv.s.x v8, a2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
 ; CHECK-NEXT:    vle64.v v12, (a1)
+; CHECK-NEXT:    li a1, 6
+; CHECK-NEXT:    vmv.s.x v8, a1
 ; CHECK-NEXT:    vadd.vv v8, v8, v12
 ; CHECK-NEXT:    vse64.v v8, (a0)
 ; CHECK-NEXT:    ret
   %a = load <8 x i64>, <8 x i64>* %x
   %b = insertelement <8 x i64> %a, i64 6, i32 0
   %c = load <8 x i64>, <8 x i64>* %y
   %d = add <8 x i64> %b, %c
   store <8 x i64> %d, <8 x i64>* %x
   ret void
 }

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll

 ; RV32-NEXT:    vle32.v v8, (a1)
 ; RV32-NEXT:    vse32.v v8, (a0)
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: buildvec_dominant0_v2i32:
 ; RV64:       # %bb.0:
 ; RV64-NEXT:    lui a1, %hi(.LCPI20_0)
 ; RV64-NEXT:    ld a1, %lo(.LCPI20_0)(a1)
-; RV64-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
+; RV64-NEXT:    vsetivli zero, 2, e64, m1, tu, ma
 ; RV64-NEXT:    vmv.v.i v8, -1
-; RV64-NEXT:    vsetvli zero, zero, e64, m1, tu, ma
 ; RV64-NEXT:    vmv.s.x v8, a1
 ; RV64-NEXT:    vse64.v v8, (a0)
 ; RV64-NEXT:    ret
   store <2 x i64> <i64 2049638230412172402, i64 -1>, <2 x i64>* %x
   ret void
 }
 
 define void @buildvec_dominant1_optsize_v2i32(<2 x i64>* %x) optsize {

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll

 ; RV32-NEXT:    li a0, 5
 ; RV32-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
 ; RV32-NEXT:    vmv.s.x v16, a0
 ; RV32-NEXT:    vmv.v.i v20, 2
 ; RV32-NEXT:    vsetvli zero, zero, e16, m1, tu, ma
 ; RV32-NEXT:    vslideup.vi v20, v16, 7
 ; RV32-NEXT:    lui a0, %hi(.LCPI11_0)
 ; RV32-NEXT:    addi a0, a0, %lo(.LCPI11_0)
-; RV32-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; RV32-NEXT:    vle16.v v21, (a0)
+; RV32-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; RV32-NEXT:    li a0, 164
 ; RV32-NEXT:    vmv.s.x v0, a0
 ; RV32-NEXT:    vrgatherei16.vv v16, v8, v21
 ; RV32-NEXT:    vrgatherei16.vv v16, v12, v20, v0.t
 ; RV32-NEXT:    vmv.v.v v8, v16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: vrgather_shuffle_vv_v8i64:
 ; RV64:       # %bb.0:
 ; RV64-NEXT:    li a0, 5
 ; RV64-NEXT:    vsetivli zero, 8, e64, m4, ta, ma
 ; RV64-NEXT:    vmv.s.x v16, a0
 ; RV64-NEXT:    vmv.v.i v20, 2
 ; RV64-NEXT:    vsetvli zero, zero, e64, m4, tu, ma
-; RV64-NEXT:    vslideup.vi v20, v16, 7
 ; RV64-NEXT:    lui a0, %hi(.LCPI11_0)
 ; RV64-NEXT:    addi a0, a0, %lo(.LCPI11_0)
-; RV64-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; RV64-NEXT:    vle64.v v24, (a0)
+; RV64-NEXT:    vslideup.vi v20, v16, 7
+; RV64-NEXT:    vrgather.vv v16, v8, v24
 ; RV64-NEXT:    li a0, 164
 ; RV64-NEXT:    vmv.s.x v0, a0
-; RV64-NEXT:    vrgather.vv v16, v8, v24
+; RV64-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; RV64-NEXT:    vrgather.vv v16, v12, v20, v0.t
 ; RV64-NEXT:    vmv.v.v v8, v16
 ; RV64-NEXT:    ret
   %s = shufflevector <8 x i64> %x, <8 x i64> %y, <8 x i32> <i32 1, i32 2, i32 10, i32 5, i32 1, i32 10, i32 3, i32 13>
   ret <8 x i64> %s
 }
 
 define <8 x i64> @vrgather_shuffle_xv_v8i64(<8 x i64> %x) {

 ; CHECK-NEXT:    ret
   %shuff = shufflevector <8 x i8> %v, <8 x i8> poison, <8 x i32> <i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4>
   ret <8 x i8> %shuff
 }
 
 define <8 x i8> @splat_ve4_ins_i0ve2(<8 x i8> %v) {
 ; CHECK-LABEL: splat_ve4_ins_i0ve2:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, tu, ma
 ; CHECK-NEXT:    vmv.v.i v10, 4
 ; CHECK-NEXT:    li a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf2, tu, ma
 ; CHECK-NEXT:    vmv.s.x v10, a0
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf2, ta, ma
 ; CHECK-NEXT:    vrgather.vv v9, v8, v10
 ; CHECK-NEXT:    vmv1r.v v8, v9
 ; CHECK-NEXT:    ret
   %shuff = shufflevector <8 x i8> %v, <8 x i8> poison, <8 x i32> <i32 2, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4>
   ret <8 x i8> %shuff
 }
 
 define <8 x i8> @splat_ve4_ins_i1ve3(<8 x i8> %v) {

 ; CHECK-NEXT:    ret
   %shuff = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 2, i32 8, i32 2, i32 2, i32 2, i32 2, i32 8, i32 2>
   ret <8 x i8> %shuff
 }
 
 define <8 x i8> @splat_ve2_we0_ins_i0ve4(<8 x i8> %v, <8 x i8> %w) {
 ; CHECK-LABEL: splat_ve2_we0_ins_i0ve4:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, tu, ma
 ; CHECK-NEXT:    vmv.v.i v11, 2
 ; CHECK-NEXT:    li a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf2, tu, ma
 ; CHECK-NEXT:    vmv.s.x v11, a0
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf2, ta, mu
+; CHECK-NEXT:    vrgather.vv v10, v8, v11
 ; CHECK-NEXT:    li a0, 66
 ; CHECK-NEXT:    vmv.s.x v0, a0
-; CHECK-NEXT:    vrgather.vv v10, v8, v11
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf2, ta, mu
 ; CHECK-NEXT:    vrgather.vi v10, v9, 0, v0.t
 ; CHECK-NEXT:    vmv1r.v v8, v10
 ; CHECK-NEXT:    ret
   %shuff = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 4, i32 8, i32 2, i32 2, i32 2, i32 2, i32 8, i32 2>
   ret <8 x i8> %shuff
 }
 
 define <8 x i8> @splat_ve2_we0_ins_i0we4(<8 x i8> %v, <8 x i8> %w) {

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int.ll

 ; CHECK-NEXT:    li a1, 1
 ; CHECK-NEXT:    vmv.s.x v9, a1
 ; CHECK-NEXT:    li a1, 33
 ; CHECK-NEXT:    vmv.s.x v0, a1
 ; CHECK-NEXT:    vmv.v.i v10, 3
 ; CHECK-NEXT:    vmerge.vim v10, v10, 2, v0
 ; CHECK-NEXT:    vsetivli zero, 7, e16, m1, tu, ma
 ; CHECK-NEXT:    vslideup.vi v10, v9, 6
-; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, tu, ma
 ; CHECK-NEXT:    vmv.v.i v11, 0
 ; CHECK-NEXT:    lui a1, 1048568
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, tu, ma
-; CHECK-NEXT:    vmv.v.i v12, 0
+; CHECK-NEXT:    vmv1r.v v12, v11
 ; CHECK-NEXT:    vmv.s.x v12, a1
 ; CHECK-NEXT:    vsetivli zero, 7, e16, m1, tu, ma
 ; CHECK-NEXT:    vslideup.vi v11, v9, 6
 ; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
 ; CHECK-NEXT:    lui a1, %hi(.LCPI53_0)
 ; CHECK-NEXT:    addi a1, a1, %lo(.LCPI53_0)
 ; CHECK-NEXT:    vle16.v v9, (a1)
 ; CHECK-NEXT:    vsrl.vv v11, v8, v11

 ; CHECK-NEXT:    vsub.vv v8, v8, v9
 ; CHECK-NEXT:    vmulhu.vv v8, v8, v10
 ; CHECK-NEXT:    vadd.vv v8, v8, v9
 ; CHECK-NEXT:    li a1, 1
 ; CHECK-NEXT:    vmv.s.x v9, a1
 ; CHECK-NEXT:    vmv.v.i v10, 2
 ; CHECK-NEXT:    vsetvli zero, zero, e32, m1, tu, ma
 ; CHECK-NEXT:    vslideup.vi v10, v9, 3
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-NEXT:    vsrl.vv v8, v8, v10
 ; CHECK-NEXT:    vse32.v v8, (a0)
 ; CHECK-NEXT:    ret
   %a = load <4 x i32>, <4 x i32>* %x
   %b = udiv <4 x i32> %a, <i32 5, i32 6, i32 7, i32 9>
   store <4 x i32> %b, <4 x i32>* %x
   ret void
 }

 ; RV32-NEXT:    vle32.v v9, (a1)
 ; RV32-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
 ; RV32-NEXT:    vsrl.vv v8, v8, v9
 ; RV32-NEXT:    vse64.v v8, (a0)
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: mulhu_v2i64:
 ; RV64:       # %bb.0:
-; RV64-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
+; RV64-NEXT:    vsetivli zero, 2, e64, m1, tu, ma
 ; RV64-NEXT:    lui a1, %hi(.LCPI55_0)
 ; RV64-NEXT:    addi a1, a1, %lo(.LCPI55_0)
 ; RV64-NEXT:    vlse64.v v8, (a1), zero
 ; RV64-NEXT:    lui a1, %hi(.LCPI55_1)
 ; RV64-NEXT:    ld a1, %lo(.LCPI55_1)(a1)
 ; RV64-NEXT:    vle64.v v9, (a0)
-; RV64-NEXT:    vsetvli zero, zero, e64, m1, tu, ma
 ; RV64-NEXT:    vmv.s.x v8, a1
-; RV64-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
 ; RV64-NEXT:    vmulhu.vv v8, v9, v8
 ; RV64-NEXT:    vid.v v9
 ; RV64-NEXT:    vadd.vi v9, v9, 1
 ; RV64-NEXT:    vsrl.vv v8, v8, v9
 ; RV64-NEXT:    vse64.v v8, (a0)
 ; RV64-NEXT:    ret
   %a = load <2 x i64>, <2 x i64>* %x
   %b = udiv <2 x i64> %a, <i64 3, i64 5>

 
 define void @mulhs_v2i64(<2 x i64>* %x) {
 ; RV32-LABEL: mulhs_v2i64:
 ; RV32:       # %bb.0:
 ; RV32-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
 ; RV32-NEXT:    vle64.v v8, (a0)
 ; RV32-NEXT:    lui a1, 349525
 ; RV32-NEXT:    addi a2, a1, 1365
-; RV32-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; RV32-NEXT:    vsetivli zero, 4, e32, m1, tu, ma
 ; RV32-NEXT:    vmv.v.x v9, a2
 ; RV32-NEXT:    addi a1, a1, 1366
-; RV32-NEXT:    vsetvli zero, zero, e32, m1, tu, ma
 ; RV32-NEXT:    vmv.s.x v9, a1
 ; RV32-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
 ; RV32-NEXT:    vmulh.vv v9, v8, v9
 ; RV32-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
 ; RV32-NEXT:    vid.v v10
 ; RV32-NEXT:    vsrl.vi v10, v10, 1
 ; RV32-NEXT:    vrsub.vi v10, v10, 0
 ; RV32-NEXT:    vsetivli zero, 2, e64, m1, ta, ma

 ; RV32-NEXT:    li a1, 63
 ; RV32-NEXT:    vsrl.vx v9, v10, a1
 ; RV32-NEXT:    vadd.vv v8, v8, v9
 ; RV32-NEXT:    vse64.v v8, (a0)
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: mulhs_v2i64:
 ; RV64:       # %bb.0:
-; RV64-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
+; RV64-NEXT:    vsetivli zero, 2, e64, m1, tu, ma
 ; RV64-NEXT:    lui a1, %hi(.LCPI59_0)
 ; RV64-NEXT:    addi a1, a1, %lo(.LCPI59_0)
 ; RV64-NEXT:    vlse64.v v8, (a1), zero
 ; RV64-NEXT:    lui a1, %hi(.LCPI59_1)
 ; RV64-NEXT:    ld a1, %lo(.LCPI59_1)(a1)
 ; RV64-NEXT:    vle64.v v9, (a0)
-; RV64-NEXT:    vsetvli zero, zero, e64, m1, tu, ma
 ; RV64-NEXT:    vmv.s.x v8, a1
-; RV64-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
 ; RV64-NEXT:    vmulh.vv v8, v9, v8
 ; RV64-NEXT:    vid.v v10
 ; RV64-NEXT:    vrsub.vi v11, v10, 0
 ; RV64-NEXT:    vmadd.vv v11, v9, v8
 ; RV64-NEXT:    li a1, 63
 ; RV64-NEXT:    vsrl.vx v8, v11, a1
 ; RV64-NEXT:    vsra.vv v9, v11, v10
 ; RV64-NEXT:    vadd.vv v8, v9, v8

 ; LMULMAX1-RV32-NEXT:    vsub.vv v9, v9, v12
 ; LMULMAX1-RV32-NEXT:    vmulhu.vv v9, v9, v11
 ; LMULMAX1-RV32-NEXT:    vadd.vv v9, v9, v12
 ; LMULMAX1-RV32-NEXT:    li a2, 1
 ; LMULMAX1-RV32-NEXT:    vmv.s.x v12, a2
 ; LMULMAX1-RV32-NEXT:    vmv.v.i v13, 2
 ; LMULMAX1-RV32-NEXT:    vsetvli zero, zero, e32, m1, tu, ma
 ; LMULMAX1-RV32-NEXT:    vslideup.vi v13, v12, 3
-; LMULMAX1-RV32-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; LMULMAX1-RV32-NEXT:    vsrl.vv v9, v9, v13
 ; LMULMAX1-RV32-NEXT:    vmulhu.vv v10, v8, v10
 ; LMULMAX1-RV32-NEXT:    vsub.vv v8, v8, v10
 ; LMULMAX1-RV32-NEXT:    vmulhu.vv v8, v8, v11
 ; LMULMAX1-RV32-NEXT:    vadd.vv v8, v8, v10
 ; LMULMAX1-RV32-NEXT:    vsrl.vv v8, v8, v13
 ; LMULMAX1-RV32-NEXT:    vse32.v v8, (a0)
 ; LMULMAX1-RV32-NEXT:    vse32.v v9, (a1)

 ; LMULMAX1-RV32-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
 ; LMULMAX1-RV32-NEXT:    vdivu.vv v8, v8, v10
 ; LMULMAX1-RV32-NEXT:    vse64.v v8, (a0)
 ; LMULMAX1-RV32-NEXT:    vse64.v v9, (a1)
 ; LMULMAX1-RV32-NEXT:    ret
 ;
 ; LMULMAX1-RV64-LABEL: mulhu_v4i64:
 ; LMULMAX1-RV64:       # %bb.0:
-; LMULMAX1-RV64-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
-; LMULMAX1-RV64-NEXT:    vle64.v v8, (a0)
+; LMULMAX1-RV64-NEXT:    vsetivli zero, 2, e64, m1, tu, ma
 ; LMULMAX1-RV64-NEXT:    addi a1, a0, 16
-; LMULMAX1-RV64-NEXT:    vle64.v v9, (a1)
-; LMULMAX1-RV64-NEXT:    vmv.v.i v10, 0
+; LMULMAX1-RV64-NEXT:    vle64.v v8, (a1)
+; LMULMAX1-RV64-NEXT:    vmv.v.i v9, 0
 ; LMULMAX1-RV64-NEXT:    li a2, -1
+; LMULMAX1-RV64-NEXT:    lui a3, %hi(.LCPI156_0)
+; LMULMAX1-RV64-NEXT:    addi a3, a3, %lo(.LCPI156_0)
+; LMULMAX1-RV64-NEXT:    vlse64.v v10, (a3), zero
+; LMULMAX1-RV64-NEXT:    lui a3, %hi(.LCPI156_1)
+; LMULMAX1-RV64-NEXT:    ld a3, %lo(.LCPI156_1)(a3)
 ; LMULMAX1-RV64-NEXT:    slli a2, a2, 63
-; LMULMAX1-RV64-NEXT:    vsetvli zero, zero, e64, m1, tu, ma
-; LMULMAX1-RV64-NEXT:    vmv.s.x v10, a2
-; LMULMAX1-RV64-NEXT:    lui a2, %hi(.LCPI156_0)
-; LMULMAX1-RV64-NEXT:    addi a2, a2, %lo(.LCPI156_0)
-; LMULMAX1-RV64-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
-; LMULMAX1-RV64-NEXT:    vlse64.v v11, (a2), zero
-; LMULMAX1-RV64-NEXT:    lui a2, %hi(.LCPI156_1)
-; LMULMAX1-RV64-NEXT:    ld a2, %lo(.LCPI156_1)(a2)
-; LMULMAX1-RV64-NEXT:    vsetvli zero, zero, e64, m1, tu, ma
-; LMULMAX1-RV64-NEXT:    vmv.s.x v11, a2
-; LMULMAX1-RV64-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
-; LMULMAX1-RV64-NEXT:    vmulhu.vv v11, v9, v11
-; LMULMAX1-RV64-NEXT:    vsub.vv v9, v9, v11
-; LMULMAX1-RV64-NEXT:    vmulhu.vv v9, v9, v10
-; LMULMAX1-RV64-NEXT:    vadd.vv v9, v9, v11
-; LMULMAX1-RV64-NEXT:    vid.v v10
+; LMULMAX1-RV64-NEXT:    vmv.s.x v9, a2
+; LMULMAX1-RV64-NEXT:    vle64.v v11, (a0)
+; LMULMAX1-RV64-NEXT:    vmv.s.x v10, a3
+; LMULMAX1-RV64-NEXT:    vmulhu.vv v10, v8, v10
+; LMULMAX1-RV64-NEXT:    vsub.vv v8, v8, v10
+; LMULMAX1-RV64-NEXT:    vmulhu.vv v8, v8, v9
+; LMULMAX1-RV64-NEXT:    vadd.vv v8, v8, v10
 ; LMULMAX1-RV64-NEXT:    lui a2, %hi(.LCPI156_2)
 ; LMULMAX1-RV64-NEXT:    addi a2, a2, %lo(.LCPI156_2)
-; LMULMAX1-RV64-NEXT:    vlse64.v v11, (a2), zero
+; LMULMAX1-RV64-NEXT:    vlse64.v v9, (a2), zero
 ; LMULMAX1-RV64-NEXT:    lui a2, %hi(.LCPI156_3)
 ; LMULMAX1-RV64-NEXT:    ld a2, %lo(.LCPI156_3)(a2)
+; LMULMAX1-RV64-NEXT:    vid.v v10
 ; LMULMAX1-RV64-NEXT:    vadd.vi v12, v10, 2
-; LMULMAX1-RV64-NEXT:    vsrl.vv v9, v9, v12
-; LMULMAX1-RV64-NEXT:    vsetvli zero, zero, e64, m1, tu, ma
-; LMULMAX1-RV64-NEXT:    vmv.s.x v11, a2
-; LMULMAX1-RV64-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
-; LMULMAX1-RV64-NEXT:    vmulhu.vv v8, v8, v11
+; LMULMAX1-RV64-NEXT:    vsrl.vv v8, v8, v12
+; LMULMAX1-RV64-NEXT:    vmv.s.x v9, a2
+; LMULMAX1-RV64-NEXT:    vmulhu.vv v9, v11, v9
 ; LMULMAX1-RV64-NEXT:    vadd.vi v10, v10, 1
-; LMULMAX1-RV64-NEXT:    vsrl.vv v8, v8, v10
-; LMULMAX1-RV64-NEXT:    vse64.v v8, (a0)
-; LMULMAX1-RV64-NEXT:    vse64.v v9, (a1)
+; LMULMAX1-RV64-NEXT:    vsrl.vv v9, v9, v10
+; LMULMAX1-RV64-NEXT:    vse64.v v9, (a0)
+; LMULMAX1-RV64-NEXT:    vse64.v v8, (a1)
 ; LMULMAX1-RV64-NEXT:    ret
   %a = load <4 x i64>, <4 x i64>* %x
   %b = udiv <4 x i64> %a, <i64 3, i64 5, i64 7, i64 9>
   store <4 x i64> %b, <4 x i64>* %x
   ret void
 }
 
 define void @mulhs_v32i8(<32 x i8>* %x) {

 ; LMULMAX1-RV32-NEXT:    vdiv.vv v9, v9, v10
 ; LMULMAX1-RV32-NEXT:    vdiv.vv v8, v8, v10
 ; LMULMAX1-RV32-NEXT:    vse64.v v8, (a0)
 ; LMULMAX1-RV32-NEXT:    vse64.v v9, (a1)
 ; LMULMAX1-RV32-NEXT:    ret
 ;
 ; LMULMAX1-RV64-LABEL: mulhs_v4i64:
 ; LMULMAX1-RV64:       # %bb.0:
-; LMULMAX1-RV64-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
-; LMULMAX1-RV64-NEXT:    vle64.v v8, (a0)
-; LMULMAX1-RV64-NEXT:    lui a1, %hi(.LCPI160_0)
-; LMULMAX1-RV64-NEXT:    addi a1, a1, %lo(.LCPI160_0)
-; LMULMAX1-RV64-NEXT:    vlse64.v v9, (a1), zero
-; LMULMAX1-RV64-NEXT:    lui a1, %hi(.LCPI160_1)
-; LMULMAX1-RV64-NEXT:    ld a1, %lo(.LCPI160_1)(a1)
-; LMULMAX1-RV64-NEXT:    addi a2, a0, 16
-; LMULMAX1-RV64-NEXT:    vle64.v v10, (a2)
-; LMULMAX1-RV64-NEXT:    vsetvli zero, zero, e64, m1, tu, ma
-; LMULMAX1-RV64-NEXT:    vmv.s.x v9, a1
-; LMULMAX1-RV64-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
-; LMULMAX1-RV64-NEXT:    vmulh.vv v11, v10, v9
+; LMULMAX1-RV64-NEXT:    vsetivli zero, 2, e64, m1, tu, ma
+; LMULMAX1-RV64-NEXT:    addi a1, a0, 16
+; LMULMAX1-RV64-NEXT:    lui a2, %hi(.LCPI160_0)
+; LMULMAX1-RV64-NEXT:    addi a2, a2, %lo(.LCPI160_0)
+; LMULMAX1-RV64-NEXT:    vlse64.v v8, (a2), zero
+; LMULMAX1-RV64-NEXT:    lui a2, %hi(.LCPI160_1)
+; LMULMAX1-RV64-NEXT:    ld a2, %lo(.LCPI160_1)(a2)
+; LMULMAX1-RV64-NEXT:    vle64.v v9, (a1)
+; LMULMAX1-RV64-NEXT:    vle64.v v10, (a0)
+; LMULMAX1-RV64-NEXT:    vmv.s.x v8, a2
+; LMULMAX1-RV64-NEXT:    vmulh.vv v11, v9, v8
 ; LMULMAX1-RV64-NEXT:    vid.v v12
 ; LMULMAX1-RV64-NEXT:    vrsub.vi v13, v12, 0
-; LMULMAX1-RV64-NEXT:    vmacc.vv v11, v13, v10
-; LMULMAX1-RV64-NEXT:    li a1, 63
-; LMULMAX1-RV64-NEXT:    vsrl.vx v10, v11, a1
+; LMULMAX1-RV64-NEXT:    vmacc.vv v11, v13, v9
+; LMULMAX1-RV64-NEXT:    li a2, 63
+; LMULMAX1-RV64-NEXT:    vsrl.vx v9, v11, a2
 ; LMULMAX1-RV64-NEXT:    vsra.vv v11, v11, v12
-; LMULMAX1-RV64-NEXT:    vadd.vv v10, v11, v10
-; LMULMAX1-RV64-NEXT:    vmulh.vv v9, v8, v9
-; LMULMAX1-RV64-NEXT:    vmacc.vv v9, v8, v13
-; LMULMAX1-RV64-NEXT:    vsrl.vx v8, v9, a1
-; LMULMAX1-RV64-NEXT:    vsra.vv v9, v9, v12
-; LMULMAX1-RV64-NEXT:    vadd.vv v8, v9, v8
+; LMULMAX1-RV64-NEXT:    vadd.vv v9, v11, v9
+; LMULMAX1-RV64-NEXT:    vmulh.vv v8, v10, v8
+; LMULMAX1-RV64-NEXT:    vmacc.vv v8, v10, v13
+; LMULMAX1-RV64-NEXT:    vsrl.vx v10, v8, a2
+; LMULMAX1-RV64-NEXT:    vsra.vv v8, v8, v12
+; LMULMAX1-RV64-NEXT:    vadd.vv v8, v8, v10
 ; LMULMAX1-RV64-NEXT:    vse64.v v8, (a0)
-; LMULMAX1-RV64-NEXT:    vse64.v v10, (a2)
+; LMULMAX1-RV64-NEXT:    vse64.v v9, (a1)
 ; LMULMAX1-RV64-NEXT:    ret
   %a = load <4 x i64>, <4 x i64>* %x
   %b = sdiv <4 x i64> %a, <i64 3, i64 -3, i64 3, i64 -3>
   store <4 x i64> %b, <4 x i64>* %x
   ret void
 }
 
 define void @smin_v32i8(<32 x i8>* %x, <32 x i8>* %y) {

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-mask-buildvec.ll

 ; ZVE32F-NEXT:    ret
   %1 = insertelement <1 x i1> poison, i1 %x, i32 0
   ret <1 x i1> %1
 }
 
 define <2 x i1> @buildvec_mask_nonconst_v2i1(i1 %x, i1 %y) {
 ; CHECK-LABEL: buildvec_mask_nonconst_v2i1:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
+; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, tu, ma
 ; CHECK-NEXT:    vmv.v.x v8, a1
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, tu, ma
 ; CHECK-NEXT:    vmv.s.x v8, a0
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, ta, ma
 ; CHECK-NEXT:    vand.vi v8, v8, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
 ;
 ; ZVE32F-LABEL: buildvec_mask_nonconst_v2i1:
 ; ZVE32F:       # %bb.0:
-; ZVE32F-NEXT:    vsetivli zero, 2, e8, mf4, ta, ma
+; ZVE32F-NEXT:    vsetivli zero, 2, e8, mf4, tu, ma
 ; ZVE32F-NEXT:    vmv.v.x v8, a1
-; ZVE32F-NEXT:    vsetvli zero, zero, e8, mf4, tu, ma
 ; ZVE32F-NEXT:    vmv.s.x v8, a0
-; ZVE32F-NEXT:    vsetvli zero, zero, e8, mf4, ta, ma
 ; ZVE32F-NEXT:    vand.vi v8, v8, 1
 ; ZVE32F-NEXT:    vmsne.vi v0, v8, 0
 ; ZVE32F-NEXT:    ret
   %1 = insertelement <2 x i1> poison, i1 %x, i32 0
   %2 = insertelement <2 x i1> %1,  i1 %y, i32 1
   ret <2 x i1> %2
 }
 

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-scatter.ll

 ; RV64-NEXT:    vnsrl.wi v8, v8, 0
 ; RV64-NEXT:    vsoxei64.v v8, (zero), v9, v0.t
 ; RV64-NEXT:    ret
 ;
 ; RV32ZVE32F-LABEL: mscatter_v2i64_truncstore_v2i32:
 ; RV32ZVE32F:       # %bb.0:
 ; RV32ZVE32F-NEXT:    lw a1, 0(a0)
 ; RV32ZVE32F-NEXT:    addi a0, a0, 8
-; RV32ZVE32F-NEXT:    vsetivli zero, 2, e32, m1, ta, ma
+; RV32ZVE32F-NEXT:    vsetivli zero, 2, e32, m1, tu, ma
 ; RV32ZVE32F-NEXT:    vlse32.v v9, (a0), zero
-; RV32ZVE32F-NEXT:    vsetvli zero, zero, e32, m1, tu, ma
 ; RV32ZVE32F-NEXT:    vmv.s.x v9, a1
 ; RV32ZVE32F-NEXT:    vsoxei32.v v9, (zero), v8, v0.t
 ; RV32ZVE32F-NEXT:    ret
 ;
 ; RV64ZVE32F-LABEL: mscatter_v2i64_truncstore_v2i32:
 ; RV64ZVE32F:       # %bb.0:
-; RV64ZVE32F-NEXT:    vsetivli zero, 2, e32, m1, ta, ma
+; RV64ZVE32F-NEXT:    vsetivli zero, 2, e32, m1, tu, ma
 ; RV64ZVE32F-NEXT:    vmv.v.x v8, a1
-; RV64ZVE32F-NEXT:    vsetvli zero, zero, e32, m1, tu, ma
 ; RV64ZVE32F-NEXT:    vmv.s.x v8, a0
 ; RV64ZVE32F-NEXT:    vsetvli zero, zero, e8, mf4, ta, ma
 ; RV64ZVE32F-NEXT:    vmv.x.s a0, v0
 ; RV64ZVE32F-NEXT:    andi a1, a0, 1
 ; RV64ZVE32F-NEXT:    bnez a1, .LBB24_3
 ; RV64ZVE32F-NEXT:  # %bb.1: # %else
 ; RV64ZVE32F-NEXT:    andi a0, a0, 2
 ; RV64ZVE32F-NEXT:    bnez a0, .LBB24_4

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-peephole-vmerge-vops.ll

; CHECK-NEXT:    ret
   ret <8 x i32> %b
 }
 
 ; Test glued node of merge should not be deleted.
 declare <8 x i1> @llvm.vp.icmp.v8i32(<8 x i32>, <8 x i32>, metadata, <8 x i1>, i32)
 define <8 x i32> @vpmerge_vpadd2(<8 x i32> %passthru, <8 x i32> %x, <8 x i32> %y, i32 zeroext %vl) {
 ; CHECK-LABEL: vpmerge_vpadd2:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, mu
 ; CHECK-NEXT:    vmseq.vv v0, v9, v10
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, tu, mu
 ; CHECK-NEXT:    vadd.vv v8, v9, v10, v0.t
 ; CHECK-NEXT:    ret
   %splat = insertelement <8 x i1> poison, i1 true, i32 0
   %mask = shufflevector <8 x i1> %splat, <8 x i1> poison, <8 x i32> zeroinitializer
   %a = call <8 x i32> @llvm.vp.add.v8i32(<8 x i32> %x, <8 x i32> %y, <8 x i1> %mask, i32 %vl)
   %m = call <8 x i1> @llvm.vp.icmp.v8i32(<8 x i32> %x, <8 x i32> %y, metadata !"eq", <8 x i1> %mask, i32 %vl)
   %b = call <8 x i32> @llvm.vp.merge.v8i32(<8 x i1> %m, <8 x i32> %a, <8 x i32> %passthru, i32 %vl)
   ret <8 x i32> %b
; CHECK-NEXT:    ret
   %b = call <8 x i32> @llvm.vp.merge.v8i32(<8 x i1> %m, <8 x i32> %a, <8 x i32> %passthru, i32 %vl)
   ret <8 x i32> %b
 }
 
 ; Test result have chain and glued node.
 define <8 x i32> @vpmerge_vpload2(<8 x i32> %passthru, <8 x i32>* %p, <8 x i32> %x, <8 x i32> %y, i32 zeroext %vl) {
 ; CHECK-LABEL: vpmerge_vpload2:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli zero, a1, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a1, e32, m1, tu, mu
 ; CHECK-NEXT:    vmseq.vv v0, v9, v10
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, tu, mu
 ; CHECK-NEXT:    vle32.v v8, (a0), v0.t
 ; CHECK-NEXT:    ret
   %splat = insertelement <8 x i1> poison, i1 true, i32 0
   %mask = shufflevector <8 x i1> %splat, <8 x i1> poison, <8 x i32> zeroinitializer
   %a = call <8 x i32> @llvm.vp.load.v8i32.p0v8i32(<8 x i32>* %p, <8 x i1> %mask, i32 %vl)
   %m = call <8 x i1> @llvm.vp.icmp.v8i32(<8 x i32> %x, <8 x i32> %y, metadata !"eq", <8 x i1> %mask, i32 %vl)
   %b = call <8 x i32> @llvm.vp.merge.v8i32(<8 x i1> %m, <8 x i32> %a, <8 x i32> %passthru, i32 %vl)
   ret <8 x i32> %b

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-round-vp.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=ilp32d -riscv-v-vector-bits-min=128 \
 ; RUN:   -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=lp64d -riscv-v-vector-bits-min=128 \
 ; RUN:   -verify-machineinstrs < %s | FileCheck %s
 
 declare <2 x half> @llvm.vp.round.v2f16(<2 x half>, <2 x i1>, i32)
 
 define <2 x half> @vp_round_v2f16(<2 x half> %va, <2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v2f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI0_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI0_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <2 x half> @llvm.vp.round.v2f16(<2 x half> %va, <2 x i1> %m, i32 %evl)
   ret <2 x half> %v
 }
 
 define <2 x half> @vp_round_v2f16_unmasked(<2 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v2f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI1_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI1_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <2 x i1> poison, i1 true, i32 0
   %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
   %v = call <2 x half> @llvm.vp.round.v2f16(<2 x half> %va, <2 x i1> %m, i32 %evl)
   ret <2 x half> %v
 }
 
 declare <4 x half> @llvm.vp.round.v4f16(<4 x half>, <4 x i1>, i32)
 
 define <4 x half> @vp_round_v4f16(<4 x half> %va, <4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v4f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI2_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI2_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <4 x half> @llvm.vp.round.v4f16(<4 x half> %va, <4 x i1> %m, i32 %evl)
   ret <4 x half> %v
 }
 
 define <4 x half> @vp_round_v4f16_unmasked(<4 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v4f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI3_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI3_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <4 x i1> poison, i1 true, i32 0
   %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
   %v = call <4 x half> @llvm.vp.round.v4f16(<4 x half> %va, <4 x i1> %m, i32 %evl)
   ret <4 x half> %v
 }
 
 declare <8 x half> @llvm.vp.round.v8f16(<8 x half>, <8 x i1>, i32)
 
 define <8 x half> @vp_round_v8f16(<8 x half> %va, <8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v8f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI4_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI4_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <8 x half> @llvm.vp.round.v8f16(<8 x half> %va, <8 x i1> %m, i32 %evl)
   ret <8 x half> %v
 }
 
 define <8 x half> @vp_round_v8f16_unmasked(<8 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v8f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI5_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI5_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <8 x i1> poison, i1 true, i32 0
   %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
   %v = call <8 x half> @llvm.vp.round.v8f16(<8 x half> %va, <8 x i1> %m, i32 %evl)
   ret <8 x half> %v
 }
 
 declare <16 x half> @llvm.vp.round.v16f16(<16 x half>, <16 x i1>, i32)
 
 define <16 x half> @vp_round_v16f16(<16 x half> %va, <16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v16f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI6_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI6_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <16 x half> @llvm.vp.round.v16f16(<16 x half> %va, <16 x i1> %m, i32 %evl)
   ret <16 x half> %v
 }
 
 define <16 x half> @vp_round_v16f16_unmasked(<16 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v16f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI7_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI7_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vmset.m v10
-; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <16 x i1> poison, i1 true, i32 0
   %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
   %v = call <16 x half> @llvm.vp.round.v16f16(<16 x half> %va, <16 x i1> %m, i32 %evl)
   ret <16 x half> %v
 }
 
 declare <2 x float> @llvm.vp.round.v2f32(<2 x float>, <2 x i1>, i32)
 
 define <2 x float> @vp_round_v2f32(<2 x float> %va, <2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v2f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI8_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI8_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <2 x float> @llvm.vp.round.v2f32(<2 x float> %va, <2 x i1> %m, i32 %evl)
   ret <2 x float> %v
 }
 
 define <2 x float> @vp_round_v2f32_unmasked(<2 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v2f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI9_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI9_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <2 x i1> poison, i1 true, i32 0
   %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
   %v = call <2 x float> @llvm.vp.round.v2f32(<2 x float> %va, <2 x i1> %m, i32 %evl)
   ret <2 x float> %v
 }
 
 declare <4 x float> @llvm.vp.round.v4f32(<4 x float>, <4 x i1>, i32)
 
 define <4 x float> @vp_round_v4f32(<4 x float> %va, <4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v4f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI10_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI10_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <4 x float> @llvm.vp.round.v4f32(<4 x float> %va, <4 x i1> %m, i32 %evl)
   ret <4 x float> %v
 }
 
 define <4 x float> @vp_round_v4f32_unmasked(<4 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v4f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI11_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI11_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <4 x i1> poison, i1 true, i32 0
   %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
   %v = call <4 x float> @llvm.vp.round.v4f32(<4 x float> %va, <4 x i1> %m, i32 %evl)
   ret <4 x float> %v
 }
 
 declare <8 x float> @llvm.vp.round.v8f32(<8 x float>, <8 x i1>, i32)
 
 define <8 x float> @vp_round_v8f32(<8 x float> %va, <8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v8f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI12_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI12_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <8 x float> @llvm.vp.round.v8f32(<8 x float> %va, <8 x i1> %m, i32 %evl)
   ret <8 x float> %v
 }
 
 define <8 x float> @vp_round_v8f32_unmasked(<8 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v8f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI13_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI13_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
 ; CHECK-NEXT:    vmset.m v10
-; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <8 x i1> poison, i1 true, i32 0
   %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
   %v = call <8 x float> @llvm.vp.round.v8f32(<8 x float> %va, <8 x i1> %m, i32 %evl)
   ret <8 x float> %v
 }
 
 declare <16 x float> @llvm.vp.round.v16f32(<16 x float>, <16 x i1>, i32)
 
 define <16 x float> @vp_round_v16f32(<16 x float> %va, <16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v16f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI14_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI14_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <16 x float> @llvm.vp.round.v16f32(<16 x float> %va, <16 x i1> %m, i32 %evl)
   ret <16 x float> %v
 }
 
 define <16 x float> @vp_round_v16f32_unmasked(<16 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v16f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI15_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI15_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vmset.m v12
-; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <16 x i1> poison, i1 true, i32 0
   %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
   %v = call <16 x float> @llvm.vp.round.v16f32(<16 x float> %va, <16 x i1> %m, i32 %evl)
   ret <16 x float> %v
 }
 
 declare <2 x double> @llvm.vp.round.v2f64(<2 x double>, <2 x i1>, i32)
 
 define <2 x double> @vp_round_v2f64(<2 x double> %va, <2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v2f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI16_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI16_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <2 x double> @llvm.vp.round.v2f64(<2 x double> %va, <2 x i1> %m, i32 %evl)
   ret <2 x double> %v
 }
 
 define <2 x double> @vp_round_v2f64_unmasked(<2 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v2f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI17_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI17_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <2 x i1> poison, i1 true, i32 0
   %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
   %v = call <2 x double> @llvm.vp.round.v2f64(<2 x double> %va, <2 x i1> %m, i32 %evl)
   ret <2 x double> %v
 }
 
 declare <4 x double> @llvm.vp.round.v4f64(<4 x double>, <4 x i1>, i32)
 
 define <4 x double> @vp_round_v4f64(<4 x double> %va, <4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v4f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI18_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI18_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <4 x double> @llvm.vp.round.v4f64(<4 x double> %va, <4 x i1> %m, i32 %evl)
   ret <4 x double> %v
 }
 
 define <4 x double> @vp_round_v4f64_unmasked(<4 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v4f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI19_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI19_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
 ; CHECK-NEXT:    vmset.m v10
-; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <4 x i1> poison, i1 true, i32 0
   %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
   %v = call <4 x double> @llvm.vp.round.v4f64(<4 x double> %va, <4 x i1> %m, i32 %evl)
   ret <4 x double> %v
 }
 
 declare <8 x double> @llvm.vp.round.v8f64(<8 x double>, <8 x i1>, i32)
 
 define <8 x double> @vp_round_v8f64(<8 x double> %va, <8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v8f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI20_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI20_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <8 x double> @llvm.vp.round.v8f64(<8 x double> %va, <8 x i1> %m, i32 %evl)
   ret <8 x double> %v
 }
 
 define <8 x double> @vp_round_v8f64_unmasked(<8 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v8f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI21_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI21_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
 ; CHECK-NEXT:    vmset.m v12
-; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <8 x i1> poison, i1 true, i32 0
   %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
   %v = call <8 x double> @llvm.vp.round.v8f64(<8 x double> %va, <8 x i1> %m, i32 %evl)
   ret <8 x double> %v
 }
 
 declare <15 x double> @llvm.vp.round.v15f64(<15 x double>, <15 x i1>, i32)
 
 define <15 x double> @vp_round_v15f64(<15 x double> %va, <15 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v15f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI22_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI22_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <15 x double> @llvm.vp.round.v15f64(<15 x double> %va, <15 x i1> %m, i32 %evl)
   ret <15 x double> %v
 }
 
 define <15 x double> @vp_round_v15f64_unmasked(<15 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v15f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI23_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI23_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vmset.m v16
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <15 x i1> poison, i1 true, i32 0
   %m = shufflevector <15 x i1> %head, <15 x i1> poison, <15 x i32> zeroinitializer
   %v = call <15 x double> @llvm.vp.round.v15f64(<15 x double> %va, <15 x i1> %m, i32 %evl)
   ret <15 x double> %v
 }
 
 declare <16 x double> @llvm.vp.round.v16f64(<16 x double>, <16 x i1>, i32)
 
 define <16 x double> @vp_round_v16f64(<16 x double> %va, <16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v16f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI24_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI24_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <16 x double> @llvm.vp.round.v16f64(<16 x double> %va, <16 x i1> %m, i32 %evl)
   ret <16 x double> %v
 }
 
 define <16 x double> @vp_round_v16f64_unmasked(<16 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v16f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI25_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI25_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vmset.m v16
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <16 x i1> poison, i1 true, i32 0
   %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
   %v = call <16 x double> @llvm.vp.round.v16f64(<16 x double> %va, <16 x i1> %m, i32 %evl)
   ret <16 x double> %v
 }
 
 declare <32 x double> @llvm.vp.round.v32f64(<32 x double>, <32 x i1>, i32)
 
 define <32 x double> @vp_round_v32f64(<32 x double> %va, <32 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v32f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    slli a1, a1, 4
-; CHECK-NEXT:    sub sp, sp, a1
-; CHECK-NEXT:    vmv1r.v v24, v0
-; CHECK-NEXT:    addi a1, sp, 16
-; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT:    vmv1r.v v1, v0
 ; CHECK-NEXT:    li a1, 0
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf4, ta, ma
 ; CHECK-NEXT:    addi a2, a0, -16
-; CHECK-NEXT:    vslidedown.vi v25, v0, 2
+; CHECK-NEXT:    vslidedown.vi v2, v0, 2
 ; CHECK-NEXT:    bltu a0, a2, .LBB26_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    mv a1, a2
 ; CHECK-NEXT:  .LBB26_2:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a2, vlenb
+; CHECK-NEXT:    slli a2, a2, 3
+; CHECK-NEXT:    sub sp, sp, a2
 ; CHECK-NEXT:    lui a2, %hi(.LCPI26_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI26_0)(a2)
-; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfabs.v v8, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v25, v8, ft0, v0.t
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfabs.v v24, v16, v0.t
+; CHECK-NEXT:    vmflt.vf v2, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a1, 4
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfcvt.x.f.v v8, v16, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
 ; CHECK-NEXT:    fsrm a1
-; CHECK-NEXT:    vfcvt.f.x.v v8, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    addi a1, sp, 16
+; CHECK-NEXT:    vs8r.v v24, (a1) # Unknown-size Folded Spill
 ; CHECK-NEXT:    li a1, 16
-; CHECK-NEXT:    vfsgnj.vv v16, v8, v16, v0.t
-; CHECK-NEXT:    csrr a2, vlenb
-; CHECK-NEXT:    slli a2, a2, 3
-; CHECK-NEXT:    add a2, sp, a2
-; CHECK-NEXT:    addi a2, a2, 16
+; CHECK-NEXT:    addi a2, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a2) # Unknown-size Folded Reload
+; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
+; CHECK-NEXT:    addi a2, sp, 16
 ; CHECK-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
 ; CHECK-NEXT:    bltu a0, a1, .LBB26_4
 ; CHECK-NEXT:  # %bb.3:
 ; CHECK-NEXT:    li a0, 16
 ; CHECK-NEXT:  .LBB26_4:
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vl8re8.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v24, v16, ft0, v0.t
+; CHECK-NEXT:    vmflt.vf v1, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
+; CHECK-NEXT:    vmv1r.v v0, v1
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    add a0, sp, a0
-; CHECK-NEXT:    addi a0, a0, 16
+; CHECK-NEXT:    addi a0, sp, 16
 ; CHECK-NEXT:    vl8re8.v v16, (a0) # Unknown-size Folded Reload
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 4
+; CHECK-NEXT:    slli a0, a0, 3
 ; CHECK-NEXT:    add sp, sp, a0
 ; CHECK-NEXT:    addi sp, sp, 16
 ; CHECK-NEXT:    ret
   %v = call <32 x double> @llvm.vp.round.v32f64(<32 x double> %va, <32 x i1> %m, i32 %evl)
   ret <32 x double> %v
 }
 
 define <32 x double> @vp_round_v32f64_unmasked(<32 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_v32f64_unmasked:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    slli a1, a1, 4
-; CHECK-NEXT:    sub sp, sp, a1
-; CHECK-NEXT:    addi a1, sp, 16
-; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
 ; CHECK-NEXT:    li a1, 0
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    addi a2, a0, -16
-; CHECK-NEXT:    vmset.m v24
+; CHECK-NEXT:    vmset.m v1
 ; CHECK-NEXT:    bltu a0, a2, .LBB27_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    mv a1, a2
 ; CHECK-NEXT:  .LBB27_2:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a2, vlenb
+; CHECK-NEXT:    slli a2, a2, 3
+; CHECK-NEXT:    sub sp, sp, a2
 ; CHECK-NEXT:    lui a2, %hi(.LCPI27_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI27_0)(a2)
-; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    vfabs.v v8, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmv1r.v v25, v24
-; CHECK-NEXT:    vmflt.vf v25, v8, ft0, v0.t
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    vfabs.v v24, v16, v0.t
+; CHECK-NEXT:    vmv1r.v v2, v1
+; CHECK-NEXT:    vmflt.vf v2, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a1, 4
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfcvt.x.f.v v8, v16, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
 ; CHECK-NEXT:    fsrm a1
-; CHECK-NEXT:    vfcvt.f.x.v v8, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    addi a1, sp, 16
+; CHECK-NEXT:    vs8r.v v24, (a1) # Unknown-size Folded Spill
 ; CHECK-NEXT:    li a1, 16
-; CHECK-NEXT:    vfsgnj.vv v16, v8, v16, v0.t
+; CHECK-NEXT:    addi a2, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a2) # Unknown-size Folded Reload
+; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
 ; CHECK-NEXT:    csrr a2, vlenb
 ; CHECK-NEXT:    slli a2, a2, 3
-; CHECK-NEXT:    add a2, sp, a2
-; CHECK-NEXT:    addi a2, a2, 16
-; CHECK-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
+; CHECK-NEXT:    add sp, sp, a2
+; CHECK-NEXT:    addi sp, sp, 16
 ; CHECK-NEXT:    bltu a0, a1, .LBB27_4
 ; CHECK-NEXT:  # %bb.3:
 ; CHECK-NEXT:    li a0, 16
 ; CHECK-NEXT:  .LBB27_4:
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vl8re8.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v24, v16, ft0, v0.t
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    vfabs.v v24, v8, v0.t
+; CHECK-NEXT:    vmflt.vf v1, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
-; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    add a0, sp, a0
-; CHECK-NEXT:    addi a0, a0, 16
-; CHECK-NEXT:    vl8re8.v v16, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 4
-; CHECK-NEXT:    add sp, sp, a0
-; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <32 x i1> poison, i1 true, i32 0
   %m = shufflevector <32 x i1> %head, <32 x i1> poison, <32 x i32> zeroinitializer
   %v = call <32 x double> @llvm.vp.round.v32f64(<32 x double> %va, <32 x i1> %m, i32 %evl)
   ret <32 x double> %v
 }

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-roundeven-vp.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=ilp32d -riscv-v-vector-bits-min=128 \
 ; RUN:   -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=lp64d -riscv-v-vector-bits-min=128 \
 ; RUN:   -verify-machineinstrs < %s | FileCheck %s
 
 declare <2 x half> @llvm.vp.roundeven.v2f16(<2 x half>, <2 x i1>, i32)
 
 define <2 x half> @vp_roundeven_v2f16(<2 x half> %va, <2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v2f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI0_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI0_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <2 x half> @llvm.vp.roundeven.v2f16(<2 x half> %va, <2 x i1> %m, i32 %evl)
   ret <2 x half> %v
 }
 
 define <2 x half> @vp_roundeven_v2f16_unmasked(<2 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v2f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI1_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI1_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <2 x i1> poison, i1 true, i32 0
   %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
   %v = call <2 x half> @llvm.vp.roundeven.v2f16(<2 x half> %va, <2 x i1> %m, i32 %evl)
   ret <2 x half> %v
 }
 
 declare <4 x half> @llvm.vp.roundeven.v4f16(<4 x half>, <4 x i1>, i32)
 
 define <4 x half> @vp_roundeven_v4f16(<4 x half> %va, <4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v4f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI2_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI2_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <4 x half> @llvm.vp.roundeven.v4f16(<4 x half> %va, <4 x i1> %m, i32 %evl)
   ret <4 x half> %v
 }
 
 define <4 x half> @vp_roundeven_v4f16_unmasked(<4 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v4f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI3_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI3_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <4 x i1> poison, i1 true, i32 0
   %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
   %v = call <4 x half> @llvm.vp.roundeven.v4f16(<4 x half> %va, <4 x i1> %m, i32 %evl)
   ret <4 x half> %v
 }
 
 declare <8 x half> @llvm.vp.roundeven.v8f16(<8 x half>, <8 x i1>, i32)
 
 define <8 x half> @vp_roundeven_v8f16(<8 x half> %va, <8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v8f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI4_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI4_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <8 x half> @llvm.vp.roundeven.v8f16(<8 x half> %va, <8 x i1> %m, i32 %evl)
   ret <8 x half> %v
 }
 
 define <8 x half> @vp_roundeven_v8f16_unmasked(<8 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v8f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI5_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI5_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <8 x i1> poison, i1 true, i32 0
   %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
   %v = call <8 x half> @llvm.vp.roundeven.v8f16(<8 x half> %va, <8 x i1> %m, i32 %evl)
   ret <8 x half> %v
 }
 
 declare <16 x half> @llvm.vp.roundeven.v16f16(<16 x half>, <16 x i1>, i32)
 
 define <16 x half> @vp_roundeven_v16f16(<16 x half> %va, <16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v16f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI6_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI6_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <16 x half> @llvm.vp.roundeven.v16f16(<16 x half> %va, <16 x i1> %m, i32 %evl)
   ret <16 x half> %v
 }
 
 define <16 x half> @vp_roundeven_v16f16_unmasked(<16 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v16f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI7_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI7_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vmset.m v10
-; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <16 x i1> poison, i1 true, i32 0
   %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
   %v = call <16 x half> @llvm.vp.roundeven.v16f16(<16 x half> %va, <16 x i1> %m, i32 %evl)
   ret <16 x half> %v
 }
 
 declare <2 x float> @llvm.vp.roundeven.v2f32(<2 x float>, <2 x i1>, i32)
 
 define <2 x float> @vp_roundeven_v2f32(<2 x float> %va, <2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v2f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI8_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI8_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <2 x float> @llvm.vp.roundeven.v2f32(<2 x float> %va, <2 x i1> %m, i32 %evl)
   ret <2 x float> %v
 }
 
 define <2 x float> @vp_roundeven_v2f32_unmasked(<2 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v2f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI9_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI9_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <2 x i1> poison, i1 true, i32 0
   %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
   %v = call <2 x float> @llvm.vp.roundeven.v2f32(<2 x float> %va, <2 x i1> %m, i32 %evl)
   ret <2 x float> %v
 }
 
 declare <4 x float> @llvm.vp.roundeven.v4f32(<4 x float>, <4 x i1>, i32)
 
 define <4 x float> @vp_roundeven_v4f32(<4 x float> %va, <4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v4f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI10_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI10_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <4 x float> @llvm.vp.roundeven.v4f32(<4 x float> %va, <4 x i1> %m, i32 %evl)
   ret <4 x float> %v
 }
 
 define <4 x float> @vp_roundeven_v4f32_unmasked(<4 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v4f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI11_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI11_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <4 x i1> poison, i1 true, i32 0
   %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
   %v = call <4 x float> @llvm.vp.roundeven.v4f32(<4 x float> %va, <4 x i1> %m, i32 %evl)
   ret <4 x float> %v
 }
 
 declare <8 x float> @llvm.vp.roundeven.v8f32(<8 x float>, <8 x i1>, i32)
 
 define <8 x float> @vp_roundeven_v8f32(<8 x float> %va, <8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v8f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI12_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI12_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <8 x float> @llvm.vp.roundeven.v8f32(<8 x float> %va, <8 x i1> %m, i32 %evl)
   ret <8 x float> %v
 }
 
 define <8 x float> @vp_roundeven_v8f32_unmasked(<8 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v8f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI13_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI13_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
 ; CHECK-NEXT:    vmset.m v10
-; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <8 x i1> poison, i1 true, i32 0
   %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
   %v = call <8 x float> @llvm.vp.roundeven.v8f32(<8 x float> %va, <8 x i1> %m, i32 %evl)
   ret <8 x float> %v
 }
 
 declare <16 x float> @llvm.vp.roundeven.v16f32(<16 x float>, <16 x i1>, i32)
 
 define <16 x float> @vp_roundeven_v16f32(<16 x float> %va, <16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v16f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI14_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI14_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <16 x float> @llvm.vp.roundeven.v16f32(<16 x float> %va, <16 x i1> %m, i32 %evl)
   ret <16 x float> %v
 }
 
 define <16 x float> @vp_roundeven_v16f32_unmasked(<16 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v16f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI15_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI15_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vmset.m v12
-; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <16 x i1> poison, i1 true, i32 0
   %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
   %v = call <16 x float> @llvm.vp.roundeven.v16f32(<16 x float> %va, <16 x i1> %m, i32 %evl)
   ret <16 x float> %v
 }
 
 declare <2 x double> @llvm.vp.roundeven.v2f64(<2 x double>, <2 x i1>, i32)
 
 define <2 x double> @vp_roundeven_v2f64(<2 x double> %va, <2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v2f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI16_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI16_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <2 x double> @llvm.vp.roundeven.v2f64(<2 x double> %va, <2 x i1> %m, i32 %evl)
   ret <2 x double> %v
 }
 
 define <2 x double> @vp_roundeven_v2f64_unmasked(<2 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v2f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI17_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI17_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <2 x i1> poison, i1 true, i32 0
   %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
   %v = call <2 x double> @llvm.vp.roundeven.v2f64(<2 x double> %va, <2 x i1> %m, i32 %evl)
   ret <2 x double> %v
 }
 
 declare <4 x double> @llvm.vp.roundeven.v4f64(<4 x double>, <4 x i1>, i32)
 
 define <4 x double> @vp_roundeven_v4f64(<4 x double> %va, <4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v4f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI18_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI18_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <4 x double> @llvm.vp.roundeven.v4f64(<4 x double> %va, <4 x i1> %m, i32 %evl)
   ret <4 x double> %v
 }
 
 define <4 x double> @vp_roundeven_v4f64_unmasked(<4 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v4f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI19_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI19_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
 ; CHECK-NEXT:    vmset.m v10
-; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <4 x i1> poison, i1 true, i32 0
   %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
   %v = call <4 x double> @llvm.vp.roundeven.v4f64(<4 x double> %va, <4 x i1> %m, i32 %evl)
   ret <4 x double> %v
 }
 
 declare <8 x double> @llvm.vp.roundeven.v8f64(<8 x double>, <8 x i1>, i32)
 
 define <8 x double> @vp_roundeven_v8f64(<8 x double> %va, <8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v8f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI20_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI20_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <8 x double> @llvm.vp.roundeven.v8f64(<8 x double> %va, <8 x i1> %m, i32 %evl)
   ret <8 x double> %v
 }
 
 define <8 x double> @vp_roundeven_v8f64_unmasked(<8 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v8f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI21_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI21_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
 ; CHECK-NEXT:    vmset.m v12
-; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <8 x i1> poison, i1 true, i32 0
   %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
   %v = call <8 x double> @llvm.vp.roundeven.v8f64(<8 x double> %va, <8 x i1> %m, i32 %evl)
   ret <8 x double> %v
 }
 
 declare <15 x double> @llvm.vp.roundeven.v15f64(<15 x double>, <15 x i1>, i32)
 
 define <15 x double> @vp_roundeven_v15f64(<15 x double> %va, <15 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v15f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI22_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI22_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <15 x double> @llvm.vp.roundeven.v15f64(<15 x double> %va, <15 x i1> %m, i32 %evl)
   ret <15 x double> %v
 }
 
 define <15 x double> @vp_roundeven_v15f64_unmasked(<15 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v15f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI23_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI23_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vmset.m v16
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <15 x i1> poison, i1 true, i32 0
   %m = shufflevector <15 x i1> %head, <15 x i1> poison, <15 x i32> zeroinitializer
   %v = call <15 x double> @llvm.vp.roundeven.v15f64(<15 x double> %va, <15 x i1> %m, i32 %evl)
   ret <15 x double> %v
 }
 
 declare <16 x double> @llvm.vp.roundeven.v16f64(<16 x double>, <16 x i1>, i32)
 
 define <16 x double> @vp_roundeven_v16f64(<16 x double> %va, <16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v16f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI24_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI24_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <16 x double> @llvm.vp.roundeven.v16f64(<16 x double> %va, <16 x i1> %m, i32 %evl)
   ret <16 x double> %v
 }
 
 define <16 x double> @vp_roundeven_v16f64_unmasked(<16 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v16f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI25_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI25_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vmset.m v16
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <16 x i1> poison, i1 true, i32 0
   %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
   %v = call <16 x double> @llvm.vp.roundeven.v16f64(<16 x double> %va, <16 x i1> %m, i32 %evl)
   ret <16 x double> %v
 }
 
 declare <32 x double> @llvm.vp.roundeven.v32f64(<32 x double>, <32 x i1>, i32)
 
 define <32 x double> @vp_roundeven_v32f64(<32 x double> %va, <32 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v32f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    slli a1, a1, 4
-; CHECK-NEXT:    sub sp, sp, a1
-; CHECK-NEXT:    vmv1r.v v24, v0
-; CHECK-NEXT:    addi a1, sp, 16
-; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT:    vmv1r.v v1, v0
 ; CHECK-NEXT:    li a1, 0
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf4, ta, ma
 ; CHECK-NEXT:    addi a2, a0, -16
-; CHECK-NEXT:    vslidedown.vi v25, v0, 2
+; CHECK-NEXT:    vslidedown.vi v2, v0, 2
 ; CHECK-NEXT:    bltu a0, a2, .LBB26_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    mv a1, a2
 ; CHECK-NEXT:  .LBB26_2:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a2, vlenb
+; CHECK-NEXT:    slli a2, a2, 3
+; CHECK-NEXT:    sub sp, sp, a2
 ; CHECK-NEXT:    lui a2, %hi(.LCPI26_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI26_0)(a2)
-; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfabs.v v8, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v25, v8, ft0, v0.t
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfabs.v v24, v16, v0.t
+; CHECK-NEXT:    vmflt.vf v2, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a1, 0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfcvt.x.f.v v8, v16, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
 ; CHECK-NEXT:    fsrm a1
-; CHECK-NEXT:    vfcvt.f.x.v v8, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    addi a1, sp, 16
+; CHECK-NEXT:    vs8r.v v24, (a1) # Unknown-size Folded Spill
 ; CHECK-NEXT:    li a1, 16
-; CHECK-NEXT:    vfsgnj.vv v16, v8, v16, v0.t
-; CHECK-NEXT:    csrr a2, vlenb
-; CHECK-NEXT:    slli a2, a2, 3
-; CHECK-NEXT:    add a2, sp, a2
-; CHECK-NEXT:    addi a2, a2, 16
+; CHECK-NEXT:    addi a2, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a2) # Unknown-size Folded Reload
+; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
+; CHECK-NEXT:    addi a2, sp, 16
 ; CHECK-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
 ; CHECK-NEXT:    bltu a0, a1, .LBB26_4
 ; CHECK-NEXT:  # %bb.3:
 ; CHECK-NEXT:    li a0, 16
 ; CHECK-NEXT:  .LBB26_4:
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vl8re8.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v24, v16, ft0, v0.t
+; CHECK-NEXT:    vmflt.vf v1, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
+; CHECK-NEXT:    vmv1r.v v0, v1
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    add a0, sp, a0
-; CHECK-NEXT:    addi a0, a0, 16
+; CHECK-NEXT:    addi a0, sp, 16
 ; CHECK-NEXT:    vl8re8.v v16, (a0) # Unknown-size Folded Reload
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 4
+; CHECK-NEXT:    slli a0, a0, 3
 ; CHECK-NEXT:    add sp, sp, a0
 ; CHECK-NEXT:    addi sp, sp, 16
 ; CHECK-NEXT:    ret
   %v = call <32 x double> @llvm.vp.roundeven.v32f64(<32 x double> %va, <32 x i1> %m, i32 %evl)
   ret <32 x double> %v
 }
 
 define <32 x double> @vp_roundeven_v32f64_unmasked(<32 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_v32f64_unmasked:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    slli a1, a1, 4
-; CHECK-NEXT:    sub sp, sp, a1
-; CHECK-NEXT:    addi a1, sp, 16
-; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
 ; CHECK-NEXT:    li a1, 0
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    addi a2, a0, -16
-; CHECK-NEXT:    vmset.m v24
+; CHECK-NEXT:    vmset.m v1
 ; CHECK-NEXT:    bltu a0, a2, .LBB27_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    mv a1, a2
 ; CHECK-NEXT:  .LBB27_2:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a2, vlenb
+; CHECK-NEXT:    slli a2, a2, 3
+; CHECK-NEXT:    sub sp, sp, a2
 ; CHECK-NEXT:    lui a2, %hi(.LCPI27_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI27_0)(a2)
-; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    vfabs.v v8, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmv1r.v v25, v24
-; CHECK-NEXT:    vmflt.vf v25, v8, ft0, v0.t
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    vfabs.v v24, v16, v0.t
+; CHECK-NEXT:    vmv1r.v v2, v1
+; CHECK-NEXT:    vmflt.vf v2, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a1, 0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfcvt.x.f.v v8, v16, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
 ; CHECK-NEXT:    fsrm a1
-; CHECK-NEXT:    vfcvt.f.x.v v8, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    addi a1, sp, 16
+; CHECK-NEXT:    vs8r.v v24, (a1) # Unknown-size Folded Spill
 ; CHECK-NEXT:    li a1, 16
-; CHECK-NEXT:    vfsgnj.vv v16, v8, v16, v0.t
+; CHECK-NEXT:    addi a2, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a2) # Unknown-size Folded Reload
+; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
 ; CHECK-NEXT:    csrr a2, vlenb
 ; CHECK-NEXT:    slli a2, a2, 3
-; CHECK-NEXT:    add a2, sp, a2
-; CHECK-NEXT:    addi a2, a2, 16
-; CHECK-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
+; CHECK-NEXT:    add sp, sp, a2
+; CHECK-NEXT:    addi sp, sp, 16
 ; CHECK-NEXT:    bltu a0, a1, .LBB27_4
 ; CHECK-NEXT:  # %bb.3:
 ; CHECK-NEXT:    li a0, 16
 ; CHECK-NEXT:  .LBB27_4:
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vl8re8.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v24, v16, ft0, v0.t
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    vfabs.v v24, v8, v0.t
+; CHECK-NEXT:    vmflt.vf v1, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
-; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    add a0, sp, a0
-; CHECK-NEXT:    addi a0, a0, 16
-; CHECK-NEXT:    vl8re8.v v16, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 4
-; CHECK-NEXT:    add sp, sp, a0
-; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <32 x i1> poison, i1 true, i32 0
   %m = shufflevector <32 x i1> %head, <32 x i1> poison, <32 x i32> zeroinitializer
   %v = call <32 x double> @llvm.vp.roundeven.v32f64(<32 x double> %va, <32 x i1> %m, i32 %evl)
   ret <32 x double> %v
 }

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-roundtozero-vp.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=ilp32d -riscv-v-vector-bits-min=128 \
 ; RUN:   -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=lp64d -riscv-v-vector-bits-min=128 \
 ; RUN:   -verify-machineinstrs < %s | FileCheck %s
 
 declare <2 x half> @llvm.vp.roundtozero.v2f16(<2 x half>, <2 x i1>, i32)
 
 define <2 x half> @vp_roundtozero_v2f16(<2 x half> %va, <2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v2f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI0_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI0_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <2 x half> @llvm.vp.roundtozero.v2f16(<2 x half> %va, <2 x i1> %m, i32 %evl)
   ret <2 x half> %v
 }
 
 define <2 x half> @vp_roundtozero_v2f16_unmasked(<2 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v2f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI1_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI1_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <2 x i1> poison, i1 true, i32 0
   %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
   %v = call <2 x half> @llvm.vp.roundtozero.v2f16(<2 x half> %va, <2 x i1> %m, i32 %evl)
   ret <2 x half> %v
 }
 
 declare <4 x half> @llvm.vp.roundtozero.v4f16(<4 x half>, <4 x i1>, i32)
 
 define <4 x half> @vp_roundtozero_v4f16(<4 x half> %va, <4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v4f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI2_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI2_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <4 x half> @llvm.vp.roundtozero.v4f16(<4 x half> %va, <4 x i1> %m, i32 %evl)
   ret <4 x half> %v
 }
 
 define <4 x half> @vp_roundtozero_v4f16_unmasked(<4 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v4f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI3_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI3_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <4 x i1> poison, i1 true, i32 0
   %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
   %v = call <4 x half> @llvm.vp.roundtozero.v4f16(<4 x half> %va, <4 x i1> %m, i32 %evl)
   ret <4 x half> %v
 }
 
 declare <8 x half> @llvm.vp.roundtozero.v8f16(<8 x half>, <8 x i1>, i32)
 
 define <8 x half> @vp_roundtozero_v8f16(<8 x half> %va, <8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v8f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI4_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI4_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <8 x half> @llvm.vp.roundtozero.v8f16(<8 x half> %va, <8 x i1> %m, i32 %evl)
   ret <8 x half> %v
 }
 
 define <8 x half> @vp_roundtozero_v8f16_unmasked(<8 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v8f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI5_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI5_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <8 x i1> poison, i1 true, i32 0
   %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
   %v = call <8 x half> @llvm.vp.roundtozero.v8f16(<8 x half> %va, <8 x i1> %m, i32 %evl)
   ret <8 x half> %v
 }
 
 declare <16 x half> @llvm.vp.roundtozero.v16f16(<16 x half>, <16 x i1>, i32)
 
 define <16 x half> @vp_roundtozero_v16f16(<16 x half> %va, <16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v16f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI6_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI6_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <16 x half> @llvm.vp.roundtozero.v16f16(<16 x half> %va, <16 x i1> %m, i32 %evl)
   ret <16 x half> %v
 }
 
 define <16 x half> @vp_roundtozero_v16f16_unmasked(<16 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v16f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI7_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI7_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vmset.m v10
-; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <16 x i1> poison, i1 true, i32 0
   %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
   %v = call <16 x half> @llvm.vp.roundtozero.v16f16(<16 x half> %va, <16 x i1> %m, i32 %evl)
   ret <16 x half> %v
 }
 
 declare <2 x float> @llvm.vp.roundtozero.v2f32(<2 x float>, <2 x i1>, i32)
 
 define <2 x float> @vp_roundtozero_v2f32(<2 x float> %va, <2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v2f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI8_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI8_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <2 x float> @llvm.vp.roundtozero.v2f32(<2 x float> %va, <2 x i1> %m, i32 %evl)
   ret <2 x float> %v
 }
 
 define <2 x float> @vp_roundtozero_v2f32_unmasked(<2 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v2f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI9_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI9_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <2 x i1> poison, i1 true, i32 0
   %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
   %v = call <2 x float> @llvm.vp.roundtozero.v2f32(<2 x float> %va, <2 x i1> %m, i32 %evl)
   ret <2 x float> %v
 }
 
 declare <4 x float> @llvm.vp.roundtozero.v4f32(<4 x float>, <4 x i1>, i32)
 
 define <4 x float> @vp_roundtozero_v4f32(<4 x float> %va, <4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v4f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI10_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI10_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <4 x float> @llvm.vp.roundtozero.v4f32(<4 x float> %va, <4 x i1> %m, i32 %evl)
   ret <4 x float> %v
 }
 
 define <4 x float> @vp_roundtozero_v4f32_unmasked(<4 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v4f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI11_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI11_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <4 x i1> poison, i1 true, i32 0
   %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
   %v = call <4 x float> @llvm.vp.roundtozero.v4f32(<4 x float> %va, <4 x i1> %m, i32 %evl)
   ret <4 x float> %v
 }
 
 declare <8 x float> @llvm.vp.roundtozero.v8f32(<8 x float>, <8 x i1>, i32)
 
 define <8 x float> @vp_roundtozero_v8f32(<8 x float> %va, <8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v8f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI12_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI12_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <8 x float> @llvm.vp.roundtozero.v8f32(<8 x float> %va, <8 x i1> %m, i32 %evl)
   ret <8 x float> %v
 }
 
 define <8 x float> @vp_roundtozero_v8f32_unmasked(<8 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v8f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI13_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI13_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
 ; CHECK-NEXT:    vmset.m v10
-; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <8 x i1> poison, i1 true, i32 0
   %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
   %v = call <8 x float> @llvm.vp.roundtozero.v8f32(<8 x float> %va, <8 x i1> %m, i32 %evl)
   ret <8 x float> %v
 }
 
 declare <16 x float> @llvm.vp.roundtozero.v16f32(<16 x float>, <16 x i1>, i32)
 
 define <16 x float> @vp_roundtozero_v16f32(<16 x float> %va, <16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v16f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI14_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI14_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <16 x float> @llvm.vp.roundtozero.v16f32(<16 x float> %va, <16 x i1> %m, i32 %evl)
   ret <16 x float> %v
 }
 
 define <16 x float> @vp_roundtozero_v16f32_unmasked(<16 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v16f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI15_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI15_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vmset.m v12
-; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <16 x i1> poison, i1 true, i32 0
   %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
   %v = call <16 x float> @llvm.vp.roundtozero.v16f32(<16 x float> %va, <16 x i1> %m, i32 %evl)
   ret <16 x float> %v
 }
 
 declare <2 x double> @llvm.vp.roundtozero.v2f64(<2 x double>, <2 x i1>, i32)
 
 define <2 x double> @vp_roundtozero_v2f64(<2 x double> %va, <2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v2f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI16_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI16_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <2 x double> @llvm.vp.roundtozero.v2f64(<2 x double> %va, <2 x i1> %m, i32 %evl)
   ret <2 x double> %v
 }
 
 define <2 x double> @vp_roundtozero_v2f64_unmasked(<2 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v2f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI17_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI17_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
 ; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <2 x i1> poison, i1 true, i32 0
   %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
   %v = call <2 x double> @llvm.vp.roundtozero.v2f64(<2 x double> %va, <2 x i1> %m, i32 %evl)
   ret <2 x double> %v
 }
 
 declare <4 x double> @llvm.vp.roundtozero.v4f64(<4 x double>, <4 x i1>, i32)
 
 define <4 x double> @vp_roundtozero_v4f64(<4 x double> %va, <4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v4f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI18_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI18_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <4 x double> @llvm.vp.roundtozero.v4f64(<4 x double> %va, <4 x i1> %m, i32 %evl)
   ret <4 x double> %v
 }
 
 define <4 x double> @vp_roundtozero_v4f64_unmasked(<4 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v4f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI19_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI19_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
 ; CHECK-NEXT:    vmset.m v10
-; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <4 x i1> poison, i1 true, i32 0
   %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
   %v = call <4 x double> @llvm.vp.roundtozero.v4f64(<4 x double> %va, <4 x i1> %m, i32 %evl)
   ret <4 x double> %v
 }
 
 declare <8 x double> @llvm.vp.roundtozero.v8f64(<8 x double>, <8 x i1>, i32)
 
 define <8 x double> @vp_roundtozero_v8f64(<8 x double> %va, <8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v8f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI20_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI20_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <8 x double> @llvm.vp.roundtozero.v8f64(<8 x double> %va, <8 x i1> %m, i32 %evl)
   ret <8 x double> %v
 }
 
 define <8 x double> @vp_roundtozero_v8f64_unmasked(<8 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v8f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI21_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI21_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
 ; CHECK-NEXT:    vmset.m v12
-; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <8 x i1> poison, i1 true, i32 0
   %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
   %v = call <8 x double> @llvm.vp.roundtozero.v8f64(<8 x double> %va, <8 x i1> %m, i32 %evl)
   ret <8 x double> %v
 }
 
 declare <15 x double> @llvm.vp.roundtozero.v15f64(<15 x double>, <15 x i1>, i32)
 
 define <15 x double> @vp_roundtozero_v15f64(<15 x double> %va, <15 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v15f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI22_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI22_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <15 x double> @llvm.vp.roundtozero.v15f64(<15 x double> %va, <15 x i1> %m, i32 %evl)
   ret <15 x double> %v
 }
 
 define <15 x double> @vp_roundtozero_v15f64_unmasked(<15 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v15f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI23_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI23_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vmset.m v16
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <15 x i1> poison, i1 true, i32 0
   %m = shufflevector <15 x i1> %head, <15 x i1> poison, <15 x i32> zeroinitializer
   %v = call <15 x double> @llvm.vp.roundtozero.v15f64(<15 x double> %va, <15 x i1> %m, i32 %evl)
   ret <15 x double> %v
 }
 
 declare <16 x double> @llvm.vp.roundtozero.v16f64(<16 x double>, <16 x i1>, i32)
 
 define <16 x double> @vp_roundtozero_v16f64(<16 x double> %va, <16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v16f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI24_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI24_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <16 x double> @llvm.vp.roundtozero.v16f64(<16 x double> %va, <16 x i1> %m, i32 %evl)
   ret <16 x double> %v
 }
 
 define <16 x double> @vp_roundtozero_v16f64_unmasked(<16 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v16f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI25_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI25_0)(a1)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vmset.m v16
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <16 x i1> poison, i1 true, i32 0
   %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
   %v = call <16 x double> @llvm.vp.roundtozero.v16f64(<16 x double> %va, <16 x i1> %m, i32 %evl)
   ret <16 x double> %v
 }
 
 declare <32 x double> @llvm.vp.roundtozero.v32f64(<32 x double>, <32 x i1>, i32)
 
 define <32 x double> @vp_roundtozero_v32f64(<32 x double> %va, <32 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v32f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    slli a1, a1, 4
-; CHECK-NEXT:    sub sp, sp, a1
-; CHECK-NEXT:    vmv1r.v v24, v0
-; CHECK-NEXT:    addi a1, sp, 16
-; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT:    vmv1r.v v1, v0
 ; CHECK-NEXT:    li a1, 0
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf4, ta, ma
 ; CHECK-NEXT:    addi a2, a0, -16
-; CHECK-NEXT:    vslidedown.vi v25, v0, 2
+; CHECK-NEXT:    vslidedown.vi v2, v0, 2
 ; CHECK-NEXT:    bltu a0, a2, .LBB26_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    mv a1, a2
 ; CHECK-NEXT:  .LBB26_2:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a2, vlenb
+; CHECK-NEXT:    slli a2, a2, 3
+; CHECK-NEXT:    sub sp, sp, a2
 ; CHECK-NEXT:    lui a2, %hi(.LCPI26_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI26_0)(a2)
-; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfabs.v v8, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v25, v8, ft0, v0.t
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfabs.v v24, v16, v0.t
+; CHECK-NEXT:    vmflt.vf v2, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a1, 1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfcvt.x.f.v v8, v16, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
 ; CHECK-NEXT:    fsrm a1
-; CHECK-NEXT:    vfcvt.f.x.v v8, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    addi a1, sp, 16
+; CHECK-NEXT:    vs8r.v v24, (a1) # Unknown-size Folded Spill
 ; CHECK-NEXT:    li a1, 16
-; CHECK-NEXT:    vfsgnj.vv v16, v8, v16, v0.t
-; CHECK-NEXT:    csrr a2, vlenb
-; CHECK-NEXT:    slli a2, a2, 3
-; CHECK-NEXT:    add a2, sp, a2
-; CHECK-NEXT:    addi a2, a2, 16
+; CHECK-NEXT:    addi a2, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a2) # Unknown-size Folded Reload
+; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
+; CHECK-NEXT:    addi a2, sp, 16
 ; CHECK-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
 ; CHECK-NEXT:    bltu a0, a1, .LBB26_4
 ; CHECK-NEXT:  # %bb.3:
 ; CHECK-NEXT:    li a0, 16
 ; CHECK-NEXT:  .LBB26_4:
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vl8re8.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v24, v16, ft0, v0.t
+; CHECK-NEXT:    vmflt.vf v1, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
+; CHECK-NEXT:    vmv1r.v v0, v1
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    add a0, sp, a0
-; CHECK-NEXT:    addi a0, a0, 16
+; CHECK-NEXT:    addi a0, sp, 16
 ; CHECK-NEXT:    vl8re8.v v16, (a0) # Unknown-size Folded Reload
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 4
+; CHECK-NEXT:    slli a0, a0, 3
 ; CHECK-NEXT:    add sp, sp, a0
 ; CHECK-NEXT:    addi sp, sp, 16
 ; CHECK-NEXT:    ret
   %v = call <32 x double> @llvm.vp.roundtozero.v32f64(<32 x double> %va, <32 x i1> %m, i32 %evl)
   ret <32 x double> %v
 }
 
 define <32 x double> @vp_roundtozero_v32f64_unmasked(<32 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_v32f64_unmasked:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    slli a1, a1, 4
-; CHECK-NEXT:    sub sp, sp, a1
-; CHECK-NEXT:    addi a1, sp, 16
-; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
 ; CHECK-NEXT:    li a1, 0
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    addi a2, a0, -16
-; CHECK-NEXT:    vmset.m v24
+; CHECK-NEXT:    vmset.m v1
 ; CHECK-NEXT:    bltu a0, a2, .LBB27_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    mv a1, a2
 ; CHECK-NEXT:  .LBB27_2:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a2, vlenb
+; CHECK-NEXT:    slli a2, a2, 3
+; CHECK-NEXT:    sub sp, sp, a2
 ; CHECK-NEXT:    lui a2, %hi(.LCPI27_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI27_0)(a2)
-; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    vfabs.v v8, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmv1r.v v25, v24
-; CHECK-NEXT:    vmflt.vf v25, v8, ft0, v0.t
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    vfabs.v v24, v16, v0.t
+; CHECK-NEXT:    vmv1r.v v2, v1
+; CHECK-NEXT:    vmflt.vf v2, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a1, 1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfcvt.x.f.v v8, v16, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
 ; CHECK-NEXT:    fsrm a1
-; CHECK-NEXT:    vfcvt.f.x.v v8, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    addi a1, sp, 16
+; CHECK-NEXT:    vs8r.v v24, (a1) # Unknown-size Folded Spill
 ; CHECK-NEXT:    li a1, 16
-; CHECK-NEXT:    vfsgnj.vv v16, v8, v16, v0.t
+; CHECK-NEXT:    addi a2, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a2) # Unknown-size Folded Reload
+; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
 ; CHECK-NEXT:    csrr a2, vlenb
 ; CHECK-NEXT:    slli a2, a2, 3
-; CHECK-NEXT:    add a2, sp, a2
-; CHECK-NEXT:    addi a2, a2, 16
-; CHECK-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
+; CHECK-NEXT:    add sp, sp, a2
+; CHECK-NEXT:    addi sp, sp, 16
 ; CHECK-NEXT:    bltu a0, a1, .LBB27_4
 ; CHECK-NEXT:  # %bb.3:
 ; CHECK-NEXT:    li a0, 16
 ; CHECK-NEXT:  .LBB27_4:
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vl8re8.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v24, v16, ft0, v0.t
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    vfabs.v v24, v8, v0.t
+; CHECK-NEXT:    vmflt.vf v1, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
-; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    add a0, sp, a0
-; CHECK-NEXT:    addi a0, a0, 16
-; CHECK-NEXT:    vl8re8.v v16, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 4
-; CHECK-NEXT:    add sp, sp, a0
-; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <32 x i1> poison, i1 true, i32 0
   %m = shufflevector <32 x i1> %head, <32 x i1> poison, <32 x i32> zeroinitializer
   %v = call <32 x double> @llvm.vp.roundtozero.v32f64(<32 x double> %va, <32 x i1> %m, i32 %evl)
   ret <32 x double> %v
 }

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vpgather.ll

 ; RV32-NEXT:    vmv1r.v v1, v0
 ; RV32-NEXT:    li a2, 0
 ; RV32-NEXT:    vsetivli zero, 16, e32, m4, ta, ma
 ; RV32-NEXT:    vnsrl.wi v24, v16, 0
 ; RV32-NEXT:    vnsrl.wi v16, v8, 0
 ; RV32-NEXT:    li a3, 32
 ; RV32-NEXT:    vsetvli zero, a3, e32, m8, tu, ma
 ; RV32-NEXT:    vslideup.vi v16, v24, 16
-; RV32-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
 ; RV32-NEXT:    addi a3, a1, -16
 ; RV32-NEXT:    vsll.vi v24, v16, 3
 ; RV32-NEXT:    bltu a1, a3, .LBB96_2
 ; RV32-NEXT:  # %bb.1:
 ; RV32-NEXT:    mv a2, a3
 ; RV32-NEXT:  .LBB96_2:
 ; RV32-NEXT:    vsetivli zero, 16, e32, m8, ta, ma
 ; RV32-NEXT:    vslidedown.vi v8, v24, 16

llvm/test/CodeGen/RISCV/rvv/floor-vp.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=ilp32d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=lp64d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 
 declare <vscale x 1 x half> @llvm.vp.floor.nxv1f16(<vscale x 1 x half>, <vscale x 1 x i1>, i32)
 
 define <vscale x 1 x half> @vp_floor_nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv1f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI0_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI0_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 1 x half> @llvm.vp.floor.nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x half> %v
 }
 
 define <vscale x 1 x half> @vp_floor_nxv1f16_unmasked(<vscale x 1 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv1f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI1_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI1_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
   %v = call <vscale x 1 x half> @llvm.vp.floor.nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x half> %v
 }
 
 declare <vscale x 2 x half> @llvm.vp.floor.nxv2f16(<vscale x 2 x half>, <vscale x 2 x i1>, i32)
 
 define <vscale x 2 x half> @vp_floor_nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv2f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI2_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI2_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 2 x half> @llvm.vp.floor.nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x half> %v
 }
 
 define <vscale x 2 x half> @vp_floor_nxv2f16_unmasked(<vscale x 2 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv2f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI3_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI3_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
   %v = call <vscale x 2 x half> @llvm.vp.floor.nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x half> %v
 }
 
 declare <vscale x 4 x half> @llvm.vp.floor.nxv4f16(<vscale x 4 x half>, <vscale x 4 x i1>, i32)
 
 define <vscale x 4 x half> @vp_floor_nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv4f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI4_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI4_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 4 x half> @llvm.vp.floor.nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x half> %v
 }
 
 define <vscale x 4 x half> @vp_floor_nxv4f16_unmasked(<vscale x 4 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv4f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI5_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI5_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
   %v = call <vscale x 4 x half> @llvm.vp.floor.nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x half> %v
 }
 
 declare <vscale x 8 x half> @llvm.vp.floor.nxv8f16(<vscale x 8 x half>, <vscale x 8 x i1>, i32)
 
 define <vscale x 8 x half> @vp_floor_nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv8f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI6_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI6_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 8 x half> @llvm.vp.floor.nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x half> %v
 }
 
 define <vscale x 8 x half> @vp_floor_nxv8f16_unmasked(<vscale x 8 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv8f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI7_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI7_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
   %v = call <vscale x 8 x half> @llvm.vp.floor.nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x half> %v
 }
 
 declare <vscale x 16 x half> @llvm.vp.floor.nxv16f16(<vscale x 16 x half>, <vscale x 16 x i1>, i32)
 
 define <vscale x 16 x half> @vp_floor_nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv16f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI8_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI8_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 16 x half> @llvm.vp.floor.nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x half> %v
 }
 
 define <vscale x 16 x half> @vp_floor_nxv16f16_unmasked(<vscale x 16 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv16f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI9_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI9_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
   %v = call <vscale x 16 x half> @llvm.vp.floor.nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x half> %v
 }
 
 declare <vscale x 32 x half> @llvm.vp.floor.nxv32f16(<vscale x 32 x half>, <vscale x 32 x i1>, i32)
 
 define <vscale x 32 x half> @vp_floor_nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv32f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI10_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI10_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 32 x half> @llvm.vp.floor.nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x i1> %m, i32 %evl)
   ret <vscale x 32 x half> %v
 }
 
 define <vscale x 32 x half> @vp_floor_nxv32f16_unmasked(<vscale x 32 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv32f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI11_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI11_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 32 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 32 x i1> %head, <vscale x 32 x i1> poison, <vscale x 32 x i32> zeroinitializer
   %v = call <vscale x 32 x half> @llvm.vp.floor.nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x i1> %m, i32 %evl)
   ret <vscale x 32 x half> %v
 }
 
 declare <vscale x 1 x float> @llvm.vp.floor.nxv1f32(<vscale x 1 x float>, <vscale x 1 x i1>, i32)
 
 define <vscale x 1 x float> @vp_floor_nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv1f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI12_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI12_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 1 x float> @llvm.vp.floor.nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x float> %v
 }
 
 define <vscale x 1 x float> @vp_floor_nxv1f32_unmasked(<vscale x 1 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv1f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI13_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI13_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
   %v = call <vscale x 1 x float> @llvm.vp.floor.nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x float> %v
 }
 
 declare <vscale x 2 x float> @llvm.vp.floor.nxv2f32(<vscale x 2 x float>, <vscale x 2 x i1>, i32)
 
 define <vscale x 2 x float> @vp_floor_nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv2f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI14_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI14_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 2 x float> @llvm.vp.floor.nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x float> %v
 }
 
 define <vscale x 2 x float> @vp_floor_nxv2f32_unmasked(<vscale x 2 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv2f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI15_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI15_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
   %v = call <vscale x 2 x float> @llvm.vp.floor.nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x float> %v
 }
 
 declare <vscale x 4 x float> @llvm.vp.floor.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, i32)
 
 define <vscale x 4 x float> @vp_floor_nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv4f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI16_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI16_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 4 x float> @llvm.vp.floor.nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x float> %v
 }
 
 define <vscale x 4 x float> @vp_floor_nxv4f32_unmasked(<vscale x 4 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv4f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI17_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI17_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
   %v = call <vscale x 4 x float> @llvm.vp.floor.nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x float> %v
 }
 
 declare <vscale x 8 x float> @llvm.vp.floor.nxv8f32(<vscale x 8 x float>, <vscale x 8 x i1>, i32)
 
 define <vscale x 8 x float> @vp_floor_nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv8f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI18_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI18_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 8 x float> @llvm.vp.floor.nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x float> %v
 }
 
 define <vscale x 8 x float> @vp_floor_nxv8f32_unmasked(<vscale x 8 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv8f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI19_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI19_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
   %v = call <vscale x 8 x float> @llvm.vp.floor.nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x float> %v
 }
 
 declare <vscale x 16 x float> @llvm.vp.floor.nxv16f32(<vscale x 16 x float>, <vscale x 16 x i1>, i32)
 
 define <vscale x 16 x float> @vp_floor_nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv16f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI20_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI20_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 16 x float> @llvm.vp.floor.nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x float> %v
 }
 
 define <vscale x 16 x float> @vp_floor_nxv16f32_unmasked(<vscale x 16 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv16f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI21_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI21_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
   %v = call <vscale x 16 x float> @llvm.vp.floor.nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x float> %v
 }
 
 declare <vscale x 1 x double> @llvm.vp.floor.nxv1f64(<vscale x 1 x double>, <vscale x 1 x i1>, i32)
 
 define <vscale x 1 x double> @vp_floor_nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv1f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI22_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI22_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 1 x double> @llvm.vp.floor.nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x double> %v
 }
 
 define <vscale x 1 x double> @vp_floor_nxv1f64_unmasked(<vscale x 1 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv1f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI23_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI23_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
   %v = call <vscale x 1 x double> @llvm.vp.floor.nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x double> %v
 }
 
 declare <vscale x 2 x double> @llvm.vp.floor.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, i32)
 
 define <vscale x 2 x double> @vp_floor_nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv2f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI24_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI24_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 2 x double> @llvm.vp.floor.nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x double> %v
 }
 
 define <vscale x 2 x double> @vp_floor_nxv2f64_unmasked(<vscale x 2 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv2f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI25_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI25_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
   %v = call <vscale x 2 x double> @llvm.vp.floor.nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x double> %v
 }
 
 declare <vscale x 4 x double> @llvm.vp.floor.nxv4f64(<vscale x 4 x double>, <vscale x 4 x i1>, i32)
 
 define <vscale x 4 x double> @vp_floor_nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv4f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI26_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI26_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 4 x double> @llvm.vp.floor.nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x double> %v
 }
 
 define <vscale x 4 x double> @vp_floor_nxv4f64_unmasked(<vscale x 4 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv4f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI27_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI27_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
   %v = call <vscale x 4 x double> @llvm.vp.floor.nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x double> %v
 }
 
 declare <vscale x 7 x double> @llvm.vp.floor.nxv7f64(<vscale x 7 x double>, <vscale x 7 x i1>, i32)
 
 define <vscale x 7 x double> @vp_floor_nxv7f64(<vscale x 7 x double> %va, <vscale x 7 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv7f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI28_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI28_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 7 x double> @llvm.vp.floor.nxv7f64(<vscale x 7 x double> %va, <vscale x 7 x i1> %m, i32 %evl)
   ret <vscale x 7 x double> %v
 }
 
 define <vscale x 7 x double> @vp_floor_nxv7f64_unmasked(<vscale x 7 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv7f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI29_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI29_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 7 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 7 x i1> %head, <vscale x 7 x i1> poison, <vscale x 7 x i32> zeroinitializer
   %v = call <vscale x 7 x double> @llvm.vp.floor.nxv7f64(<vscale x 7 x double> %va, <vscale x 7 x i1> %m, i32 %evl)
   ret <vscale x 7 x double> %v
 }
 
 declare <vscale x 8 x double> @llvm.vp.floor.nxv8f64(<vscale x 8 x double>, <vscale x 8 x i1>, i32)
 
 define <vscale x 8 x double> @vp_floor_nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv8f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI30_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI30_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 8 x double> @llvm.vp.floor.nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x double> %v
 }
 
 define <vscale x 8 x double> @vp_floor_nxv8f64_unmasked(<vscale x 8 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv8f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI31_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI31_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
   %v = call <vscale x 8 x double> @llvm.vp.floor.nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x double> %v
 }
 
 ; Test splitting.
 declare <vscale x 16 x double> @llvm.vp.floor.nxv16f64(<vscale x 16 x double>, <vscale x 16 x i1>, i32)
 
 define <vscale x 16 x double> @vp_floor_nxv16f64(<vscale x 16 x double> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv16f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    slli a1, a1, 4
-; CHECK-NEXT:    sub sp, sp, a1
-; CHECK-NEXT:    vmv1r.v v24, v0
-; CHECK-NEXT:    addi a1, sp, 16
-; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT:    vmv1r.v v1, v0
 ; CHECK-NEXT:    li a2, 0
 ; CHECK-NEXT:    csrr a1, vlenb
 ; CHECK-NEXT:    srli a4, a1, 3
 ; CHECK-NEXT:    vsetvli a3, zero, e8, mf4, ta, ma
 ; CHECK-NEXT:    sub a3, a0, a1
-; CHECK-NEXT:    vslidedown.vx v25, v0, a4
+; CHECK-NEXT:    vslidedown.vx v2, v0, a4
 ; CHECK-NEXT:    bltu a0, a3, .LBB32_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    mv a2, a3
 ; CHECK-NEXT:  .LBB32_2:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a3, vlenb
+; CHECK-NEXT:    slli a3, a3, 3
+; CHECK-NEXT:    sub sp, sp, a3
 ; CHECK-NEXT:    lui a3, %hi(.LCPI32_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI32_0)(a3)
-; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfabs.v v8, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v25, v8, ft0, v0.t
+; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfabs.v v24, v16, v0.t
+; CHECK-NEXT:    vmflt.vf v2, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a2, 2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfcvt.x.f.v v8, v16, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
+; CHECK-NEXT:    addi a3, sp, 16
+; CHECK-NEXT:    vs8r.v v24, (a3) # Unknown-size Folded Spill
 ; CHECK-NEXT:    fsrm a2
-; CHECK-NEXT:    vfcvt.f.x.v v8, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vfsgnj.vv v16, v8, v16, v0.t
-; CHECK-NEXT:    csrr a2, vlenb
-; CHECK-NEXT:    slli a2, a2, 3
-; CHECK-NEXT:    add a2, sp, a2
-; CHECK-NEXT:    addi a2, a2, 16
+; CHECK-NEXT:    addi a2, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a2) # Unknown-size Folded Reload
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
+; CHECK-NEXT:    addi a2, sp, 16
 ; CHECK-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
 ; CHECK-NEXT:    bltu a0, a1, .LBB32_4
 ; CHECK-NEXT:  # %bb.3:
 ; CHECK-NEXT:    mv a0, a1
 ; CHECK-NEXT:  .LBB32_4:
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vl8re8.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v24, v16, ft0, v0.t
+; CHECK-NEXT:    vmflt.vf v1, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 2
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
+; CHECK-NEXT:    vmv1r.v v0, v1
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    add a0, sp, a0
-; CHECK-NEXT:    addi a0, a0, 16
+; CHECK-NEXT:    addi a0, sp, 16
 ; CHECK-NEXT:    vl8re8.v v16, (a0) # Unknown-size Folded Reload
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 4
+; CHECK-NEXT:    slli a0, a0, 3
 ; CHECK-NEXT:    add sp, sp, a0
 ; CHECK-NEXT:    addi sp, sp, 16
 ; CHECK-NEXT:    ret
   %v = call <vscale x 16 x double> @llvm.vp.floor.nxv16f64(<vscale x 16 x double> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x double> %v
 }
 
 define <vscale x 16 x double> @vp_floor_nxv16f64_unmasked(<vscale x 16 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_floor_nxv16f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    csrr a1, vlenb
 ; CHECK-NEXT:    mv a2, a0
 ; CHECK-NEXT:    bltu a0, a1, .LBB33_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    mv a2, a1
 ; CHECK-NEXT:  .LBB33_2:
 ; CHECK-NEXT:    lui a3, %hi(.LCPI33_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI33_0)(a3)
 ; CHECK-NEXT:    li a3, 0
-; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8
 ; CHECK-NEXT:    vmflt.vf v0, v24, ft0
 ; CHECK-NEXT:    fsrmi a2, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a2
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    sub a1, a0, a1
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    bltu a0, a1, .LBB33_4
 ; CHECK-NEXT:  # %bb.3:
 ; CHECK-NEXT:    mv a3, a1
 ; CHECK-NEXT:  .LBB33_4:
-; CHECK-NEXT:    vsetvli zero, a3, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a3, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v16
 ; CHECK-NEXT:    vmflt.vf v0, v24, ft0
 ; CHECK-NEXT:    fsrmi a0, 2
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
   %v = call <vscale x 16 x double> @llvm.vp.floor.nxv16f64(<vscale x 16 x double> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x double> %v
 }

llvm/test/CodeGen/RISCV/rvv/fround-sdnode.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=ilp32d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=lp64d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 
 ; This file tests the code generation for `llvm.round.*` on scalable vector type.
 
 define <vscale x 1 x half> @round_nxv1f16(<vscale x 1 x half> %x) {
 ; CHECK-LABEL: round_nxv1f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI0_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI0_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 1 x half> @llvm.round.nxv1f16(<vscale x 1 x half> %x)
   ret <vscale x 1 x half> %a
 }
 declare <vscale x 1 x half> @llvm.round.nxv1f16(<vscale x 1 x half>)
 
 define <vscale x 2 x half> @round_nxv2f16(<vscale x 2 x half> %x) {
 ; CHECK-LABEL: round_nxv2f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI1_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI1_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 2 x half> @llvm.round.nxv2f16(<vscale x 2 x half> %x)
   ret <vscale x 2 x half> %a
 }
 declare <vscale x 2 x half> @llvm.round.nxv2f16(<vscale x 2 x half>)
 
 define <vscale x 4 x half> @round_nxv4f16(<vscale x 4 x half> %x) {
 ; CHECK-LABEL: round_nxv4f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI2_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI2_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 4 x half> @llvm.round.nxv4f16(<vscale x 4 x half> %x)
   ret <vscale x 4 x half> %a
 }
 declare <vscale x 4 x half> @llvm.round.nxv4f16(<vscale x 4 x half>)
 
 define <vscale x 8 x half> @round_nxv8f16(<vscale x 8 x half> %x) {
 ; CHECK-LABEL: round_nxv8f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI3_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI3_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, m2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 8 x half> @llvm.round.nxv8f16(<vscale x 8 x half> %x)
   ret <vscale x 8 x half> %a
 }
 declare <vscale x 8 x half> @llvm.round.nxv8f16(<vscale x 8 x half>)
 
 define <vscale x 16 x half> @round_nxv16f16(<vscale x 16 x half> %x) {
 ; CHECK-LABEL: round_nxv16f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI4_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI4_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, m4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 16 x half> @llvm.round.nxv16f16(<vscale x 16 x half> %x)
   ret <vscale x 16 x half> %a
 }
 declare <vscale x 16 x half> @llvm.round.nxv16f16(<vscale x 16 x half>)
 
 define <vscale x 32 x half> @round_nxv32f16(<vscale x 32 x half> %x) {
 ; CHECK-LABEL: round_nxv32f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI5_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI5_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, m8, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 32 x half> @llvm.round.nxv32f16(<vscale x 32 x half> %x)
   ret <vscale x 32 x half> %a
 }
 declare <vscale x 32 x half> @llvm.round.nxv32f16(<vscale x 32 x half>)
 
 define <vscale x 1 x float> @round_nxv1f32(<vscale x 1 x float> %x) {
 ; CHECK-LABEL: round_nxv1f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI6_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI6_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 1 x float> @llvm.round.nxv1f32(<vscale x 1 x float> %x)
   ret <vscale x 1 x float> %a
 }
 declare <vscale x 1 x float> @llvm.round.nxv1f32(<vscale x 1 x float>)
 
 define <vscale x 2 x float> @round_nxv2f32(<vscale x 2 x float> %x) {
 ; CHECK-LABEL: round_nxv2f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI7_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI7_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 2 x float> @llvm.round.nxv2f32(<vscale x 2 x float> %x)
   ret <vscale x 2 x float> %a
 }
 declare <vscale x 2 x float> @llvm.round.nxv2f32(<vscale x 2 x float>)
 
 define <vscale x 4 x float> @round_nxv4f32(<vscale x 4 x float> %x) {
 ; CHECK-LABEL: round_nxv4f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI8_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI8_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 4 x float> @llvm.round.nxv4f32(<vscale x 4 x float> %x)
   ret <vscale x 4 x float> %a
 }
 declare <vscale x 4 x float> @llvm.round.nxv4f32(<vscale x 4 x float>)
 
 define <vscale x 8 x float> @round_nxv8f32(<vscale x 8 x float> %x) {
 ; CHECK-LABEL: round_nxv8f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI9_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI9_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 8 x float> @llvm.round.nxv8f32(<vscale x 8 x float> %x)
   ret <vscale x 8 x float> %a
 }
 declare <vscale x 8 x float> @llvm.round.nxv8f32(<vscale x 8 x float>)
 
 define <vscale x 16 x float> @round_nxv16f32(<vscale x 16 x float> %x) {
 ; CHECK-LABEL: round_nxv16f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI10_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI10_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m8, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 16 x float> @llvm.round.nxv16f32(<vscale x 16 x float> %x)
   ret <vscale x 16 x float> %a
 }
 declare <vscale x 16 x float> @llvm.round.nxv16f32(<vscale x 16 x float>)
 
 define <vscale x 1 x double> @round_nxv1f64(<vscale x 1 x double> %x) {
 ; CHECK-LABEL: round_nxv1f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI11_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI11_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 1 x double> @llvm.round.nxv1f64(<vscale x 1 x double> %x)
   ret <vscale x 1 x double> %a
 }
 declare <vscale x 1 x double> @llvm.round.nxv1f64(<vscale x 1 x double>)
 
 define <vscale x 2 x double> @round_nxv2f64(<vscale x 2 x double> %x) {
 ; CHECK-LABEL: round_nxv2f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI12_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI12_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e64, m2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 2 x double> @llvm.round.nxv2f64(<vscale x 2 x double> %x)
   ret <vscale x 2 x double> %a
 }
 declare <vscale x 2 x double> @llvm.round.nxv2f64(<vscale x 2 x double>)
 
 define <vscale x 4 x double> @round_nxv4f64(<vscale x 4 x double> %x) {
 ; CHECK-LABEL: round_nxv4f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI13_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI13_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e64, m4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 4 x double> @llvm.round.nxv4f64(<vscale x 4 x double> %x)
   ret <vscale x 4 x double> %a
 }
 declare <vscale x 4 x double> @llvm.round.nxv4f64(<vscale x 4 x double>)
 
 define <vscale x 8 x double> @round_nxv8f64(<vscale x 8 x double> %x) {
 ; CHECK-LABEL: round_nxv8f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI14_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI14_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 8 x double> @llvm.round.nxv8f64(<vscale x 8 x double> %x)
   ret <vscale x 8 x double> %a
 }
 declare <vscale x 8 x double> @llvm.round.nxv8f64(<vscale x 8 x double>)

llvm/test/CodeGen/RISCV/rvv/froundeven-sdnode.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=ilp32d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=lp64d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 
 ; This file tests the code generation for `llvm.roundeven.*` on scalable vector type.
 
 define <vscale x 1 x half> @roundeven_nxv1f16(<vscale x 1 x half> %x) {
 ; CHECK-LABEL: roundeven_nxv1f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI0_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI0_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 1 x half> @llvm.roundeven.nxv1f16(<vscale x 1 x half> %x)
   ret <vscale x 1 x half> %a
 }
 declare <vscale x 1 x half> @llvm.roundeven.nxv1f16(<vscale x 1 x half>)
 
 define <vscale x 2 x half> @roundeven_nxv2f16(<vscale x 2 x half> %x) {
 ; CHECK-LABEL: roundeven_nxv2f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI1_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI1_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 2 x half> @llvm.roundeven.nxv2f16(<vscale x 2 x half> %x)
   ret <vscale x 2 x half> %a
 }
 declare <vscale x 2 x half> @llvm.roundeven.nxv2f16(<vscale x 2 x half>)
 
 define <vscale x 4 x half> @roundeven_nxv4f16(<vscale x 4 x half> %x) {
 ; CHECK-LABEL: roundeven_nxv4f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI2_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI2_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 4 x half> @llvm.roundeven.nxv4f16(<vscale x 4 x half> %x)
   ret <vscale x 4 x half> %a
 }
 declare <vscale x 4 x half> @llvm.roundeven.nxv4f16(<vscale x 4 x half>)
 
 define <vscale x 8 x half> @roundeven_nxv8f16(<vscale x 8 x half> %x) {
 ; CHECK-LABEL: roundeven_nxv8f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI3_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI3_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, m2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 8 x half> @llvm.roundeven.nxv8f16(<vscale x 8 x half> %x)
   ret <vscale x 8 x half> %a
 }
 declare <vscale x 8 x half> @llvm.roundeven.nxv8f16(<vscale x 8 x half>)
 
 define <vscale x 16 x half> @roundeven_nxv16f16(<vscale x 16 x half> %x) {
 ; CHECK-LABEL: roundeven_nxv16f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI4_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI4_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, m4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 16 x half> @llvm.roundeven.nxv16f16(<vscale x 16 x half> %x)
   ret <vscale x 16 x half> %a
 }
 declare <vscale x 16 x half> @llvm.roundeven.nxv16f16(<vscale x 16 x half>)
 
 define <vscale x 32 x half> @roundeven_nxv32f16(<vscale x 32 x half> %x) {
 ; CHECK-LABEL: roundeven_nxv32f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI5_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI5_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, m8, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 32 x half> @llvm.roundeven.nxv32f16(<vscale x 32 x half> %x)
   ret <vscale x 32 x half> %a
 }
 declare <vscale x 32 x half> @llvm.roundeven.nxv32f16(<vscale x 32 x half>)
 
 define <vscale x 1 x float> @roundeven_nxv1f32(<vscale x 1 x float> %x) {
 ; CHECK-LABEL: roundeven_nxv1f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI6_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI6_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 1 x float> @llvm.roundeven.nxv1f32(<vscale x 1 x float> %x)
   ret <vscale x 1 x float> %a
 }
 declare <vscale x 1 x float> @llvm.roundeven.nxv1f32(<vscale x 1 x float>)
 
 define <vscale x 2 x float> @roundeven_nxv2f32(<vscale x 2 x float> %x) {
 ; CHECK-LABEL: roundeven_nxv2f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI7_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI7_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 2 x float> @llvm.roundeven.nxv2f32(<vscale x 2 x float> %x)
   ret <vscale x 2 x float> %a
 }
 declare <vscale x 2 x float> @llvm.roundeven.nxv2f32(<vscale x 2 x float>)
 
 define <vscale x 4 x float> @roundeven_nxv4f32(<vscale x 4 x float> %x) {
 ; CHECK-LABEL: roundeven_nxv4f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI8_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI8_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 4 x float> @llvm.roundeven.nxv4f32(<vscale x 4 x float> %x)
   ret <vscale x 4 x float> %a
 }
 declare <vscale x 4 x float> @llvm.roundeven.nxv4f32(<vscale x 4 x float>)
 
 define <vscale x 8 x float> @roundeven_nxv8f32(<vscale x 8 x float> %x) {
 ; CHECK-LABEL: roundeven_nxv8f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI9_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI9_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 8 x float> @llvm.roundeven.nxv8f32(<vscale x 8 x float> %x)
   ret <vscale x 8 x float> %a
 }
 declare <vscale x 8 x float> @llvm.roundeven.nxv8f32(<vscale x 8 x float>)
 
 define <vscale x 16 x float> @roundeven_nxv16f32(<vscale x 16 x float> %x) {
 ; CHECK-LABEL: roundeven_nxv16f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI10_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI10_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m8, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 16 x float> @llvm.roundeven.nxv16f32(<vscale x 16 x float> %x)
   ret <vscale x 16 x float> %a
 }
 declare <vscale x 16 x float> @llvm.roundeven.nxv16f32(<vscale x 16 x float>)
 
 define <vscale x 1 x double> @roundeven_nxv1f64(<vscale x 1 x double> %x) {
 ; CHECK-LABEL: roundeven_nxv1f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI11_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI11_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 1 x double> @llvm.roundeven.nxv1f64(<vscale x 1 x double> %x)
   ret <vscale x 1 x double> %a
 }
 declare <vscale x 1 x double> @llvm.roundeven.nxv1f64(<vscale x 1 x double>)
 
 define <vscale x 2 x double> @roundeven_nxv2f64(<vscale x 2 x double> %x) {
 ; CHECK-LABEL: roundeven_nxv2f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI12_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI12_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e64, m2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 2 x double> @llvm.roundeven.nxv2f64(<vscale x 2 x double> %x)
   ret <vscale x 2 x double> %a
 }
 declare <vscale x 2 x double> @llvm.roundeven.nxv2f64(<vscale x 2 x double>)
 
 define <vscale x 4 x double> @roundeven_nxv4f64(<vscale x 4 x double> %x) {
 ; CHECK-LABEL: roundeven_nxv4f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI13_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI13_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e64, m4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 4 x double> @llvm.roundeven.nxv4f64(<vscale x 4 x double> %x)
   ret <vscale x 4 x double> %a
 }
 declare <vscale x 4 x double> @llvm.roundeven.nxv4f64(<vscale x 4 x double>)
 
 define <vscale x 8 x double> @roundeven_nxv8f64(<vscale x 8 x double> %x) {
 ; CHECK-LABEL: roundeven_nxv8f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI14_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI14_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 8 x double> @llvm.roundeven.nxv8f64(<vscale x 8 x double> %x)
   ret <vscale x 8 x double> %a
 }
 declare <vscale x 8 x double> @llvm.roundeven.nxv8f64(<vscale x 8 x double>)

llvm/test/CodeGen/RISCV/rvv/ftrunc-sdnode.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=ilp32d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=lp64d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 
 define <vscale x 1 x half> @trunc_nxv1f16(<vscale x 1 x half> %x) {
 ; CHECK-LABEL: trunc_nxv1f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI0_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI0_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    vfcvt.rtz.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 1 x half> @llvm.trunc.nxv1f16(<vscale x 1 x half> %x)
   ret <vscale x 1 x half> %a
 }
 declare <vscale x 1 x half> @llvm.trunc.nxv1f16(<vscale x 1 x half>)
 
 define <vscale x 2 x half> @trunc_nxv2f16(<vscale x 2 x half> %x) {
 ; CHECK-LABEL: trunc_nxv2f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI1_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI1_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    vfcvt.rtz.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 2 x half> @llvm.trunc.nxv2f16(<vscale x 2 x half> %x)
   ret <vscale x 2 x half> %a
 }
 declare <vscale x 2 x half> @llvm.trunc.nxv2f16(<vscale x 2 x half>)
 
 define <vscale x 4 x half> @trunc_nxv4f16(<vscale x 4 x half> %x) {
 ; CHECK-LABEL: trunc_nxv4f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI2_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI2_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    vfcvt.rtz.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 4 x half> @llvm.trunc.nxv4f16(<vscale x 4 x half> %x)
   ret <vscale x 4 x half> %a
 }
 declare <vscale x 4 x half> @llvm.trunc.nxv4f16(<vscale x 4 x half>)
 
 define <vscale x 8 x half> @trunc_nxv8f16(<vscale x 8 x half> %x) {
 ; CHECK-LABEL: trunc_nxv8f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI3_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI3_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, m2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    vfcvt.rtz.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 8 x half> @llvm.trunc.nxv8f16(<vscale x 8 x half> %x)
   ret <vscale x 8 x half> %a
 }
 declare <vscale x 8 x half> @llvm.trunc.nxv8f16(<vscale x 8 x half>)
 
 define <vscale x 16 x half> @trunc_nxv16f16(<vscale x 16 x half> %x) {
 ; CHECK-LABEL: trunc_nxv16f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI4_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI4_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, m4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    vfcvt.rtz.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 16 x half> @llvm.trunc.nxv16f16(<vscale x 16 x half> %x)
   ret <vscale x 16 x half> %a
 }
 declare <vscale x 16 x half> @llvm.trunc.nxv16f16(<vscale x 16 x half>)
 
 define <vscale x 32 x half> @trunc_nxv32f16(<vscale x 32 x half> %x) {
 ; CHECK-LABEL: trunc_nxv32f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI5_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI5_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e16, m8, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    vfcvt.rtz.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 32 x half> @llvm.trunc.nxv32f16(<vscale x 32 x half> %x)
   ret <vscale x 32 x half> %a
 }
 declare <vscale x 32 x half> @llvm.trunc.nxv32f16(<vscale x 32 x half>)
 
 define <vscale x 1 x float> @trunc_nxv1f32(<vscale x 1 x float> %x) {
 ; CHECK-LABEL: trunc_nxv1f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI6_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI6_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    vfcvt.rtz.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 1 x float> @llvm.trunc.nxv1f32(<vscale x 1 x float> %x)
   ret <vscale x 1 x float> %a
 }
 declare <vscale x 1 x float> @llvm.trunc.nxv1f32(<vscale x 1 x float>)
 
 define <vscale x 2 x float> @trunc_nxv2f32(<vscale x 2 x float> %x) {
 ; CHECK-LABEL: trunc_nxv2f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI7_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI7_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    vfcvt.rtz.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 2 x float> @llvm.trunc.nxv2f32(<vscale x 2 x float> %x)
   ret <vscale x 2 x float> %a
 }
 declare <vscale x 2 x float> @llvm.trunc.nxv2f32(<vscale x 2 x float>)
 
 define <vscale x 4 x float> @trunc_nxv4f32(<vscale x 4 x float> %x) {
 ; CHECK-LABEL: trunc_nxv4f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI8_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI8_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    vfcvt.rtz.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 4 x float> @llvm.trunc.nxv4f32(<vscale x 4 x float> %x)
   ret <vscale x 4 x float> %a
 }
 declare <vscale x 4 x float> @llvm.trunc.nxv4f32(<vscale x 4 x float>)
 
 define <vscale x 8 x float> @trunc_nxv8f32(<vscale x 8 x float> %x) {
 ; CHECK-LABEL: trunc_nxv8f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI9_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI9_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    vfcvt.rtz.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 8 x float> @llvm.trunc.nxv8f32(<vscale x 8 x float> %x)
   ret <vscale x 8 x float> %a
 }
 declare <vscale x 8 x float> @llvm.trunc.nxv8f32(<vscale x 8 x float>)
 
 define <vscale x 16 x float> @trunc_nxv16f32(<vscale x 16 x float> %x) {
 ; CHECK-LABEL: trunc_nxv16f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI10_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI10_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m8, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    vfcvt.rtz.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 16 x float> @llvm.trunc.nxv16f32(<vscale x 16 x float> %x)
   ret <vscale x 16 x float> %a
 }
 declare <vscale x 16 x float> @llvm.trunc.nxv16f32(<vscale x 16 x float>)
 
 define <vscale x 1 x double> @trunc_nxv1f64(<vscale x 1 x double> %x) {
 ; CHECK-LABEL: trunc_nxv1f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI11_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI11_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    vfcvt.rtz.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 1 x double> @llvm.trunc.nxv1f64(<vscale x 1 x double> %x)
   ret <vscale x 1 x double> %a
 }
 declare <vscale x 1 x double> @llvm.trunc.nxv1f64(<vscale x 1 x double>)
 
 define <vscale x 2 x double> @trunc_nxv2f64(<vscale x 2 x double> %x) {
 ; CHECK-LABEL: trunc_nxv2f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI12_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI12_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e64, m2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    vfcvt.rtz.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 2 x double> @llvm.trunc.nxv2f64(<vscale x 2 x double> %x)
   ret <vscale x 2 x double> %a
 }
 declare <vscale x 2 x double> @llvm.trunc.nxv2f64(<vscale x 2 x double>)
 
 define <vscale x 4 x double> @trunc_nxv4f64(<vscale x 4 x double> %x) {
 ; CHECK-LABEL: trunc_nxv4f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI13_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI13_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e64, m4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    vfcvt.rtz.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 4 x double> @llvm.trunc.nxv4f64(<vscale x 4 x double> %x)
   ret <vscale x 4 x double> %a
 }
 declare <vscale x 4 x double> @llvm.trunc.nxv4f64(<vscale x 4 x double>)
 
 define <vscale x 8 x double> @trunc_nxv8f64(<vscale x 8 x double> %x) {
 ; CHECK-LABEL: trunc_nxv8f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a0, %hi(.LCPI14_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI14_0)(a0)
-; CHECK-NEXT:    vsetvli a0, zero, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    vfcvt.rtz.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 8 x double> @llvm.trunc.nxv8f64(<vscale x 8 x double> %x)
   ret <vscale x 8 x double> %a
 }
 declare <vscale x 8 x double> @llvm.trunc.nxv8f64(<vscale x 8 x double>)

llvm/test/CodeGen/RISCV/rvv/round-vp.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=ilp32d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=lp64d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 
 declare <vscale x 1 x half> @llvm.vp.round.nxv1f16(<vscale x 1 x half>, <vscale x 1 x i1>, i32)
 
 define <vscale x 1 x half> @vp_round_nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv1f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI0_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI0_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 1 x half> @llvm.vp.round.nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x half> %v
 }
 
 define <vscale x 1 x half> @vp_round_nxv1f16_unmasked(<vscale x 1 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv1f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI1_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI1_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
   %v = call <vscale x 1 x half> @llvm.vp.round.nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x half> %v
 }
 
 declare <vscale x 2 x half> @llvm.vp.round.nxv2f16(<vscale x 2 x half>, <vscale x 2 x i1>, i32)
 
 define <vscale x 2 x half> @vp_round_nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv2f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI2_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI2_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 2 x half> @llvm.vp.round.nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x half> %v
 }
 
 define <vscale x 2 x half> @vp_round_nxv2f16_unmasked(<vscale x 2 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv2f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI3_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI3_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
   %v = call <vscale x 2 x half> @llvm.vp.round.nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x half> %v
 }
 
 declare <vscale x 4 x half> @llvm.vp.round.nxv4f16(<vscale x 4 x half>, <vscale x 4 x i1>, i32)
 
 define <vscale x 4 x half> @vp_round_nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv4f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI4_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI4_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 4 x half> @llvm.vp.round.nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x half> %v
 }
 
 define <vscale x 4 x half> @vp_round_nxv4f16_unmasked(<vscale x 4 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv4f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI5_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI5_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
   %v = call <vscale x 4 x half> @llvm.vp.round.nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x half> %v
 }
 
 declare <vscale x 8 x half> @llvm.vp.round.nxv8f16(<vscale x 8 x half>, <vscale x 8 x i1>, i32)
 
 define <vscale x 8 x half> @vp_round_nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv8f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI6_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI6_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 8 x half> @llvm.vp.round.nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x half> %v
 }
 
 define <vscale x 8 x half> @vp_round_nxv8f16_unmasked(<vscale x 8 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv8f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI7_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI7_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
   %v = call <vscale x 8 x half> @llvm.vp.round.nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x half> %v
 }
 
 declare <vscale x 16 x half> @llvm.vp.round.nxv16f16(<vscale x 16 x half>, <vscale x 16 x i1>, i32)
 
 define <vscale x 16 x half> @vp_round_nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv16f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI8_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI8_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 16 x half> @llvm.vp.round.nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x half> %v
 }
 
 define <vscale x 16 x half> @vp_round_nxv16f16_unmasked(<vscale x 16 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv16f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI9_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI9_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
   %v = call <vscale x 16 x half> @llvm.vp.round.nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x half> %v
 }
 
 declare <vscale x 32 x half> @llvm.vp.round.nxv32f16(<vscale x 32 x half>, <vscale x 32 x i1>, i32)
 
 define <vscale x 32 x half> @vp_round_nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv32f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI10_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI10_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 32 x half> @llvm.vp.round.nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x i1> %m, i32 %evl)
   ret <vscale x 32 x half> %v
 }
 
 define <vscale x 32 x half> @vp_round_nxv32f16_unmasked(<vscale x 32 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv32f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI11_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI11_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 32 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 32 x i1> %head, <vscale x 32 x i1> poison, <vscale x 32 x i32> zeroinitializer
   %v = call <vscale x 32 x half> @llvm.vp.round.nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x i1> %m, i32 %evl)
   ret <vscale x 32 x half> %v
 }
 
 declare <vscale x 1 x float> @llvm.vp.round.nxv1f32(<vscale x 1 x float>, <vscale x 1 x i1>, i32)
 
 define <vscale x 1 x float> @vp_round_nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv1f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI12_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI12_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 1 x float> @llvm.vp.round.nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x float> %v
 }
 
 define <vscale x 1 x float> @vp_round_nxv1f32_unmasked(<vscale x 1 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv1f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI13_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI13_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
   %v = call <vscale x 1 x float> @llvm.vp.round.nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x float> %v
 }
 
 declare <vscale x 2 x float> @llvm.vp.round.nxv2f32(<vscale x 2 x float>, <vscale x 2 x i1>, i32)
 
 define <vscale x 2 x float> @vp_round_nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv2f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI14_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI14_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 2 x float> @llvm.vp.round.nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x float> %v
 }
 
 define <vscale x 2 x float> @vp_round_nxv2f32_unmasked(<vscale x 2 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv2f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI15_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI15_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
   %v = call <vscale x 2 x float> @llvm.vp.round.nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x float> %v
 }
 
 declare <vscale x 4 x float> @llvm.vp.round.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, i32)
 
 define <vscale x 4 x float> @vp_round_nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv4f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI16_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI16_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 4 x float> @llvm.vp.round.nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x float> %v
 }
 
 define <vscale x 4 x float> @vp_round_nxv4f32_unmasked(<vscale x 4 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv4f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI17_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI17_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
   %v = call <vscale x 4 x float> @llvm.vp.round.nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x float> %v
 }
 
 declare <vscale x 8 x float> @llvm.vp.round.nxv8f32(<vscale x 8 x float>, <vscale x 8 x i1>, i32)
 
 define <vscale x 8 x float> @vp_round_nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv8f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI18_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI18_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 8 x float> @llvm.vp.round.nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x float> %v
 }
 
 define <vscale x 8 x float> @vp_round_nxv8f32_unmasked(<vscale x 8 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv8f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI19_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI19_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
   %v = call <vscale x 8 x float> @llvm.vp.round.nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x float> %v
 }
 
 declare <vscale x 16 x float> @llvm.vp.round.nxv16f32(<vscale x 16 x float>, <vscale x 16 x i1>, i32)
 
 define <vscale x 16 x float> @vp_round_nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv16f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI20_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI20_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 16 x float> @llvm.vp.round.nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x float> %v
 }
 
 define <vscale x 16 x float> @vp_round_nxv16f32_unmasked(<vscale x 16 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv16f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI21_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI21_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
   %v = call <vscale x 16 x float> @llvm.vp.round.nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x float> %v
 }
 
 declare <vscale x 1 x double> @llvm.vp.round.nxv1f64(<vscale x 1 x double>, <vscale x 1 x i1>, i32)
 
 define <vscale x 1 x double> @vp_round_nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv1f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI22_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI22_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 1 x double> @llvm.vp.round.nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x double> %v
 }
 
 define <vscale x 1 x double> @vp_round_nxv1f64_unmasked(<vscale x 1 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv1f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI23_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI23_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
   %v = call <vscale x 1 x double> @llvm.vp.round.nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x double> %v
 }
 
 declare <vscale x 2 x double> @llvm.vp.round.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, i32)
 
 define <vscale x 2 x double> @vp_round_nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv2f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI24_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI24_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 2 x double> @llvm.vp.round.nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x double> %v
 }
 
 define <vscale x 2 x double> @vp_round_nxv2f64_unmasked(<vscale x 2 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv2f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI25_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI25_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
   %v = call <vscale x 2 x double> @llvm.vp.round.nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x double> %v
 }
 
 declare <vscale x 4 x double> @llvm.vp.round.nxv4f64(<vscale x 4 x double>, <vscale x 4 x i1>, i32)
 
 define <vscale x 4 x double> @vp_round_nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv4f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI26_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI26_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 4 x double> @llvm.vp.round.nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x double> %v
 }
 
 define <vscale x 4 x double> @vp_round_nxv4f64_unmasked(<vscale x 4 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv4f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI27_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI27_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
   %v = call <vscale x 4 x double> @llvm.vp.round.nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x double> %v
 }
 
 declare <vscale x 7 x double> @llvm.vp.round.nxv7f64(<vscale x 7 x double>, <vscale x 7 x i1>, i32)
 
 define <vscale x 7 x double> @vp_round_nxv7f64(<vscale x 7 x double> %va, <vscale x 7 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv7f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI28_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI28_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 7 x double> @llvm.vp.round.nxv7f64(<vscale x 7 x double> %va, <vscale x 7 x i1> %m, i32 %evl)
   ret <vscale x 7 x double> %v
 }
 
 define <vscale x 7 x double> @vp_round_nxv7f64_unmasked(<vscale x 7 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv7f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI29_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI29_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 7 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 7 x i1> %head, <vscale x 7 x i1> poison, <vscale x 7 x i32> zeroinitializer
   %v = call <vscale x 7 x double> @llvm.vp.round.nxv7f64(<vscale x 7 x double> %va, <vscale x 7 x i1> %m, i32 %evl)
   ret <vscale x 7 x double> %v
 }
 
 declare <vscale x 8 x double> @llvm.vp.round.nxv8f64(<vscale x 8 x double>, <vscale x 8 x i1>, i32)
 
 define <vscale x 8 x double> @vp_round_nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv8f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI30_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI30_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 8 x double> @llvm.vp.round.nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x double> %v
 }
 
 define <vscale x 8 x double> @vp_round_nxv8f64_unmasked(<vscale x 8 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv8f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI31_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI31_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
   %v = call <vscale x 8 x double> @llvm.vp.round.nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x double> %v
 }
 
 ; Test splitting.
 declare <vscale x 16 x double> @llvm.vp.round.nxv16f64(<vscale x 16 x double>, <vscale x 16 x i1>, i32)
 
 define <vscale x 16 x double> @vp_round_nxv16f64(<vscale x 16 x double> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv16f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    slli a1, a1, 4
-; CHECK-NEXT:    sub sp, sp, a1
-; CHECK-NEXT:    vmv1r.v v24, v0
-; CHECK-NEXT:    addi a1, sp, 16
-; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT:    vmv1r.v v1, v0
 ; CHECK-NEXT:    li a2, 0
 ; CHECK-NEXT:    csrr a1, vlenb
 ; CHECK-NEXT:    srli a4, a1, 3
 ; CHECK-NEXT:    vsetvli a3, zero, e8, mf4, ta, ma
 ; CHECK-NEXT:    sub a3, a0, a1
-; CHECK-NEXT:    vslidedown.vx v25, v0, a4
+; CHECK-NEXT:    vslidedown.vx v2, v0, a4
 ; CHECK-NEXT:    bltu a0, a3, .LBB32_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    mv a2, a3
 ; CHECK-NEXT:  .LBB32_2:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a3, vlenb
+; CHECK-NEXT:    slli a3, a3, 3
+; CHECK-NEXT:    sub sp, sp, a3
 ; CHECK-NEXT:    lui a3, %hi(.LCPI32_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI32_0)(a3)
-; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfabs.v v8, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v25, v8, ft0, v0.t
+; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfabs.v v24, v16, v0.t
+; CHECK-NEXT:    vmflt.vf v2, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a2, 4
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfcvt.x.f.v v8, v16, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
+; CHECK-NEXT:    addi a3, sp, 16
+; CHECK-NEXT:    vs8r.v v24, (a3) # Unknown-size Folded Spill
 ; CHECK-NEXT:    fsrm a2
-; CHECK-NEXT:    vfcvt.f.x.v v8, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vfsgnj.vv v16, v8, v16, v0.t
-; CHECK-NEXT:    csrr a2, vlenb
-; CHECK-NEXT:    slli a2, a2, 3
-; CHECK-NEXT:    add a2, sp, a2
-; CHECK-NEXT:    addi a2, a2, 16
+; CHECK-NEXT:    addi a2, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a2) # Unknown-size Folded Reload
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
+; CHECK-NEXT:    addi a2, sp, 16
 ; CHECK-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
 ; CHECK-NEXT:    bltu a0, a1, .LBB32_4
 ; CHECK-NEXT:  # %bb.3:
 ; CHECK-NEXT:    mv a0, a1
 ; CHECK-NEXT:  .LBB32_4:
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vl8re8.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v24, v16, ft0, v0.t
+; CHECK-NEXT:    vmflt.vf v1, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 4
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
+; CHECK-NEXT:    vmv1r.v v0, v1
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    add a0, sp, a0
-; CHECK-NEXT:    addi a0, a0, 16
+; CHECK-NEXT:    addi a0, sp, 16
 ; CHECK-NEXT:    vl8re8.v v16, (a0) # Unknown-size Folded Reload
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 4
+; CHECK-NEXT:    slli a0, a0, 3
 ; CHECK-NEXT:    add sp, sp, a0
 ; CHECK-NEXT:    addi sp, sp, 16
 ; CHECK-NEXT:    ret
   %v = call <vscale x 16 x double> @llvm.vp.round.nxv16f64(<vscale x 16 x double> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x double> %v
 }
 
 define <vscale x 16 x double> @vp_round_nxv16f64_unmasked(<vscale x 16 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_round_nxv16f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    csrr a1, vlenb
 ; CHECK-NEXT:    mv a2, a0
 ; CHECK-NEXT:    bltu a0, a1, .LBB33_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    mv a2, a1
 ; CHECK-NEXT:  .LBB33_2:
 ; CHECK-NEXT:    lui a3, %hi(.LCPI33_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI33_0)(a3)
 ; CHECK-NEXT:    li a3, 0
-; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8
 ; CHECK-NEXT:    vmflt.vf v0, v24, ft0
 ; CHECK-NEXT:    fsrmi a2, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a2
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    sub a1, a0, a1
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    bltu a0, a1, .LBB33_4
 ; CHECK-NEXT:  # %bb.3:
 ; CHECK-NEXT:    mv a3, a1
 ; CHECK-NEXT:  .LBB33_4:
-; CHECK-NEXT:    vsetvli zero, a3, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a3, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v16
 ; CHECK-NEXT:    vmflt.vf v0, v24, ft0
 ; CHECK-NEXT:    fsrmi a0, 4
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
   %v = call <vscale x 16 x double> @llvm.vp.round.nxv16f64(<vscale x 16 x double> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x double> %v
 }

llvm/test/CodeGen/RISCV/rvv/roundeven-vp.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=ilp32d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=lp64d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 
 declare <vscale x 1 x half> @llvm.vp.roundeven.nxv1f16(<vscale x 1 x half>, <vscale x 1 x i1>, i32)
 
 define <vscale x 1 x half> @vp_roundeven_nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv1f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI0_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI0_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 1 x half> @llvm.vp.roundeven.nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x half> %v
 }
 
 define <vscale x 1 x half> @vp_roundeven_nxv1f16_unmasked(<vscale x 1 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv1f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI1_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI1_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
   %v = call <vscale x 1 x half> @llvm.vp.roundeven.nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x half> %v
 }
 
 declare <vscale x 2 x half> @llvm.vp.roundeven.nxv2f16(<vscale x 2 x half>, <vscale x 2 x i1>, i32)
 
 define <vscale x 2 x half> @vp_roundeven_nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv2f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI2_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI2_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 2 x half> @llvm.vp.roundeven.nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x half> %v
 }
 
 define <vscale x 2 x half> @vp_roundeven_nxv2f16_unmasked(<vscale x 2 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv2f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI3_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI3_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
   %v = call <vscale x 2 x half> @llvm.vp.roundeven.nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x half> %v
 }
 
 declare <vscale x 4 x half> @llvm.vp.roundeven.nxv4f16(<vscale x 4 x half>, <vscale x 4 x i1>, i32)
 
 define <vscale x 4 x half> @vp_roundeven_nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv4f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI4_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI4_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 4 x half> @llvm.vp.roundeven.nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x half> %v
 }
 
 define <vscale x 4 x half> @vp_roundeven_nxv4f16_unmasked(<vscale x 4 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv4f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI5_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI5_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
   %v = call <vscale x 4 x half> @llvm.vp.roundeven.nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x half> %v
 }
 
 declare <vscale x 8 x half> @llvm.vp.roundeven.nxv8f16(<vscale x 8 x half>, <vscale x 8 x i1>, i32)
 
 define <vscale x 8 x half> @vp_roundeven_nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv8f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI6_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI6_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 8 x half> @llvm.vp.roundeven.nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x half> %v
 }
 
 define <vscale x 8 x half> @vp_roundeven_nxv8f16_unmasked(<vscale x 8 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv8f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI7_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI7_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
   %v = call <vscale x 8 x half> @llvm.vp.roundeven.nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x half> %v
 }
 
 declare <vscale x 16 x half> @llvm.vp.roundeven.nxv16f16(<vscale x 16 x half>, <vscale x 16 x i1>, i32)
 
 define <vscale x 16 x half> @vp_roundeven_nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv16f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI8_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI8_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 16 x half> @llvm.vp.roundeven.nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x half> %v
 }
 
 define <vscale x 16 x half> @vp_roundeven_nxv16f16_unmasked(<vscale x 16 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv16f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI9_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI9_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
   %v = call <vscale x 16 x half> @llvm.vp.roundeven.nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x half> %v
 }
 
 declare <vscale x 32 x half> @llvm.vp.roundeven.nxv32f16(<vscale x 32 x half>, <vscale x 32 x i1>, i32)
 
 define <vscale x 32 x half> @vp_roundeven_nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv32f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI10_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI10_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 32 x half> @llvm.vp.roundeven.nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x i1> %m, i32 %evl)
   ret <vscale x 32 x half> %v
 }
 
 define <vscale x 32 x half> @vp_roundeven_nxv32f16_unmasked(<vscale x 32 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv32f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI11_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI11_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 32 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 32 x i1> %head, <vscale x 32 x i1> poison, <vscale x 32 x i32> zeroinitializer
   %v = call <vscale x 32 x half> @llvm.vp.roundeven.nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x i1> %m, i32 %evl)
   ret <vscale x 32 x half> %v
 }
 
 declare <vscale x 1 x float> @llvm.vp.roundeven.nxv1f32(<vscale x 1 x float>, <vscale x 1 x i1>, i32)
 
 define <vscale x 1 x float> @vp_roundeven_nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv1f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI12_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI12_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 1 x float> @llvm.vp.roundeven.nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x float> %v
 }
 
 define <vscale x 1 x float> @vp_roundeven_nxv1f32_unmasked(<vscale x 1 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv1f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI13_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI13_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
   %v = call <vscale x 1 x float> @llvm.vp.roundeven.nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x float> %v
 }
 
 declare <vscale x 2 x float> @llvm.vp.roundeven.nxv2f32(<vscale x 2 x float>, <vscale x 2 x i1>, i32)
 
 define <vscale x 2 x float> @vp_roundeven_nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv2f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI14_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI14_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 2 x float> @llvm.vp.roundeven.nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x float> %v
 }
 
 define <vscale x 2 x float> @vp_roundeven_nxv2f32_unmasked(<vscale x 2 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv2f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI15_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI15_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
   %v = call <vscale x 2 x float> @llvm.vp.roundeven.nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x float> %v
 }
 
 declare <vscale x 4 x float> @llvm.vp.roundeven.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, i32)
 
 define <vscale x 4 x float> @vp_roundeven_nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv4f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI16_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI16_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 4 x float> @llvm.vp.roundeven.nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x float> %v
 }
 
 define <vscale x 4 x float> @vp_roundeven_nxv4f32_unmasked(<vscale x 4 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv4f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI17_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI17_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
   %v = call <vscale x 4 x float> @llvm.vp.roundeven.nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x float> %v
 }
 
 declare <vscale x 8 x float> @llvm.vp.roundeven.nxv8f32(<vscale x 8 x float>, <vscale x 8 x i1>, i32)
 
 define <vscale x 8 x float> @vp_roundeven_nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv8f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI18_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI18_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 8 x float> @llvm.vp.roundeven.nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x float> %v
 }
 
 define <vscale x 8 x float> @vp_roundeven_nxv8f32_unmasked(<vscale x 8 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv8f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI19_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI19_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
   %v = call <vscale x 8 x float> @llvm.vp.roundeven.nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x float> %v
 }
 
 declare <vscale x 16 x float> @llvm.vp.roundeven.nxv16f32(<vscale x 16 x float>, <vscale x 16 x i1>, i32)
 
 define <vscale x 16 x float> @vp_roundeven_nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv16f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI20_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI20_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 16 x float> @llvm.vp.roundeven.nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x float> %v
 }
 
 define <vscale x 16 x float> @vp_roundeven_nxv16f32_unmasked(<vscale x 16 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv16f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI21_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI21_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
   %v = call <vscale x 16 x float> @llvm.vp.roundeven.nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x float> %v
 }
 
 declare <vscale x 1 x double> @llvm.vp.roundeven.nxv1f64(<vscale x 1 x double>, <vscale x 1 x i1>, i32)
 
 define <vscale x 1 x double> @vp_roundeven_nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv1f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI22_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI22_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 1 x double> @llvm.vp.roundeven.nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x double> %v
 }
 
 define <vscale x 1 x double> @vp_roundeven_nxv1f64_unmasked(<vscale x 1 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv1f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI23_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI23_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
   %v = call <vscale x 1 x double> @llvm.vp.roundeven.nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x double> %v
 }
 
 declare <vscale x 2 x double> @llvm.vp.roundeven.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, i32)
 
 define <vscale x 2 x double> @vp_roundeven_nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv2f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI24_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI24_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 2 x double> @llvm.vp.roundeven.nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x double> %v
 }
 
 define <vscale x 2 x double> @vp_roundeven_nxv2f64_unmasked(<vscale x 2 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv2f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI25_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI25_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
   %v = call <vscale x 2 x double> @llvm.vp.roundeven.nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x double> %v
 }
 
 declare <vscale x 4 x double> @llvm.vp.roundeven.nxv4f64(<vscale x 4 x double>, <vscale x 4 x i1>, i32)
 
 define <vscale x 4 x double> @vp_roundeven_nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv4f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI26_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI26_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 4 x double> @llvm.vp.roundeven.nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x double> %v
 }
 
 define <vscale x 4 x double> @vp_roundeven_nxv4f64_unmasked(<vscale x 4 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv4f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI27_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI27_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
   %v = call <vscale x 4 x double> @llvm.vp.roundeven.nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x double> %v
 }
 
 declare <vscale x 7 x double> @llvm.vp.roundeven.nxv7f64(<vscale x 7 x double>, <vscale x 7 x i1>, i32)
 
 define <vscale x 7 x double> @vp_roundeven_nxv7f64(<vscale x 7 x double> %va, <vscale x 7 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv7f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI28_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI28_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 7 x double> @llvm.vp.roundeven.nxv7f64(<vscale x 7 x double> %va, <vscale x 7 x i1> %m, i32 %evl)
   ret <vscale x 7 x double> %v
 }
 
 define <vscale x 7 x double> @vp_roundeven_nxv7f64_unmasked(<vscale x 7 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv7f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI29_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI29_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 7 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 7 x i1> %head, <vscale x 7 x i1> poison, <vscale x 7 x i32> zeroinitializer
   %v = call <vscale x 7 x double> @llvm.vp.roundeven.nxv7f64(<vscale x 7 x double> %va, <vscale x 7 x i1> %m, i32 %evl)
   ret <vscale x 7 x double> %v
 }
 
 declare <vscale x 8 x double> @llvm.vp.roundeven.nxv8f64(<vscale x 8 x double>, <vscale x 8 x i1>, i32)
 
 define <vscale x 8 x double> @vp_roundeven_nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv8f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI30_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI30_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 8 x double> @llvm.vp.roundeven.nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x double> %v
 }
 
 define <vscale x 8 x double> @vp_roundeven_nxv8f64_unmasked(<vscale x 8 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv8f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI31_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI31_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
   %v = call <vscale x 8 x double> @llvm.vp.roundeven.nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x double> %v
 }
 
 ; Test splitting.
 declare <vscale x 16 x double> @llvm.vp.roundeven.nxv16f64(<vscale x 16 x double>, <vscale x 16 x i1>, i32)
 
 define <vscale x 16 x double> @vp_roundeven_nxv16f64(<vscale x 16 x double> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv16f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    slli a1, a1, 4
-; CHECK-NEXT:    sub sp, sp, a1
-; CHECK-NEXT:    vmv1r.v v24, v0
-; CHECK-NEXT:    addi a1, sp, 16
-; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT:    vmv1r.v v1, v0
 ; CHECK-NEXT:    li a2, 0
 ; CHECK-NEXT:    csrr a1, vlenb
 ; CHECK-NEXT:    srli a4, a1, 3
 ; CHECK-NEXT:    vsetvli a3, zero, e8, mf4, ta, ma
 ; CHECK-NEXT:    sub a3, a0, a1
-; CHECK-NEXT:    vslidedown.vx v25, v0, a4
+; CHECK-NEXT:    vslidedown.vx v2, v0, a4
 ; CHECK-NEXT:    bltu a0, a3, .LBB32_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    mv a2, a3
 ; CHECK-NEXT:  .LBB32_2:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a3, vlenb
+; CHECK-NEXT:    slli a3, a3, 3
+; CHECK-NEXT:    sub sp, sp, a3
 ; CHECK-NEXT:    lui a3, %hi(.LCPI32_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI32_0)(a3)
-; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfabs.v v8, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v25, v8, ft0, v0.t
+; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfabs.v v24, v16, v0.t
+; CHECK-NEXT:    vmflt.vf v2, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a2, 0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfcvt.x.f.v v8, v16, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
+; CHECK-NEXT:    addi a3, sp, 16
+; CHECK-NEXT:    vs8r.v v24, (a3) # Unknown-size Folded Spill
 ; CHECK-NEXT:    fsrm a2
-; CHECK-NEXT:    vfcvt.f.x.v v8, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vfsgnj.vv v16, v8, v16, v0.t
-; CHECK-NEXT:    csrr a2, vlenb
-; CHECK-NEXT:    slli a2, a2, 3
-; CHECK-NEXT:    add a2, sp, a2
-; CHECK-NEXT:    addi a2, a2, 16
+; CHECK-NEXT:    addi a2, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a2) # Unknown-size Folded Reload
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
+; CHECK-NEXT:    addi a2, sp, 16
 ; CHECK-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
 ; CHECK-NEXT:    bltu a0, a1, .LBB32_4
 ; CHECK-NEXT:  # %bb.3:
 ; CHECK-NEXT:    mv a0, a1
 ; CHECK-NEXT:  .LBB32_4:
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vl8re8.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v24, v16, ft0, v0.t
+; CHECK-NEXT:    vmflt.vf v1, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
+; CHECK-NEXT:    vmv1r.v v0, v1
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    add a0, sp, a0
-; CHECK-NEXT:    addi a0, a0, 16
+; CHECK-NEXT:    addi a0, sp, 16
 ; CHECK-NEXT:    vl8re8.v v16, (a0) # Unknown-size Folded Reload
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 4
+; CHECK-NEXT:    slli a0, a0, 3
 ; CHECK-NEXT:    add sp, sp, a0
 ; CHECK-NEXT:    addi sp, sp, 16
 ; CHECK-NEXT:    ret
   %v = call <vscale x 16 x double> @llvm.vp.roundeven.nxv16f64(<vscale x 16 x double> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x double> %v
 }
 
 define <vscale x 16 x double> @vp_roundeven_nxv16f64_unmasked(<vscale x 16 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundeven_nxv16f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    csrr a1, vlenb
 ; CHECK-NEXT:    mv a2, a0
 ; CHECK-NEXT:    bltu a0, a1, .LBB33_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    mv a2, a1
 ; CHECK-NEXT:  .LBB33_2:
 ; CHECK-NEXT:    lui a3, %hi(.LCPI33_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI33_0)(a3)
 ; CHECK-NEXT:    li a3, 0
-; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8
 ; CHECK-NEXT:    vmflt.vf v0, v24, ft0
 ; CHECK-NEXT:    fsrmi a2, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a2
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    sub a1, a0, a1
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    bltu a0, a1, .LBB33_4
 ; CHECK-NEXT:  # %bb.3:
 ; CHECK-NEXT:    mv a3, a1
 ; CHECK-NEXT:  .LBB33_4:
-; CHECK-NEXT:    vsetvli zero, a3, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a3, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v16
 ; CHECK-NEXT:    vmflt.vf v0, v24, ft0
 ; CHECK-NEXT:    fsrmi a0, 0
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
   %v = call <vscale x 16 x double> @llvm.vp.roundeven.nxv16f64(<vscale x 16 x double> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x double> %v
 }

llvm/test/CodeGen/RISCV/rvv/roundtozero-vp.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=ilp32d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=lp64d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 
 declare <vscale x 1 x half> @llvm.vp.roundtozero.nxv1f16(<vscale x 1 x half>, <vscale x 1 x i1>, i32)
 
 define <vscale x 1 x half> @vp_roundtozero_nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv1f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI0_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI0_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 1 x half> @llvm.vp.roundtozero.nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x half> %v
 }
 
 define <vscale x 1 x half> @vp_roundtozero_nxv1f16_unmasked(<vscale x 1 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv1f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI1_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI1_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 1
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
   %v = call <vscale x 1 x half> @llvm.vp.roundtozero.nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x half> %v
 }
 
 declare <vscale x 2 x half> @llvm.vp.roundtozero.nxv2f16(<vscale x 2 x half>, <vscale x 2 x i1>, i32)
 
 define <vscale x 2 x half> @vp_roundtozero_nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv2f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI2_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI2_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 2 x half> @llvm.vp.roundtozero.nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x half> %v
 }
 
 define <vscale x 2 x half> @vp_roundtozero_nxv2f16_unmasked(<vscale x 2 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv2f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI3_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI3_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 1
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
   %v = call <vscale x 2 x half> @llvm.vp.roundtozero.nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x half> %v
 }
 
 declare <vscale x 4 x half> @llvm.vp.roundtozero.nxv4f16(<vscale x 4 x half>, <vscale x 4 x i1>, i32)
 
 define <vscale x 4 x half> @vp_roundtozero_nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv4f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI4_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI4_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 4 x half> @llvm.vp.roundtozero.nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x half> %v
 }
 
 define <vscale x 4 x half> @vp_roundtozero_nxv4f16_unmasked(<vscale x 4 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv4f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI5_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI5_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 1
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
   %v = call <vscale x 4 x half> @llvm.vp.roundtozero.nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x half> %v
 }
 
 declare <vscale x 8 x half> @llvm.vp.roundtozero.nxv8f16(<vscale x 8 x half>, <vscale x 8 x i1>, i32)
 
 define <vscale x 8 x half> @vp_roundtozero_nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv8f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI6_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI6_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 8 x half> @llvm.vp.roundtozero.nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x half> %v
 }
 
 define <vscale x 8 x half> @vp_roundtozero_nxv8f16_unmasked(<vscale x 8 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv8f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI7_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI7_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 1
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
   %v = call <vscale x 8 x half> @llvm.vp.roundtozero.nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x half> %v
 }
 
 declare <vscale x 16 x half> @llvm.vp.roundtozero.nxv16f16(<vscale x 16 x half>, <vscale x 16 x i1>, i32)
 
 define <vscale x 16 x half> @vp_roundtozero_nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv16f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI8_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI8_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 16 x half> @llvm.vp.roundtozero.nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x half> %v
 }
 
 define <vscale x 16 x half> @vp_roundtozero_nxv16f16_unmasked(<vscale x 16 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv16f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI9_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI9_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 1
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
   %v = call <vscale x 16 x half> @llvm.vp.roundtozero.nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x half> %v
 }
 
 declare <vscale x 32 x half> @llvm.vp.roundtozero.nxv32f16(<vscale x 32 x half>, <vscale x 32 x i1>, i32)
 
 define <vscale x 32 x half> @vp_roundtozero_nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv32f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI10_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI10_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 32 x half> @llvm.vp.roundtozero.nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x i1> %m, i32 %evl)
   ret <vscale x 32 x half> %v
 }
 
 define <vscale x 32 x half> @vp_roundtozero_nxv32f16_unmasked(<vscale x 32 x half> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv32f16_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI11_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI11_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 1
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 32 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 32 x i1> %head, <vscale x 32 x i1> poison, <vscale x 32 x i32> zeroinitializer
   %v = call <vscale x 32 x half> @llvm.vp.roundtozero.nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x i1> %m, i32 %evl)
   ret <vscale x 32 x half> %v
 }
 
 declare <vscale x 1 x float> @llvm.vp.roundtozero.nxv1f32(<vscale x 1 x float>, <vscale x 1 x i1>, i32)
 
 define <vscale x 1 x float> @vp_roundtozero_nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv1f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI12_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI12_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 1 x float> @llvm.vp.roundtozero.nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x float> %v
 }
 
 define <vscale x 1 x float> @vp_roundtozero_nxv1f32_unmasked(<vscale x 1 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv1f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI13_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI13_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 1
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
   %v = call <vscale x 1 x float> @llvm.vp.roundtozero.nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x float> %v
 }
 
 declare <vscale x 2 x float> @llvm.vp.roundtozero.nxv2f32(<vscale x 2 x float>, <vscale x 2 x i1>, i32)
 
 define <vscale x 2 x float> @vp_roundtozero_nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv2f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI14_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI14_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 2 x float> @llvm.vp.roundtozero.nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x float> %v
 }
 
 define <vscale x 2 x float> @vp_roundtozero_nxv2f32_unmasked(<vscale x 2 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv2f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI15_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI15_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 1
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
   %v = call <vscale x 2 x float> @llvm.vp.roundtozero.nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x float> %v
 }
 
 declare <vscale x 4 x float> @llvm.vp.roundtozero.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, i32)
 
 define <vscale x 4 x float> @vp_roundtozero_nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv4f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI16_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI16_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 4 x float> @llvm.vp.roundtozero.nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x float> %v
 }
 
 define <vscale x 4 x float> @vp_roundtozero_nxv4f32_unmasked(<vscale x 4 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv4f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI17_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI17_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 1
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
   %v = call <vscale x 4 x float> @llvm.vp.roundtozero.nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x float> %v
 }
 
 declare <vscale x 8 x float> @llvm.vp.roundtozero.nxv8f32(<vscale x 8 x float>, <vscale x 8 x i1>, i32)
 
 define <vscale x 8 x float> @vp_roundtozero_nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv8f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI18_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI18_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 8 x float> @llvm.vp.roundtozero.nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x float> %v
 }
 
 define <vscale x 8 x float> @vp_roundtozero_nxv8f32_unmasked(<vscale x 8 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv8f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI19_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI19_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 1
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
   %v = call <vscale x 8 x float> @llvm.vp.roundtozero.nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x float> %v
 }
 
 declare <vscale x 16 x float> @llvm.vp.roundtozero.nxv16f32(<vscale x 16 x float>, <vscale x 16 x i1>, i32)
 
 define <vscale x 16 x float> @vp_roundtozero_nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv16f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI20_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI20_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 16 x float> @llvm.vp.roundtozero.nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x float> %v
 }
 
 define <vscale x 16 x float> @vp_roundtozero_nxv16f32_unmasked(<vscale x 16 x float> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv16f32_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI21_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI21_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 1
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
   %v = call <vscale x 16 x float> @llvm.vp.roundtozero.nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x float> %v
 }
 
 declare <vscale x 1 x double> @llvm.vp.roundtozero.nxv1f64(<vscale x 1 x double>, <vscale x 1 x i1>, i32)
 
 define <vscale x 1 x double> @vp_roundtozero_nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv1f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI22_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI22_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 1 x double> @llvm.vp.roundtozero.nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x double> %v
 }
 
 define <vscale x 1 x double> @vp_roundtozero_nxv1f64_unmasked(<vscale x 1 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv1f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI23_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI23_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
 ; CHECK-NEXT:    fsrmi a0, 1
 ; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
   %v = call <vscale x 1 x double> @llvm.vp.roundtozero.nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x i1> %m, i32 %evl)
   ret <vscale x 1 x double> %v
 }
 
 declare <vscale x 2 x double> @llvm.vp.roundtozero.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, i32)
 
 define <vscale x 2 x double> @vp_roundtozero_nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv2f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v10, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI24_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI24_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v10
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 2 x double> @llvm.vp.roundtozero.nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x double> %v
 }
 
 define <vscale x 2 x double> @vp_roundtozero_nxv2f64_unmasked(<vscale x 2 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv2f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI25_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI25_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
 ; CHECK-NEXT:    fsrmi a0, 1
 ; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
   %v = call <vscale x 2 x double> @llvm.vp.roundtozero.nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x i1> %m, i32 %evl)
   ret <vscale x 2 x double> %v
 }
 
 declare <vscale x 4 x double> @llvm.vp.roundtozero.nxv4f64(<vscale x 4 x double>, <vscale x 4 x i1>, i32)
 
 define <vscale x 4 x double> @vp_roundtozero_nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv4f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v12, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI26_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI26_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v12
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 4 x double> @llvm.vp.roundtozero.nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x double> %v
 }
 
 define <vscale x 4 x double> @vp_roundtozero_nxv4f64_unmasked(<vscale x 4 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv4f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI27_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI27_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
 ; CHECK-NEXT:    fsrmi a0, 1
 ; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
   %v = call <vscale x 4 x double> @llvm.vp.roundtozero.nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x i1> %m, i32 %evl)
   ret <vscale x 4 x double> %v
 }
 
 declare <vscale x 7 x double> @llvm.vp.roundtozero.nxv7f64(<vscale x 7 x double>, <vscale x 7 x i1>, i32)
 
 define <vscale x 7 x double> @vp_roundtozero_nxv7f64(<vscale x 7 x double> %va, <vscale x 7 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv7f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI28_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI28_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 7 x double> @llvm.vp.roundtozero.nxv7f64(<vscale x 7 x double> %va, <vscale x 7 x i1> %m, i32 %evl)
   ret <vscale x 7 x double> %v
 }
 
 define <vscale x 7 x double> @vp_roundtozero_nxv7f64_unmasked(<vscale x 7 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv7f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI29_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI29_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 1
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 7 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 7 x i1> %head, <vscale x 7 x i1> poison, <vscale x 7 x i32> zeroinitializer
   %v = call <vscale x 7 x double> @llvm.vp.roundtozero.nxv7f64(<vscale x 7 x double> %va, <vscale x 7 x i1> %m, i32 %evl)
   ret <vscale x 7 x double> %v
 }
 
 declare <vscale x 8 x double> @llvm.vp.roundtozero.nxv8f64(<vscale x 8 x double>, <vscale x 8 x i1>, i32)
 
 define <vscale x 8 x double> @vp_roundtozero_nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv8f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vmv1r.v v16, v0
 ; CHECK-NEXT:    lui a1, %hi(.LCPI30_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI30_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v16, v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vmv1r.v v0, v16
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    ret
   %v = call <vscale x 8 x double> @llvm.vp.roundtozero.nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x double> %v
 }
 
 define <vscale x 8 x double> @vp_roundtozero_nxv8f64_unmasked(<vscale x 8 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv8f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    lui a1, %hi(.LCPI31_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI31_0)(a1)
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
 ; CHECK-NEXT:    fsrmi a0, 1
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
   %v = call <vscale x 8 x double> @llvm.vp.roundtozero.nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x i1> %m, i32 %evl)
   ret <vscale x 8 x double> %v
 }
 
 ; Test splitting.
 declare <vscale x 16 x double> @llvm.vp.roundtozero.nxv16f64(<vscale x 16 x double>, <vscale x 16 x i1>, i32)
 
 define <vscale x 16 x double> @vp_roundtozero_nxv16f64(<vscale x 16 x double> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv16f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    slli a1, a1, 4
-; CHECK-NEXT:    sub sp, sp, a1
-; CHECK-NEXT:    vmv1r.v v24, v0
-; CHECK-NEXT:    addi a1, sp, 16
-; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT:    vmv1r.v v1, v0
 ; CHECK-NEXT:    li a2, 0
 ; CHECK-NEXT:    csrr a1, vlenb
 ; CHECK-NEXT:    srli a4, a1, 3
 ; CHECK-NEXT:    vsetvli a3, zero, e8, mf4, ta, ma
 ; CHECK-NEXT:    sub a3, a0, a1
-; CHECK-NEXT:    vslidedown.vx v25, v0, a4
+; CHECK-NEXT:    vslidedown.vx v2, v0, a4
 ; CHECK-NEXT:    bltu a0, a3, .LBB32_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    mv a2, a3
 ; CHECK-NEXT:  .LBB32_2:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a3, vlenb
+; CHECK-NEXT:    slli a3, a3, 3
+; CHECK-NEXT:    sub sp, sp, a3
 ; CHECK-NEXT:    lui a3, %hi(.LCPI32_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI32_0)(a3)
-; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfabs.v v8, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v25, v8, ft0, v0.t
+; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfabs.v v24, v16, v0.t
+; CHECK-NEXT:    vmflt.vf v2, v24, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a2, 1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v25
-; CHECK-NEXT:    vfcvt.x.f.v v8, v16, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
+; CHECK-NEXT:    addi a3, sp, 16
+; CHECK-NEXT:    vs8r.v v24, (a3) # Unknown-size Folded Spill
 ; CHECK-NEXT:    fsrm a2
-; CHECK-NEXT:    vfcvt.f.x.v v8, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vfsgnj.vv v16, v8, v16, v0.t
-; CHECK-NEXT:    csrr a2, vlenb
-; CHECK-NEXT:    slli a2, a2, 3
-; CHECK-NEXT:    add a2, sp, a2
-; CHECK-NEXT:    addi a2, a2, 16
+; CHECK-NEXT:    addi a2, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a2) # Unknown-size Folded Reload
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
+; CHECK-NEXT:    addi a2, sp, 16
 ; CHECK-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
 ; CHECK-NEXT:    bltu a0, a1, .LBB32_4
 ; CHECK-NEXT:  # %bb.3:
 ; CHECK-NEXT:    mv a0, a1
 ; CHECK-NEXT:  .LBB32_4:
-; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vl8re8.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
 ; CHECK-NEXT:    vfabs.v v16, v8, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v24, v16, ft0, v0.t
+; CHECK-NEXT:    vmflt.vf v1, v16, ft0, v0.t
 ; CHECK-NEXT:    fsrmi a0, 1
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vmv1r.v v0, v24
+; CHECK-NEXT:    vmv1r.v v0, v1
 ; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    add a0, sp, a0
-; CHECK-NEXT:    addi a0, a0, 16
+; CHECK-NEXT:    addi a0, sp, 16
 ; CHECK-NEXT:    vl8re8.v v16, (a0) # Unknown-size Folded Reload
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 4
+; CHECK-NEXT:    slli a0, a0, 3
 ; CHECK-NEXT:    add sp, sp, a0
 ; CHECK-NEXT:    addi sp, sp, 16
 ; CHECK-NEXT:    ret
   %v = call <vscale x 16 x double> @llvm.vp.roundtozero.nxv16f64(<vscale x 16 x double> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x double> %v
 }
 
 define <vscale x 16 x double> @vp_roundtozero_nxv16f64_unmasked(<vscale x 16 x double> %va, i32 zeroext %evl) {
 ; CHECK-LABEL: vp_roundtozero_nxv16f64_unmasked:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    csrr a1, vlenb
 ; CHECK-NEXT:    mv a2, a0
 ; CHECK-NEXT:    bltu a0, a1, .LBB33_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    mv a2, a1
 ; CHECK-NEXT:  .LBB33_2:
 ; CHECK-NEXT:    lui a3, %hi(.LCPI33_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI33_0)(a3)
 ; CHECK-NEXT:    li a3, 0
-; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v8
 ; CHECK-NEXT:    vmflt.vf v0, v24, ft0
 ; CHECK-NEXT:    fsrmi a2, 1
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a2
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    sub a1, a0, a1
 ; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    bltu a0, a1, .LBB33_4
 ; CHECK-NEXT:  # %bb.3:
 ; CHECK-NEXT:    mv a3, a1
 ; CHECK-NEXT:  .LBB33_4:
-; CHECK-NEXT:    vsetvli zero, a3, e64, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a3, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v24, v16
 ; CHECK-NEXT:    vmflt.vf v0, v24, ft0
 ; CHECK-NEXT:    fsrmi a0, 1
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
 ; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
   %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
   %v = call <vscale x 16 x double> @llvm.vp.roundtozero.nxv16f64(<vscale x 16 x double> %va, <vscale x 16 x i1> %m, i32 %evl)
   ret <vscale x 16 x double> %v
 }

llvm/test/CodeGen/RISCV/rvv/rvv-peephole-vmerge-vops.ll

; CHECK-NEXT:    ret
   ret <vscale x 2 x i32> %b
 }
 
 ; Test glued node of merge should not be deleted.
 declare <vscale x 2 x i1> @llvm.vp.icmp.nxv2i32(<vscale x 2 x i32>, <vscale x 2 x i32>, metadata, <vscale x 2 x i1>, i32)
 define <vscale x 2 x i32> @vpmerge_vpadd2(<vscale x 2 x i32> %passthru, <vscale x 2 x i32> %x, <vscale x 2 x i32> %y, i32 zeroext %vl) {
 ; CHECK-LABEL: vpmerge_vpadd2:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, mu
 ; CHECK-NEXT:    vmseq.vv v0, v9, v10
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, tu, mu
 ; CHECK-NEXT:    vadd.vv v8, v9, v10, v0.t
 ; CHECK-NEXT:    ret
   %splat = insertelement <vscale x 2 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 2 x i1> %splat, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
   %a = call <vscale x 2 x i32> @llvm.vp.add.nxv2i32(<vscale x 2 x i32> %x, <vscale x 2 x i32> %y, <vscale x 2 x i1> %mask, i32 %vl)
   %m = call <vscale x 2 x i1> @llvm.vp.icmp.nxv2i32(<vscale x 2 x i32> %x, <vscale x 2 x i32> %y, metadata !"eq", <vscale x 2 x i1> %mask, i32 %vl)
   %b = call <vscale x 2 x i32> @llvm.vp.merge.nxv2i32(<vscale x 2 x i1> %m, <vscale x 2 x i32> %a, <vscale x 2 x i32> %passthru, i32 %vl)
   ret <vscale x 2 x i32> %b
; CHECK-NEXT:    ret
   %b = call <vscale x 2 x i32> @llvm.vp.merge.nxv2i32(<vscale x 2 x i1> %m, <vscale x 2 x i32> %a, <vscale x 2 x i32> %passthru, i32 %vl)
   ret <vscale x 2 x i32> %b
 }
 
 ; Test result has chain and glued node.
 define <vscale x 2 x i32> @vpmerge_vpload2(<vscale x 2 x i32> %passthru, <vscale x 2 x i32> * %p, <vscale x 2 x i32> %x, <vscale x 2 x i32> %y, i32 zeroext %vl) {
 ; CHECK-LABEL: vpmerge_vpload2:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli zero, a1, e32, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a1, e32, m1, tu, mu
 ; CHECK-NEXT:    vmseq.vv v0, v9, v10
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, tu, mu
 ; CHECK-NEXT:    vle32.v v8, (a0), v0.t
 ; CHECK-NEXT:    ret
   %splat = insertelement <vscale x 2 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 2 x i1> %splat, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
   %a = call <vscale x 2 x i32> @llvm.vp.load.nxv2i32.p0nxv2i32(<vscale x 2 x i32> * %p, <vscale x 2 x i1> %mask, i32 %vl)
   %m = call <vscale x 2 x i1> @llvm.vp.icmp.nxv2i32(<vscale x 2 x i32> %x, <vscale x 2 x i32> %y, metadata !"eq", <vscale x 2 x i1> %mask, i32 %vl)
   %b = call <vscale x 2 x i32> @llvm.vp.merge.nxv2i32(<vscale x 2 x i1> %m, <vscale x 2 x i32> %a, <vscale x 2 x i32> %passthru, i32 %vl)
   ret <vscale x 2 x i32> %b

 ; CHECK-NEXT:    vsetivli zero, 1, e16, m8, ta, ma
 ; CHECK-NEXT:    vle16.v v8, (zero)
 ; CHECK-NEXT:    vsetvli a0, zero, e8, m4, ta, ma
 ; CHECK-NEXT:    vmclr.m v0
 ; CHECK-NEXT:    vmv.v.i v16, 0
 ; CHECK-NEXT:    vsetivli zero, 0, e8, m4, tu, mu
 ; CHECK-NEXT:    vmv4r.v v20, v16
 ; CHECK-NEXT:    vssubu.vx v20, v16, zero, v0.t
-; CHECK-NEXT:    vsetvli zero, zero, e8, m4, ta, ma
 ; CHECK-NEXT:    vmseq.vv v0, v20, v16
 ; CHECK-NEXT:    vsetvli a0, zero, e16, m8, ta, ma
 ; CHECK-NEXT:    vmv.v.i v16, 0
 ; CHECK-NEXT:    vsetivli zero, 1, e16, m8, tu, ma
 ; CHECK-NEXT:    vmerge.vvm v16, v16, v8, v0
 ; CHECK-NEXT:    vsetivli zero, 0, e16, m8, ta, ma
 ; CHECK-NEXT:    vse16.v v16, (zero)
 ; CHECK-NEXT:    ret

llvm/test/CodeGen/RISCV/rvv/unmasked-tu.ll

 
 define <vscale x 1 x i64> @intrinsic_vrsub_vx_nxv1i64_nxv1i64_i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, i64 %2, iXLen %3) nounwind {
 ; RV32-LABEL: intrinsic_vrsub_vx_nxv1i64_nxv1i64_i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, tu, ma
 ; RV32-NEXT:    vlse64.v v10, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m1, tu, ma
 ; RV32-NEXT:    vsub.vv v8, v10, v9
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vrsub_vx_nxv1i64_nxv1i64_i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m1, tu, ma
 ; RV64-NEXT:    vrsub.vx v8, v9, a0

 
 define <vscale x 1 x i64> @intrinsic_vsadd_vx_nxv1i64_nxv1i64_i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, i64 %2, iXLen %3) nounwind {
 ; RV32-LABEL: intrinsic_vsadd_vx_nxv1i64_nxv1i64_i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, tu, ma
 ; RV32-NEXT:    vlse64.v v10, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m1, tu, ma
 ; RV32-NEXT:    vsadd.vv v8, v9, v10
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vsadd_vx_nxv1i64_nxv1i64_i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m1, tu, ma
 ; RV64-NEXT:    vsadd.vx v8, v9, a0

 
 define <vscale x 1 x i64> @intrinsic_vsmul_vx_nxv1i64_nxv1i64_i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, i64 %2, iXLen %3) nounwind {
 ; RV32-LABEL: intrinsic_vsmul_vx_nxv1i64_nxv1i64_i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, tu, ma
 ; RV32-NEXT:    vlse64.v v10, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m1, tu, ma
 ; RV32-NEXT:    vsmul.vv v8, v9, v10
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vsmul_vx_nxv1i64_nxv1i64_i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m1, tu, ma
 ; RV64-NEXT:    vsmul.vx v8, v9, a0

 
 define <vscale x 1 x i64> @intrinsic_vssub_vx_nxv1i64_nxv1i64_i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, i64 %2, iXLen %3) nounwind {
 ; RV32-LABEL: intrinsic_vssub_vx_nxv1i64_nxv1i64_i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, tu, ma
 ; RV32-NEXT:    vlse64.v v10, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m1, tu, ma
 ; RV32-NEXT:    vssub.vv v8, v9, v10
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vssub_vx_nxv1i64_nxv1i64_i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m1, tu, ma
 ; RV64-NEXT:    vssub.vx v8, v9, a0

 
 define <vscale x 1 x i64> @intrinsic_vssubu_vx_nxv1i64_nxv1i64_i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, i64 %2, iXLen %3) nounwind {
 ; RV32-LABEL: intrinsic_vssubu_vx_nxv1i64_nxv1i64_i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, tu, ma
 ; RV32-NEXT:    vlse64.v v10, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m1, tu, ma
 ; RV32-NEXT:    vssubu.vv v8, v9, v10
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vssubu_vx_nxv1i64_nxv1i64_i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m1, tu, ma
 ; RV64-NEXT:    vssubu.vx v8, v9, a0

 
 define <vscale x 8 x i64> @intrinsic_vmerge_vxm_nxv8i64_nxv8i64_i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, i64 %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
 ; RV32-LABEL: intrinsic_vmerge_vxm_nxv8i64_nxv8i64_i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m8, tu, ma
 ; RV32-NEXT:    vlse64.v v24, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m8, tu, ma
 ; RV32-NEXT:    vmerge.vvm v8, v16, v24, v0
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vmerge_vxm_nxv8i64_nxv8i64_i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m8, tu, ma
 ; RV64-NEXT:    vmerge.vxm v8, v16, a0, v0

 ; RV32-LABEL: intrinsic_vmerge_vim_nxv8i64_nxv8i64_i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    li a1, 15
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    li a1, -1
 ; RV32-NEXT:    sw a1, 8(sp)
 ; RV32-NEXT:    addi a1, sp, 8
-; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, tu, ma
 ; RV32-NEXT:    vlse64.v v24, (a1), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m8, tu, ma
 ; RV32-NEXT:    vmerge.vvm v8, v16, v24, v0
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vmerge_vim_nxv8i64_nxv8i64_i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    li a1, -1
 ; RV64-NEXT:    srli a1, a1, 28

llvm/test/CodeGen/RISCV/rvv/vector-splice.ll

 ; CHECK-NEXT:    vsetvli a0, zero, e8, mf8, ta, ma
 ; CHECK-NEXT:    vmv.v.i v9, 0
 ; CHECK-NEXT:    vmerge.vim v10, v9, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    srli a0, a0, 3
 ; CHECK-NEXT:    addi a0, a0, -1
 ; CHECK-NEXT:    vsetivli zero, 1, e8, mf8, ta, ma
 ; CHECK-NEXT:    vslidedown.vx v10, v10, a0
-; CHECK-NEXT:    vsetvli a0, zero, e8, mf8, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e8, mf8, tu, ma
 ; CHECK-NEXT:    vmv1r.v v0, v8
 ; CHECK-NEXT:    vmerge.vim v8, v9, 1, v0
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, tu, ma
 ; CHECK-NEXT:    vslideup.vi v10, v8, 1
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, ta, ma
 ; CHECK-NEXT:    vand.vi v8, v10, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %res = call <vscale x 1 x i1> @llvm.experimental.vector.splice.nxv1i1(<vscale x 1 x i1> %a, <vscale x 1 x i1> %b, i32 -1)
   ret <vscale x 1 x i1> %res
 }
 
 define <vscale x 1 x i1> @splice_nxv1i1_offset_max(<vscale x 1 x i1> %a, <vscale x 1 x i1> %b) #0 {
 ; CHECK-LABEL: splice_nxv1i1_offset_max:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a0, zero, e8, mf8, ta, ma
 ; CHECK-NEXT:    vmv.v.i v9, 0
 ; CHECK-NEXT:    vmerge.vim v10, v9, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    srli a0, a0, 3
 ; CHECK-NEXT:    addi a0, a0, -1
 ; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, ma
 ; CHECK-NEXT:    vslidedown.vi v10, v10, 1
-; CHECK-NEXT:    vsetvli a1, zero, e8, mf8, ta, ma
+; CHECK-NEXT:    vsetvli a1, zero, e8, mf8, tu, ma
 ; CHECK-NEXT:    vmv1r.v v0, v8
 ; CHECK-NEXT:    vmerge.vim v8, v9, 1, v0
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, tu, ma
 ; CHECK-NEXT:    vslideup.vx v10, v8, a0
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, ta, ma
 ; CHECK-NEXT:    vand.vi v8, v10, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %res = call <vscale x 1 x i1> @llvm.experimental.vector.splice.nxv1i1(<vscale x 1 x i1> %a, <vscale x 1 x i1> %b, i32 1)
   ret <vscale x 1 x i1> %res
 }
 
 declare <vscale x 2 x i1> @llvm.experimental.vector.splice.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, i32)
 
 define <vscale x 2 x i1> @splice_nxv2i1_offset_negone(<vscale x 2 x i1> %a, <vscale x 2 x i1> %b) #0 {
 ; CHECK-LABEL: splice_nxv2i1_offset_negone:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a0, zero, e8, mf4, ta, ma
 ; CHECK-NEXT:    vmv.v.i v9, 0
 ; CHECK-NEXT:    vmerge.vim v10, v9, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    srli a0, a0, 2
 ; CHECK-NEXT:    addi a0, a0, -1
 ; CHECK-NEXT:    vsetivli zero, 1, e8, mf4, ta, ma
 ; CHECK-NEXT:    vslidedown.vx v10, v10, a0
-; CHECK-NEXT:    vsetvli a0, zero, e8, mf4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e8, mf4, tu, ma
 ; CHECK-NEXT:    vmv1r.v v0, v8
 ; CHECK-NEXT:    vmerge.vim v8, v9, 1, v0
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf4, tu, ma
 ; CHECK-NEXT:    vslideup.vi v10, v8, 1
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf4, ta, ma
 ; CHECK-NEXT:    vand.vi v8, v10, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %res = call <vscale x 2 x i1> @llvm.experimental.vector.splice.nxv2i1(<vscale x 2 x i1> %a, <vscale x 2 x i1> %b, i32 -1)
   ret <vscale x 2 x i1> %res
 }
 
 define <vscale x 2 x i1> @splice_nxv2i1_offset_max(<vscale x 2 x i1> %a, <vscale x 2 x i1> %b) #0 {
 ; CHECK-LABEL: splice_nxv2i1_offset_max:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a0, zero, e8, mf4, ta, ma
 ; CHECK-NEXT:    vmv.v.i v9, 0
 ; CHECK-NEXT:    vmerge.vim v10, v9, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    srli a0, a0, 2
 ; CHECK-NEXT:    addi a0, a0, -3
 ; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, ma
 ; CHECK-NEXT:    vslidedown.vi v10, v10, 3
-; CHECK-NEXT:    vsetvli a1, zero, e8, mf4, ta, ma
+; CHECK-NEXT:    vsetvli a1, zero, e8, mf4, tu, ma
 ; CHECK-NEXT:    vmv1r.v v0, v8
 ; CHECK-NEXT:    vmerge.vim v8, v9, 1, v0
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf4, tu, ma
 ; CHECK-NEXT:    vslideup.vx v10, v8, a0
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf4, ta, ma
 ; CHECK-NEXT:    vand.vi v8, v10, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %res = call <vscale x 2 x i1> @llvm.experimental.vector.splice.nxv2i1(<vscale x 2 x i1> %a, <vscale x 2 x i1> %b, i32 3)
   ret <vscale x 2 x i1> %res
 }
 
 declare <vscale x 4 x i1> @llvm.experimental.vector.splice.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, i32)
 
 define <vscale x 4 x i1> @splice_nxv4i1_offset_negone(<vscale x 4 x i1> %a, <vscale x 4 x i1> %b) #0 {
 ; CHECK-LABEL: splice_nxv4i1_offset_negone:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a0, zero, e8, mf2, ta, ma
 ; CHECK-NEXT:    vmv.v.i v9, 0
 ; CHECK-NEXT:    vmerge.vim v10, v9, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    srli a0, a0, 1
 ; CHECK-NEXT:    addi a0, a0, -1
 ; CHECK-NEXT:    vsetivli zero, 1, e8, mf2, ta, ma
 ; CHECK-NEXT:    vslidedown.vx v10, v10, a0
-; CHECK-NEXT:    vsetvli a0, zero, e8, mf2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e8, mf2, tu, ma
 ; CHECK-NEXT:    vmv1r.v v0, v8
 ; CHECK-NEXT:    vmerge.vim v8, v9, 1, v0
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf2, tu, ma
 ; CHECK-NEXT:    vslideup.vi v10, v8, 1
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf2, ta, ma
 ; CHECK-NEXT:    vand.vi v8, v10, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %res = call <vscale x 4 x i1> @llvm.experimental.vector.splice.nxv4i1(<vscale x 4 x i1> %a, <vscale x 4 x i1> %b, i32 -1)
   ret <vscale x 4 x i1> %res
 }
 
 define <vscale x 4 x i1> @splice_nxv4i1_offset_max(<vscale x 4 x i1> %a, <vscale x 4 x i1> %b) #0 {
 ; CHECK-LABEL: splice_nxv4i1_offset_max:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a0, zero, e8, mf2, ta, ma
 ; CHECK-NEXT:    vmv.v.i v9, 0
 ; CHECK-NEXT:    vmerge.vim v10, v9, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    srli a0, a0, 1
 ; CHECK-NEXT:    addi a0, a0, -7
 ; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
 ; CHECK-NEXT:    vslidedown.vi v10, v10, 7
-; CHECK-NEXT:    vsetvli a1, zero, e8, mf2, ta, ma
+; CHECK-NEXT:    vsetvli a1, zero, e8, mf2, tu, ma
 ; CHECK-NEXT:    vmv1r.v v0, v8
 ; CHECK-NEXT:    vmerge.vim v8, v9, 1, v0
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf2, tu, ma
 ; CHECK-NEXT:    vslideup.vx v10, v8, a0
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf2, ta, ma
 ; CHECK-NEXT:    vand.vi v8, v10, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %res = call <vscale x 4 x i1> @llvm.experimental.vector.splice.nxv4i1(<vscale x 4 x i1> %a, <vscale x 4 x i1> %b, i32 7)
   ret <vscale x 4 x i1> %res
 }
 
 declare <vscale x 8 x i1> @llvm.experimental.vector.splice.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, i32)
 
 define <vscale x 8 x i1> @splice_nxv8i1_offset_negone(<vscale x 8 x i1> %a, <vscale x 8 x i1> %b) #0 {
 ; CHECK-LABEL: splice_nxv8i1_offset_negone:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a0, zero, e8, m1, ta, ma
 ; CHECK-NEXT:    vmv.v.i v9, 0
 ; CHECK-NEXT:    vmerge.vim v10, v9, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    addi a0, a0, -1
 ; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
 ; CHECK-NEXT:    vslidedown.vx v10, v10, a0
-; CHECK-NEXT:    vsetvli a0, zero, e8, m1, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e8, m1, tu, ma
 ; CHECK-NEXT:    vmv1r.v v0, v8
 ; CHECK-NEXT:    vmerge.vim v8, v9, 1, v0
-; CHECK-NEXT:    vsetvli zero, zero, e8, m1, tu, ma
 ; CHECK-NEXT:    vslideup.vi v10, v8, 1
-; CHECK-NEXT:    vsetvli zero, zero, e8, m1, ta, ma
 ; CHECK-NEXT:    vand.vi v8, v10, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %res = call <vscale x 8 x i1> @llvm.experimental.vector.splice.nxv8i1(<vscale x 8 x i1> %a, <vscale x 8 x i1> %b, i32 -1)
   ret <vscale x 8 x i1> %res
 }
 
 define <vscale x 8 x i1> @splice_nxv8i1_offset_max(<vscale x 8 x i1> %a, <vscale x 8 x i1> %b) #0 {
 ; CHECK-LABEL: splice_nxv8i1_offset_max:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a0, zero, e8, m1, ta, ma
 ; CHECK-NEXT:    vmv.v.i v9, 0
 ; CHECK-NEXT:    vmerge.vim v10, v9, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    addi a0, a0, -15
 ; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, ma
 ; CHECK-NEXT:    vslidedown.vi v10, v10, 15
-; CHECK-NEXT:    vsetvli a1, zero, e8, m1, ta, ma
+; CHECK-NEXT:    vsetvli a1, zero, e8, m1, tu, ma
 ; CHECK-NEXT:    vmv1r.v v0, v8
 ; CHECK-NEXT:    vmerge.vim v8, v9, 1, v0
-; CHECK-NEXT:    vsetvli zero, zero, e8, m1, tu, ma
 ; CHECK-NEXT:    vslideup.vx v10, v8, a0
-; CHECK-NEXT:    vsetvli zero, zero, e8, m1, ta, ma
 ; CHECK-NEXT:    vand.vi v8, v10, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %res = call <vscale x 8 x i1> @llvm.experimental.vector.splice.nxv8i1(<vscale x 8 x i1> %a, <vscale x 8 x i1> %b, i32 15)
   ret <vscale x 8 x i1> %res
 }
 
 declare <vscale x 16 x i1> @llvm.experimental.vector.splice.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, i32)
 
 define <vscale x 16 x i1> @splice_nxv16i1_offset_negone(<vscale x 16 x i1> %a, <vscale x 16 x i1> %b) #0 {
 ; CHECK-LABEL: splice_nxv16i1_offset_negone:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a0, zero, e8, m2, ta, ma
 ; CHECK-NEXT:    vmv.v.i v10, 0
 ; CHECK-NEXT:    vmerge.vim v12, v10, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    slli a0, a0, 1
 ; CHECK-NEXT:    addi a0, a0, -1
 ; CHECK-NEXT:    vsetivli zero, 1, e8, m2, ta, ma
 ; CHECK-NEXT:    vslidedown.vx v12, v12, a0
-; CHECK-NEXT:    vsetvli a0, zero, e8, m2, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e8, m2, tu, ma
 ; CHECK-NEXT:    vmv1r.v v0, v8
 ; CHECK-NEXT:    vmerge.vim v8, v10, 1, v0
-; CHECK-NEXT:    vsetvli zero, zero, e8, m2, tu, ma
 ; CHECK-NEXT:    vslideup.vi v12, v8, 1
-; CHECK-NEXT:    vsetvli zero, zero, e8, m2, ta, ma
 ; CHECK-NEXT:    vand.vi v8, v12, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %res = call <vscale x 16 x i1> @llvm.experimental.vector.splice.nxv16i1(<vscale x 16 x i1> %a, <vscale x 16 x i1> %b, i32 -1)
   ret <vscale x 16 x i1> %res
 }
 
 define <vscale x 16 x i1> @splice_nxv16i1_offset_max(<vscale x 16 x i1> %a, <vscale x 16 x i1> %b) #0 {
 ; CHECK-LABEL: splice_nxv16i1_offset_max:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a0, zero, e8, m2, ta, ma
 ; CHECK-NEXT:    vmv.v.i v10, 0
 ; CHECK-NEXT:    vmerge.vim v12, v10, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    slli a0, a0, 1
 ; CHECK-NEXT:    addi a0, a0, -31
 ; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, ma
 ; CHECK-NEXT:    vslidedown.vi v12, v12, 31
-; CHECK-NEXT:    vsetvli a1, zero, e8, m2, ta, ma
+; CHECK-NEXT:    vsetvli a1, zero, e8, m2, tu, ma
 ; CHECK-NEXT:    vmv1r.v v0, v8
 ; CHECK-NEXT:    vmerge.vim v8, v10, 1, v0
-; CHECK-NEXT:    vsetvli zero, zero, e8, m2, tu, ma
 ; CHECK-NEXT:    vslideup.vx v12, v8, a0
-; CHECK-NEXT:    vsetvli zero, zero, e8, m2, ta, ma
 ; CHECK-NEXT:    vand.vi v8, v12, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %res = call <vscale x 16 x i1> @llvm.experimental.vector.splice.nxv16i1(<vscale x 16 x i1> %a, <vscale x 16 x i1> %b, i32 31)
   ret <vscale x 16 x i1> %res
 }
 
 declare <vscale x 32 x i1> @llvm.experimental.vector.splice.nxv32i1(<vscale x 32 x i1>, <vscale x 32 x i1>, i32)
 
 define <vscale x 32 x i1> @splice_nxv32i1_offset_negone(<vscale x 32 x i1> %a, <vscale x 32 x i1> %b) #0 {
 ; CHECK-LABEL: splice_nxv32i1_offset_negone:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a0, zero, e8, m4, ta, ma
 ; CHECK-NEXT:    vmv.v.i v12, 0
 ; CHECK-NEXT:    vmerge.vim v16, v12, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    slli a0, a0, 2
 ; CHECK-NEXT:    addi a0, a0, -1
 ; CHECK-NEXT:    vsetivli zero, 1, e8, m4, ta, ma
 ; CHECK-NEXT:    vslidedown.vx v16, v16, a0
-; CHECK-NEXT:    vsetvli a0, zero, e8, m4, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e8, m4, tu, ma
 ; CHECK-NEXT:    vmv1r.v v0, v8
 ; CHECK-NEXT:    vmerge.vim v8, v12, 1, v0
-; CHECK-NEXT:    vsetvli zero, zero, e8, m4, tu, ma
 ; CHECK-NEXT:    vslideup.vi v16, v8, 1
-; CHECK-NEXT:    vsetvli zero, zero, e8, m4, ta, ma
 ; CHECK-NEXT:    vand.vi v8, v16, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %res = call <vscale x 32 x i1> @llvm.experimental.vector.splice.nxv32i1(<vscale x 32 x i1> %a, <vscale x 32 x i1> %b, i32 -1)
   ret <vscale x 32 x i1> %res
 }
 
 define <vscale x 32 x i1> @splice_nxv32i1_offset_max(<vscale x 32 x i1> %a, <vscale x 32 x i1> %b) #0 {
 ; CHECK-LABEL: splice_nxv32i1_offset_max:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a0, zero, e8, m4, ta, ma
 ; CHECK-NEXT:    vmv.v.i v12, 0
 ; CHECK-NEXT:    vmerge.vim v16, v12, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    slli a0, a0, 2
 ; CHECK-NEXT:    addi a0, a0, -63
 ; CHECK-NEXT:    li a1, 63
 ; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, ma
 ; CHECK-NEXT:    vslidedown.vx v16, v16, a1
-; CHECK-NEXT:    vsetvli a1, zero, e8, m4, ta, ma
+; CHECK-NEXT:    vsetvli a1, zero, e8, m4, tu, ma
 ; CHECK-NEXT:    vmv1r.v v0, v8
 ; CHECK-NEXT:    vmerge.vim v8, v12, 1, v0
-; CHECK-NEXT:    vsetvli zero, zero, e8, m4, tu, ma
 ; CHECK-NEXT:    vslideup.vx v16, v8, a0
-; CHECK-NEXT:    vsetvli zero, zero, e8, m4, ta, ma
 ; CHECK-NEXT:    vand.vi v8, v16, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %res = call <vscale x 32 x i1> @llvm.experimental.vector.splice.nxv32i1(<vscale x 32 x i1> %a, <vscale x 32 x i1> %b, i32 63)
   ret <vscale x 32 x i1> %res
 }
 
 declare <vscale x 64 x i1> @llvm.experimental.vector.splice.nxv64i1(<vscale x 64 x i1>, <vscale x 64 x i1>, i32)
 
 define <vscale x 64 x i1> @splice_nxv64i1_offset_negone(<vscale x 64 x i1> %a, <vscale x 64 x i1> %b) #0 {
 ; CHECK-LABEL: splice_nxv64i1_offset_negone:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a0, zero, e8, m8, ta, ma
 ; CHECK-NEXT:    vmv.v.i v16, 0
 ; CHECK-NEXT:    vmerge.vim v24, v16, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    slli a0, a0, 3
 ; CHECK-NEXT:    addi a0, a0, -1
 ; CHECK-NEXT:    vsetivli zero, 1, e8, m8, ta, ma
 ; CHECK-NEXT:    vslidedown.vx v24, v24, a0
-; CHECK-NEXT:    vsetvli a0, zero, e8, m8, ta, ma
+; CHECK-NEXT:    vsetvli a0, zero, e8, m8, tu, ma
 ; CHECK-NEXT:    vmv1r.v v0, v8
 ; CHECK-NEXT:    vmerge.vim v8, v16, 1, v0
-; CHECK-NEXT:    vsetvli zero, zero, e8, m8, tu, ma
 ; CHECK-NEXT:    vslideup.vi v24, v8, 1
-; CHECK-NEXT:    vsetvli zero, zero, e8, m8, ta, ma
 ; CHECK-NEXT:    vand.vi v8, v24, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %res = call <vscale x 64 x i1> @llvm.experimental.vector.splice.nxv64i1(<vscale x 64 x i1> %a, <vscale x 64 x i1> %b, i32 -1)
   ret <vscale x 64 x i1> %res
 }
 
 define <vscale x 64 x i1> @splice_nxv64i1_offset_max(<vscale x 64 x i1> %a, <vscale x 64 x i1> %b) #0 {
 ; CHECK-LABEL: splice_nxv64i1_offset_max:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a0, zero, e8, m8, ta, ma
 ; CHECK-NEXT:    vmv.v.i v16, 0
 ; CHECK-NEXT:    vmerge.vim v24, v16, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    slli a0, a0, 3
 ; CHECK-NEXT:    addi a0, a0, -127
 ; CHECK-NEXT:    li a1, 127
 ; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
 ; CHECK-NEXT:    vslidedown.vx v24, v24, a1
-; CHECK-NEXT:    vsetvli a1, zero, e8, m8, ta, ma
+; CHECK-NEXT:    vsetvli a1, zero, e8, m8, tu, ma
 ; CHECK-NEXT:    vmv1r.v v0, v8
 ; CHECK-NEXT:    vmerge.vim v8, v16, 1, v0
-; CHECK-NEXT:    vsetvli zero, zero, e8, m8, tu, ma
 ; CHECK-NEXT:    vslideup.vx v24, v8, a0
-; CHECK-NEXT:    vsetvli zero, zero, e8, m8, ta, ma
 ; CHECK-NEXT:    vand.vi v8, v24, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %res = call <vscale x 64 x i1> @llvm.experimental.vector.splice.nxv64i1(<vscale x 64 x i1> %a, <vscale x 64 x i1> %b, i32 127)
   ret <vscale x 64 x i1> %res
 }
 
 declare <vscale x 1 x i8> @llvm.experimental.vector.splice.nxv1i8(<vscale x 1 x i8>, <vscale x 1 x i8>, i32)

llvm/test/CodeGen/RISCV/rvv/vmacc.ll

 
 define <vscale x 1 x i64>  @intrinsic_vmacc_vx_nxv1i64_i64_nxv1i64(<vscale x 1 x i64> %0, i64 %1, <vscale x 1 x i64> %2, iXLen %3) nounwind {
 ; RV32-LABEL: intrinsic_vmacc_vx_nxv1i64_i64_nxv1i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, tu, ma
 ; RV32-NEXT:    vlse64.v v10, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m1, tu, ma
 ; RV32-NEXT:    vmacc.vv v8, v10, v9
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vmacc_vx_nxv1i64_i64_nxv1i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m1, tu, ma
 ; RV64-NEXT:    vmacc.vx v8, a0, v9

 
 define <vscale x 1 x i64> @intrinsic_vmacc_mask_vx_nxv1i64_i64_nxv1i64(<vscale x 1 x i64> %0, i64 %1, <vscale x 1 x i64> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
 ; RV32-LABEL: intrinsic_vmacc_mask_vx_nxv1i64_i64_nxv1i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, tu, mu
 ; RV32-NEXT:    vlse64.v v10, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m1, tu, mu
 ; RV32-NEXT:    vmacc.vv v8, v10, v9, v0.t
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vmacc_mask_vx_nxv1i64_i64_nxv1i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m1, tu, mu
 ; RV64-NEXT:    vmacc.vx v8, a0, v9, v0.t

 
 define <vscale x 2 x i64>  @intrinsic_vmacc_vx_nxv2i64_i64_nxv2i64(<vscale x 2 x i64> %0, i64 %1, <vscale x 2 x i64> %2, iXLen %3) nounwind {
 ; RV32-LABEL: intrinsic_vmacc_vx_nxv2i64_i64_nxv2i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m2, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m2, tu, ma
 ; RV32-NEXT:    vlse64.v v12, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m2, tu, ma
 ; RV32-NEXT:    vmacc.vv v8, v12, v10
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vmacc_vx_nxv2i64_i64_nxv2i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m2, tu, ma
 ; RV64-NEXT:    vmacc.vx v8, a0, v10

 
 define <vscale x 2 x i64> @intrinsic_vmacc_mask_vx_nxv2i64_i64_nxv2i64(<vscale x 2 x i64> %0, i64 %1, <vscale x 2 x i64> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
 ; RV32-LABEL: intrinsic_vmacc_mask_vx_nxv2i64_i64_nxv2i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m2, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m2, tu, mu
 ; RV32-NEXT:    vlse64.v v12, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m2, tu, mu
 ; RV32-NEXT:    vmacc.vv v8, v12, v10, v0.t
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vmacc_mask_vx_nxv2i64_i64_nxv2i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m2, tu, mu
 ; RV64-NEXT:    vmacc.vx v8, a0, v10, v0.t

 
 define <vscale x 4 x i64>  @intrinsic_vmacc_vx_nxv4i64_i64_nxv4i64(<vscale x 4 x i64> %0, i64 %1, <vscale x 4 x i64> %2, iXLen %3) nounwind {
 ; RV32-LABEL: intrinsic_vmacc_vx_nxv4i64_i64_nxv4i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m4, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m4, tu, ma
 ; RV32-NEXT:    vlse64.v v16, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m4, tu, ma
 ; RV32-NEXT:    vmacc.vv v8, v16, v12
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vmacc_vx_nxv4i64_i64_nxv4i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m4, tu, ma
 ; RV64-NEXT:    vmacc.vx v8, a0, v12

 
 define <vscale x 4 x i64> @intrinsic_vmacc_mask_vx_nxv4i64_i64_nxv4i64(<vscale x 4 x i64> %0, i64 %1, <vscale x 4 x i64> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
 ; RV32-LABEL: intrinsic_vmacc_mask_vx_nxv4i64_i64_nxv4i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m4, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m4, tu, mu
 ; RV32-NEXT:    vlse64.v v16, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m4, tu, mu
 ; RV32-NEXT:    vmacc.vv v8, v16, v12, v0.t
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vmacc_mask_vx_nxv4i64_i64_nxv4i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m4, tu, mu
 ; RV64-NEXT:    vmacc.vx v8, a0, v12, v0.t

llvm/test/CodeGen/RISCV/rvv/vmadd.ll

 
 define <vscale x 1 x i64>  @intrinsic_vmadd_vx_nxv1i64_i64_nxv1i64(<vscale x 1 x i64> %0, i64 %1, <vscale x 1 x i64> %2, iXLen %3) nounwind {
 ; RV32-LABEL: intrinsic_vmadd_vx_nxv1i64_i64_nxv1i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, tu, ma
 ; RV32-NEXT:    vlse64.v v10, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m1, tu, ma
 ; RV32-NEXT:    vmadd.vv v8, v10, v9
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vmadd_vx_nxv1i64_i64_nxv1i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m1, tu, ma
 ; RV64-NEXT:    vmadd.vx v8, a0, v9

 
 define <vscale x 1 x i64> @intrinsic_vmadd_mask_vx_nxv1i64_i64_nxv1i64(<vscale x 1 x i64> %0, i64 %1, <vscale x 1 x i64> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
 ; RV32-LABEL: intrinsic_vmadd_mask_vx_nxv1i64_i64_nxv1i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, tu, mu
 ; RV32-NEXT:    vlse64.v v10, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m1, tu, mu
 ; RV32-NEXT:    vmadd.vv v8, v10, v9, v0.t
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vmadd_mask_vx_nxv1i64_i64_nxv1i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m1, tu, mu
 ; RV64-NEXT:    vmadd.vx v8, a0, v9, v0.t

 
 define <vscale x 2 x i64>  @intrinsic_vmadd_vx_nxv2i64_i64_nxv2i64(<vscale x 2 x i64> %0, i64 %1, <vscale x 2 x i64> %2, iXLen %3) nounwind {
 ; RV32-LABEL: intrinsic_vmadd_vx_nxv2i64_i64_nxv2i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m2, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m2, tu, ma
 ; RV32-NEXT:    vlse64.v v12, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m2, tu, ma
 ; RV32-NEXT:    vmadd.vv v8, v12, v10
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vmadd_vx_nxv2i64_i64_nxv2i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m2, tu, ma
 ; RV64-NEXT:    vmadd.vx v8, a0, v10

 
 define <vscale x 2 x i64> @intrinsic_vmadd_mask_vx_nxv2i64_i64_nxv2i64(<vscale x 2 x i64> %0, i64 %1, <vscale x 2 x i64> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
 ; RV32-LABEL: intrinsic_vmadd_mask_vx_nxv2i64_i64_nxv2i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m2, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m2, tu, mu
 ; RV32-NEXT:    vlse64.v v12, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m2, tu, mu
 ; RV32-NEXT:    vmadd.vv v8, v12, v10, v0.t
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vmadd_mask_vx_nxv2i64_i64_nxv2i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m2, tu, mu
 ; RV64-NEXT:    vmadd.vx v8, a0, v10, v0.t

 
 define <vscale x 4 x i64>  @intrinsic_vmadd_vx_nxv4i64_i64_nxv4i64(<vscale x 4 x i64> %0, i64 %1, <vscale x 4 x i64> %2, iXLen %3) nounwind {
 ; RV32-LABEL: intrinsic_vmadd_vx_nxv4i64_i64_nxv4i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m4, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m4, tu, ma
 ; RV32-NEXT:    vlse64.v v16, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m4, tu, ma
 ; RV32-NEXT:    vmadd.vv v8, v16, v12
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vmadd_vx_nxv4i64_i64_nxv4i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m4, tu, ma
 ; RV64-NEXT:    vmadd.vx v8, a0, v12

 
 define <vscale x 4 x i64> @intrinsic_vmadd_mask_vx_nxv4i64_i64_nxv4i64(<vscale x 4 x i64> %0, i64 %1, <vscale x 4 x i64> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
 ; RV32-LABEL: intrinsic_vmadd_mask_vx_nxv4i64_i64_nxv4i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m4, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m4, tu, mu
 ; RV32-NEXT:    vlse64.v v16, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m4, tu, mu
 ; RV32-NEXT:    vmadd.vv v8, v16, v12, v0.t
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vmadd_mask_vx_nxv4i64_i64_nxv4i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m4, tu, mu
 ; RV64-NEXT:    vmadd.vx v8, a0, v12, v0.t

llvm/test/CodeGen/RISCV/rvv/vnmsac.ll

 
 define <vscale x 1 x i64>  @intrinsic_vnmsac_vx_nxv1i64_i64_nxv1i64(<vscale x 1 x i64> %0, i64 %1, <vscale x 1 x i64> %2, iXLen %3) nounwind {
 ; RV32-LABEL: intrinsic_vnmsac_vx_nxv1i64_i64_nxv1i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, tu, ma
 ; RV32-NEXT:    vlse64.v v10, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m1, tu, ma
 ; RV32-NEXT:    vnmsac.vv v8, v10, v9
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vnmsac_vx_nxv1i64_i64_nxv1i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m1, tu, ma
 ; RV64-NEXT:    vnmsac.vx v8, a0, v9

 
 define <vscale x 1 x i64> @intrinsic_vnmsac_mask_vx_nxv1i64_i64_nxv1i64(<vscale x 1 x i64> %0, i64 %1, <vscale x 1 x i64> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
 ; RV32-LABEL: intrinsic_vnmsac_mask_vx_nxv1i64_i64_nxv1i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, tu, mu
 ; RV32-NEXT:    vlse64.v v10, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m1, tu, mu
 ; RV32-NEXT:    vnmsac.vv v8, v10, v9, v0.t
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vnmsac_mask_vx_nxv1i64_i64_nxv1i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m1, tu, mu
 ; RV64-NEXT:    vnmsac.vx v8, a0, v9, v0.t

 
 define <vscale x 2 x i64>  @intrinsic_vnmsac_vx_nxv2i64_i64_nxv2i64(<vscale x 2 x i64> %0, i64 %1, <vscale x 2 x i64> %2, iXLen %3) nounwind {
 ; RV32-LABEL: intrinsic_vnmsac_vx_nxv2i64_i64_nxv2i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m2, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m2, tu, ma
 ; RV32-NEXT:    vlse64.v v12, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m2, tu, ma
 ; RV32-NEXT:    vnmsac.vv v8, v12, v10
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vnmsac_vx_nxv2i64_i64_nxv2i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m2, tu, ma
 ; RV64-NEXT:    vnmsac.vx v8, a0, v10

 
 define <vscale x 2 x i64> @intrinsic_vnmsac_mask_vx_nxv2i64_i64_nxv2i64(<vscale x 2 x i64> %0, i64 %1, <vscale x 2 x i64> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
 ; RV32-LABEL: intrinsic_vnmsac_mask_vx_nxv2i64_i64_nxv2i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m2, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m2, tu, mu
 ; RV32-NEXT:    vlse64.v v12, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m2, tu, mu
 ; RV32-NEXT:    vnmsac.vv v8, v12, v10, v0.t
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vnmsac_mask_vx_nxv2i64_i64_nxv2i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m2, tu, mu
 ; RV64-NEXT:    vnmsac.vx v8, a0, v10, v0.t

 
 define <vscale x 4 x i64>  @intrinsic_vnmsac_vx_nxv4i64_i64_nxv4i64(<vscale x 4 x i64> %0, i64 %1, <vscale x 4 x i64> %2, iXLen %3) nounwind {
 ; RV32-LABEL: intrinsic_vnmsac_vx_nxv4i64_i64_nxv4i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m4, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m4, tu, ma
 ; RV32-NEXT:    vlse64.v v16, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m4, tu, ma
 ; RV32-NEXT:    vnmsac.vv v8, v16, v12
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vnmsac_vx_nxv4i64_i64_nxv4i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m4, tu, ma
 ; RV64-NEXT:    vnmsac.vx v8, a0, v12

 
 define <vscale x 4 x i64> @intrinsic_vnmsac_mask_vx_nxv4i64_i64_nxv4i64(<vscale x 4 x i64> %0, i64 %1, <vscale x 4 x i64> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
 ; RV32-LABEL: intrinsic_vnmsac_mask_vx_nxv4i64_i64_nxv4i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m4, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m4, tu, mu
 ; RV32-NEXT:    vlse64.v v16, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m4, tu, mu
 ; RV32-NEXT:    vnmsac.vv v8, v16, v12, v0.t
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vnmsac_mask_vx_nxv4i64_i64_nxv4i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m4, tu, mu
 ; RV64-NEXT:    vnmsac.vx v8, a0, v12, v0.t

llvm/test/CodeGen/RISCV/rvv/vnmsub.ll

 
 define <vscale x 1 x i64>  @intrinsic_vnmsub_vx_nxv1i64_i64_nxv1i64(<vscale x 1 x i64> %0, i64 %1, <vscale x 1 x i64> %2, iXLen %3) nounwind {
 ; RV32-LABEL: intrinsic_vnmsub_vx_nxv1i64_i64_nxv1i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, tu, ma
 ; RV32-NEXT:    vlse64.v v10, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m1, tu, ma
 ; RV32-NEXT:    vnmsub.vv v8, v10, v9
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vnmsub_vx_nxv1i64_i64_nxv1i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m1, tu, ma
 ; RV64-NEXT:    vnmsub.vx v8, a0, v9

 
 define <vscale x 1 x i64> @intrinsic_vnmsub_mask_vx_nxv1i64_i64_nxv1i64(<vscale x 1 x i64> %0, i64 %1, <vscale x 1 x i64> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
 ; RV32-LABEL: intrinsic_vnmsub_mask_vx_nxv1i64_i64_nxv1i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, tu, mu
 ; RV32-NEXT:    vlse64.v v10, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m1, tu, mu
 ; RV32-NEXT:    vnmsub.vv v8, v10, v9, v0.t
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vnmsub_mask_vx_nxv1i64_i64_nxv1i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m1, tu, mu
 ; RV64-NEXT:    vnmsub.vx v8, a0, v9, v0.t

 
 define <vscale x 2 x i64>  @intrinsic_vnmsub_vx_nxv2i64_i64_nxv2i64(<vscale x 2 x i64> %0, i64 %1, <vscale x 2 x i64> %2, iXLen %3) nounwind {
 ; RV32-LABEL: intrinsic_vnmsub_vx_nxv2i64_i64_nxv2i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m2, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m2, tu, ma
 ; RV32-NEXT:    vlse64.v v12, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m2, tu, ma
 ; RV32-NEXT:    vnmsub.vv v8, v12, v10
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vnmsub_vx_nxv2i64_i64_nxv2i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m2, tu, ma
 ; RV64-NEXT:    vnmsub.vx v8, a0, v10

 
 define <vscale x 2 x i64> @intrinsic_vnmsub_mask_vx_nxv2i64_i64_nxv2i64(<vscale x 2 x i64> %0, i64 %1, <vscale x 2 x i64> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
 ; RV32-LABEL: intrinsic_vnmsub_mask_vx_nxv2i64_i64_nxv2i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m2, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m2, tu, mu
 ; RV32-NEXT:    vlse64.v v12, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m2, tu, mu
 ; RV32-NEXT:    vnmsub.vv v8, v12, v10, v0.t
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vnmsub_mask_vx_nxv2i64_i64_nxv2i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m2, tu, mu
 ; RV64-NEXT:    vnmsub.vx v8, a0, v10, v0.t

 
 define <vscale x 4 x i64>  @intrinsic_vnmsub_vx_nxv4i64_i64_nxv4i64(<vscale x 4 x i64> %0, i64 %1, <vscale x 4 x i64> %2, iXLen %3) nounwind {
 ; RV32-LABEL: intrinsic_vnmsub_vx_nxv4i64_i64_nxv4i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m4, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m4, tu, ma
 ; RV32-NEXT:    vlse64.v v16, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m4, tu, ma
 ; RV32-NEXT:    vnmsub.vv v8, v16, v12
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vnmsub_vx_nxv4i64_i64_nxv4i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m4, tu, ma
 ; RV64-NEXT:    vnmsub.vx v8, a0, v12

 
 define <vscale x 4 x i64> @intrinsic_vnmsub_mask_vx_nxv4i64_i64_nxv4i64(<vscale x 4 x i64> %0, i64 %1, <vscale x 4 x i64> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
 ; RV32-LABEL: intrinsic_vnmsub_mask_vx_nxv4i64_i64_nxv4i64:
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    sw a1, 12(sp)
 ; RV32-NEXT:    sw a0, 8(sp)
 ; RV32-NEXT:    addi a0, sp, 8
-; RV32-NEXT:    vsetvli zero, a2, e64, m4, ta, ma
+; RV32-NEXT:    vsetvli zero, a2, e64, m4, tu, mu
 ; RV32-NEXT:    vlse64.v v16, (a0), zero
-; RV32-NEXT:    vsetvli zero, zero, e64, m4, tu, mu
 ; RV32-NEXT:    vnmsub.vv v8, v16, v12, v0.t
 ; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: intrinsic_vnmsub_mask_vx_nxv4i64_i64_nxv4i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m4, tu, mu
 ; RV64-NEXT:    vnmsub.vx v8, a0, v12, v0.t

llvm/test/CodeGen/RISCV/rvv/vsetvli-insert-crossbb.ll

 
 define void @saxpy_vec(i64 %n, float %a, float* nocapture readonly %x, float* nocapture %y) {
 ; CHECK-LABEL: saxpy_vec:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    vsetvli a3, a0, e32, m8, ta, mu
 ; CHECK-NEXT:    beqz a3, .LBB8_2
 ; CHECK-NEXT:  .LBB8_1: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    vsetvli zero, a3, e32, m8, ta, ma
+; CHECK-NEXT:    vsetvli zero, a3, e32, m8, tu, ma
 ; CHECK-NEXT:    vle32.v v8, (a1)
 ; CHECK-NEXT:    vle32.v v16, (a2)
 ; CHECK-NEXT:    slli a4, a3, 2
 ; CHECK-NEXT:    add a1, a1, a4
-; CHECK-NEXT:    vsetvli zero, zero, e32, m8, tu, ma
 ; CHECK-NEXT:    vfmacc.vf v16, fa0, v8
 ; CHECK-NEXT:    vse32.v v16, (a2)
 ; CHECK-NEXT:    sub a0, a0, a3
 ; CHECK-NEXT:    vsetvli a3, a0, e32, m8, ta, mu
 ; CHECK-NEXT:    add a2, a2, a4
 ; CHECK-NEXT:    bnez a3, .LBB8_1
 ; CHECK-NEXT:  .LBB8_2: # %for.end
 ; CHECK-NEXT:    ret

llvm/test/CodeGen/RISCV/rvv/vsetvli-insert-crossbb.mir

body:             |
   ; CHECK-NEXT: {{  $}}
   ; CHECK-NEXT: bb.1:
   ; CHECK-NEXT:   successors: %bb.2(0x40000000), %bb.3(0x40000000)
   ; CHECK-NEXT: {{  $}}
   ; CHECK-NEXT:   [[PseudoVMSEQ_VI_MF2_:%[0-9]+]]:vmv0 = PseudoVMSEQ_VI_MF2 killed [[PseudoVID_V_MF2_]], 0, -1, 5 /* e32 */, implicit $vl, implicit $vtype
   ; CHECK-NEXT:   $v0 = COPY [[PseudoVMSEQ_VI_MF2_]]
   ; CHECK-NEXT:   dead $x0 = PseudoVSETVLIX0 killed $x0, 23 /* e32, mf2, tu, mu */, implicit-def $vl, implicit-def $vtype, implicit $vl
   ; CHECK-NEXT:   [[PseudoVLE32_V_MF2_MASK:%[0-9]+]]:vrnov0 = PseudoVLE32_V_MF2_MASK [[PseudoVMV_V_I_MF2_]], killed [[COPY]], $v0, -1, 5 /* e32 */, 0 /* tu, mu */, implicit $vl, implicit $vtype
-  ; CHECK-NEXT:   dead $x0 = PseudoVSETVLIX0 killed $x0, 197 /* e8, mf8, ta, ma */, implicit-def $vl, implicit-def $vtype, implicit $vl
   ; CHECK-NEXT:   [[PseudoVCPOP_M_B1_:%[0-9]+]]:gpr = PseudoVCPOP_M_B1 [[PseudoVMSEQ_VI_MF2_]], -1, 0 /* e8 */, implicit $vl, implicit $vtype
   ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:gpr = COPY $x0
   ; CHECK-NEXT:   BEQ killed [[PseudoVCPOP_M_B1_]], [[COPY2]], %bb.3
   ; CHECK-NEXT:   PseudoBR %bb.2
   ; CHECK-NEXT: {{  $}}
   ; CHECK-NEXT: bb.2:
   ; CHECK-NEXT:   successors: %bb.3(0x80000000)
   ; CHECK-NEXT: {{  $}}
   ; CHECK-NEXT:   [[LWU:%[0-9]+]]:gpr = LWU [[COPY1]], 0
   ; CHECK-NEXT: {{  $}}
   ; CHECK-NEXT: bb.3:
   ; CHECK-NEXT:   [[PHI:%[0-9]+]]:gpr = PHI [[DEF]], %bb.1, [[LWU]], %bb.2
-  ; CHECK-NEXT:   dead $x0 = PseudoVSETVLIX0 killed $x0, 215 /* e32, mf2, ta, ma */, implicit-def $vl, implicit-def $vtype, implicit $vl
   ; CHECK-NEXT:   [[PseudoVADD_VX_MF2_:%[0-9]+]]:vr = nsw PseudoVADD_VX_MF2 [[PseudoVLE32_V_MF2_MASK]], [[PHI]], -1, 5 /* e32 */, implicit $vl, implicit $vtype
   ; CHECK-NEXT:   $v0 = COPY [[PseudoVADD_VX_MF2_]]
   ; CHECK-NEXT:   PseudoRET implicit $v0
   bb.0:
     successors: %bb.1(0x80000000)
     liveins: $x10, $x11
 
     %0:gpr = COPY $x11

llvm/test/CodeGen/RISCV/rvv/vsetvli-insert.ll

entry:
   ret double %c3
 }
 
 
 define <vscale x 1 x double> @test18(<vscale x 1 x double> %a, double %b) nounwind {
 ; CHECK-LABEL: test18:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    vsetivli zero, 6, e64, m1, tu, ma
-; CHECK-NEXT:    vmv1r.v v9, v8
-; CHECK-NEXT:    vfmv.s.f v9, fa0
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
-; CHECK-NEXT:    vfadd.vv v8, v8, v8
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, tu, ma
+; CHECK-NEXT:    vfadd.vv v9, v8, v8
 ; CHECK-NEXT:    vfmv.s.f v8, fa0
+; CHECK-NEXT:    vfmv.s.f v9, fa0
 ; CHECK-NEXT:    vsetvli a0, zero, e64, m1, ta, ma
-; CHECK-NEXT:    vfadd.vv v8, v9, v8
+; CHECK-NEXT:    vfadd.vv v8, v8, v9
 ; CHECK-NEXT:    ret
 entry:
   %x = tail call i64 @llvm.riscv.vsetvli(i64 6, i64 3, i64 0)
   %y = call <vscale x 1 x double> @llvm.riscv.vfmv.s.f.nxv1f64(
     <vscale x 1 x double> %a, double %b, i64 2)
   %f2 = tail call <vscale x 1 x double> @llvm.riscv.vfadd.nxv1f64.nxv1f64(
     <vscale x 1 x double> undef,
     <vscale x 1 x double> %a,

 }
 
 ; Fault first loads can modify VL.
 ; TODO: The VSETVLI of vadd could be removed here.
 define <vscale x 1 x i64> @vleNff(i64* %str, i64 %n, i64 %x) {
 ; CHECK-LABEL: vleNff:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    vsetvli a1, a1, e8, m4, ta, mu
-; CHECK-NEXT:    vsetvli zero, a1, e64, m1, ta, ma
+; CHECK-NEXT:    vsetvli zero, a1, e64, m1, tu, ma
 ; CHECK-NEXT:    vle64ff.v v8, (a0)
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, tu, ma
 ; CHECK-NEXT:    vadd.vx v8, v8, a2
 ; CHECK-NEXT:    ret
 entry:
   %0 = tail call i64 @llvm.riscv.vsetvli.i64(i64 %n, i64 0, i64 2)
   %1 = bitcast i64* %str to <vscale x 1 x i64>*
   %2 = tail call { <vscale x 1 x i64>, i64 } @llvm.riscv.vleff.nxv1i64.i64(<vscale x 1 x i64> undef, <vscale x 1 x i64>* %1, i64 %0)
   %3 = extractvalue { <vscale x 1 x i64>, i64 } %2, 0
   %4 = extractvalue { <vscale x 1 x i64>, i64 } %2, 1

llvm/test/CodeGen/RISCV/urem-seteq-illegal-types.ll

 ; RV32MV-NEXT:    sh a2, 10(sp)
 ; RV32MV-NEXT:    lb a2, 4(a0)
 ; RV32MV-NEXT:    slli a2, a2, 10
 ; RV32MV-NEXT:    srli a1, a1, 22
 ; RV32MV-NEXT:    or a1, a1, a2
 ; RV32MV-NEXT:    andi a1, a1, 2047
 ; RV32MV-NEXT:    sh a1, 12(sp)
 ; RV32MV-NEXT:    addi a1, sp, 8
-; RV32MV-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; RV32MV-NEXT:    vsetivli zero, 4, e16, mf2, tu, ma
 ; RV32MV-NEXT:    vle16.v v8, (a1)
 ; RV32MV-NEXT:    vmv.v.i v9, 10
 ; RV32MV-NEXT:    li a1, 9
-; RV32MV-NEXT:    vsetvli zero, zero, e16, mf2, tu, ma
+; RV32MV-NEXT:    lui a2, %hi(.LCPI4_0)
+; RV32MV-NEXT:    addi a2, a2, %lo(.LCPI4_0)
+; RV32MV-NEXT:    vle16.v v10, (a2)
 ; RV32MV-NEXT:    vmv.s.x v9, a1
-; RV32MV-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
-; RV32MV-NEXT:    lui a1, %hi(.LCPI4_0)
-; RV32MV-NEXT:    addi a1, a1, %lo(.LCPI4_0)
-; RV32MV-NEXT:    vle16.v v10, (a1)
 ; RV32MV-NEXT:    vid.v v11
 ; RV32MV-NEXT:    vsub.vv v8, v8, v11
 ; RV32MV-NEXT:    vmul.vv v8, v8, v10
 ; RV32MV-NEXT:    vadd.vv v10, v8, v8
 ; RV32MV-NEXT:    vsll.vv v9, v10, v9
 ; RV32MV-NEXT:    vmv.v.i v10, 0
 ; RV32MV-NEXT:    li a1, 1
-; RV32MV-NEXT:    vsetvli zero, zero, e16, mf2, tu, ma
 ; RV32MV-NEXT:    vmv1r.v v11, v10
 ; RV32MV-NEXT:    vmv.s.x v11, a1
 ; RV32MV-NEXT:    li a1, 2047
-; RV32MV-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
 ; RV32MV-NEXT:    vand.vx v8, v8, a1
 ; RV32MV-NEXT:    lui a2, %hi(.LCPI4_1)
 ; RV32MV-NEXT:    addi a2, a2, %lo(.LCPI4_1)
 ; RV32MV-NEXT:    vle16.v v12, (a2)
 ; RV32MV-NEXT:    vsrl.vv v8, v8, v11
 ; RV32MV-NEXT:    vor.vv v8, v8, v9
 ; RV32MV-NEXT:    vand.vx v8, v8, a1
 ; RV32MV-NEXT:    vmsltu.vv v0, v12, v8

 ; RV64MV-NEXT:    srli a2, a1, 22
 ; RV64MV-NEXT:    sh a2, 12(sp)
 ; RV64MV-NEXT:    andi a2, a1, 2047
 ; RV64MV-NEXT:    sh a2, 8(sp)
 ; RV64MV-NEXT:    slli a1, a1, 42
 ; RV64MV-NEXT:    srli a1, a1, 53
 ; RV64MV-NEXT:    sh a1, 10(sp)
 ; RV64MV-NEXT:    addi a1, sp, 8
-; RV64MV-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; RV64MV-NEXT:    vsetivli zero, 4, e16, mf2, tu, ma
 ; RV64MV-NEXT:    vle16.v v8, (a1)
 ; RV64MV-NEXT:    vmv.v.i v9, 10
 ; RV64MV-NEXT:    li a1, 9
-; RV64MV-NEXT:    vsetvli zero, zero, e16, mf2, tu, ma
+; RV64MV-NEXT:    lui a2, %hi(.LCPI4_0)
+; RV64MV-NEXT:    addi a2, a2, %lo(.LCPI4_0)
+; RV64MV-NEXT:    vle16.v v10, (a2)
 ; RV64MV-NEXT:    vmv.s.x v9, a1
-; RV64MV-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
-; RV64MV-NEXT:    lui a1, %hi(.LCPI4_0)
-; RV64MV-NEXT:    addi a1, a1, %lo(.LCPI4_0)
-; RV64MV-NEXT:    vle16.v v10, (a1)
 ; RV64MV-NEXT:    vid.v v11
 ; RV64MV-NEXT:    vsub.vv v8, v8, v11
 ; RV64MV-NEXT:    vmul.vv v8, v8, v10
 ; RV64MV-NEXT:    vadd.vv v10, v8, v8
 ; RV64MV-NEXT:    vsll.vv v9, v10, v9
 ; RV64MV-NEXT:    vmv.v.i v10, 0
 ; RV64MV-NEXT:    li a1, 1
-; RV64MV-NEXT:    vsetvli zero, zero, e16, mf2, tu, ma
 ; RV64MV-NEXT:    vmv1r.v v11, v10
 ; RV64MV-NEXT:    vmv.s.x v11, a1
 ; RV64MV-NEXT:    li a1, 2047
-; RV64MV-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
 ; RV64MV-NEXT:    vand.vx v8, v8, a1
 ; RV64MV-NEXT:    lui a2, %hi(.LCPI4_1)
 ; RV64MV-NEXT:    addi a2, a2, %lo(.LCPI4_1)
 ; RV64MV-NEXT:    vle16.v v12, (a2)
 ; RV64MV-NEXT:    vsrl.vv v8, v8, v11
 ; RV64MV-NEXT:    vor.vv v8, v8, v9
 ; RV64MV-NEXT:    vand.vx v8, v8, a1
 ; RV64MV-NEXT:    vmsltu.vv v0, v12, v8