diff --git a/llvm/lib/Target/RISCV/RISCVFrameLowering.h b/llvm/lib/Target/RISCV/RISCVFrameLowering.h
--- a/llvm/lib/Target/RISCV/RISCVFrameLowering.h
+++ b/llvm/lib/Target/RISCV/RISCVFrameLowering.h
@@ -68,6 +68,9 @@
   bool isSupportedStackID(TargetStackID::Value ID) const override;
   TargetStackID::Value getStackIDForScalableVectors() const override;
 
+  void processFunctionBeforeFrameIndicesReplaced(
+      MachineFunction &MF, RegScavenger *RS = nullptr) const override;
+
 protected:
   const RISCVSubtarget &STI;
 
diff --git a/llvm/lib/Target/RISCV/RISCVFrameLowering.cpp b/llvm/lib/Target/RISCV/RISCVFrameLowering.cpp
--- a/llvm/lib/Target/RISCV/RISCVFrameLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVFrameLowering.cpp
@@ -480,6 +480,9 @@
     }
   }
 
+  if (RVVStackSize)
+    adjustStackForRVV(MF, MBB, MBBI, DL, -RVVStackSize);
+
   if (hasFP(MF)) {
     // Realign Stack
     const RISCVRegisterInfo *RI = STI.getRegisterInfo();
@@ -511,9 +514,6 @@
       }
     }
   }
-
-  if (RVVStackSize)
-    adjustStackForRVV(MF, MBB, MBBI, DL, -RVVStackSize);
 }
 
 void RISCVFrameLowering::emitEpilogue(MachineFunction &MF,
@@ -645,35 +645,36 @@
     if (hasBP(MF)) {
       FrameReg = RISCVABI::getBPReg();
       // |--------------------------| -- <-- FP
-      // | callee-saved registers   | |
-      // |--------------------------| | MFI.getStackSize()
-      // | scalar local variables   | |
-      // |--------------------------| --
-      // | Realignment              | |
+      // | callee-saved registers   | | <---------.
+      // |--------------------------| --          |
+      // | RVV objects              | |           |
+      // |--------------------------| --          |-- MFI.getStackSize()
+      // | realignment              | |           |
+      // |--------------------------| --          |
+      // | scalar local variables   | | <---------'
       // |--------------------------| -- <-- BP
-      // | RVV objects              | | RVFI->getRVVStackSize()
-      // |--------------------------| --
       // | VarSize objects          | |
       // |--------------------------| -- <-- SP
     } else {
       FrameReg = RISCV::X2;
-      // When using SP to access frame objects, we need to add RVV stack size.
-      //
       // |--------------------------| -- <-- FP
-      // | callee-saved registers   | |
-      // |--------------------------| | MFI.getStackSize()
-      // | scalar local variables   | |
-      // |--------------------------| --
-      // | Realignment              | |
-      // |--------------------------| --
-      // | RVV objects              | | RVFI->getRVVStackSize()
+      // | callee-saved registers   | | <---------.
+      // |--------------------------| --          |
+      // | RVV objects              | |           |
+      // |--------------------------| --          |-- MFI.getStackSize()
+      // | realignment              | |           |
+      // |--------------------------| --          |
+      // | scalar local variables   | | <---------'
       // |--------------------------| -- <-- SP
-      Offset += StackOffset::getScalable(RVFI->getRVVStackSize());
     }
     if (MFI.getStackID(FI) == TargetStackID::Default) {
       Offset += StackOffset::getFixed(MFI.getStackSize());
       if (FI < 0)
         Offset += StackOffset::getFixed(RVFI->getLibCallStackSize());
+    } else if (MFI.getStackID(FI) == TargetStackID::ScalableVector) {
+      Offset +=
+          StackOffset::get(MFI.getStackSize() - RVFI->getCalleeSavedStackSize(),
+                           RVFI->getRVVStackSize());
     }
   } else {
     FrameReg = RI->getFrameRegister(MF);
@@ -683,33 +684,37 @@
         Offset -= StackOffset::getFixed(RVFI->getLibCallStackSize());
       // When using FP to access scalable vector objects, we need to minus
       // the frame size.
-      //
       // |--------------------------| -- <-- FP
-      // | callee-saved registers   | |
-      // |--------------------------| | MFI.getStackSize()
-      // | scalar local variables   | |
-      // |--------------------------| -- (Offset of RVV objects is from here.)
-      // | RVV objects              |
+      // | callee-saved registers   | |<--------.
+      // |--------------------------| --        |
+      // | RVV objects              | |         |-- MFI.getStackSize()
+      // |--------------------------| --        |
+      // | scalar local variables   | |<--------'
       // |--------------------------|
       // | VarSize objects          |
       // |--------------------------| <-- SP
       if (MFI.getStackID(FI) == TargetStackID::ScalableVector)
-        Offset -= StackOffset::getFixed(MFI.getStackSize());
+        Offset -= StackOffset::getFixed(RVFI->getCalleeSavedStackSize());
+      else if (MFI.getStackID(FI) == TargetStackID::Default)
+        Offset -= StackOffset::getScalable(RVFI->getRVVStackSize());
     } else {
       // When using SP to access frame objects, we need to add RVV stack size.
       //
       // |--------------------------| -- <-- FP
-      // | callee-saved registers   | |
-      // |--------------------------| | MFI.getStackSize()
-      // | scalar local variables   | |
-      // |--------------------------| --
-      // | RVV objects              | | RVFI->getRVVStackSize()
+      // | callee-saved registers   | |<--------.
+      // |--------------------------| --        |
+      // | RVV objects              | |         |-- MFI.getStackSize()
+      // |--------------------------| --        |
+      // | scalar local variables   | |<--------'
       // |--------------------------| -- <-- SP
-      Offset += StackOffset::getScalable(RVFI->getRVVStackSize());
       if (MFI.getStackID(FI) == TargetStackID::Default) {
         Offset += StackOffset::getFixed(MFI.getStackSize());
         if (FI < 0)
           Offset += StackOffset::getFixed(RVFI->getLibCallStackSize());
+      } else if (MFI.getStackID(FI) == TargetStackID::ScalableVector) {
+        Offset += StackOffset::get(MFI.getStackSize() -
+                                       RVFI->getCalleeSavedStackSize(),
+                                   RVFI->getRVVStackSize());
       }
     }
   }
@@ -798,21 +803,46 @@
   const TargetRegisterInfo *RegInfo = MF.getSubtarget().getRegisterInfo();
   MachineFrameInfo &MFI = MF.getFrameInfo();
   const TargetRegisterClass *RC = &RISCV::GPRRegClass;
+
+  auto *RVFI = MF.getInfo<RISCVMachineFunctionInfo>();
+  int64_t RVVStackSize = assignRVVStackObjectOffsets(MFI);
+  RVFI->setRVVStackSize(RVVStackSize);
+
   // estimateStackSize has been observed to under-estimate the final stack
   // size, so give ourselves wiggle-room by checking for stack size
   // representable an 11-bit signed field rather than 12-bits.
   // FIXME: It may be possible to craft a function with a small stack that
   // still needs an emergency spill slot for branch relaxation. This case
   // would currently be missed.
-  if (!isInt<11>(MFI.estimateStackSize(MF))) {
+  if (!isInt<11>(MFI.estimateStackSize(MF)) || RVVStackSize != 0) {
     int RegScavFI = MFI.CreateStackObject(RegInfo->getSpillSize(*RC),
                                           RegInfo->getSpillAlign(*RC), false);
     RS->addScavengingFrameIndex(RegScavFI);
   }
+}
 
+void RISCVFrameLowering::processFunctionBeforeFrameIndicesReplaced(
+    MachineFunction &MF, RegScavenger *RS) const {
   auto *RVFI = MF.getInfo<RISCVMachineFunctionInfo>();
-  int64_t RVVStackSize = assignRVVStackObjectOffsets(MFI);
-  RVFI->setRVVStackSize(RVVStackSize);
+  const MachineFrameInfo &MFI = MF.getFrameInfo();
+  if (MFI.getCalleeSavedInfo().empty() || RVFI->useSaveRestoreLibCalls(MF)) {
+    RVFI->setCalleeSavedStackSize(0);
+    return;
+  }
+  int64_t MinOffset = std::numeric_limits<int64_t>::max();
+  int64_t MaxOffset = std::numeric_limits<int64_t>::min();
+  for (const auto &Info : MFI.getCalleeSavedInfo()) {
+    int FrameIdx = Info.getFrameIdx();
+    if (MFI.getStackID(FrameIdx) != TargetStackID::Default)
+      continue;
+    int64_t Offset = MFI.getObjectOffset(FrameIdx);
+    int64_t ObjSize = MFI.getObjectSize(FrameIdx);
+    MinOffset = std::min<int64_t>(Offset, MinOffset);
+    MaxOffset = std::max<int64_t>(Offset + ObjSize, MaxOffset);
+  }
+
+  unsigned Size = alignTo(MaxOffset - MinOffset, 16);
+  RVFI->setCalleeSavedStackSize(Size);
 }
 
 // Not preserve stack space within prologue for outgoing variables when the
diff --git a/llvm/lib/Target/RISCV/RISCVMachineFunctionInfo.h b/llvm/lib/Target/RISCV/RISCVMachineFunctionInfo.h
--- a/llvm/lib/Target/RISCV/RISCVMachineFunctionInfo.h
+++ b/llvm/lib/Target/RISCV/RISCVMachineFunctionInfo.h
@@ -34,6 +34,8 @@
   unsigned LibCallStackSize = 0;
   /// Size of RVV stack.
   uint64_t RVVStackSize = 0;
+  /// Size of stack frame to save callee saved registers
+  unsigned CalleeSavedStackSize = 0;
 
 public:
   RISCVMachineFunctionInfo(const MachineFunction &MF) {}
@@ -63,6 +65,9 @@
 
   uint64_t getRVVStackSize() const { return RVVStackSize; }
   void setRVVStackSize(uint64_t Size) { RVVStackSize = Size; }
+
+  unsigned getCalleeSavedStackSize() const { return CalleeSavedStackSize; }
+  void setCalleeSavedStackSize(unsigned Size) { CalleeSavedStackSize = Size; }
 };
 
 } // end namespace llvm
diff --git a/llvm/test/CodeGen/RISCV/rvv/access-fixed-objects-by-rvv.ll b/llvm/test/CodeGen/RISCV/rvv/access-fixed-objects-by-rvv.ll
--- a/llvm/test/CodeGen/RISCV/rvv/access-fixed-objects-by-rvv.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/access-fixed-objects-by-rvv.ll
@@ -30,23 +30,20 @@
 define <vscale x 1 x i64> @access_fixed_and_vector_objects(i64 *%val) {
 ; RV64IV-LABEL: access_fixed_and_vector_objects:
 ; RV64IV:       # %bb.0:
-; RV64IV-NEXT:    addi sp, sp, -528
+; RV64IV-NEXT:    addi	sp, sp, -528
 ; RV64IV-NEXT:    .cfi_def_cfa_offset 528
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    sub sp, sp, a0
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    add a0, sp, a0
-; RV64IV-NEXT:    addi a0, a0, 8
-; RV64IV-NEXT:    vl1re64.v v25, (a0)
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    add a0, sp, a0
-; RV64IV-NEXT:    ld a0, 520(a0)
-; RV64IV-NEXT:    vl1re64.v v26, (sp)
-; RV64IV-NEXT:    vsetvli a0, a0, e64,m1,ta,mu
-; RV64IV-NEXT:    vadd.vv v8, v25, v26
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    add sp, sp, a0
-; RV64IV-NEXT:    addi sp, sp, 528
+; RV64IV-NEXT:    csrr	a0, vlenb
+; RV64IV-NEXT:    sub	sp, sp, a0
+; RV64IV-NEXT:    addi	a0, sp, 8
+; RV64IV-NEXT:    vl1re64.v	v25, (a0)
+; RV64IV-NEXT:    ld	a0, 520(sp)
+; RV64IV-NEXT:    addi	a1, sp, 528
+; RV64IV-NEXT:    vl1re64.v	v26, (a1)
+; RV64IV-NEXT:    vsetvli	a0, a0, e64,m1,ta,mu
+; RV64IV-NEXT:    vadd.vv	v8, v25, v26
+; RV64IV-NEXT:    csrr	a0, vlenb
+; RV64IV-NEXT:    add	sp, sp, a0
+; RV64IV-NEXT:    addi	sp, sp, 528
 ; RV64IV-NEXT:    ret
   %local = alloca i64
   %vector = alloca <vscale x 1 x i64>
diff --git a/llvm/test/CodeGen/RISCV/rvv/allocate-lmul-2-4-8.ll b/llvm/test/CodeGen/RISCV/rvv/allocate-lmul-2-4-8.ll
--- a/llvm/test/CodeGen/RISCV/rvv/allocate-lmul-2-4-8.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/allocate-lmul-2-4-8.ll
@@ -5,10 +5,12 @@
 define void @lmul1() nounwind {
 ; CHECK-LABEL: lmul1:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    add sp, sp, a0
+; CHECK-NEXT:    addi	sp, sp, -16
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    add	sp, sp, a0
+; CHECK-NEXT:    addi	sp, sp, 16
 ; CHECK-NEXT:    ret
   %v = alloca <vscale x 1 x i64>
   ret void
@@ -17,12 +19,14 @@
 define void @lmul2() nounwind {
 ; CHECK-LABEL: lmul2:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 1
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 1
-; CHECK-NEXT:    add sp, sp, a0
+; CHECK-NEXT:    addi	sp, sp, -16
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 1
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 1
+; CHECK-NEXT:    add	sp, sp, a0
+; CHECK-NEXT:    addi	sp, sp, 16
 ; CHECK-NEXT:    ret
   %v = alloca <vscale x 2 x i64>
   ret void
@@ -31,18 +35,18 @@
 define void @lmul4() nounwind {
 ; CHECK-LABEL: lmul4:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -32
-; CHECK-NEXT:    sd ra, 24(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    sd s0, 16(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    addi s0, sp, 32
-; CHECK-NEXT:    andi sp, sp, -32
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 2
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    addi sp, s0, -32
-; CHECK-NEXT:    ld s0, 16(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    ld ra, 24(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    addi sp, sp, 32
+; CHECK-NEXT:    addi	sp, sp, -32
+; CHECK-NEXT:    sd	ra, 24(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    sd	s0, 16(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    addi	s0, sp, 32
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 2
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    andi	sp, sp, -32
+; CHECK-NEXT:    addi	sp, s0, -32
+; CHECK-NEXT:    ld	s0, 16(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    ld	ra, 24(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    addi	sp, sp, 32
 ; CHECK-NEXT:    ret
   %v = alloca <vscale x 4 x i64>
   ret void
@@ -51,18 +55,18 @@
 define void @lmul8() nounwind {
 ; CHECK-LABEL: lmul8:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -64
-; CHECK-NEXT:    sd ra, 56(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    sd s0, 48(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    addi s0, sp, 64
-; CHECK-NEXT:    andi sp, sp, -64
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    addi sp, s0, -64
-; CHECK-NEXT:    ld s0, 48(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    ld ra, 56(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    addi sp, sp, 64
+; CHECK-NEXT:    addi	sp, sp, -64
+; CHECK-NEXT:    sd	ra, 56(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    sd	s0, 48(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    addi	s0, sp, 64
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 3
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    andi	sp, sp, -64
+; CHECK-NEXT:    addi	sp, s0, -64
+; CHECK-NEXT:    ld	s0, 48(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    ld	ra, 56(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    addi	sp, sp, 64
 ; CHECK-NEXT:    ret
   %v = alloca <vscale x 8 x i64>
   ret void
@@ -71,14 +75,16 @@
 define void @lmul1_and_2() nounwind {
 ; CHECK-LABEL: lmul1_and_2:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    addi a1, zero, 3
-; CHECK-NEXT:    mul a0, a0, a1
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    addi a1, zero, 3
-; CHECK-NEXT:    mul a0, a0, a1
-; CHECK-NEXT:    add sp, sp, a0
+; CHECK-NEXT:    addi	sp, sp, -16
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    addi	a1, zero, 3
+; CHECK-NEXT:    mul	a0, a0, a1
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    addi	a1, zero, 3
+; CHECK-NEXT:    mul	a0, a0, a1
+; CHECK-NEXT:    add	sp, sp, a0
+; CHECK-NEXT:    addi	sp, sp, 16
 ; CHECK-NEXT:    ret
   %v1 = alloca <vscale x 1 x i64>
   %v2 = alloca <vscale x 2 x i64>
@@ -88,19 +94,19 @@
 define void @lmul2_and_4() nounwind {
 ; CHECK-LABEL: lmul2_and_4:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -32
-; CHECK-NEXT:    sd ra, 24(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    sd s0, 16(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    addi s0, sp, 32
-; CHECK-NEXT:    andi sp, sp, -32
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    addi a1, zero, 6
-; CHECK-NEXT:    mul a0, a0, a1
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    addi sp, s0, -32
-; CHECK-NEXT:    ld s0, 16(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    ld ra, 24(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    addi sp, sp, 32
+; CHECK-NEXT:    addi	sp, sp, -32
+; CHECK-NEXT:    sd	ra, 24(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    sd	s0, 16(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    addi	s0, sp, 32
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    addi	a1, zero, 6
+; CHECK-NEXT:    mul	a0, a0, a1
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    andi	sp, sp, -32
+; CHECK-NEXT:    addi	sp, s0, -32
+; CHECK-NEXT:    ld	s0, 16(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    ld	ra, 24(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    addi	sp, sp, 32
 ; CHECK-NEXT:    ret
   %v1 = alloca <vscale x 2 x i64>
   %v2 = alloca <vscale x 4 x i64>
@@ -110,19 +116,19 @@
 define void @lmul1_and_4() nounwind {
 ; CHECK-LABEL: lmul1_and_4:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -32
-; CHECK-NEXT:    sd ra, 24(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    sd s0, 16(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    addi s0, sp, 32
-; CHECK-NEXT:    andi sp, sp, -32
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    addi a1, zero, 5
-; CHECK-NEXT:    mul a0, a0, a1
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    addi sp, s0, -32
-; CHECK-NEXT:    ld s0, 16(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    ld ra, 24(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    addi sp, sp, 32
+; CHECK-NEXT:    addi	sp, sp, -32
+; CHECK-NEXT:    sd	ra, 24(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    sd	s0, 16(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    addi	s0, sp, 32
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    addi	a1, zero, 5
+; CHECK-NEXT:    mul	a0, a0, a1
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    andi	sp, sp, -32
+; CHECK-NEXT:    addi	sp, s0, -32
+; CHECK-NEXT:    ld	s0, 16(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    ld	ra, 24(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    addi	sp, sp, 32
 ; CHECK-NEXT:    ret
   %v1 = alloca <vscale x 1 x i64>
   %v2 = alloca <vscale x 4 x i64>
@@ -132,14 +138,16 @@
 define void @lmul2_and_1() nounwind {
 ; CHECK-LABEL: lmul2_and_1:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    addi a1, zero, 3
-; CHECK-NEXT:    mul a0, a0, a1
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    addi a1, zero, 3
-; CHECK-NEXT:    mul a0, a0, a1
-; CHECK-NEXT:    add sp, sp, a0
+; CHECK-NEXT:    addi	sp, sp, -16
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    addi	a1, zero, 3
+; CHECK-NEXT:    mul	a0, a0, a1
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    addi	a1, zero, 3
+; CHECK-NEXT:    mul	a0, a0, a1
+; CHECK-NEXT:    add	sp, sp, a0
+; CHECK-NEXT:    addi	sp, sp, 16
 ; CHECK-NEXT:    ret
   %v1 = alloca <vscale x 2 x i64>
   %v2 = alloca <vscale x 1 x i64>
@@ -149,19 +157,19 @@
 define void @lmul4_and_1() nounwind {
 ; CHECK-LABEL: lmul4_and_1:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -32
-; CHECK-NEXT:    sd ra, 24(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    sd s0, 16(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    addi s0, sp, 32
-; CHECK-NEXT:    andi sp, sp, -32
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    addi a1, zero, 5
-; CHECK-NEXT:    mul a0, a0, a1
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    addi sp, s0, -32
-; CHECK-NEXT:    ld s0, 16(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    ld ra, 24(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    addi sp, sp, 32
+; CHECK-NEXT:    addi	sp, sp, -32
+; CHECK-NEXT:    sd	ra, 24(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    sd	s0, 16(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    addi	s0, sp, 32
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    addi	a1, zero, 5
+; CHECK-NEXT:    mul	a0, a0, a1
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    andi	sp, sp, -32
+; CHECK-NEXT:    addi	sp, s0, -32
+; CHECK-NEXT:    ld	s0, 16(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    ld	ra, 24(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    addi	sp, sp, 32
 ; CHECK-NEXT:    ret
   %v1 = alloca <vscale x 4 x i64>
   %v2 = alloca <vscale x 1 x i64>
@@ -171,19 +179,19 @@
 define void @lmul4_and_2() nounwind {
 ; CHECK-LABEL: lmul4_and_2:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -32
-; CHECK-NEXT:    sd ra, 24(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    sd s0, 16(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    addi s0, sp, 32
-; CHECK-NEXT:    andi sp, sp, -32
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    addi a1, zero, 6
-; CHECK-NEXT:    mul a0, a0, a1
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    addi sp, s0, -32
-; CHECK-NEXT:    ld s0, 16(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    ld ra, 24(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    addi sp, sp, 32
+; CHECK-NEXT:    addi	sp, sp, -32
+; CHECK-NEXT:    sd	ra, 24(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    sd	s0, 16(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    addi	s0, sp, 32
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    addi	a1, zero, 6
+; CHECK-NEXT:    mul	a0, a0, a1
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    andi	sp, sp, -32
+; CHECK-NEXT:    addi	sp, s0, -32
+; CHECK-NEXT:    ld	s0, 16(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    ld	ra, 24(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    addi	sp, sp, 32
 ; CHECK-NEXT:    ret
   %v1 = alloca <vscale x 4 x i64>
   %v2 = alloca <vscale x 2 x i64>
@@ -193,19 +201,19 @@
 define void @lmul4_and_2_x2_0() nounwind {
 ; CHECK-LABEL: lmul4_and_2_x2_0:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -32
-; CHECK-NEXT:    sd ra, 24(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    sd s0, 16(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    addi s0, sp, 32
-; CHECK-NEXT:    andi sp, sp, -32
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    addi a1, zero, 12
-; CHECK-NEXT:    mul a0, a0, a1
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    addi sp, s0, -32
-; CHECK-NEXT:    ld s0, 16(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    ld ra, 24(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    addi sp, sp, 32
+; CHECK-NEXT:    addi	sp, sp, -32
+; CHECK-NEXT:    sd	ra, 24(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    sd	s0, 16(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    addi	s0, sp, 32
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    addi	a1, zero, 12
+; CHECK-NEXT:    mul	a0, a0, a1
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    andi	sp, sp, -32
+; CHECK-NEXT:    addi	sp, s0, -32
+; CHECK-NEXT:    ld	s0, 16(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    ld	ra, 24(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    addi	sp, sp, 32
 ; CHECK-NEXT:    ret
   %v1 = alloca <vscale x 4 x i64>
   %v2 = alloca <vscale x 2 x i64>
@@ -217,19 +225,19 @@
 define void @lmul4_and_2_x2_1() nounwind {
 ; CHECK-LABEL: lmul4_and_2_x2_1:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -32
-; CHECK-NEXT:    sd ra, 24(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    sd s0, 16(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    addi s0, sp, 32
-; CHECK-NEXT:    andi sp, sp, -32
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    addi a1, zero, 12
-; CHECK-NEXT:    mul a0, a0, a1
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    addi sp, s0, -32
-; CHECK-NEXT:    ld s0, 16(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    ld ra, 24(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    addi sp, sp, 32
+; CHECK-NEXT:    addi	sp, sp, -32
+; CHECK-NEXT:    sd	ra, 24(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    sd	s0, 16(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    addi	s0, sp, 32
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    addi	a1, zero, 12
+; CHECK-NEXT:    mul	a0, a0, a1
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    andi	sp, sp, -32
+; CHECK-NEXT:    addi	sp, s0, -32
+; CHECK-NEXT:    ld	s0, 16(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    ld	ra, 24(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    addi	sp, sp, 32
 ; CHECK-NEXT:    ret
   %v1 = alloca <vscale x 4 x i64>
   %v3 = alloca <vscale x 4 x i64>
@@ -242,22 +250,18 @@
 define void @gpr_and_lmul1_and_2() nounwind {
 ; CHECK-LABEL: gpr_and_lmul1_and_2:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    addi a1, zero, 3
-; CHECK-NEXT:    mul a0, a0, a1
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    addi a0, zero, 3
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    addi a2, zero, 3
-; CHECK-NEXT:    mul a1, a1, a2
-; CHECK-NEXT:    add a1, sp, a1
-; CHECK-NEXT:    sd a0, 8(a1)
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    addi a1, zero, 3
-; CHECK-NEXT:    mul a0, a0, a1
-; CHECK-NEXT:    add sp, sp, a0
-; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    addi	sp, sp, -16
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    addi	a1, zero, 3
+; CHECK-NEXT:    mul	a0, a0, a1
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    addi	a0, zero, 3
+; CHECK-NEXT:    sd	a0, 8(sp)
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    addi	a1, zero, 3
+; CHECK-NEXT:    mul	a0, a0, a1
+; CHECK-NEXT:    add	sp, sp, a0
+; CHECK-NEXT:    addi	sp, sp, 16
 ; CHECK-NEXT:    ret
   %x1 = alloca i64
   %v1 = alloca <vscale x 1 x i64>
@@ -269,25 +273,21 @@
 define void @gpr_and_lmul1_and_4() nounwind {
 ; CHECK-LABEL: gpr_and_lmul1_and_4:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -32
-; CHECK-NEXT:    sd ra, 24(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    sd s0, 16(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    addi s0, sp, 32
-; CHECK-NEXT:    andi sp, sp, -32
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    addi a1, zero, 5
-; CHECK-NEXT:    mul a0, a0, a1
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    addi a0, zero, 3
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    addi a2, zero, 5
-; CHECK-NEXT:    mul a1, a1, a2
-; CHECK-NEXT:    add a1, sp, a1
-; CHECK-NEXT:    sd a0, 8(a1)
-; CHECK-NEXT:    addi sp, s0, -32
-; CHECK-NEXT:    ld s0, 16(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    ld ra, 24(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    addi sp, sp, 32
+; CHECK-NEXT:    addi	sp, sp, -32
+; CHECK-NEXT:    sd	ra, 24(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    sd	s0, 16(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    addi	s0, sp, 32
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    addi	a1, zero, 5
+; CHECK-NEXT:    mul	a0, a0, a1
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    andi	sp, sp, -32
+; CHECK-NEXT:    addi	a0, zero, 3
+; CHECK-NEXT:    sd	a0, 8(sp)
+; CHECK-NEXT:    addi	sp, s0, -32
+; CHECK-NEXT:    ld	s0, 16(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    ld	ra, 24(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    addi	sp, sp, 32
 ; CHECK-NEXT:    ret
   %x1 = alloca i64
   %v1 = alloca <vscale x 1 x i64>
@@ -299,19 +299,19 @@
 define void @lmul_1_2_4_8() nounwind {
 ; CHECK-LABEL: lmul_1_2_4_8:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -64
-; CHECK-NEXT:    sd ra, 56(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    sd s0, 48(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    addi s0, sp, 64
-; CHECK-NEXT:    andi sp, sp, -64
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    addi a1, zero, 15
-; CHECK-NEXT:    mul a0, a0, a1
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    addi sp, s0, -64
-; CHECK-NEXT:    ld s0, 48(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    ld ra, 56(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    addi sp, sp, 64
+; CHECK-NEXT:    addi	sp, sp, -64
+; CHECK-NEXT:    sd	ra, 56(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    sd	s0, 48(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    addi	s0, sp, 64
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    addi	a1, zero, 15
+; CHECK-NEXT:    mul	a0, a0, a1
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    andi	sp, sp, -64
+; CHECK-NEXT:    addi	sp, s0, -64
+; CHECK-NEXT:    ld	s0, 48(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    ld	ra, 56(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    addi	sp, sp, 64
 ; CHECK-NEXT:    ret
   %v1 = alloca <vscale x 1 x i64>
   %v2 = alloca <vscale x 2 x i64>
@@ -323,19 +323,19 @@
 define void @lmul_1_2_4_8_x2_0() nounwind {
 ; CHECK-LABEL: lmul_1_2_4_8_x2_0:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -64
-; CHECK-NEXT:    sd ra, 56(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    sd s0, 48(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    addi s0, sp, 64
-; CHECK-NEXT:    andi sp, sp, -64
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    addi a1, zero, 30
-; CHECK-NEXT:    mul a0, a0, a1
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    addi sp, s0, -64
-; CHECK-NEXT:    ld s0, 48(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    ld ra, 56(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    addi sp, sp, 64
+; CHECK-NEXT:    addi	sp, sp, -64
+; CHECK-NEXT:    sd	ra, 56(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    sd	s0, 48(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    addi	s0, sp, 64
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    addi	a1, zero, 30
+; CHECK-NEXT:    mul	a0, a0, a1
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    andi	sp, sp, -64
+; CHECK-NEXT:    addi	sp, s0, -64
+; CHECK-NEXT:    ld	s0, 48(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    ld	ra, 56(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    addi	sp, sp, 64
 ; CHECK-NEXT:    ret
   %v1 = alloca <vscale x 1 x i64>
   %v2 = alloca <vscale x 1 x i64>
@@ -351,19 +351,19 @@
 define void @lmul_1_2_4_8_x2_1() nounwind {
 ; CHECK-LABEL: lmul_1_2_4_8_x2_1:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -64
-; CHECK-NEXT:    sd ra, 56(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    sd s0, 48(sp) # 8-byte Folded Spill
-; CHECK-NEXT:    addi s0, sp, 64
-; CHECK-NEXT:    andi sp, sp, -64
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    addi a1, zero, 30
-; CHECK-NEXT:    mul a0, a0, a1
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    addi sp, s0, -64
-; CHECK-NEXT:    ld s0, 48(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    ld ra, 56(sp) # 8-byte Folded Reload
-; CHECK-NEXT:    addi sp, sp, 64
+; CHECK-NEXT:    addi	sp, sp, -64
+; CHECK-NEXT:    sd	ra, 56(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    sd	s0, 48(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    addi	s0, sp, 64
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    addi	a1, zero, 30
+; CHECK-NEXT:    mul	a0, a0, a1
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    andi	sp, sp, -64
+; CHECK-NEXT:    addi	sp, s0, -64
+; CHECK-NEXT:    ld	s0, 48(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    ld	ra, 56(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    addi	sp, sp, 64
 ; CHECK-NEXT:    ret
   %v8 = alloca <vscale x 8 x i64>
   %v7 = alloca <vscale x 8 x i64>
@@ -379,12 +379,14 @@
 define void @masks() nounwind {
 ; CHECK-LABEL: masks:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 2
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 2
-; CHECK-NEXT:    add sp, sp, a0
+; CHECK-NEXT:    addi	sp, sp, -16
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 2
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 2
+; CHECK-NEXT:    add	sp, sp, a0
+; CHECK-NEXT:    addi	sp, sp, 16
 ; CHECK-NEXT:    ret
   %v1 = alloca <vscale x 1 x i1>
   %v2 = alloca <vscale x 2 x i1>
diff --git a/llvm/test/CodeGen/RISCV/rvv/localvar.ll b/llvm/test/CodeGen/RISCV/rvv/localvar.ll
--- a/llvm/test/CodeGen/RISCV/rvv/localvar.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/localvar.ll
@@ -5,19 +5,19 @@
 define void @local_var_mf8() {
 ; RV64IV-LABEL: local_var_mf8:
 ; RV64IV:       # %bb.0:
-; RV64IV-NEXT:    .cfi_def_cfa_offset 0
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 1
-; RV64IV-NEXT:    sub sp, sp, a0
-; RV64IV-NEXT:    vsetvli a0, zero, e8,mf8,ta,mu
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    add a0, sp, a0
-; RV64IV-NEXT:    vle8.v v25, (a0)
-; RV64IV-NEXT:    vle8.v v25, (sp)
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 1
-; RV64IV-NEXT:    add sp, sp, a0
-; RV64IV-NEXT:    ret
+; CHECK-NEXT:    .cfi_def_cfa_offset 0
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 1
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    vsetvli	a0, zero, e8,mf8,ta,mu
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    add	a0, sp, a0
+; CHECK-NEXT:    vle8.v	v25, (a0)
+; CHECK-NEXT:    vle8.v	v25, (sp)
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 1
+; CHECK-NEXT:    add	sp, sp, a0
+; CHECK-NEXT:    ret
   %local0 = alloca <vscale x 1 x i8>
   %local1 = alloca <vscale x 1 x i8>
   load volatile <vscale x 1 x i8>, <vscale x 1 x i8>* %local0
@@ -28,18 +28,18 @@
 define void @local_var_m1() {
 ; RV64IV-LABEL: local_var_m1:
 ; RV64IV:       # %bb.0:
-; RV64IV-NEXT:    .cfi_def_cfa_offset 0
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 1
-; RV64IV-NEXT:    sub sp, sp, a0
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    add a0, sp, a0
-; RV64IV-NEXT:    vl1r.v v25, (a0)
-; RV64IV-NEXT:    vl1r.v v25, (sp)
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 1
-; RV64IV-NEXT:    add sp, sp, a0
-; RV64IV-NEXT:    ret
+; CHECK-NEXT:    .cfi_def_cfa_offset 0
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 1
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    add	a0, sp, a0
+; CHECK-NEXT:    vl1r.v	v25, (a0)
+; CHECK-NEXT:    vl1r.v	v25, (sp)
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 1
+; CHECK-NEXT:    add	sp, sp, a0
+; CHECK-NEXT:    ret
   %local0 = alloca <vscale x 8 x i8>
   %local1 = alloca <vscale x 8 x i8>
   load volatile <vscale x 8 x i8>, <vscale x 8 x i8>* %local0
@@ -50,19 +50,19 @@
 define void @local_var_m2() {
 ; RV64IV-LABEL: local_var_m2:
 ; RV64IV:       # %bb.0:
-; RV64IV-NEXT:    .cfi_def_cfa_offset 0
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 2
-; RV64IV-NEXT:    sub sp, sp, a0
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 1
-; RV64IV-NEXT:    add a0, sp, a0
-; RV64IV-NEXT:    vl2r.v v26, (a0)
-; RV64IV-NEXT:    vl2r.v v26, (sp)
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 2
-; RV64IV-NEXT:    add sp, sp, a0
-; RV64IV-NEXT:    ret
+; CHECK-NEXT:    .cfi_def_cfa_offset 0
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 2
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 1
+; CHECK-NEXT:    add	a0, sp, a0
+; CHECK-NEXT:    vl2r.v	v26, (a0)
+; CHECK-NEXT:    vl2r.v	v26, (sp)
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 2
+; CHECK-NEXT:    add	sp, sp, a0
+; CHECK-NEXT:    ret
   %local0 = alloca <vscale x 16 x i8>
   %local1 = alloca <vscale x 16 x i8>
   load volatile <vscale x 16 x i8>, <vscale x 16 x i8>* %local0
@@ -73,28 +73,30 @@
 define void @local_var_m4() {
 ; RV64IV-LABEL: local_var_m4:
 ; RV64IV:       # %bb.0:
-; RV64IV-NEXT:    addi sp, sp, -32
-; RV64IV-NEXT:    .cfi_def_cfa_offset 32
-; RV64IV-NEXT:    sd ra, 24(sp) # 8-byte Folded Spill
-; RV64IV-NEXT:    sd s0, 16(sp) # 8-byte Folded Spill
-; RV64IV-NEXT:    .cfi_offset ra, -8
-; RV64IV-NEXT:    .cfi_offset s0, -16
-; RV64IV-NEXT:    addi s0, sp, 32
-; RV64IV-NEXT:    .cfi_def_cfa s0, 0
-; RV64IV-NEXT:    andi sp, sp, -32
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 3
-; RV64IV-NEXT:    sub sp, sp, a0
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 2
-; RV64IV-NEXT:    add a0, sp, a0
-; RV64IV-NEXT:    vl4r.v v28, (a0)
-; RV64IV-NEXT:    vl4r.v v28, (sp)
-; RV64IV-NEXT:    addi sp, s0, -32
-; RV64IV-NEXT:    ld s0, 16(sp) # 8-byte Folded Reload
-; RV64IV-NEXT:    ld ra, 24(sp) # 8-byte Folded Reload
-; RV64IV-NEXT:    addi sp, sp, 32
-; RV64IV-NEXT:    ret
+; CHECK-NEXT:    addi	sp, sp, -32
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
+; CHECK-NEXT:    sd	ra, 24(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    sd	s0, 16(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_offset ra, -8
+; CHECK-NEXT:    .cfi_offset s0, -16
+; CHECK-NEXT:    addi	s0, sp, 32
+; CHECK-NEXT:    .cfi_def_cfa s0, 0
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 3
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    andi	sp, sp, -32
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 2
+; CHECK-NEXT:    add	a0, sp, a0
+; CHECK-NEXT:    addi	a0, a0, 16
+; CHECK-NEXT:    vl4r.v	v28, (a0)
+; CHECK-NEXT:    addi	a0, sp, 16
+; CHECK-NEXT:    vl4r.v	v28, (a0)
+; CHECK-NEXT:    addi	sp, s0, -32
+; CHECK-NEXT:    ld	s0, 16(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    ld	ra, 24(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    addi	sp, sp, 32
+; CHECK-NEXT:    ret
   %local0 = alloca <vscale x 32 x i8>
   %local1 = alloca <vscale x 32 x i8>
   load volatile <vscale x 32 x i8>, <vscale x 32 x i8>* %local0
@@ -105,28 +107,30 @@
 define void @local_var_m8() {
 ; RV64IV-LABEL: local_var_m8:
 ; RV64IV:       # %bb.0:
-; RV64IV-NEXT:    addi sp, sp, -64
-; RV64IV-NEXT:    .cfi_def_cfa_offset 64
-; RV64IV-NEXT:    sd ra, 56(sp) # 8-byte Folded Spill
-; RV64IV-NEXT:    sd s0, 48(sp) # 8-byte Folded Spill
-; RV64IV-NEXT:    .cfi_offset ra, -8
-; RV64IV-NEXT:    .cfi_offset s0, -16
-; RV64IV-NEXT:    addi s0, sp, 64
-; RV64IV-NEXT:    .cfi_def_cfa s0, 0
-; RV64IV-NEXT:    andi sp, sp, -64
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 4
-; RV64IV-NEXT:    sub sp, sp, a0
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 3
-; RV64IV-NEXT:    add a0, sp, a0
-; RV64IV-NEXT:    vl8r.v v8, (a0)
-; RV64IV-NEXT:    vl8r.v v8, (sp)
-; RV64IV-NEXT:    addi sp, s0, -64
-; RV64IV-NEXT:    ld s0, 48(sp) # 8-byte Folded Reload
-; RV64IV-NEXT:    ld ra, 56(sp) # 8-byte Folded Reload
-; RV64IV-NEXT:    addi sp, sp, 64
-; RV64IV-NEXT:    ret
+; CHECK-NEXT:    addi	sp, sp, -64
+; CHECK-NEXT:    .cfi_def_cfa_offset 64
+; CHECK-NEXT:    sd	ra, 56(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    sd	s0, 48(sp)                      # 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_offset ra, -8
+; CHECK-NEXT:    .cfi_offset s0, -16
+; CHECK-NEXT:    addi	s0, sp, 64
+; CHECK-NEXT:    .cfi_def_cfa s0, 0
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 4
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    andi	sp, sp, -64
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 3
+; CHECK-NEXT:    add	a0, sp, a0
+; CHECK-NEXT:    addi	a0, a0, 48
+; CHECK-NEXT:    vl8r.v	v8, (a0)
+; CHECK-NEXT:    addi	a0, sp, 48
+; CHECK-NEXT:    vl8r.v	v8, (a0)
+; CHECK-NEXT:    addi	sp, s0, -64
+; CHECK-NEXT:    ld	s0, 48(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    ld	ra, 56(sp)                      # 8-byte Folded Reload
+; CHECK-NEXT:    addi	sp, sp, 64
+; CHECK-NEXT:    ret
   %local0 = alloca <vscale x 64 x i8>
   %local1 = alloca <vscale x 64 x i8>
   load volatile <vscale x 64 x i8>, <vscale x 64 x i8>* %local0
@@ -137,29 +141,25 @@
 define void @local_var_m2_mix_local_scalar() {
 ; RV64IV-LABEL: local_var_m2_mix_local_scalar:
 ; RV64IV:       # %bb.0:
-; RV64IV-NEXT:    addi sp, sp, -16
-; RV64IV-NEXT:    .cfi_def_cfa_offset 16
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 2
-; RV64IV-NEXT:    sub sp, sp, a0
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 2
-; RV64IV-NEXT:    add a0, sp, a0
-; RV64IV-NEXT:    lw a0, 12(a0)
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 1
-; RV64IV-NEXT:    add a0, sp, a0
-; RV64IV-NEXT:    vl2r.v v26, (a0)
-; RV64IV-NEXT:    vl2r.v v26, (sp)
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 2
-; RV64IV-NEXT:    add a0, sp, a0
-; RV64IV-NEXT:    lw a0, 8(a0)
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 2
-; RV64IV-NEXT:    add sp, sp, a0
-; RV64IV-NEXT:    addi sp, sp, 16
-; RV64IV-NEXT:    ret
+; CHECK-NEXT:    addi	sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 2
+; CHECK-NEXT:    sub	sp, sp, a0
+; CHECK-NEXT:    lw	a0, 12(sp)
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 1
+; CHECK-NEXT:    add	a0, sp, a0
+; CHECK-NEXT:    addi	a0, a0, 16
+; CHECK-NEXT:    vl2r.v	v26, (a0)
+; CHECK-NEXT:    addi	a0, sp, 16
+; CHECK-NEXT:    vl2r.v	v26, (a0)
+; CHECK-NEXT:    lw	a0, 8(sp)
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 2
+; CHECK-NEXT:    add	sp, sp, a0
+; CHECK-NEXT:    addi	sp, sp, 16
+; CHECK-NEXT:    ret
   %local_scalar0 = alloca i32
   %local0 = alloca <vscale x 16 x i8>
   %local1 = alloca <vscale x 16 x i8>
@@ -174,41 +174,41 @@
 define void @local_var_m2_with_varsize_object(i64 %n) {
 ; RV64IV-LABEL: local_var_m2_with_varsize_object:
 ; RV64IV:       # %bb.0:
-; RV64IV-NEXT:    addi sp, sp, -16
-; RV64IV-NEXT:    .cfi_def_cfa_offset 16
-; RV64IV-NEXT:    sd ra, 8(sp) # 8-byte Folded Spill
-; RV64IV-NEXT:    sd s0, 0(sp) # 8-byte Folded Spill
-; RV64IV-NEXT:    .cfi_offset ra, -8
-; RV64IV-NEXT:    .cfi_offset s0, -16
-; RV64IV-NEXT:    addi s0, sp, 16
-; RV64IV-NEXT:    .cfi_def_cfa s0, 0
-; RV64IV-NEXT:    csrr a1, vlenb
-; RV64IV-NEXT:    slli a1, a1, 2
-; RV64IV-NEXT:    sub sp, sp, a1
-; RV64IV-NEXT:    addi a0, a0, 15
-; RV64IV-NEXT:    andi a0, a0, -16
-; RV64IV-NEXT:    sub a0, sp, a0
-; RV64IV-NEXT:    mv sp, a0
-; RV64IV-NEXT:    csrr a1, vlenb
-; RV64IV-NEXT:    slli a1, a1, 1
-; RV64IV-NEXT:    sub a1, s0, a1
-; RV64IV-NEXT:    addi a1, a1, -16
-; RV64IV-NEXT:    call notdead@plt
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 1
-; RV64IV-NEXT:    sub a0, s0, a0
-; RV64IV-NEXT:    addi a0, a0, -16
-; RV64IV-NEXT:    vl2r.v v26, (a0)
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 2
-; RV64IV-NEXT:    sub a0, s0, a0
-; RV64IV-NEXT:    addi a0, a0, -16
-; RV64IV-NEXT:    vl2r.v v26, (a0)
-; RV64IV-NEXT:    addi sp, s0, -16
-; RV64IV-NEXT:    ld s0, 0(sp) # 8-byte Folded Reload
-; RV64IV-NEXT:    ld ra, 8(sp) # 8-byte Folded Reload
-; RV64IV-NEXT:    addi sp, sp, 16
-; RV64IV-NEXT:    ret
+; CHECK-NEXT:    addi	sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    sd	ra, 8(sp)                       # 8-byte Folded Spill
+; CHECK-NEXT:    sd	s0, 0(sp)                       # 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_offset ra, -8
+; CHECK-NEXT:    .cfi_offset s0, -16
+; CHECK-NEXT:    addi	s0, sp, 16
+; CHECK-NEXT:    .cfi_def_cfa s0, 0
+; CHECK-NEXT:    csrr	a1, vlenb
+; CHECK-NEXT:    slli	a1, a1, 2
+; CHECK-NEXT:    sub	sp, sp, a1
+; CHECK-NEXT:    addi	a0, a0, 15
+; CHECK-NEXT:    andi	a0, a0, -16
+; CHECK-NEXT:    sub	a0, sp, a0
+; CHECK-NEXT:    mv	sp, a0
+; CHECK-NEXT:    csrr	a1, vlenb
+; CHECK-NEXT:    slli	a1, a1, 1
+; CHECK-NEXT:    sub	a1, s0, a1
+; CHECK-NEXT:    addi	a1, a1, -16
+; CHECK-NEXT:    call	notdead@plt
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 1
+; CHECK-NEXT:    sub	a0, s0, a0
+; CHECK-NEXT:    addi	a0, a0, -16
+; CHECK-NEXT:    vl2r.v	v26, (a0)
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 2
+; CHECK-NEXT:    sub	a0, s0, a0
+; CHECK-NEXT:    addi	a0, a0, -16
+; CHECK-NEXT:    vl2r.v	v26, (a0)
+; CHECK-NEXT:    addi	sp, s0, -16
+; CHECK-NEXT:    ld	s0, 0(sp)                       # 8-byte Folded Reload
+; CHECK-NEXT:    ld	ra, 8(sp)                       # 8-byte Folded Reload
+; CHECK-NEXT:    addi	sp, sp, 16
+; CHECK-NEXT:    ret
   %1 = alloca i8, i64 %n
   %2 = alloca <vscale x 16 x i8>
   %3 = alloca <vscale x 16 x i8>
@@ -221,47 +221,46 @@
 define void @local_var_m2_with_bp(i64 %n) {
 ; RV64IV-LABEL: local_var_m2_with_bp:
 ; RV64IV:       # %bb.0:
-; RV64IV-NEXT:    addi sp, sp, -256
-; RV64IV-NEXT:    .cfi_def_cfa_offset 256
-; RV64IV-NEXT:    sd ra, 248(sp) # 8-byte Folded Spill
-; RV64IV-NEXT:    sd s0, 240(sp) # 8-byte Folded Spill
-; RV64IV-NEXT:    sd s1, 232(sp) # 8-byte Folded Spill
-; RV64IV-NEXT:    .cfi_offset ra, -8
-; RV64IV-NEXT:    .cfi_offset s0, -16
-; RV64IV-NEXT:    .cfi_offset s1, -24
-; RV64IV-NEXT:    addi s0, sp, 256
-; RV64IV-NEXT:    .cfi_def_cfa s0, 0
-; RV64IV-NEXT:    andi sp, sp, -128
-; RV64IV-NEXT:    mv s1, sp
-; RV64IV-NEXT:    csrr a1, vlenb
-; RV64IV-NEXT:    slli a1, a1, 2
-; RV64IV-NEXT:    sub sp, sp, a1
-; RV64IV-NEXT:    addi a0, a0, 15
-; RV64IV-NEXT:    andi a0, a0, -16
-; RV64IV-NEXT:    sub a0, sp, a0
-; RV64IV-NEXT:    mv sp, a0
-; RV64IV-NEXT:    addi a1, s1, 128
-; RV64IV-NEXT:    csrr a2, vlenb
-; RV64IV-NEXT:    slli a2, a2, 1
-; RV64IV-NEXT:    sub a2, s1, a2
-; RV64IV-NEXT:    mv a2, a2
-; RV64IV-NEXT:    call notdead2@plt
-; RV64IV-NEXT:    lw a0, 124(s1)
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 1
-; RV64IV-NEXT:    sub a0, s1, a0
-; RV64IV-NEXT:    vl2r.v v26, (a0)
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 2
-; RV64IV-NEXT:    sub a0, s1, a0
-; RV64IV-NEXT:    vl2r.v v26, (a0)
-; RV64IV-NEXT:    lw a0, 120(s1)
-; RV64IV-NEXT:    addi sp, s0, -256
-; RV64IV-NEXT:    ld s1, 232(sp) # 8-byte Folded Reload
-; RV64IV-NEXT:    ld s0, 240(sp) # 8-byte Folded Reload
-; RV64IV-NEXT:    ld ra, 248(sp) # 8-byte Folded Reload
-; RV64IV-NEXT:    addi sp, sp, 256
-; RV64IV-NEXT:    ret
+; CHECK-NEXT:    addi	sp, sp, -256
+; CHECK-NEXT:    .cfi_def_cfa_offset 256
+; CHECK-NEXT:    sd	ra, 248(sp)                     # 8-byte Folded Spill
+; CHECK-NEXT:    sd	s0, 240(sp)                     # 8-byte Folded Spill
+; CHECK-NEXT:    sd	s1, 232(sp)                     # 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_offset ra, -8
+; CHECK-NEXT:    .cfi_offset s0, -16
+; CHECK-NEXT:    .cfi_offset s1, -24
+; CHECK-NEXT:    addi	s0, sp, 256
+; CHECK-NEXT:    .cfi_def_cfa s0, 0
+; CHECK-NEXT:    csrr	a1, vlenb
+; CHECK-NEXT:    slli	a1, a1, 2
+; CHECK-NEXT:    sub	sp, sp, a1
+; CHECK-NEXT:    andi	sp, sp, -128
+; CHECK-NEXT:    mv	s1, sp
+; CHECK-NEXT:    addi	a0, a0, 15
+; CHECK-NEXT:    andi	a0, a0, -16
+; CHECK-NEXT:    sub	a0, sp, a0
+; CHECK-NEXT:    mv	sp, a0
+; CHECK-NEXT:    addi	a1, s1, 128
+; CHECK-NEXT:    csrr	a2, vlenb
+; CHECK-NEXT:    slli	a2, a2, 1
+; CHECK-NEXT:    add	a2, s1, a2
+; CHECK-NEXT:    addi	a2, a2, 224
+; CHECK-NEXT:    call	notdead2@plt
+; CHECK-NEXT:    lw	a0, 124(s1)
+; CHECK-NEXT:    csrr	a0, vlenb
+; CHECK-NEXT:    slli	a0, a0, 1
+; CHECK-NEXT:    add	a0, s1, a0
+; CHECK-NEXT:    addi	a0, a0, 224
+; CHECK-NEXT:    vl2r.v	v26, (a0)
+; CHECK-NEXT:    addi	a0, s1, 224
+; CHECK-NEXT:    vl2r.v	v26, (a0)
+; CHECK-NEXT:    lw	a0, 120(s1)
+; CHECK-NEXT:    addi	sp, s0, -256
+; CHECK-NEXT:    ld	s1, 232(sp)                     # 8-byte Folded Reload
+; CHECK-NEXT:    ld	s0, 240(sp)                     # 8-byte Folded Reload
+; CHECK-NEXT:    ld	ra, 248(sp)                     # 8-byte Folded Reload
+; CHECK-NEXT:    addi	sp, sp, 256
+; CHECK-NEXT:    ret
   %1 = alloca i8, i64 %n
   %2 = alloca i32, align 128
   %local_scalar0 = alloca i32
diff --git a/llvm/test/CodeGen/RISCV/rvv/memory-args.ll b/llvm/test/CodeGen/RISCV/rvv/memory-args.ll
--- a/llvm/test/CodeGen/RISCV/rvv/memory-args.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/memory-args.ll
@@ -26,38 +26,42 @@
 define <vscale x 64 x i8> @caller() {
 ; RV64IV-LABEL: caller:
 ; RV64IV:       # %bb.0:
-; RV64IV-NEXT:    addi sp, sp, -64
+; RV64IV-NEXT:    addi	sp, sp, -64
 ; RV64IV-NEXT:    .cfi_def_cfa_offset 64
-; RV64IV-NEXT:    sd ra, 56(sp) # 8-byte Folded Spill
-; RV64IV-NEXT:    sd s0, 48(sp) # 8-byte Folded Spill
+; RV64IV-NEXT:    sd	ra, 56(sp)                      # 8-byte Folded Spill
+; RV64IV-NEXT:    sd	s0, 48(sp)                      # 8-byte Folded Spill
 ; RV64IV-NEXT:    .cfi_offset ra, -8
 ; RV64IV-NEXT:    .cfi_offset s0, -16
-; RV64IV-NEXT:    addi s0, sp, 64
+; RV64IV-NEXT:    addi	s0, sp, 64
 ; RV64IV-NEXT:    .cfi_def_cfa s0, 0
-; RV64IV-NEXT:    andi sp, sp, -64
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 5
-; RV64IV-NEXT:    sub sp, sp, a0
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    addi a1, zero, 24
-; RV64IV-NEXT:    mul a0, a0, a1
-; RV64IV-NEXT:    add a0, sp, a0
-; RV64IV-NEXT:    vl8r.v v8, (a0)
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 4
-; RV64IV-NEXT:    add a0, sp, a0
-; RV64IV-NEXT:    vl8r.v v16, (a0)
-; RV64IV-NEXT:    csrr a0, vlenb
-; RV64IV-NEXT:    slli a0, a0, 3
-; RV64IV-NEXT:    add a0, sp, a0
-; RV64IV-NEXT:    vl8r.v v24, (a0)
-; RV64IV-NEXT:    mv a0, sp
-; RV64IV-NEXT:    vs8r.v v24, (sp)
-; RV64IV-NEXT:    call callee@plt
-; RV64IV-NEXT:    addi sp, s0, -64
-; RV64IV-NEXT:    ld s0, 48(sp) # 8-byte Folded Reload
-; RV64IV-NEXT:    ld ra, 56(sp) # 8-byte Folded Reload
-; RV64IV-NEXT:    addi sp, sp, 64
+; RV64IV-NEXT:    csrr	a0, vlenb
+; RV64IV-NEXT:    slli	a0, a0, 5
+; RV64IV-NEXT:    sub	sp, sp, a0
+; RV64IV-NEXT:    andi	sp, sp, -64
+; RV64IV-NEXT:    csrr	a0, vlenb
+; RV64IV-NEXT:    addi	a1, zero, 24
+; RV64IV-NEXT:    mul	a0, a0, a1
+; RV64IV-NEXT:    add	a0, sp, a0
+; RV64IV-NEXT:    addi	a0, a0, 48
+; RV64IV-NEXT:    vl8r.v	v8, (a0)
+; RV64IV-NEXT:    csrr	a0, vlenb
+; RV64IV-NEXT:    slli	a0, a0, 4
+; RV64IV-NEXT:    add	a0, sp, a0
+; RV64IV-NEXT:    addi	a0, a0, 48
+; RV64IV-NEXT:    vl8r.v	v16, (a0)
+; RV64IV-NEXT:    csrr	a0, vlenb
+; RV64IV-NEXT:    slli	a0, a0, 3
+; RV64IV-NEXT:    add	a0, sp, a0
+; RV64IV-NEXT:    addi	a0, a0, 48
+; RV64IV-NEXT:    vl8r.v	v24, (a0)
+; RV64IV-NEXT:    addi	a0, sp, 48
+; RV64IV-NEXT:    addi	a1, sp, 48
+; RV64IV-NEXT:    vs8r.v	v24, (a1)
+; RV64IV-NEXT:    call	callee@plt
+; RV64IV-NEXT:    addi	sp, s0, -64
+; RV64IV-NEXT:    ld	s0, 48(sp)                      # 8-byte Folded Reload
+; RV64IV-NEXT:    ld	ra, 56(sp)                      # 8-byte Folded Reload
+; RV64IV-NEXT:    addi	sp, sp, 64
 ; RV64IV-NEXT:    ret
   %local0 = alloca <vscale x 64 x i8>
   %local1 = alloca <vscale x 64 x i8>
diff --git a/llvm/test/CodeGen/RISCV/rvv/rv32-spill-vector-csr.ll b/llvm/test/CodeGen/RISCV/rvv/rv32-spill-vector-csr.ll
--- a/llvm/test/CodeGen/RISCV/rvv/rv32-spill-vector-csr.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/rv32-spill-vector-csr.ll
@@ -9,72 +9,66 @@
 define <vscale x 1 x double> @foo(<vscale x 1 x double> %a, <vscale x 1 x double> %b, <vscale x 1 x double> %c, i32 %gvl) nounwind
 ; SPILL-O0-LABEL: foo:
 ; SPILL-O0:       # %bb.0:
-; SPILL-O0-NEXT:    addi sp, sp, -16
-; SPILL-O0-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
-; SPILL-O0-NEXT:    csrr a1, vlenb
-; SPILL-O0-NEXT:    slli a1, a1, 1
-; SPILL-O0-NEXT:    sub sp, sp, a1
-; SPILL-O0-NEXT:    csrr a1, vlenb
-; SPILL-O0-NEXT:    slli a1, a1, 1
-; SPILL-O0-NEXT:    add a1, sp, a1
-; SPILL-O0-NEXT:    sw a0, 8(a1) # 4-byte Folded Spill
-; SPILL-O0-NEXT:    csrr a1, vlenb
-; SPILL-O0-NEXT:    add a1, sp, a1
-; SPILL-O0-NEXT:    vs1r.v v8, (a1) # Unknown-size Folded Spill
-; SPILL-O0-NEXT:    vsetvli a0, a0, e64,m1,ta,mu
-; SPILL-O0-NEXT:    vfadd.vv v25, v8, v9
-; SPILL-O0-NEXT:    vs1r.v v25, (sp) # Unknown-size Folded Spill
-; SPILL-O0-NEXT:    lui a0, %hi(.L.str)
-; SPILL-O0-NEXT:    addi a0, a0, %lo(.L.str)
-; SPILL-O0-NEXT:    call puts@plt
-; SPILL-O0-NEXT:    vl1r.v v25, (sp) # Unknown-size Folded Reload
-; SPILL-O0-NEXT:    csrr a1, vlenb
-; SPILL-O0-NEXT:    add a1, sp, a1
-; SPILL-O0-NEXT:    vl1r.v v8, (a1) # Unknown-size Folded Reload
-; SPILL-O0-NEXT:    # kill: def $x11 killed $x10
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    slli a0, a0, 1
-; SPILL-O0-NEXT:    add a0, sp, a0
-; SPILL-O0-NEXT:    lw a0, 8(a0) # 4-byte Folded Reload
-; SPILL-O0-NEXT:    vsetvli a0, a0, e64,m1,ta,mu
-; SPILL-O0-NEXT:    vfadd.vv v8, v8, v25
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    slli a0, a0, 1
-; SPILL-O0-NEXT:    add sp, sp, a0
-; SPILL-O0-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
-; SPILL-O0-NEXT:    addi sp, sp, 16
+; SPILL-O0-NEXT:    addi	sp, sp, -16
+; SPILL-O0-NEXT:    sw	ra, 12(sp)                      # 4-byte Folded Spill
+; SPILL-O0-NEXT:    csrr	a1, vlenb
+; SPILL-O0-NEXT:    slli	a1, a1, 1
+; SPILL-O0-NEXT:    sub	sp, sp, a1
+; SPILL-O0-NEXT:    sw	a0, 8(sp)                       # 4-byte Folded Spill
+; SPILL-O0-NEXT:    csrr	a1, vlenb
+; SPILL-O0-NEXT:    add	a1, sp, a1
+; SPILL-O0-NEXT:    vs1r.v	v8, (a1)                        # Unknown-size Folded Spill
+; SPILL-O0-NEXT:    vsetvli	a0, a0, e64,m1,ta,mu
+; SPILL-O0-NEXT:    vfadd.vv	v25, v8, v9
+; SPILL-O0-NEXT:    vs1r.v	v25, (sp)                       # Unknown-size Folded Spill
+; SPILL-O0-NEXT:    lui	a0, %hi(.L.str)
+; SPILL-O0-NEXT:    addi	a0, a0, %lo(.L.str)
+; SPILL-O0-NEXT:    call	puts@plt
+; SPILL-O0-NEXT:    vl1r.v	v25, (sp)                       # Unknown-size Folded Reload
+; SPILL-O0-NEXT:    csrr	a1, vlenb
+; SPILL-O0-NEXT:    add	a1, sp, a1
+; SPILL-O0-NEXT:    vl1r.v	v8, (a1)                        # Unknown-size Folded Reload
+; SPILL-O0-NEXT:                                            # kill: def $x11 killed $x10
+; SPILL-O0-NEXT:    lw	a0, 8(sp)                       # 4-byte Folded Reload
+; SPILL-O0-NEXT:    vsetvli	a0, a0, e64,m1,ta,mu
+; SPILL-O0-NEXT:    vfadd.vv	v8, v8, v25
+; SPILL-O0-NEXT:    csrr	a0, vlenb
+; SPILL-O0-NEXT:    slli	a0, a0, 1
+; SPILL-O0-NEXT:    add	sp, sp, a0
+; SPILL-O0-NEXT:    lw	ra, 12(sp)                      # 4-byte Folded Reload
+; SPILL-O0-NEXT:    addi	sp, sp, 16
 ; SPILL-O0-NEXT:    ret
 ;
 ; SPILL-O2-LABEL: foo:
 ; SPILL-O2:       # %bb.0:
-; SPILL-O2-NEXT:    addi sp, sp, -16
-; SPILL-O2-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
-; SPILL-O2-NEXT:    sw s0, 8(sp) # 4-byte Folded Spill
-; SPILL-O2-NEXT:    csrr a1, vlenb
-; SPILL-O2-NEXT:    slli a1, a1, 1
-; SPILL-O2-NEXT:    sub sp, sp, a1
-; SPILL-O2-NEXT:    mv s0, a0
-; SPILL-O2-NEXT:    vs1r.v v8, (sp) # Unknown-size Folded Spill
-; SPILL-O2-NEXT:    vsetvli a0, a0, e64,m1,ta,mu
-; SPILL-O2-NEXT:    vfadd.vv v25, v8, v9
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    add a0, sp, a0
-; SPILL-O2-NEXT:    vs1r.v v25, (a0) # Unknown-size Folded Spill
-; SPILL-O2-NEXT:    lui a0, %hi(.L.str)
-; SPILL-O2-NEXT:    addi a0, a0, %lo(.L.str)
-; SPILL-O2-NEXT:    call puts@plt
-; SPILL-O2-NEXT:    vsetvli a0, s0, e64,m1,ta,mu
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    add a0, sp, a0
-; SPILL-O2-NEXT:    vl1r.v v25, (a0) # Unknown-size Folded Reload
-; SPILL-O2-NEXT:    vl1r.v v26, (sp) # Unknown-size Folded Reload
-; SPILL-O2-NEXT:    vfadd.vv v8, v26, v25
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    slli a0, a0, 1
-; SPILL-O2-NEXT:    add sp, sp, a0
-; SPILL-O2-NEXT:    lw s0, 8(sp) # 4-byte Folded Reload
-; SPILL-O2-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
-; SPILL-O2-NEXT:    addi sp, sp, 16
+; SPILL-O2-NEXT:    addi	sp, sp, -16
+; SPILL-O2-NEXT:    sw	ra, 12(sp)                      # 4-byte Folded Spill
+; SPILL-O2-NEXT:    sw	s0, 8(sp)                       # 4-byte Folded Spill
+; SPILL-O2-NEXT:    csrr	a1, vlenb
+; SPILL-O2-NEXT:    slli	a1, a1, 1
+; SPILL-O2-NEXT:    sub	sp, sp, a1
+; SPILL-O2-NEXT:    mv	s0, a0
+; SPILL-O2-NEXT:    vs1r.v	v8, (sp)                        # Unknown-size Folded Spill
+; SPILL-O2-NEXT:    vsetvli	a0, a0, e64,m1,ta,mu
+; SPILL-O2-NEXT:    vfadd.vv	v25, v8, v9
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    add	a0, sp, a0
+; SPILL-O2-NEXT:    vs1r.v	v25, (a0)                       # Unknown-size Folded Spill
+; SPILL-O2-NEXT:    lui	a0, %hi(.L.str)
+; SPILL-O2-NEXT:    addi	a0, a0, %lo(.L.str)
+; SPILL-O2-NEXT:    call	puts@plt
+; SPILL-O2-NEXT:    vsetvli	a0, s0, e64,m1,ta,mu
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    add	a0, sp, a0
+; SPILL-O2-NEXT:    vl1r.v	v25, (a0)                       # Unknown-size Folded Reload
+; SPILL-O2-NEXT:    vl1r.v	v26, (sp)                       # Unknown-size Folded Reload
+; SPILL-O2-NEXT:    vfadd.vv	v8, v26, v25
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    slli	a0, a0, 1
+; SPILL-O2-NEXT:    add	sp, sp, a0
+; SPILL-O2-NEXT:    lw	s0, 8(sp)                       # 4-byte Folded Reload
+; SPILL-O2-NEXT:    lw	ra, 12(sp)                      # 4-byte Folded Reload
+; SPILL-O2-NEXT:    addi	sp, sp, 16
 ; SPILL-O2-NEXT:    ret
 {
    %x = call <vscale x 1 x double> @llvm.riscv.vfadd.nxv1f64.nxv1f64(<vscale x 1 x double> %a, <vscale x 1 x double> %b, i32 %gvl)
diff --git a/llvm/test/CodeGen/RISCV/rvv/rv32-spill-vector.ll b/llvm/test/CodeGen/RISCV/rvv/rv32-spill-vector.ll
--- a/llvm/test/CodeGen/RISCV/rvv/rv32-spill-vector.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/rv32-spill-vector.ll
@@ -7,26 +7,34 @@
 define <vscale x 1 x i32> @spill_lmul_mf2(<vscale x 1 x i32> %va) nounwind {
 ; SPILL-O0-LABEL: spill_lmul_mf2:
 ; SPILL-O0:       # %bb.0: # %entry
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    sub sp, sp, a0
-; SPILL-O0-NEXT:    vs1r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O0-NEXT:    addi	sp, sp, -16
+; SPILL-O0-NEXT:    csrr	a0, vlenb
+; SPILL-O0-NEXT:    sub	sp, sp, a0
+; SPILL-O0-NEXT:    addi	a0, sp, 16
+; SPILL-O0-NEXT:    vs1r.v	v8, (a0)                        # Unknown-size Folded Spill
 ; SPILL-O0-NEXT:    #APP
 ; SPILL-O0-NEXT:    #NO_APP
-; SPILL-O0-NEXT:    vl1r.v v8, (sp) # Unknown-size Folded Reload
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    add sp, sp, a0
+; SPILL-O0-NEXT:    addi	a0, sp, 16
+; SPILL-O0-NEXT:    vl1r.v	v8, (a0)                        # Unknown-size Folded Reload
+; SPILL-O0-NEXT:    csrr	a0, vlenb
+; SPILL-O0-NEXT:    add	sp, sp, a0
+; SPILL-O0-NEXT:    addi	sp, sp, 16
 ; SPILL-O0-NEXT:    ret
 ;
 ; SPILL-O2-LABEL: spill_lmul_mf2:
 ; SPILL-O2:       # %bb.0: # %entry
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    sub sp, sp, a0
-; SPILL-O2-NEXT:    vs1r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O2-NEXT:    addi	sp, sp, -16
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    sub	sp, sp, a0
+; SPILL-O2-NEXT:    addi	a0, sp, 16
+; SPILL-O2-NEXT:    vs1r.v	v8, (a0)                        # Unknown-size Folded Spill
 ; SPILL-O2-NEXT:    #APP
 ; SPILL-O2-NEXT:    #NO_APP
-; SPILL-O2-NEXT:    vl1r.v v8, (sp) # Unknown-size Folded Reload
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    add sp, sp, a0
+; SPILL-O2-NEXT:    addi	a0, sp, 16
+; SPILL-O2-NEXT:    vl1r.v	v8, (a0)                        # Unknown-size Folded Reload
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    add	sp, sp, a0
+; SPILL-O2-NEXT:    addi	sp, sp, 16
 ; SPILL-O2-NEXT:    ret
 entry:
   call void asm sideeffect "",
@@ -38,26 +46,34 @@
 define <vscale x 2 x i32> @spill_lmul_1(<vscale x 2 x i32> %va) nounwind {
 ; SPILL-O0-LABEL: spill_lmul_1:
 ; SPILL-O0:       # %bb.0: # %entry
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    sub sp, sp, a0
-; SPILL-O0-NEXT:    vs1r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O0-NEXT:    addi	sp, sp, -16
+; SPILL-O0-NEXT:    csrr	a0, vlenb
+; SPILL-O0-NEXT:    sub	sp, sp, a0
+; SPILL-O0-NEXT:    addi	a0, sp, 16
+; SPILL-O0-NEXT:    vs1r.v	v8, (a0)                        # Unknown-size Folded Spill
 ; SPILL-O0-NEXT:    #APP
 ; SPILL-O0-NEXT:    #NO_APP
-; SPILL-O0-NEXT:    vl1r.v v8, (sp) # Unknown-size Folded Reload
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    add sp, sp, a0
+; SPILL-O0-NEXT:    addi	a0, sp, 16
+; SPILL-O0-NEXT:    vl1r.v	v8, (a0)                        # Unknown-size Folded Reload
+; SPILL-O0-NEXT:    csrr	a0, vlenb
+; SPILL-O0-NEXT:    add	sp, sp, a0
+; SPILL-O0-NEXT:    addi	sp, sp, 16
 ; SPILL-O0-NEXT:    ret
 ;
 ; SPILL-O2-LABEL: spill_lmul_1:
 ; SPILL-O2:       # %bb.0: # %entry
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    sub sp, sp, a0
-; SPILL-O2-NEXT:    vs1r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O2-NEXT:    addi	sp, sp, -16
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    sub	sp, sp, a0
+; SPILL-O2-NEXT:    addi	a0, sp, 16
+; SPILL-O2-NEXT:    vs1r.v	v8, (a0)                        # Unknown-size Folded Spill
 ; SPILL-O2-NEXT:    #APP
 ; SPILL-O2-NEXT:    #NO_APP
-; SPILL-O2-NEXT:    vl1r.v v8, (sp) # Unknown-size Folded Reload
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    add sp, sp, a0
+; SPILL-O2-NEXT:    addi	a0, sp, 16
+; SPILL-O2-NEXT:    vl1r.v	v8, (a0)                        # Unknown-size Folded Reload
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    add	sp, sp, a0
+; SPILL-O2-NEXT:    addi	sp, sp, 16
 ; SPILL-O2-NEXT:    ret
 entry:
   call void asm sideeffect "",
@@ -69,30 +85,38 @@
 define <vscale x 4 x i32> @spill_lmul_2(<vscale x 4 x i32> %va) nounwind {
 ; SPILL-O0-LABEL: spill_lmul_2:
 ; SPILL-O0:       # %bb.0: # %entry
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    slli a0, a0, 1
-; SPILL-O0-NEXT:    sub sp, sp, a0
-; SPILL-O0-NEXT:    vs2r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O0-NEXT:    addi	sp, sp, -16
+; SPILL-O0-NEXT:    csrr	a0, vlenb
+; SPILL-O0-NEXT:    slli	a0, a0, 1
+; SPILL-O0-NEXT:    sub	sp, sp, a0
+; SPILL-O0-NEXT:    addi	a0, sp, 16
+; SPILL-O0-NEXT:    vs2r.v	v8, (a0)                        # Unknown-size Folded Spill
 ; SPILL-O0-NEXT:    #APP
 ; SPILL-O0-NEXT:    #NO_APP
-; SPILL-O0-NEXT:    vl2re8.v v8, (sp) # Unknown-size Folded Reload
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    slli a0, a0, 1
-; SPILL-O0-NEXT:    add sp, sp, a0
+; SPILL-O0-NEXT:    addi	a0, sp, 16
+; SPILL-O0-NEXT:    vl2re8.v	v8, (a0)                        # Unknown-size Folded Reload
+; SPILL-O0-NEXT:    csrr	a0, vlenb
+; SPILL-O0-NEXT:    slli	a0, a0, 1
+; SPILL-O0-NEXT:    add	sp, sp, a0
+; SPILL-O0-NEXT:    addi	sp, sp, 16
 ; SPILL-O0-NEXT:    ret
 ;
 ; SPILL-O2-LABEL: spill_lmul_2:
 ; SPILL-O2:       # %bb.0: # %entry
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    slli a0, a0, 1
-; SPILL-O2-NEXT:    sub sp, sp, a0
-; SPILL-O2-NEXT:    vs2r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O2-NEXT:    addi	sp, sp, -16
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    slli	a0, a0, 1
+; SPILL-O2-NEXT:    sub	sp, sp, a0
+; SPILL-O2-NEXT:    addi	a0, sp, 16
+; SPILL-O2-NEXT:    vs2r.v	v8, (a0)                        # Unknown-size Folded Spill
 ; SPILL-O2-NEXT:    #APP
 ; SPILL-O2-NEXT:    #NO_APP
-; SPILL-O2-NEXT:    vl2re8.v v8, (sp) # Unknown-size Folded Reload
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    slli a0, a0, 1
-; SPILL-O2-NEXT:    add sp, sp, a0
+; SPILL-O2-NEXT:    addi	a0, sp, 16
+; SPILL-O2-NEXT:    vl2re8.v	v8, (a0)                        # Unknown-size Folded Reload
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    slli	a0, a0, 1
+; SPILL-O2-NEXT:    add	sp, sp, a0
+; SPILL-O2-NEXT:    addi	sp, sp, 16
 ; SPILL-O2-NEXT:    ret
 entry:
   call void asm sideeffect "",
@@ -104,30 +128,38 @@
 define <vscale x 8 x i32> @spill_lmul_4(<vscale x 8 x i32> %va) nounwind {
 ; SPILL-O0-LABEL: spill_lmul_4:
 ; SPILL-O0:       # %bb.0: # %entry
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    slli a0, a0, 2
-; SPILL-O0-NEXT:    sub sp, sp, a0
-; SPILL-O0-NEXT:    vs4r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O0-NEXT:    addi	sp, sp, -16
+; SPILL-O0-NEXT:    csrr	a0, vlenb
+; SPILL-O0-NEXT:    slli	a0, a0, 2
+; SPILL-O0-NEXT:    sub	sp, sp, a0
+; SPILL-O0-NEXT:    addi	a0, sp, 16
+; SPILL-O0-NEXT:    vs4r.v	v8, (a0)                        # Unknown-size Folded Spill
 ; SPILL-O0-NEXT:    #APP
 ; SPILL-O0-NEXT:    #NO_APP
-; SPILL-O0-NEXT:    vl4re8.v v8, (sp) # Unknown-size Folded Reload
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    slli a0, a0, 2
-; SPILL-O0-NEXT:    add sp, sp, a0
+; SPILL-O0-NEXT:    addi	a0, sp, 16
+; SPILL-O0-NEXT:    vl4re8.v	v8, (a0)                        # Unknown-size Folded Reload
+; SPILL-O0-NEXT:    csrr	a0, vlenb
+; SPILL-O0-NEXT:    slli	a0, a0, 2
+; SPILL-O0-NEXT:    add	sp, sp, a0
+; SPILL-O0-NEXT:    addi	sp, sp, 16
 ; SPILL-O0-NEXT:    ret
 ;
 ; SPILL-O2-LABEL: spill_lmul_4:
 ; SPILL-O2:       # %bb.0: # %entry
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    slli a0, a0, 2
-; SPILL-O2-NEXT:    sub sp, sp, a0
-; SPILL-O2-NEXT:    vs4r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O2-NEXT:    addi	sp, sp, -16
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    slli	a0, a0, 2
+; SPILL-O2-NEXT:    sub	sp, sp, a0
+; SPILL-O2-NEXT:    addi	a0, sp, 16
+; SPILL-O2-NEXT:    vs4r.v	v8, (a0)                        # Unknown-size Folded Spill
 ; SPILL-O2-NEXT:    #APP
 ; SPILL-O2-NEXT:    #NO_APP
-; SPILL-O2-NEXT:    vl4re8.v v8, (sp) # Unknown-size Folded Reload
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    slli a0, a0, 2
-; SPILL-O2-NEXT:    add sp, sp, a0
+; SPILL-O2-NEXT:    addi	a0, sp, 16
+; SPILL-O2-NEXT:    vl4re8.v	v8, (a0)                        # Unknown-size Folded Reload
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    slli	a0, a0, 2
+; SPILL-O2-NEXT:    add	sp, sp, a0
+; SPILL-O2-NEXT:    addi	sp, sp, 16
 ; SPILL-O2-NEXT:    ret
 entry:
   call void asm sideeffect "",
@@ -139,30 +171,38 @@
 define <vscale x 16 x i32> @spill_lmul_8(<vscale x 16 x i32> %va) nounwind {
 ; SPILL-O0-LABEL: spill_lmul_8:
 ; SPILL-O0:       # %bb.0: # %entry
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    slli a0, a0, 3
-; SPILL-O0-NEXT:    sub sp, sp, a0
-; SPILL-O0-NEXT:    vs8r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O0-NEXT:    addi	sp, sp, -16
+; SPILL-O0-NEXT:    csrr	a0, vlenb
+; SPILL-O0-NEXT:    slli	a0, a0, 3
+; SPILL-O0-NEXT:    sub	sp, sp, a0
+; SPILL-O0-NEXT:    addi	a0, sp, 16
+; SPILL-O0-NEXT:    vs8r.v	v8, (a0)                        # Unknown-size Folded Spill
 ; SPILL-O0-NEXT:    #APP
 ; SPILL-O0-NEXT:    #NO_APP
-; SPILL-O0-NEXT:    vl8re8.v v8, (sp) # Unknown-size Folded Reload
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    slli a0, a0, 3
-; SPILL-O0-NEXT:    add sp, sp, a0
+; SPILL-O0-NEXT:    addi	a0, sp, 16
+; SPILL-O0-NEXT:    vl8re8.v	v8, (a0)                        # Unknown-size Folded Reload
+; SPILL-O0-NEXT:    csrr	a0, vlenb
+; SPILL-O0-NEXT:    slli	a0, a0, 3
+; SPILL-O0-NEXT:    add	sp, sp, a0
+; SPILL-O0-NEXT:    addi	sp, sp, 16
 ; SPILL-O0-NEXT:    ret
 ;
 ; SPILL-O2-LABEL: spill_lmul_8:
 ; SPILL-O2:       # %bb.0: # %entry
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    slli a0, a0, 3
-; SPILL-O2-NEXT:    sub sp, sp, a0
-; SPILL-O2-NEXT:    vs8r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O2-NEXT:    addi	sp, sp, -16
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    slli	a0, a0, 3
+; SPILL-O2-NEXT:    sub	sp, sp, a0
+; SPILL-O2-NEXT:    addi	a0, sp, 16
+; SPILL-O2-NEXT:    vs8r.v	v8, (a0)                        # Unknown-size Folded Spill
 ; SPILL-O2-NEXT:    #APP
 ; SPILL-O2-NEXT:    #NO_APP
-; SPILL-O2-NEXT:    vl8re8.v v8, (sp) # Unknown-size Folded Reload
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    slli a0, a0, 3
-; SPILL-O2-NEXT:    add sp, sp, a0
+; SPILL-O2-NEXT:    addi	a0, sp, 16
+; SPILL-O2-NEXT:    vl8re8.v	v8, (a0)                        # Unknown-size Folded Reload
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    slli	a0, a0, 3
+; SPILL-O2-NEXT:    add	sp, sp, a0
+; SPILL-O2-NEXT:    addi	sp, sp, 16
 ; SPILL-O2-NEXT:    ret
 entry:
   call void asm sideeffect "",
diff --git a/llvm/test/CodeGen/RISCV/rvv/rv64-spill-vector-csr.ll b/llvm/test/CodeGen/RISCV/rvv/rv64-spill-vector-csr.ll
--- a/llvm/test/CodeGen/RISCV/rvv/rv64-spill-vector-csr.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/rv64-spill-vector-csr.ll
@@ -9,72 +9,74 @@
 define <vscale x 1 x double> @foo(<vscale x 1 x double> %a, <vscale x 1 x double> %b, <vscale x 1 x double> %c, i64 %gvl) nounwind
 ; SPILL-O0-LABEL: foo:
 ; SPILL-O0:       # %bb.0:
-; SPILL-O0-NEXT:    addi sp, sp, -16
-; SPILL-O0-NEXT:    sd ra, 8(sp) # 8-byte Folded Spill
-; SPILL-O0-NEXT:    csrr a1, vlenb
-; SPILL-O0-NEXT:    slli a1, a1, 1
-; SPILL-O0-NEXT:    sub sp, sp, a1
-; SPILL-O0-NEXT:    csrr a1, vlenb
-; SPILL-O0-NEXT:    slli a1, a1, 1
-; SPILL-O0-NEXT:    add a1, sp, a1
-; SPILL-O0-NEXT:    sd a0, 0(a1) # 8-byte Folded Spill
-; SPILL-O0-NEXT:    csrr a1, vlenb
-; SPILL-O0-NEXT:    add a1, sp, a1
-; SPILL-O0-NEXT:    vs1r.v v8, (a1) # Unknown-size Folded Spill
-; SPILL-O0-NEXT:    vsetvli a0, a0, e64,m1,ta,mu
-; SPILL-O0-NEXT:    vfadd.vv v25, v8, v9
-; SPILL-O0-NEXT:    vs1r.v v25, (sp) # Unknown-size Folded Spill
-; SPILL-O0-NEXT:    lui a0, %hi(.L.str)
-; SPILL-O0-NEXT:    addi a0, a0, %lo(.L.str)
-; SPILL-O0-NEXT:    call puts@plt
-; SPILL-O0-NEXT:    vl1r.v v25, (sp) # Unknown-size Folded Reload
-; SPILL-O0-NEXT:    csrr a1, vlenb
-; SPILL-O0-NEXT:    add a1, sp, a1
-; SPILL-O0-NEXT:    vl1r.v v8, (a1) # Unknown-size Folded Reload
-; SPILL-O0-NEXT:    # kill: def $x11 killed $x10
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    slli a0, a0, 1
-; SPILL-O0-NEXT:    add a0, sp, a0
-; SPILL-O0-NEXT:    ld a0, 0(a0) # 8-byte Folded Reload
-; SPILL-O0-NEXT:    vsetvli a0, a0, e64,m1,ta,mu
-; SPILL-O0-NEXT:    vfadd.vv v8, v8, v25
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    slli a0, a0, 1
-; SPILL-O0-NEXT:    add sp, sp, a0
-; SPILL-O0-NEXT:    ld ra, 8(sp) # 8-byte Folded Reload
-; SPILL-O0-NEXT:    addi sp, sp, 16
+; SPILL-O0-NEXT:    addi	sp, sp, -32
+; SPILL-O0-NEXT:    sd	ra, 24(sp)                      # 8-byte Folded Spill
+; SPILL-O0-NEXT:    csrr	a1, vlenb
+; SPILL-O0-NEXT:    slli	a1, a1, 1
+; SPILL-O0-NEXT:    sub	sp, sp, a1
+; SPILL-O0-NEXT:    sd	a0, 16(sp)                      # 8-byte Folded Spill
+; SPILL-O0-NEXT:    csrr	a1, vlenb
+; SPILL-O0-NEXT:    add	a1, sp, a1
+; SPILL-O0-NEXT:    addi	a1, a1, 16
+; SPILL-O0-NEXT:    vs1r.v	v8, (a1)                        # Unknown-size Folded Spill
+; SPILL-O0-NEXT:    vsetvli	a0, a0, e64,m1,ta,mu
+; SPILL-O0-NEXT:    vfadd.vv	v25, v8, v9
+; SPILL-O0-NEXT:    addi	a0, sp, 16
+; SPILL-O0-NEXT:    vs1r.v	v25, (a0)                       # Unknown-size Folded Spill
+; SPILL-O0-NEXT:    lui	a0, %hi(.L.str)
+; SPILL-O0-NEXT:    addi	a0, a0, %lo(.L.str)
+; SPILL-O0-NEXT:    call	puts@plt
+; SPILL-O0-NEXT:    addi	a1, sp, 16
+; SPILL-O0-NEXT:    vl1r.v	v25, (a1)                       # Unknown-size Folded Reload
+; SPILL-O0-NEXT:    csrr	a1, vlenb
+; SPILL-O0-NEXT:    add	a1, sp, a1
+; SPILL-O0-NEXT:    addi	a1, a1, 16
+; SPILL-O0-NEXT:    vl1r.v	v8, (a1)                        # Unknown-size Folded Reload
+; SPILL-O0-NEXT:                                            # kill: def $x11 killed $x10
+; SPILL-O0-NEXT:    ld	a0, 16(sp)                      # 8-byte Folded Reload
+; SPILL-O0-NEXT:    vsetvli	a0, a0, e64,m1,ta,mu
+; SPILL-O0-NEXT:    vfadd.vv	v8, v8, v25
+; SPILL-O0-NEXT:    csrr	a0, vlenb
+; SPILL-O0-NEXT:    slli	a0, a0, 1
+; SPILL-O0-NEXT:    add	sp, sp, a0
+; SPILL-O0-NEXT:    ld	ra, 24(sp)                      # 8-byte Folded Reload
+; SPILL-O0-NEXT:    addi	sp, sp, 32
 ; SPILL-O0-NEXT:    ret
 ;
 ; SPILL-O2-LABEL: foo:
 ; SPILL-O2:       # %bb.0:
-; SPILL-O2-NEXT:    addi sp, sp, -16
-; SPILL-O2-NEXT:    sd ra, 8(sp) # 8-byte Folded Spill
-; SPILL-O2-NEXT:    sd s0, 0(sp) # 8-byte Folded Spill
-; SPILL-O2-NEXT:    csrr a1, vlenb
-; SPILL-O2-NEXT:    slli a1, a1, 1
-; SPILL-O2-NEXT:    sub sp, sp, a1
-; SPILL-O2-NEXT:    mv s0, a0
-; SPILL-O2-NEXT:    vs1r.v v8, (sp) # Unknown-size Folded Spill
-; SPILL-O2-NEXT:    vsetvli a0, a0, e64,m1,ta,mu
-; SPILL-O2-NEXT:    vfadd.vv v25, v8, v9
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    add a0, sp, a0
-; SPILL-O2-NEXT:    vs1r.v v25, (a0) # Unknown-size Folded Spill
-; SPILL-O2-NEXT:    lui a0, %hi(.L.str)
-; SPILL-O2-NEXT:    addi a0, a0, %lo(.L.str)
-; SPILL-O2-NEXT:    call puts@plt
-; SPILL-O2-NEXT:    vsetvli a0, s0, e64,m1,ta,mu
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    add a0, sp, a0
-; SPILL-O2-NEXT:    vl1r.v v25, (a0) # Unknown-size Folded Reload
-; SPILL-O2-NEXT:    vl1r.v v26, (sp) # Unknown-size Folded Reload
-; SPILL-O2-NEXT:    vfadd.vv v8, v26, v25
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    slli a0, a0, 1
-; SPILL-O2-NEXT:    add sp, sp, a0
-; SPILL-O2-NEXT:    ld s0, 0(sp) # 8-byte Folded Reload
-; SPILL-O2-NEXT:    ld ra, 8(sp) # 8-byte Folded Reload
-; SPILL-O2-NEXT:    addi sp, sp, 16
+; SPILL-O2-NEXT:    addi	sp, sp, -32
+; SPILL-O2-NEXT:    sd	ra, 24(sp)                      # 8-byte Folded Spill
+; SPILL-O2-NEXT:    sd	s0, 16(sp)                      # 8-byte Folded Spill
+; SPILL-O2-NEXT:    csrr	a1, vlenb
+; SPILL-O2-NEXT:    slli	a1, a1, 1
+; SPILL-O2-NEXT:    sub	sp, sp, a1
+; SPILL-O2-NEXT:    mv	s0, a0
+; SPILL-O2-NEXT:    addi	a1, sp, 16
+; SPILL-O2-NEXT:    vs1r.v	v8, (a1)                        # Unknown-size Folded Spill
+; SPILL-O2-NEXT:    vsetvli	a0, a0, e64,m1,ta,mu
+; SPILL-O2-NEXT:    vfadd.vv	v25, v8, v9
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    add	a0, sp, a0
+; SPILL-O2-NEXT:    addi	a0, a0, 16
+; SPILL-O2-NEXT:    vs1r.v	v25, (a0)                       # Unknown-size Folded Spill
+; SPILL-O2-NEXT:    lui	a0, %hi(.L.str)
+; SPILL-O2-NEXT:    addi	a0, a0, %lo(.L.str)
+; SPILL-O2-NEXT:    call	puts@plt
+; SPILL-O2-NEXT:    vsetvli	a0, s0, e64,m1,ta,mu
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    add	a0, sp, a0
+; SPILL-O2-NEXT:    addi	a0, a0, 16
+; SPILL-O2-NEXT:    vl1r.v	v25, (a0)                       # Unknown-size Folded Reload
+; SPILL-O2-NEXT:    addi	a0, sp, 16
+; SPILL-O2-NEXT:    vl1r.v	v26, (a0)                       # Unknown-size Folded Reload
+; SPILL-O2-NEXT:    vfadd.vv	v8, v26, v25
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    slli	a0, a0, 1
+; SPILL-O2-NEXT:    add	sp, sp, a0
+; SPILL-O2-NEXT:    ld	s0, 16(sp)                      # 8-byte Folded Reload
+; SPILL-O2-NEXT:    ld	ra, 24(sp)                      # 8-byte Folded Reload
+; SPILL-O2-NEXT:    addi	sp, sp, 32
 ; SPILL-O2-NEXT:    ret
 {
    %x = call <vscale x 1 x double> @llvm.riscv.vfadd.nxv1f64.nxv1f64(<vscale x 1 x double> %a, <vscale x 1 x double> %b, i64 %gvl)
diff --git a/llvm/test/CodeGen/RISCV/rvv/rv64-spill-vector.ll b/llvm/test/CodeGen/RISCV/rvv/rv64-spill-vector.ll
--- a/llvm/test/CodeGen/RISCV/rvv/rv64-spill-vector.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/rv64-spill-vector.ll
@@ -7,26 +7,34 @@
 define <vscale x 1 x i64> @spill_lmul_1(<vscale x 1 x i64> %va) nounwind {
 ; SPILL-O0-LABEL: spill_lmul_1:
 ; SPILL-O0:       # %bb.0: # %entry
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    sub sp, sp, a0
-; SPILL-O0-NEXT:    vs1r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O0-NEXT:    addi	sp, sp, -16
+; SPILL-O0-NEXT:    csrr	a0, vlenb
+; SPILL-O0-NEXT:    sub	sp, sp, a0
+; SPILL-O0-NEXT:    addi	a0, sp, 16
+; SPILL-O0-NEXT:    vs1r.v	v8, (a0)                        # Unknown-size Folded Spill
 ; SPILL-O0-NEXT:    #APP
 ; SPILL-O0-NEXT:    #NO_APP
-; SPILL-O0-NEXT:    vl1r.v v8, (sp) # Unknown-size Folded Reload
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    add sp, sp, a0
+; SPILL-O0-NEXT:    addi	a0, sp, 16
+; SPILL-O0-NEXT:    vl1r.v	v8, (a0)                        # Unknown-size Folded Reload
+; SPILL-O0-NEXT:    csrr	a0, vlenb
+; SPILL-O0-NEXT:    add	sp, sp, a0
+; SPILL-O0-NEXT:    addi	sp, sp, 16
 ; SPILL-O0-NEXT:    ret
 ;
 ; SPILL-O2-LABEL: spill_lmul_1:
 ; SPILL-O2:       # %bb.0: # %entry
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    sub sp, sp, a0
-; SPILL-O2-NEXT:    vs1r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O2-NEXT:    addi	sp, sp, -16
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    sub	sp, sp, a0
+; SPILL-O2-NEXT:    addi	a0, sp, 16
+; SPILL-O2-NEXT:    vs1r.v	v8, (a0)                        # Unknown-size Folded Spill
 ; SPILL-O2-NEXT:    #APP
 ; SPILL-O2-NEXT:    #NO_APP
-; SPILL-O2-NEXT:    vl1r.v v8, (sp) # Unknown-size Folded Reload
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    add sp, sp, a0
+; SPILL-O2-NEXT:    addi	a0, sp, 16
+; SPILL-O2-NEXT:    vl1r.v	v8, (a0)                        # Unknown-size Folded Reload
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    add	sp, sp, a0
+; SPILL-O2-NEXT:    addi	sp, sp, 16
 ; SPILL-O2-NEXT:    ret
 entry:
   call void asm sideeffect "",
@@ -38,30 +46,38 @@
 define <vscale x 2 x i64> @spill_lmul_2(<vscale x 2 x i64> %va) nounwind {
 ; SPILL-O0-LABEL: spill_lmul_2:
 ; SPILL-O0:       # %bb.0: # %entry
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    slli a0, a0, 1
-; SPILL-O0-NEXT:    sub sp, sp, a0
-; SPILL-O0-NEXT:    vs2r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O0-NEXT:    addi	sp, sp, -16
+; SPILL-O0-NEXT:    csrr	a0, vlenb
+; SPILL-O0-NEXT:    slli	a0, a0, 1
+; SPILL-O0-NEXT:    sub	sp, sp, a0
+; SPILL-O0-NEXT:    addi	a0, sp, 16
+; SPILL-O0-NEXT:    vs2r.v	v8, (a0)                        # Unknown-size Folded Spill
 ; SPILL-O0-NEXT:    #APP
 ; SPILL-O0-NEXT:    #NO_APP
-; SPILL-O0-NEXT:    vl2re8.v v8, (sp) # Unknown-size Folded Reload
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    slli a0, a0, 1
-; SPILL-O0-NEXT:    add sp, sp, a0
+; SPILL-O0-NEXT:    addi	a0, sp, 16
+; SPILL-O0-NEXT:    vl2re8.v	v8, (a0)                        # Unknown-size Folded Reload
+; SPILL-O0-NEXT:    csrr	a0, vlenb
+; SPILL-O0-NEXT:    slli	a0, a0, 1
+; SPILL-O0-NEXT:    add	sp, sp, a0
+; SPILL-O0-NEXT:    addi	sp, sp, 16
 ; SPILL-O0-NEXT:    ret
 ;
 ; SPILL-O2-LABEL: spill_lmul_2:
 ; SPILL-O2:       # %bb.0: # %entry
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    slli a0, a0, 1
-; SPILL-O2-NEXT:    sub sp, sp, a0
-; SPILL-O2-NEXT:    vs2r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O2-NEXT:    addi	sp, sp, -16
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    slli	a0, a0, 1
+; SPILL-O2-NEXT:    sub	sp, sp, a0
+; SPILL-O2-NEXT:    addi	a0, sp, 16
+; SPILL-O2-NEXT:    vs2r.v	v8, (a0)                        # Unknown-size Folded Spill
 ; SPILL-O2-NEXT:    #APP
 ; SPILL-O2-NEXT:    #NO_APP
-; SPILL-O2-NEXT:    vl2re8.v v8, (sp) # Unknown-size Folded Reload
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    slli a0, a0, 1
-; SPILL-O2-NEXT:    add sp, sp, a0
+; SPILL-O2-NEXT:    addi	a0, sp, 16
+; SPILL-O2-NEXT:    vl2re8.v	v8, (a0)                        # Unknown-size Folded Reload
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    slli	a0, a0, 1
+; SPILL-O2-NEXT:    add	sp, sp, a0
+; SPILL-O2-NEXT:    addi	sp, sp, 16
 ; SPILL-O2-NEXT:    ret
 entry:
   call void asm sideeffect "",
@@ -73,30 +89,38 @@
 define <vscale x 4 x i64> @spill_lmul_4(<vscale x 4 x i64> %va) nounwind {
 ; SPILL-O0-LABEL: spill_lmul_4:
 ; SPILL-O0:       # %bb.0: # %entry
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    slli a0, a0, 2
-; SPILL-O0-NEXT:    sub sp, sp, a0
-; SPILL-O0-NEXT:    vs4r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O0-NEXT:    addi	sp, sp, -16
+; SPILL-O0-NEXT:    csrr	a0, vlenb
+; SPILL-O0-NEXT:    slli	a0, a0, 2
+; SPILL-O0-NEXT:    sub	sp, sp, a0
+; SPILL-O0-NEXT:    addi	a0, sp, 16
+; SPILL-O0-NEXT:    vs4r.v	v8, (a0)                        # Unknown-size Folded Spill
 ; SPILL-O0-NEXT:    #APP
 ; SPILL-O0-NEXT:    #NO_APP
-; SPILL-O0-NEXT:    vl4re8.v v8, (sp) # Unknown-size Folded Reload
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    slli a0, a0, 2
-; SPILL-O0-NEXT:    add sp, sp, a0
+; SPILL-O0-NEXT:    addi	a0, sp, 16
+; SPILL-O0-NEXT:    vl4re8.v	v8, (a0)                        # Unknown-size Folded Reload
+; SPILL-O0-NEXT:    csrr	a0, vlenb
+; SPILL-O0-NEXT:    slli	a0, a0, 2
+; SPILL-O0-NEXT:    add	sp, sp, a0
+; SPILL-O0-NEXT:    addi	sp, sp, 16
 ; SPILL-O0-NEXT:    ret
 ;
 ; SPILL-O2-LABEL: spill_lmul_4:
 ; SPILL-O2:       # %bb.0: # %entry
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    slli a0, a0, 2
-; SPILL-O2-NEXT:    sub sp, sp, a0
-; SPILL-O2-NEXT:    vs4r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O2-NEXT:    addi	sp, sp, -16
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    slli	a0, a0, 2
+; SPILL-O2-NEXT:    sub	sp, sp, a0
+; SPILL-O2-NEXT:    addi	a0, sp, 16
+; SPILL-O2-NEXT:    vs4r.v	v8, (a0)                        # Unknown-size Folded Spill
 ; SPILL-O2-NEXT:    #APP
 ; SPILL-O2-NEXT:    #NO_APP
-; SPILL-O2-NEXT:    vl4re8.v v8, (sp) # Unknown-size Folded Reload
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    slli a0, a0, 2
-; SPILL-O2-NEXT:    add sp, sp, a0
+; SPILL-O2-NEXT:    addi	a0, sp, 16
+; SPILL-O2-NEXT:    vl4re8.v	v8, (a0)                        # Unknown-size Folded Reload
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    slli	a0, a0, 2
+; SPILL-O2-NEXT:    add	sp, sp, a0
+; SPILL-O2-NEXT:    addi	sp, sp, 16
 ; SPILL-O2-NEXT:    ret
 entry:
   call void asm sideeffect "",
@@ -108,30 +132,38 @@
 define <vscale x 8 x i64> @spill_lmul_8(<vscale x 8 x i64> %va) nounwind {
 ; SPILL-O0-LABEL: spill_lmul_8:
 ; SPILL-O0:       # %bb.0: # %entry
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    slli a0, a0, 3
-; SPILL-O0-NEXT:    sub sp, sp, a0
-; SPILL-O0-NEXT:    vs8r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O0-NEXT:    addi	sp, sp, -16
+; SPILL-O0-NEXT:    csrr	a0, vlenb
+; SPILL-O0-NEXT:    slli	a0, a0, 3
+; SPILL-O0-NEXT:    sub	sp, sp, a0
+; SPILL-O0-NEXT:    addi	a0, sp, 16
+; SPILL-O0-NEXT:    vs8r.v	v8, (a0)                        # Unknown-size Folded Spill
 ; SPILL-O0-NEXT:    #APP
 ; SPILL-O0-NEXT:    #NO_APP
-; SPILL-O0-NEXT:    vl8re8.v v8, (sp) # Unknown-size Folded Reload
-; SPILL-O0-NEXT:    csrr a0, vlenb
-; SPILL-O0-NEXT:    slli a0, a0, 3
-; SPILL-O0-NEXT:    add sp, sp, a0
+; SPILL-O0-NEXT:    addi	a0, sp, 16
+; SPILL-O0-NEXT:    vl8re8.v	v8, (a0)                        # Unknown-size Folded Reload
+; SPILL-O0-NEXT:    csrr	a0, vlenb
+; SPILL-O0-NEXT:    slli	a0, a0, 3
+; SPILL-O0-NEXT:    add	sp, sp, a0
+; SPILL-O0-NEXT:    addi	sp, sp, 16
 ; SPILL-O0-NEXT:    ret
 ;
 ; SPILL-O2-LABEL: spill_lmul_8:
 ; SPILL-O2:       # %bb.0: # %entry
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    slli a0, a0, 3
-; SPILL-O2-NEXT:    sub sp, sp, a0
-; SPILL-O2-NEXT:    vs8r.v v8, (sp) # Unknown-size Folded Spill
+; SPILL-O2-NEXT:    addi	sp, sp, -16
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    slli	a0, a0, 3
+; SPILL-O2-NEXT:    sub	sp, sp, a0
+; SPILL-O2-NEXT:    addi	a0, sp, 16
+; SPILL-O2-NEXT:    vs8r.v	v8, (a0)                        # Unknown-size Folded Spill
 ; SPILL-O2-NEXT:    #APP
 ; SPILL-O2-NEXT:    #NO_APP
-; SPILL-O2-NEXT:    vl8re8.v v8, (sp) # Unknown-size Folded Reload
-; SPILL-O2-NEXT:    csrr a0, vlenb
-; SPILL-O2-NEXT:    slli a0, a0, 3
-; SPILL-O2-NEXT:    add sp, sp, a0
+; SPILL-O2-NEXT:    addi	a0, sp, 16
+; SPILL-O2-NEXT:    vl8re8.v	v8, (a0)                        # Unknown-size Folded Reload
+; SPILL-O2-NEXT:    csrr	a0, vlenb
+; SPILL-O2-NEXT:    slli	a0, a0, 3
+; SPILL-O2-NEXT:    add	sp, sp, a0
+; SPILL-O2-NEXT:    addi	sp, sp, 16
 ; SPILL-O2-NEXT:    ret
 entry:
   call void asm sideeffect "",