diff --git a/llvm/lib/Target/RISCV/MCTargetDesc/RISCVBaseInfo.h b/llvm/lib/Target/RISCV/MCTargetDesc/RISCVBaseInfo.h --- a/llvm/lib/Target/RISCV/MCTargetDesc/RISCVBaseInfo.h +++ b/llvm/lib/Target/RISCV/MCTargetDesc/RISCVBaseInfo.h @@ -124,6 +124,7 @@ }; enum { + TAIL_UNDISTURBED_MASK_UNDISTURBED = 0, TAIL_AGNOSTIC = 1, MASK_AGNOSTIC = 2, }; diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp --- a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp +++ b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp @@ -3063,10 +3063,11 @@ return convertFromScalableVector(VT, Res, DAG, Subtarget); } -static SDValue getVSlidedown(SelectionDAG &DAG, const RISCVSubtarget &Subtarget, - SDLoc DL, EVT VT, SDValue Merge, SDValue Op, - SDValue Offset, SDValue Mask, SDValue VL, - unsigned Policy = /* TUMU */ 0) { +static SDValue +getVSlidedown(SelectionDAG &DAG, const RISCVSubtarget &Subtarget, SDLoc DL, + EVT VT, SDValue Merge, SDValue Op, SDValue Offset, SDValue Mask, + SDValue VL, + unsigned Policy = RISCVII::TAIL_UNDISTURBED_MASK_UNDISTURBED) { if (Merge.isUndef()) Policy = RISCVII::TAIL_AGNOSTIC | RISCVII::MASK_AGNOSTIC; SDValue PolicyOp = DAG.getTargetConstant(Policy, DL, Subtarget.getXLenVT()); @@ -3074,10 +3075,11 @@ return DAG.getNode(RISCVISD::VSLIDEDOWN_VL, DL, VT, Ops); } -static SDValue getVSlideup(SelectionDAG &DAG, const RISCVSubtarget &Subtarget, - SDLoc DL, EVT VT, SDValue Merge, SDValue Op, - SDValue Offset, SDValue Mask, SDValue VL, - unsigned Policy = /* TUMU */ 0) { +static SDValue +getVSlideup(SelectionDAG &DAG, const RISCVSubtarget &Subtarget, SDLoc DL, + EVT VT, SDValue Merge, SDValue Op, SDValue Offset, SDValue Mask, + SDValue VL, + unsigned Policy = RISCVII::TAIL_UNDISTURBED_MASK_UNDISTURBED) { if (Merge.isUndef()) Policy = RISCVII::TAIL_AGNOSTIC | RISCVII::MASK_AGNOSTIC; SDValue PolicyOp = DAG.getTargetConstant(Policy, DL, Subtarget.getXLenVT()); @@ -3291,7 +3293,8 @@ } if (LoV) Res = getVSlideup(DAG, Subtarget, DL, ContainerVT, Res, LoV, - DAG.getConstant(InvRotate, DL, XLenVT), TrueMask, VL); + DAG.getConstant(InvRotate, DL, XLenVT), TrueMask, VL, + RISCVII::TAIL_AGNOSTIC); return convertFromScalableVector(VT, Res, DAG, Subtarget); } @@ -5235,8 +5238,15 @@ // Now that the value is in a vector, slide it into position. SDValue InsertVL = DAG.getNode(ISD::ADD, DL, XLenVT, Idx, DAG.getConstant(1, DL, XLenVT)); + + // Use tail agnostic policy if Idx is the last index of Vec. + unsigned Policy = RISCVII::TAIL_UNDISTURBED_MASK_UNDISTURBED; + if (VecVT.isFixedLengthVector() && isa(Idx) && + cast(Idx)->getZExtValue() + 1 == + VecVT.getVectorNumElements()) + Policy = RISCVII::TAIL_AGNOSTIC; SDValue Slideup = getVSlideup(DAG, Subtarget, DL, ContainerVT, Vec, ValInVec, - Idx, Mask, InsertVL); + Idx, Mask, InsertVL, Policy); if (!VecVT.isFixedLengthVector()) return Slideup; return convertFromScalableVector(VecVT, Slideup, DAG, Subtarget); @@ -6143,8 +6153,14 @@ SDValue VL = getVLOp(OrigIdx + SubVecVT.getVectorNumElements(), DL, DAG, Subtarget); SDValue SlideupAmt = DAG.getConstant(OrigIdx, DL, XLenVT); + + // Use tail agnostic policy if OrigIdx is the last index of Vec. + unsigned Policy = RISCVII::TAIL_UNDISTURBED_MASK_UNDISTURBED; + if (VecVT.isFixedLengthVector() && + OrigIdx + 1 == VecVT.getVectorNumElements()) + Policy = RISCVII::TAIL_AGNOSTIC; SDValue Slideup = getVSlideup(DAG, Subtarget, DL, ContainerVT, Vec, SubVec, - SlideupAmt, Mask, VL); + SlideupAmt, Mask, VL, Policy); if (VecVT.isFixedLengthVector()) Slideup = convertFromScalableVector(VecVT, Slideup, DAG, Subtarget); return DAG.getBitcast(Op.getValueType(), Slideup); @@ -6483,7 +6499,8 @@ getVSlidedown(DAG, Subtarget, DL, VecVT, DAG.getUNDEF(VecVT), V1, DownOffset, TrueMask, UpOffset); return getVSlideup(DAG, Subtarget, DL, VecVT, SlideDown, V2, UpOffset, - TrueMask, DAG.getRegister(RISCV::X0, XLenVT)); + TrueMask, DAG.getRegister(RISCV::X0, XLenVT), + RISCVII::TAIL_AGNOSTIC); } SDValue diff --git a/llvm/test/CodeGen/RISCV/fpclamptosat_vec.ll b/llvm/test/CodeGen/RISCV/fpclamptosat_vec.ll --- a/llvm/test/CodeGen/RISCV/fpclamptosat_vec.ll +++ b/llvm/test/CodeGen/RISCV/fpclamptosat_vec.ll @@ -489,11 +489,10 @@ ; 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: vsetivli zero, 4, e64, m2, ta, 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 @@ -640,11 +639,10 @@ ; 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: vsetivli zero, 4, e64, m2, ta, 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 @@ -800,11 +798,10 @@ ; 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: vsetivli zero, 4, e64, m2, ta, 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 @@ -1455,11 +1452,10 @@ ; 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: vsetivli zero, 8, e32, m2, ta, 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 @@ -1731,11 +1727,10 @@ ; 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: vsetivli zero, 8, e32, m2, ta, 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 @@ -2027,11 +2022,10 @@ ; 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: vsetivli zero, 8, e32, m2, ta, 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 @@ -2224,7 +2218,7 @@ ; CHECK-V-NEXT: vle64.v v8, (a0) ; CHECK-V-NEXT: addi a0, sp, 32 ; CHECK-V-NEXT: vle64.v v9, (a0) -; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-V-NEXT: vslideup.vi v8, v9, 1 ; CHECK-V-NEXT: csrr a0, vlenb ; CHECK-V-NEXT: slli a0, a0, 1 @@ -2317,7 +2311,7 @@ ; CHECK-V-NEXT: vle64.v v8, (a0) ; CHECK-V-NEXT: addi a0, sp, 32 ; CHECK-V-NEXT: vle64.v v9, (a0) -; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-V-NEXT: vslideup.vi v8, v9, 1 ; CHECK-V-NEXT: csrr a0, vlenb ; CHECK-V-NEXT: slli a0, a0, 1 @@ -2461,7 +2455,7 @@ ; CHECK-V-NEXT: vle64.v v8, (a0) ; CHECK-V-NEXT: addi a0, sp, 32 ; CHECK-V-NEXT: vle64.v v9, (a0) -; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-V-NEXT: vslideup.vi v8, v9, 1 ; CHECK-V-NEXT: csrr a0, vlenb ; CHECK-V-NEXT: slli a0, a0, 1 @@ -2647,7 +2641,7 @@ ; CHECK-V-NEXT: vle64.v v8, (a0) ; CHECK-V-NEXT: addi a0, sp, 32 ; CHECK-V-NEXT: vle64.v v9, (a0) -; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-V-NEXT: vslideup.vi v8, v9, 1 ; CHECK-V-NEXT: csrr a0, vlenb ; CHECK-V-NEXT: slli a0, a0, 1 @@ -2740,7 +2734,7 @@ ; CHECK-V-NEXT: vle64.v v8, (a0) ; CHECK-V-NEXT: addi a0, sp, 32 ; CHECK-V-NEXT: vle64.v v9, (a0) -; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-V-NEXT: vslideup.vi v8, v9, 1 ; CHECK-V-NEXT: csrr a0, vlenb ; CHECK-V-NEXT: slli a0, a0, 1 @@ -2884,7 +2878,7 @@ ; CHECK-V-NEXT: vle64.v v8, (a0) ; CHECK-V-NEXT: addi a0, sp, 32 ; CHECK-V-NEXT: vle64.v v9, (a0) -; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-V-NEXT: vslideup.vi v8, v9, 1 ; CHECK-V-NEXT: csrr a0, vlenb ; CHECK-V-NEXT: slli a0, a0, 1 @@ -3064,7 +3058,7 @@ ; CHECK-V-NEXT: vle64.v v9, (a0) ; CHECK-V-NEXT: mv a0, sp ; CHECK-V-NEXT: vle64.v v8, (a0) -; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-V-NEXT: vslideup.vi v8, v9, 1 ; CHECK-V-NEXT: ld ra, 40(sp) # 8-byte Folded Reload ; CHECK-V-NEXT: ld s0, 32(sp) # 8-byte Folded Reload @@ -3150,7 +3144,7 @@ ; CHECK-V-NEXT: vle64.v v9, (a0) ; CHECK-V-NEXT: mv a0, sp ; CHECK-V-NEXT: vle64.v v8, (a0) -; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-V-NEXT: vslideup.vi v8, v9, 1 ; CHECK-V-NEXT: ld ra, 40(sp) # 8-byte Folded Reload ; CHECK-V-NEXT: ld s0, 32(sp) # 8-byte Folded Reload @@ -3287,7 +3281,7 @@ ; CHECK-V-NEXT: vle64.v v9, (a0) ; CHECK-V-NEXT: mv a0, sp ; CHECK-V-NEXT: vle64.v v8, (a0) -; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-V-NEXT: vslideup.vi v8, v9, 1 ; CHECK-V-NEXT: ld ra, 40(sp) # 8-byte Folded Reload ; CHECK-V-NEXT: ld s0, 32(sp) # 8-byte Folded Reload @@ -3782,11 +3776,10 @@ ; 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: vsetivli zero, 4, e64, m2, ta, 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 @@ -3931,11 +3924,10 @@ ; 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: vsetivli zero, 4, e64, m2, ta, 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 @@ -4090,11 +4082,10 @@ ; 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: vsetivli zero, 4, e64, m2, ta, 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 @@ -4733,11 +4724,10 @@ ; 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: vsetivli zero, 8, e32, m2, ta, 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 @@ -5005,11 +4995,10 @@ ; 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: vsetivli zero, 8, e32, m2, ta, 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 @@ -5300,11 +5289,10 @@ ; 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: vsetivli zero, 8, e32, m2, ta, 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 @@ -5510,7 +5498,7 @@ ; CHECK-V-NEXT: vle64.v v8, (a0) ; CHECK-V-NEXT: addi a0, sp, 32 ; CHECK-V-NEXT: vle64.v v9, (a0) -; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-V-NEXT: vslideup.vi v8, v9, 1 ; CHECK-V-NEXT: csrr a0, vlenb ; CHECK-V-NEXT: slli a0, a0, 1 @@ -5653,7 +5641,7 @@ ; CHECK-V-NEXT: vle64.v v8, (a0) ; CHECK-V-NEXT: addi a0, sp, 32 ; CHECK-V-NEXT: vle64.v v9, (a0) -; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-V-NEXT: vslideup.vi v8, v9, 1 ; CHECK-V-NEXT: csrr a0, vlenb ; CHECK-V-NEXT: slli a0, a0, 1 @@ -5801,7 +5789,7 @@ ; CHECK-V-NEXT: vle64.v v8, (a0) ; CHECK-V-NEXT: addi a0, sp, 32 ; CHECK-V-NEXT: vle64.v v9, (a0) -; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-V-NEXT: vslideup.vi v8, v9, 1 ; CHECK-V-NEXT: csrr a0, vlenb ; CHECK-V-NEXT: slli a0, a0, 1 @@ -6000,7 +5988,7 @@ ; CHECK-V-NEXT: vle64.v v8, (a0) ; CHECK-V-NEXT: addi a0, sp, 32 ; CHECK-V-NEXT: vle64.v v9, (a0) -; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-V-NEXT: vslideup.vi v8, v9, 1 ; CHECK-V-NEXT: csrr a0, vlenb ; CHECK-V-NEXT: slli a0, a0, 1 @@ -6143,7 +6131,7 @@ ; CHECK-V-NEXT: vle64.v v8, (a0) ; CHECK-V-NEXT: addi a0, sp, 32 ; CHECK-V-NEXT: vle64.v v9, (a0) -; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-V-NEXT: vslideup.vi v8, v9, 1 ; CHECK-V-NEXT: csrr a0, vlenb ; CHECK-V-NEXT: slli a0, a0, 1 @@ -6291,7 +6279,7 @@ ; CHECK-V-NEXT: vle64.v v8, (a0) ; CHECK-V-NEXT: addi a0, sp, 32 ; CHECK-V-NEXT: vle64.v v9, (a0) -; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-V-NEXT: vslideup.vi v8, v9, 1 ; CHECK-V-NEXT: csrr a0, vlenb ; CHECK-V-NEXT: slli a0, a0, 1 @@ -6485,7 +6473,7 @@ ; CHECK-V-NEXT: vle64.v v9, (a0) ; CHECK-V-NEXT: mv a0, sp ; CHECK-V-NEXT: vle64.v v8, (a0) -; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-V-NEXT: vslideup.vi v8, v9, 1 ; CHECK-V-NEXT: ld ra, 40(sp) # 8-byte Folded Reload ; CHECK-V-NEXT: ld s0, 32(sp) # 8-byte Folded Reload @@ -6622,7 +6610,7 @@ ; CHECK-V-NEXT: vle64.v v9, (a0) ; CHECK-V-NEXT: mv a0, sp ; CHECK-V-NEXT: vle64.v v8, (a0) -; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-V-NEXT: vslideup.vi v8, v9, 1 ; CHECK-V-NEXT: ld ra, 40(sp) # 8-byte Folded Reload ; CHECK-V-NEXT: ld s0, 32(sp) # 8-byte Folded Reload @@ -6764,7 +6752,7 @@ ; CHECK-V-NEXT: vle64.v v9, (a0) ; CHECK-V-NEXT: mv a0, sp ; CHECK-V-NEXT: vle64.v v8, (a0) -; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-V-NEXT: vslideup.vi v8, v9, 1 ; CHECK-V-NEXT: ld ra, 40(sp) # 8-byte Folded Reload ; CHECK-V-NEXT: ld s0, 32(sp) # 8-byte Folded Reload diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vector-shuffle-reverse.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vector-shuffle-reverse.ll --- a/llvm/test/CodeGen/RISCV/rvv/fixed-vector-shuffle-reverse.ll +++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vector-shuffle-reverse.ll @@ -2681,7 +2681,7 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e8, mf8, ta, ma ; CHECK-NEXT: vslidedown.vi v9, v8, 1 -; CHECK-NEXT: vsetivli zero, 2, e8, mf8, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e8, mf8, ta, ma ; CHECK-NEXT: vslideup.vi v9, v8, 1 ; CHECK-NEXT: vmv1r.v v8, v9 ; CHECK-NEXT: ret @@ -2771,7 +2771,7 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e16, mf4, ta, ma ; CHECK-NEXT: vslidedown.vi v9, v8, 1 -; CHECK-NEXT: vsetivli zero, 2, e16, mf4, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma ; CHECK-NEXT: vslideup.vi v9, v8, 1 ; CHECK-NEXT: vmv1r.v v8, v9 ; CHECK-NEXT: ret @@ -2846,7 +2846,7 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e32, mf2, ta, ma ; CHECK-NEXT: vslidedown.vi v9, v8, 1 -; CHECK-NEXT: vsetivli zero, 2, e32, mf2, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma ; CHECK-NEXT: vslideup.vi v9, v8, 1 ; CHECK-NEXT: vmv1r.v v8, v9 ; CHECK-NEXT: ret @@ -2906,9 +2906,9 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma ; CHECK-NEXT: vslidedown.vi v9, v8, 1 -; CHECK-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-NEXT: vslideup.vi v9, v8, 1 -; CHECK-NEXT: vmv1r.v v8, v9 +; CHECK-NEXT: vmv.v.v v8, v9 ; CHECK-NEXT: ret %res = call <2 x i64> @llvm.experimental.vector.reverse.v2i64(<2 x i64> %a) ret <2 x i64> %res @@ -3050,7 +3050,7 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e16, mf4, ta, ma ; CHECK-NEXT: vslidedown.vi v9, v8, 1 -; CHECK-NEXT: vsetivli zero, 2, e16, mf4, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma ; CHECK-NEXT: vslideup.vi v9, v8, 1 ; CHECK-NEXT: vmv1r.v v8, v9 ; CHECK-NEXT: ret @@ -3125,7 +3125,7 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e32, mf2, ta, ma ; CHECK-NEXT: vslidedown.vi v9, v8, 1 -; CHECK-NEXT: vsetivli zero, 2, e32, mf2, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma ; CHECK-NEXT: vslideup.vi v9, v8, 1 ; CHECK-NEXT: vmv1r.v v8, v9 ; CHECK-NEXT: ret @@ -3185,9 +3185,9 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma ; CHECK-NEXT: vslidedown.vi v9, v8, 1 -; CHECK-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-NEXT: vslideup.vi v9, v8, 1 -; CHECK-NEXT: vmv1r.v v8, v9 +; CHECK-NEXT: vmv.v.v v8, v9 ; CHECK-NEXT: ret %res = call <2 x double> @llvm.experimental.vector.reverse.v2f64(<2 x double> %a) ret <2 x double> %res diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-extract.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-extract.ll --- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-extract.ll +++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-extract.ll @@ -699,9 +699,7 @@ ; RV32NOM-NEXT: vsetivli zero, 4, e32, m1, ta, ma ; RV32NOM-NEXT: vmv.v.i v9, -1 ; 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) @@ -737,9 +735,7 @@ ; RV64-NEXT: vsetivli zero, 4, e32, m1, ta, ma ; RV64-NEXT: vmv.v.i v9, -1 ; 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) diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-shuffles.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-shuffles.ll --- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-shuffles.ll +++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-shuffles.ll @@ -306,9 +306,9 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 7, e32, m2, ta, ma ; CHECK-NEXT: vslidedown.vi v10, v8, 1 -; CHECK-NEXT: vsetivli zero, 8, e32, m2, tu, ma +; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; CHECK-NEXT: vslideup.vi v10, v8, 7 -; CHECK-NEXT: vmv2r.v v8, v10 +; CHECK-NEXT: vmv.v.v v8, v10 ; CHECK-NEXT: ret %s = shufflevector <8 x float> %x, <8 x float> poison, <8 x i32> ret <8 x float> %s @@ -319,9 +319,9 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 2, e64, m4, ta, ma ; CHECK-NEXT: vslidedown.vi v12, v8, 6 -; CHECK-NEXT: vsetivli zero, 8, e64, m4, tu, ma +; CHECK-NEXT: vsetivli zero, 8, e64, m4, ta, ma ; CHECK-NEXT: vslideup.vi v12, v8, 2 -; CHECK-NEXT: vmv4r.v v8, v12 +; CHECK-NEXT: vmv.v.v v8, v12 ; CHECK-NEXT: ret %s = shufflevector <8 x double> %x, <8 x double> poison, <8 x i32> ret <8 x double> %s @@ -332,7 +332,7 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 6, e32, m2, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 2 -; CHECK-NEXT: vsetivli zero, 8, e32, m2, tu, ma +; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v10, 6 ; CHECK-NEXT: ret %s = shufflevector <8 x float> %x, <8 x float> %y, <8 x i32> @@ -344,9 +344,9 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 3, e64, m4, ta, ma ; CHECK-NEXT: vslidedown.vi v12, v12, 5 -; CHECK-NEXT: vsetivli zero, 8, e64, m4, tu, ma +; CHECK-NEXT: vsetivli zero, 8, e64, m4, ta, ma ; CHECK-NEXT: vslideup.vi v12, v8, 3 -; CHECK-NEXT: vmv4r.v v8, v12 +; CHECK-NEXT: vmv.v.v v8, v12 ; CHECK-NEXT: ret %s = shufflevector <8 x double> %x, <8 x double> %y, <8 x i32> ret <8 x double> %s diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-insert-i1.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-insert-i1.ll --- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-insert-i1.ll +++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-insert-i1.ll @@ -41,9 +41,7 @@ ; 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 diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-insert.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-insert.ll --- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-insert.ll +++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-insert.ll @@ -13,7 +13,7 @@ ; RV32-NEXT: vsetivli zero, 2, e32, m2, ta, ma ; RV32-NEXT: vslide1down.vx v10, v8, a1 ; RV32-NEXT: vslide1down.vx v10, v10, a2 -; RV32-NEXT: vsetivli zero, 4, e64, m2, tu, ma +; RV32-NEXT: vsetivli zero, 4, e64, m2, ta, ma ; RV32-NEXT: vslideup.vi v8, v10, 3 ; RV32-NEXT: vse64.v v8, (a0) ; RV32-NEXT: ret @@ -23,7 +23,6 @@ ; RV64-NEXT: vsetivli zero, 4, e64, m2, ta, ma ; RV64-NEXT: vle64.v v8, (a0) ; RV64-NEXT: vmv.s.x v10, a1 -; RV64-NEXT: vsetvli zero, zero, e64, m2, tu, ma ; RV64-NEXT: vslideup.vi v8, v10, 3 ; RV64-NEXT: vse64.v v8, (a0) ; RV64-NEXT: ret diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll --- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll +++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll @@ -523,7 +523,6 @@ ; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma ; CHECK-NEXT: vse32.v v10, (a5) ; CHECK-NEXT: vmv.v.i v8, 0 -; CHECK-NEXT: vsetvli zero, zero, e32, m1, tu, ma ; CHECK-NEXT: vslideup.vi v8, v9, 3 ; CHECK-NEXT: vse32.v v8, (a6) ; CHECK-NEXT: ret @@ -556,7 +555,7 @@ ; CHECK-NEXT: vsetivli zero, 2, e16, mf2, tu, ma ; CHECK-NEXT: vmv1r.v v10, v9 ; CHECK-NEXT: vslideup.vi v10, v8, 1 -; CHECK-NEXT: vsetivli zero, 4, e16, mf2, tu, ma +; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma ; CHECK-NEXT: vse16.v v10, (a5) ; CHECK-NEXT: vslideup.vi v8, v9, 3 ; CHECK-NEXT: vse16.v v8, (a6) diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll --- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll +++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll @@ -186,12 +186,11 @@ ; RV32-NEXT: vsetivli zero, 8, e16, m1, ta, ma ; RV32-NEXT: vmv.v.i v16, 5 ; 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 @@ -204,14 +203,12 @@ ; RV64-NEXT: li a0, 5 ; RV64-NEXT: vsetivli zero, 8, e64, m1, ta, ma ; RV64-NEXT: vmv.s.x v16, a0 -; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, ma +; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu ; 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: li a0, 164 ; RV64-NEXT: vmv.s.x v0, a0 ; RV64-NEXT: vrgather.vv v16, v8, v24 @@ -591,9 +588,9 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 6, e16, m1, ta, ma ; CHECK-NEXT: vslidedown.vi v9, v8, 2 -; CHECK-NEXT: vsetivli zero, 8, e16, m1, tu, ma +; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma ; CHECK-NEXT: vslideup.vi v9, v8, 6 -; CHECK-NEXT: vmv1r.v v8, v9 +; CHECK-NEXT: vmv.v.v v8, v9 ; CHECK-NEXT: ret %s = shufflevector <8 x i16> %x, <8 x i16> poison, <8 x i32> ret <8 x i16> %s @@ -604,9 +601,9 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 3, e32, m2, ta, ma ; CHECK-NEXT: vslidedown.vi v10, v8, 5 -; CHECK-NEXT: vsetivli zero, 8, e32, m2, tu, ma +; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; CHECK-NEXT: vslideup.vi v10, v8, 3 -; CHECK-NEXT: vmv2r.v v8, v10 +; CHECK-NEXT: vmv.v.v v8, v10 ; CHECK-NEXT: ret %s = shufflevector <8 x i32> %x, <8 x i32> poison, <8 x i32> ret <8 x i32> %s @@ -617,7 +614,7 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 6, e16, m1, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 2 -; CHECK-NEXT: vsetivli zero, 8, e16, m1, tu, ma +; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 6 ; CHECK-NEXT: ret %s = shufflevector <8 x i16> %x, <8 x i16> %y, <8 x i32> @@ -629,7 +626,7 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 3, e32, m2, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 5 -; CHECK-NEXT: vsetivli zero, 8, e32, m2, tu, ma +; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v10, 3 ; CHECK-NEXT: ret %s = shufflevector <8 x i32> %x, <8 x i32> %y, <8 x i32> diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int.ll --- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int.ll +++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int.ll @@ -997,9 +997,7 @@ ; CHECK-NEXT: vadd.vv v8, v8, v9 ; CHECK-NEXT: vmv.v.i v9, 1 ; 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 @@ -4605,9 +4603,7 @@ ; LMULMAX1-RV32-NEXT: vadd.vv v9, v9, v12 ; LMULMAX1-RV32-NEXT: vmv.v.i v12, 1 ; 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 diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-mask-buildvec.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-mask-buildvec.ll --- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-mask-buildvec.ll +++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-mask-buildvec.ll @@ -667,7 +667,6 @@ ; RV32-LMULMAX4-NEXT: lui a0, 748384 ; RV32-LMULMAX4-NEXT: addi a0, a0, 1776 ; RV32-LMULMAX4-NEXT: vmv.s.x v0, a0 -; RV32-LMULMAX4-NEXT: vsetvli zero, zero, e32, mf2, tu, ma ; RV32-LMULMAX4-NEXT: vslideup.vi v0, v8, 1 ; RV32-LMULMAX4-NEXT: ret ; @@ -688,7 +687,6 @@ ; RV32-LMULMAX8-NEXT: lui a0, 748384 ; RV32-LMULMAX8-NEXT: addi a0, a0, 1776 ; RV32-LMULMAX8-NEXT: vmv.s.x v0, a0 -; RV32-LMULMAX8-NEXT: vsetvli zero, zero, e32, mf2, tu, ma ; RV32-LMULMAX8-NEXT: vslideup.vi v0, v8, 1 ; RV32-LMULMAX8-NEXT: ret ; @@ -790,7 +788,6 @@ ; RV32-LMULMAX4-NEXT: lui a0, 748384 ; RV32-LMULMAX4-NEXT: addi a0, a0, 1776 ; RV32-LMULMAX4-NEXT: vmv.s.x v0, a0 -; RV32-LMULMAX4-NEXT: vsetvli zero, zero, e32, mf2, tu, ma ; RV32-LMULMAX4-NEXT: vslideup.vi v0, v8, 1 ; RV32-LMULMAX4-NEXT: lui a0, 945060 ; RV32-LMULMAX4-NEXT: addi a0, a0, -1793 @@ -831,7 +828,7 @@ ; RV32-LMULMAX8-NEXT: lui a0, 945060 ; RV32-LMULMAX8-NEXT: addi a0, a0, -1793 ; RV32-LMULMAX8-NEXT: vmv.s.x v8, a0 -; RV32-LMULMAX8-NEXT: vsetivli zero, 4, e32, m1, tu, ma +; RV32-LMULMAX8-NEXT: vsetivli zero, 4, e32, m1, ta, ma ; RV32-LMULMAX8-NEXT: vslideup.vi v0, v8, 3 ; RV32-LMULMAX8-NEXT: ret ; @@ -844,7 +841,6 @@ ; RV64-LMULMAX8-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; RV64-LMULMAX8-NEXT: vmv.s.x v8, a0 ; RV64-LMULMAX8-NEXT: vmv.s.x v0, a1 -; RV64-LMULMAX8-NEXT: vsetvli zero, zero, e64, m1, tu, ma ; RV64-LMULMAX8-NEXT: vslideup.vi v0, v8, 1 ; RV64-LMULMAX8-NEXT: ret ret <128 x i1> diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-gather.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-gather.ll --- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-gather.ll +++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-gather.ll @@ -94,7 +94,6 @@ ; RV64ZVE32F-NEXT: lb a0, 0(a1) ; RV64ZVE32F-NEXT: vsetivli zero, 2, e8, mf4, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e8, mf4, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 1 ; RV64ZVE32F-NEXT: ret %v = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> %ptrs, i32 1, <2 x i1> %m, <2 x i8> %passthru) @@ -143,7 +142,6 @@ ; RV64ZVE32F-NEXT: lb a0, 0(a1) ; RV64ZVE32F-NEXT: vsetivli zero, 2, e8, mf4, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e8, mf4, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 1 ; RV64ZVE32F-NEXT: .LBB2_4: # %else2 ; RV64ZVE32F-NEXT: vsetivli zero, 2, e16, mf2, ta, ma @@ -197,7 +195,6 @@ ; RV64ZVE32F-NEXT: lb a0, 0(a1) ; RV64ZVE32F-NEXT: vsetivli zero, 2, e8, mf4, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e8, mf4, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 1 ; RV64ZVE32F-NEXT: .LBB3_4: # %else2 ; RV64ZVE32F-NEXT: vsetivli zero, 2, e16, mf2, ta, ma @@ -251,7 +248,6 @@ ; RV64ZVE32F-NEXT: lb a0, 0(a1) ; RV64ZVE32F-NEXT: vsetivli zero, 2, e8, mf4, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e8, mf4, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 1 ; RV64ZVE32F-NEXT: .LBB4_4: # %else2 ; RV64ZVE32F-NEXT: vsetivli zero, 2, e32, m1, ta, ma @@ -305,7 +301,6 @@ ; RV64ZVE32F-NEXT: lb a0, 0(a1) ; RV64ZVE32F-NEXT: vsetivli zero, 2, e8, mf4, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e8, mf4, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 1 ; RV64ZVE32F-NEXT: .LBB5_4: # %else2 ; RV64ZVE32F-NEXT: vsetivli zero, 2, e32, m1, ta, ma @@ -367,7 +362,6 @@ ; RV64ZVE32F-NEXT: lb a0, 0(a1) ; RV64ZVE32F-NEXT: vsetivli zero, 2, e8, mf4, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e8, mf4, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 1 ; RV64ZVE32F-NEXT: .LBB6_4: # %else2 ; RV64ZVE32F-NEXT: vsetivli zero, 1, e8, mf4, ta, ma @@ -430,7 +424,6 @@ ; RV64ZVE32F-NEXT: lb a0, 0(a1) ; RV64ZVE32F-NEXT: vsetivli zero, 2, e8, mf4, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e8, mf4, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 1 ; RV64ZVE32F-NEXT: .LBB7_4: # %else2 ; RV64ZVE32F-NEXT: vsetivli zero, 1, e8, mf4, ta, ma @@ -509,7 +502,6 @@ ; RV64ZVE32F-NEXT: lb a0, 0(a0) ; RV64ZVE32F-NEXT: vsetivli zero, 4, e8, mf4, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e8, mf4, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 3 ; RV64ZVE32F-NEXT: ret %v = call <4 x i8> @llvm.masked.gather.v4i8.v4p0(<4 x ptr> %ptrs, i32 1, <4 x i1> %m, <4 x i8> %passthru) @@ -578,7 +570,6 @@ ; RV64ZVE32F-NEXT: lb a0, 0(a0) ; RV64ZVE32F-NEXT: vsetivli zero, 4, e8, mf4, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e8, mf4, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 3 ; RV64ZVE32F-NEXT: ret %mhead = insertelement <4 x i1> poison, i1 1, i32 0 @@ -717,7 +708,6 @@ ; RV64ZVE32F-NEXT: lb a0, 0(a0) ; RV64ZVE32F-NEXT: vsetivli zero, 8, e8, mf2, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e8, mf2, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 7 ; RV64ZVE32F-NEXT: ret %v = call <8 x i8> @llvm.masked.gather.v8i8.v8p0(<8 x ptr> %ptrs, i32 1, <8 x i1> %m, <8 x i8> %passthru) @@ -849,7 +839,7 @@ ; RV64ZVE32F-NEXT: add a0, a0, a1 ; RV64ZVE32F-NEXT: lb a0, 0(a0) ; RV64ZVE32F-NEXT: vmv.s.x v8, a0 -; RV64ZVE32F-NEXT: vsetivli zero, 8, e8, mf2, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 8, e8, mf2, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v9, v8, 7 ; RV64ZVE32F-NEXT: vmv1r.v v8, v9 ; RV64ZVE32F-NEXT: ret @@ -944,7 +934,6 @@ ; RV64ZVE32F-NEXT: lh a0, 0(a1) ; RV64ZVE32F-NEXT: vsetivli zero, 2, e16, mf2, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e16, mf2, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 1 ; RV64ZVE32F-NEXT: ret %v = call <2 x i16> @llvm.masked.gather.v2i16.v2p0(<2 x ptr> %ptrs, i32 2, <2 x i1> %m, <2 x i16> %passthru) @@ -993,7 +982,6 @@ ; RV64ZVE32F-NEXT: lh a0, 0(a1) ; RV64ZVE32F-NEXT: vsetivli zero, 2, e16, mf2, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e16, mf2, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 1 ; RV64ZVE32F-NEXT: .LBB15_4: # %else2 ; RV64ZVE32F-NEXT: vsetivli zero, 2, e32, m1, ta, ma @@ -1047,7 +1035,6 @@ ; RV64ZVE32F-NEXT: lh a0, 0(a1) ; RV64ZVE32F-NEXT: vsetivli zero, 2, e16, mf2, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e16, mf2, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 1 ; RV64ZVE32F-NEXT: .LBB16_4: # %else2 ; RV64ZVE32F-NEXT: vsetivli zero, 2, e32, m1, ta, ma @@ -1109,7 +1096,6 @@ ; RV64ZVE32F-NEXT: lh a0, 0(a1) ; RV64ZVE32F-NEXT: vsetivli zero, 2, e16, mf2, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e16, mf2, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 1 ; RV64ZVE32F-NEXT: .LBB17_4: # %else2 ; RV64ZVE32F-NEXT: vsetivli zero, 1, e16, mf2, ta, ma @@ -1174,7 +1160,6 @@ ; RV64ZVE32F-NEXT: lh a0, 0(a1) ; RV64ZVE32F-NEXT: vsetivli zero, 2, e16, mf2, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e16, mf2, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 1 ; RV64ZVE32F-NEXT: .LBB18_4: # %else2 ; RV64ZVE32F-NEXT: vsetivli zero, 1, e16, mf2, ta, ma @@ -1255,7 +1240,6 @@ ; RV64ZVE32F-NEXT: lh a0, 0(a0) ; RV64ZVE32F-NEXT: vsetivli zero, 4, e16, mf2, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e16, mf2, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 3 ; RV64ZVE32F-NEXT: ret %v = call <4 x i16> @llvm.masked.gather.v4i16.v4p0(<4 x ptr> %ptrs, i32 2, <4 x i1> %m, <4 x i16> %passthru) @@ -1324,7 +1308,6 @@ ; RV64ZVE32F-NEXT: lh a0, 0(a0) ; RV64ZVE32F-NEXT: vsetivli zero, 4, e16, mf2, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e16, mf2, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 3 ; RV64ZVE32F-NEXT: ret %mhead = insertelement <4 x i1> poison, i1 1, i32 0 @@ -1463,7 +1446,6 @@ ; RV64ZVE32F-NEXT: lh a0, 0(a0) ; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e16, m1, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 7 ; RV64ZVE32F-NEXT: ret %v = call <8 x i16> @llvm.masked.gather.v8i16.v8p0(<8 x ptr> %ptrs, i32 2, <8 x i1> %m, <8 x i16> %passthru) @@ -1611,7 +1593,6 @@ ; RV64ZVE32F-NEXT: lh a0, 0(a0) ; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v8, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e16, m1, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v9, v8, 7 ; RV64ZVE32F-NEXT: vmv1r.v v8, v9 ; RV64ZVE32F-NEXT: ret @@ -1761,7 +1742,6 @@ ; RV64ZVE32F-NEXT: lh a0, 0(a0) ; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v8, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e16, m1, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v9, v8, 7 ; RV64ZVE32F-NEXT: vmv1r.v v8, v9 ; RV64ZVE32F-NEXT: ret @@ -1920,7 +1900,6 @@ ; RV64ZVE32F-NEXT: lh a0, 0(a0) ; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v8, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e16, m1, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v9, v8, 7 ; RV64ZVE32F-NEXT: vmv1r.v v8, v9 ; RV64ZVE32F-NEXT: ret @@ -2066,7 +2045,7 @@ ; RV64ZVE32F-NEXT: add a0, a0, a1 ; RV64ZVE32F-NEXT: lh a0, 0(a0) ; RV64ZVE32F-NEXT: vmv.s.x v8, a0 -; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v9, v8, 7 ; RV64ZVE32F-NEXT: vmv1r.v v8, v9 ; RV64ZVE32F-NEXT: ret @@ -2161,7 +2140,6 @@ ; RV64ZVE32F-NEXT: lw a0, 0(a1) ; RV64ZVE32F-NEXT: vsetivli zero, 2, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e32, m1, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 1 ; RV64ZVE32F-NEXT: ret %v = call <2 x i32> @llvm.masked.gather.v2i32.v2p0(<2 x ptr> %ptrs, i32 4, <2 x i1> %m, <2 x i32> %passthru) @@ -2219,7 +2197,6 @@ ; RV64ZVE32F-NEXT: lw a0, 0(a1) ; RV64ZVE32F-NEXT: vsetivli zero, 2, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e32, m1, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 1 ; RV64ZVE32F-NEXT: .LBB29_4: # %else2 ; RV64ZVE32F-NEXT: vsetivli zero, 1, e32, m1, ta, ma @@ -2279,7 +2256,6 @@ ; RV64ZVE32F-NEXT: lw a0, 0(a1) ; RV64ZVE32F-NEXT: vsetivli zero, 2, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e32, m1, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 1 ; RV64ZVE32F-NEXT: .LBB30_4: # %else2 ; RV64ZVE32F-NEXT: vsetivli zero, 1, e32, m1, ta, ma @@ -2360,7 +2336,6 @@ ; RV64ZVE32F-NEXT: lw a0, 0(a0) ; RV64ZVE32F-NEXT: vsetivli zero, 4, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e32, m1, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 3 ; RV64ZVE32F-NEXT: ret %v = call <4 x i32> @llvm.masked.gather.v4i32.v4p0(<4 x ptr> %ptrs, i32 4, <4 x i1> %m, <4 x i32> %passthru) @@ -2428,7 +2403,6 @@ ; RV64ZVE32F-NEXT: lw a0, 0(a0) ; RV64ZVE32F-NEXT: vsetivli zero, 4, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v9, a0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e32, m1, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 3 ; RV64ZVE32F-NEXT: ret %mhead = insertelement <4 x i1> poison, i1 1, i32 0 @@ -2567,7 +2541,7 @@ ; RV64ZVE32F-NEXT: lw a0, 0(a0) ; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v10, a0 -; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v10, 7 ; RV64ZVE32F-NEXT: ret %v = call <8 x i32> @llvm.masked.gather.v8i32.v8p0(<8 x ptr> %ptrs, i32 4, <8 x i1> %m, <8 x i32> %passthru) @@ -2714,7 +2688,7 @@ ; RV64ZVE32F-NEXT: lw a0, 0(a0) ; RV64ZVE32F-NEXT: vsetvli zero, zero, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v8, a0 -; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v10, v8, 7 ; RV64ZVE32F-NEXT: vmv2r.v v8, v10 ; RV64ZVE32F-NEXT: ret @@ -2863,7 +2837,7 @@ ; RV64ZVE32F-NEXT: lw a0, 0(a0) ; RV64ZVE32F-NEXT: vsetvli zero, zero, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v8, a0 -; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v10, v8, 7 ; RV64ZVE32F-NEXT: vmv2r.v v8, v10 ; RV64ZVE32F-NEXT: ret @@ -3021,7 +2995,7 @@ ; RV64ZVE32F-NEXT: lw a0, 0(a0) ; RV64ZVE32F-NEXT: vsetvli zero, zero, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v8, a0 -; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v10, v8, 7 ; RV64ZVE32F-NEXT: vmv2r.v v8, v10 ; RV64ZVE32F-NEXT: ret @@ -3172,7 +3146,7 @@ ; RV64ZVE32F-NEXT: lw a0, 0(a0) ; RV64ZVE32F-NEXT: vsetvli zero, zero, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v8, a0 -; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v10, v8, 7 ; RV64ZVE32F-NEXT: vmv2r.v v8, v10 ; RV64ZVE32F-NEXT: ret @@ -3322,7 +3296,7 @@ ; RV64ZVE32F-NEXT: lw a0, 0(a0) ; RV64ZVE32F-NEXT: vsetvli zero, zero, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v8, a0 -; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v10, v8, 7 ; RV64ZVE32F-NEXT: vmv2r.v v8, v10 ; RV64ZVE32F-NEXT: ret @@ -3483,7 +3457,7 @@ ; RV64ZVE32F-NEXT: lw a0, 0(a0) ; RV64ZVE32F-NEXT: vsetvli zero, zero, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v8, a0 -; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v10, v8, 7 ; RV64ZVE32F-NEXT: vmv2r.v v8, v10 ; RV64ZVE32F-NEXT: ret @@ -3628,7 +3602,7 @@ ; RV64ZVE32F-NEXT: add a0, a0, a1 ; RV64ZVE32F-NEXT: lw a0, 0(a0) ; RV64ZVE32F-NEXT: vmv.s.x v8, a0 -; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v10, v8, 7 ; RV64ZVE32F-NEXT: vmv2r.v v8, v10 ; RV64ZVE32F-NEXT: ret @@ -7249,7 +7223,6 @@ ; RV64ZVE32F-NEXT: flh ft0, 0(a1) ; RV64ZVE32F-NEXT: vsetivli zero, 2, e16, mf2, ta, ma ; RV64ZVE32F-NEXT: vfmv.s.f v9, ft0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e16, mf2, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 1 ; RV64ZVE32F-NEXT: ret %v = call <2 x half> @llvm.masked.gather.v2f16.v2p0(<2 x ptr> %ptrs, i32 2, <2 x i1> %m, <2 x half> %passthru) @@ -7320,7 +7293,6 @@ ; RV64ZVE32F-NEXT: flh ft0, 0(a0) ; RV64ZVE32F-NEXT: vsetivli zero, 4, e16, mf2, ta, ma ; RV64ZVE32F-NEXT: vfmv.s.f v9, ft0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e16, mf2, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 3 ; RV64ZVE32F-NEXT: ret %v = call <4 x half> @llvm.masked.gather.v4f16.v4p0(<4 x ptr> %ptrs, i32 2, <4 x i1> %m, <4 x half> %passthru) @@ -7389,7 +7361,6 @@ ; RV64ZVE32F-NEXT: flh ft0, 0(a0) ; RV64ZVE32F-NEXT: vsetivli zero, 4, e16, mf2, ta, ma ; RV64ZVE32F-NEXT: vfmv.s.f v9, ft0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e16, mf2, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 3 ; RV64ZVE32F-NEXT: ret %mhead = insertelement <4 x i1> poison, i1 1, i32 0 @@ -7528,7 +7499,6 @@ ; RV64ZVE32F-NEXT: flh ft0, 0(a0) ; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, ta, ma ; RV64ZVE32F-NEXT: vfmv.s.f v9, ft0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e16, m1, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 7 ; RV64ZVE32F-NEXT: ret %v = call <8 x half> @llvm.masked.gather.v8f16.v8p0(<8 x ptr> %ptrs, i32 2, <8 x i1> %m, <8 x half> %passthru) @@ -7676,7 +7646,6 @@ ; RV64ZVE32F-NEXT: flh ft0, 0(a0) ; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, ta, ma ; RV64ZVE32F-NEXT: vfmv.s.f v8, ft0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e16, m1, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v9, v8, 7 ; RV64ZVE32F-NEXT: vmv1r.v v8, v9 ; RV64ZVE32F-NEXT: ret @@ -7826,7 +7795,6 @@ ; RV64ZVE32F-NEXT: flh ft0, 0(a0) ; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, ta, ma ; RV64ZVE32F-NEXT: vfmv.s.f v8, ft0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e16, m1, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v9, v8, 7 ; RV64ZVE32F-NEXT: vmv1r.v v8, v9 ; RV64ZVE32F-NEXT: ret @@ -7985,7 +7953,6 @@ ; RV64ZVE32F-NEXT: flh ft0, 0(a0) ; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, ta, ma ; RV64ZVE32F-NEXT: vfmv.s.f v8, ft0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e16, m1, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v9, v8, 7 ; RV64ZVE32F-NEXT: vmv1r.v v8, v9 ; RV64ZVE32F-NEXT: ret @@ -8131,7 +8098,7 @@ ; RV64ZVE32F-NEXT: add a0, a0, a1 ; RV64ZVE32F-NEXT: flh ft0, 0(a0) ; RV64ZVE32F-NEXT: vfmv.s.f v8, ft0 -; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v9, v8, 7 ; RV64ZVE32F-NEXT: vmv1r.v v8, v9 ; RV64ZVE32F-NEXT: ret @@ -8226,7 +8193,6 @@ ; RV64ZVE32F-NEXT: flw ft0, 0(a1) ; RV64ZVE32F-NEXT: vsetivli zero, 2, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vfmv.s.f v9, ft0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e32, m1, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 1 ; RV64ZVE32F-NEXT: ret %v = call <2 x float> @llvm.masked.gather.v2f32.v2p0(<2 x ptr> %ptrs, i32 4, <2 x i1> %m, <2 x float> %passthru) @@ -8297,7 +8263,6 @@ ; RV64ZVE32F-NEXT: flw ft0, 0(a0) ; RV64ZVE32F-NEXT: vsetivli zero, 4, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vfmv.s.f v9, ft0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e32, m1, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 3 ; RV64ZVE32F-NEXT: ret %v = call <4 x float> @llvm.masked.gather.v4f32.v4p0(<4 x ptr> %ptrs, i32 4, <4 x i1> %m, <4 x float> %passthru) @@ -8365,7 +8330,6 @@ ; RV64ZVE32F-NEXT: flw ft0, 0(a0) ; RV64ZVE32F-NEXT: vsetivli zero, 4, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vfmv.s.f v9, ft0 -; RV64ZVE32F-NEXT: vsetvli zero, zero, e32, m1, tu, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 3 ; RV64ZVE32F-NEXT: ret %mhead = insertelement <4 x i1> poison, i1 1, i32 0 @@ -8504,7 +8468,7 @@ ; RV64ZVE32F-NEXT: flw ft0, 0(a0) ; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vfmv.s.f v10, ft0 -; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v10, 7 ; RV64ZVE32F-NEXT: ret %v = call <8 x float> @llvm.masked.gather.v8f32.v8p0(<8 x ptr> %ptrs, i32 4, <8 x i1> %m, <8 x float> %passthru) @@ -8651,7 +8615,7 @@ ; RV64ZVE32F-NEXT: flw ft0, 0(a0) ; RV64ZVE32F-NEXT: vsetvli zero, zero, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vfmv.s.f v8, ft0 -; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v10, v8, 7 ; RV64ZVE32F-NEXT: vmv2r.v v8, v10 ; RV64ZVE32F-NEXT: ret @@ -8800,7 +8764,7 @@ ; RV64ZVE32F-NEXT: flw ft0, 0(a0) ; RV64ZVE32F-NEXT: vsetvli zero, zero, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vfmv.s.f v8, ft0 -; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v10, v8, 7 ; RV64ZVE32F-NEXT: vmv2r.v v8, v10 ; RV64ZVE32F-NEXT: ret @@ -8958,7 +8922,7 @@ ; RV64ZVE32F-NEXT: flw ft0, 0(a0) ; RV64ZVE32F-NEXT: vsetvli zero, zero, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vfmv.s.f v8, ft0 -; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v10, v8, 7 ; RV64ZVE32F-NEXT: vmv2r.v v8, v10 ; RV64ZVE32F-NEXT: ret @@ -9109,7 +9073,7 @@ ; RV64ZVE32F-NEXT: flw ft0, 0(a0) ; RV64ZVE32F-NEXT: vsetvli zero, zero, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vfmv.s.f v8, ft0 -; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v10, v8, 7 ; RV64ZVE32F-NEXT: vmv2r.v v8, v10 ; RV64ZVE32F-NEXT: ret @@ -9259,7 +9223,7 @@ ; RV64ZVE32F-NEXT: flw ft0, 0(a0) ; RV64ZVE32F-NEXT: vsetvli zero, zero, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vfmv.s.f v8, ft0 -; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v10, v8, 7 ; RV64ZVE32F-NEXT: vmv2r.v v8, v10 ; RV64ZVE32F-NEXT: ret @@ -9420,7 +9384,7 @@ ; RV64ZVE32F-NEXT: flw ft0, 0(a0) ; RV64ZVE32F-NEXT: vsetvli zero, zero, e32, m1, ta, ma ; RV64ZVE32F-NEXT: vfmv.s.f v8, ft0 -; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v10, v8, 7 ; RV64ZVE32F-NEXT: vmv2r.v v8, v10 ; RV64ZVE32F-NEXT: ret @@ -9565,7 +9529,7 @@ ; RV64ZVE32F-NEXT: add a0, a0, a1 ; RV64ZVE32F-NEXT: flw ft0, 0(a0) ; RV64ZVE32F-NEXT: vfmv.s.f v8, ft0 -; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v10, v8, 7 ; RV64ZVE32F-NEXT: vmv2r.v v8, v10 ; RV64ZVE32F-NEXT: ret @@ -12521,7 +12485,7 @@ ; RV64ZVE32F-NEXT: add a0, a0, a1 ; RV64ZVE32F-NEXT: lb a0, 0(a0) ; RV64ZVE32F-NEXT: vmv.s.x v8, a0 -; RV64ZVE32F-NEXT: vsetivli zero, 16, e8, m1, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 16, e8, m1, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v9, v8, 15 ; RV64ZVE32F-NEXT: .LBB97_25: # %else44 ; RV64ZVE32F-NEXT: vmv1r.v v8, v9 @@ -12944,7 +12908,7 @@ ; RV64ZVE32F-NEXT: li a1, 32 ; RV64ZVE32F-NEXT: vsetvli zero, a1, e8, m1, ta, ma ; RV64ZVE32F-NEXT: vmv.s.x v8, a0 -; RV64ZVE32F-NEXT: vsetvli zero, a1, e8, m2, tu, ma +; RV64ZVE32F-NEXT: vsetvli zero, a1, e8, m2, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v10, v8, 31 ; RV64ZVE32F-NEXT: .LBB98_49: # %else92 ; RV64ZVE32F-NEXT: vmv2r.v v8, v10 diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-scatter.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-scatter.ll --- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-scatter.ll +++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-scatter.ll @@ -234,7 +234,7 @@ ; RV32ZVE32F-NEXT: vle8.v v9, (a0) ; RV32ZVE32F-NEXT: addi a0, sp, 14 ; RV32ZVE32F-NEXT: vle8.v v10, (a0) -; RV32ZVE32F-NEXT: vsetivli zero, 2, e8, mf4, tu, ma +; RV32ZVE32F-NEXT: vsetivli zero, 2, e8, mf4, ta, ma ; RV32ZVE32F-NEXT: vslideup.vi v10, v9, 1 ; RV32ZVE32F-NEXT: vsoxei32.v v10, (zero), v8, v0.t ; RV32ZVE32F-NEXT: addi sp, sp, 16 @@ -251,7 +251,7 @@ ; RV64ZVE32F-NEXT: vle8.v v9, (a0) ; RV64ZVE32F-NEXT: addi a0, sp, 14 ; RV64ZVE32F-NEXT: vle8.v v8, (a0) -; RV64ZVE32F-NEXT: vsetivli zero, 2, e8, mf4, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 2, e8, mf4, ta, ma ; RV64ZVE32F-NEXT: vmv.x.s a0, v0 ; RV64ZVE32F-NEXT: andi a1, a0, 1 ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 1 @@ -799,7 +799,7 @@ ; RV32ZVE32F-NEXT: vle16.v v9, (a0) ; RV32ZVE32F-NEXT: addi a0, sp, 12 ; RV32ZVE32F-NEXT: vle16.v v10, (a0) -; RV32ZVE32F-NEXT: vsetivli zero, 2, e16, mf2, tu, ma +; RV32ZVE32F-NEXT: vsetivli zero, 2, e16, mf2, ta, ma ; RV32ZVE32F-NEXT: vslideup.vi v10, v9, 1 ; RV32ZVE32F-NEXT: vsoxei32.v v10, (zero), v8, v0.t ; RV32ZVE32F-NEXT: addi sp, sp, 16 @@ -816,7 +816,7 @@ ; RV64ZVE32F-NEXT: vle16.v v9, (a0) ; RV64ZVE32F-NEXT: addi a0, sp, 12 ; RV64ZVE32F-NEXT: vle16.v v8, (a0) -; RV64ZVE32F-NEXT: vsetivli zero, 2, e16, mf2, tu, ma +; RV64ZVE32F-NEXT: vsetivli zero, 2, e16, mf2, ta, ma ; RV64ZVE32F-NEXT: vslideup.vi v8, v9, 1 ; RV64ZVE32F-NEXT: vsetvli zero, zero, e8, mf4, ta, ma ; RV64ZVE32F-NEXT: vmv.x.s a0, v0 diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-unaligned.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-unaligned.ll --- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-unaligned.ll +++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-unaligned.ll @@ -79,7 +79,7 @@ ; RV32-NEXT: slli a1, a1, 8 ; RV32-NEXT: or a0, a1, a0 ; RV32-NEXT: vmv.s.x v8, a0 -; RV32-NEXT: vsetivli zero, 2, e16, mf4, tu, ma +; RV32-NEXT: vsetivli zero, 2, e16, mf4, ta, ma ; RV32-NEXT: vslideup.vi v9, v8, 1 ; RV32-NEXT: vmv1r.v v8, v9 ; RV32-NEXT: ret @@ -116,7 +116,7 @@ ; RV64-NEXT: slli a1, a1, 8 ; RV64-NEXT: or a0, a1, a0 ; RV64-NEXT: vmv.s.x v8, a0 -; RV64-NEXT: vsetivli zero, 2, e16, mf4, tu, ma +; RV64-NEXT: vsetivli zero, 2, e16, mf4, ta, ma ; RV64-NEXT: vslideup.vi v9, v8, 1 ; RV64-NEXT: vmv1r.v v8, v9 ; RV64-NEXT: ret @@ -158,7 +158,7 @@ ; RV32-NEXT: vsetivli zero, 2, e32, m1, ta, ma ; RV32-NEXT: vslide1down.vx v8, v8, a1 ; RV32-NEXT: vslide1down.vx v8, v8, a0 -; RV32-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; RV32-NEXT: vslideup.vi v9, v8, 1 ; RV32-NEXT: vmv1r.v v8, v9 ; RV32-NEXT: ret @@ -195,7 +195,7 @@ ; RV64-NEXT: slli a1, a1, 32 ; RV64-NEXT: or a0, a1, a0 ; RV64-NEXT: vmv.s.x v8, a0 -; RV64-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; RV64-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; RV64-NEXT: vslideup.vi v9, v8, 1 ; RV64-NEXT: vmv1r.v v8, v9 ; RV64-NEXT: ret @@ -449,10 +449,8 @@ ; RV32-NEXT: or a2, a4, a2 ; RV32-NEXT: or a0, a0, a2 ; RV32-NEXT: vmv.s.x v9, a0 -; RV32-NEXT: vsetvli zero, zero, e32, mf2, tu, ma ; RV32-NEXT: vslideup.vi v8, v9, 1 ; RV32-NEXT: .LBB8_4: # %else2 -; RV32-NEXT: vsetvli zero, zero, e32, mf2, ta, ma ; RV32-NEXT: vse32.v v8, (a1) ; RV32-NEXT: ret ; @@ -497,10 +495,8 @@ ; RV64-NEXT: or a2, a4, a2 ; RV64-NEXT: or a0, a0, a2 ; RV64-NEXT: vmv.s.x v9, a0 -; RV64-NEXT: vsetvli zero, zero, e32, mf2, tu, ma ; RV64-NEXT: vslideup.vi v8, v9, 1 ; RV64-NEXT: .LBB8_4: # %else2 -; RV64-NEXT: vsetvli zero, zero, e32, mf2, ta, ma ; RV64-NEXT: vse32.v v8, (a1) ; RV64-NEXT: ret %mask = icmp eq <2 x i32> %m, zeroinitializer diff --git a/llvm/test/CodeGen/RISCV/rvv/vector-splice.ll b/llvm/test/CodeGen/RISCV/rvv/vector-splice.ll --- a/llvm/test/CodeGen/RISCV/rvv/vector-splice.ll +++ b/llvm/test/CodeGen/RISCV/rvv/vector-splice.ll @@ -20,9 +20,7 @@ ; CHECK-NEXT: vsetvli a0, zero, e8, mf8, ta, 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 @@ -44,9 +42,7 @@ ; CHECK-NEXT: vsetvli a1, zero, e8, mf8, ta, 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 @@ -70,9 +66,7 @@ ; CHECK-NEXT: vsetvli a0, zero, e8, mf4, ta, 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 @@ -94,9 +88,7 @@ ; CHECK-NEXT: vsetvli a1, zero, e8, mf4, ta, 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 @@ -120,9 +112,7 @@ ; CHECK-NEXT: vsetvli a0, zero, e8, mf2, ta, 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 @@ -144,9 +134,7 @@ ; CHECK-NEXT: vsetvli a1, zero, e8, mf2, ta, 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 @@ -169,9 +157,7 @@ ; CHECK-NEXT: vsetvli a0, zero, e8, m1, ta, 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 @@ -192,9 +178,7 @@ ; CHECK-NEXT: vsetvli a1, zero, e8, m1, ta, 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 @@ -218,9 +202,7 @@ ; CHECK-NEXT: vsetvli a0, zero, e8, m2, ta, 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 @@ -242,9 +224,7 @@ ; CHECK-NEXT: vsetvli a1, zero, e8, m2, ta, 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 @@ -268,9 +248,7 @@ ; CHECK-NEXT: vsetvli a0, zero, e8, m4, ta, 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 @@ -293,9 +271,7 @@ ; CHECK-NEXT: vsetvli a1, zero, e8, m4, ta, 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 @@ -319,9 +295,7 @@ ; CHECK-NEXT: vsetvli a0, zero, e8, m8, ta, 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 @@ -344,9 +318,7 @@ ; CHECK-NEXT: vsetvli a1, zero, e8, m8, ta, 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 @@ -372,7 +344,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e8, mf8, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e8, mf8, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e8, mf8, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv1i8( %a, %b, i32 -1) @@ -387,7 +359,7 @@ ; CHECK-NEXT: addi a0, a0, -2 ; CHECK-NEXT: vsetivli zero, 2, e8, mf8, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e8, mf8, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e8, mf8, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 2 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv1i8( %a, %b, i32 -2) @@ -402,7 +374,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetvli zero, a0, e8, mf8, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 1 -; CHECK-NEXT: vsetvli a1, zero, e8, mf8, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e8, mf8, ta, ma ; CHECK-NEXT: vslideup.vx v8, v9, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv1i8( %a, %b, i32 1) @@ -427,7 +399,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e8, mf4, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e8, mf4, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e8, mf4, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv2i8( %a, %b, i32 -1) @@ -442,7 +414,7 @@ ; CHECK-NEXT: addi a0, a0, -4 ; CHECK-NEXT: vsetivli zero, 4, e8, mf4, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e8, mf4, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e8, mf4, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 4 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv2i8( %a, %b, i32 -4) @@ -457,7 +429,7 @@ ; CHECK-NEXT: addi a0, a0, -3 ; CHECK-NEXT: vsetvli zero, a0, e8, mf4, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 3 -; CHECK-NEXT: vsetvli a1, zero, e8, mf4, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e8, mf4, ta, ma ; CHECK-NEXT: vslideup.vx v8, v9, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv2i8( %a, %b, i32 3) @@ -482,7 +454,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e8, mf2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e8, mf2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e8, mf2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv4i8( %a, %b, i32 -1) @@ -497,7 +469,7 @@ ; CHECK-NEXT: addi a0, a0, -8 ; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e8, mf2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e8, mf2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 8 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv4i8( %a, %b, i32 -8) @@ -512,7 +484,7 @@ ; CHECK-NEXT: addi a0, a0, -7 ; CHECK-NEXT: vsetvli zero, a0, e8, mf2, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 7 -; CHECK-NEXT: vsetvli a1, zero, e8, mf2, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e8, mf2, ta, ma ; CHECK-NEXT: vslideup.vx v8, v9, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv4i8( %a, %b, i32 7) @@ -536,7 +508,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e8, m1, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e8, m1, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv8i8( %a, %b, i32 -1) @@ -550,7 +522,7 @@ ; CHECK-NEXT: addi a0, a0, -16 ; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e8, m1, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e8, m1, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 16 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv8i8( %a, %b, i32 -16) @@ -564,7 +536,7 @@ ; CHECK-NEXT: addi a0, a0, -15 ; CHECK-NEXT: vsetvli zero, a0, e8, m1, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 15 -; CHECK-NEXT: vsetvli a1, zero, e8, m1, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e8, m1, ta, ma ; CHECK-NEXT: vslideup.vx v8, v9, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv8i8( %a, %b, i32 15) @@ -589,7 +561,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e8, m2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e8, m2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v10, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv16i8( %a, %b, i32 -1) @@ -605,7 +577,7 @@ ; CHECK-NEXT: li a1, 32 ; CHECK-NEXT: vsetvli zero, a1, e8, m2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e8, m2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e8, m2, ta, ma ; CHECK-NEXT: vslideup.vx v8, v10, a1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv16i8( %a, %b, i32 -32) @@ -620,7 +592,7 @@ ; CHECK-NEXT: addi a0, a0, -31 ; CHECK-NEXT: vsetvli zero, a0, e8, m2, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 31 -; CHECK-NEXT: vsetvli a1, zero, e8, m2, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e8, m2, ta, ma ; CHECK-NEXT: vslideup.vx v8, v10, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv16i8( %a, %b, i32 31) @@ -645,7 +617,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e8, m4, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e8, m4, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e8, m4, ta, ma ; CHECK-NEXT: vslideup.vi v8, v12, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv32i8( %a, %b, i32 -1) @@ -661,7 +633,7 @@ ; CHECK-NEXT: li a1, 64 ; CHECK-NEXT: vsetvli zero, a1, e8, m4, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e8, m4, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e8, m4, ta, ma ; CHECK-NEXT: vslideup.vx v8, v12, a1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv32i8( %a, %b, i32 -64) @@ -677,7 +649,7 @@ ; CHECK-NEXT: li a1, 63 ; CHECK-NEXT: vsetvli zero, a0, e8, m4, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a1 -; CHECK-NEXT: vsetvli a1, zero, e8, m4, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e8, m4, ta, ma ; CHECK-NEXT: vslideup.vx v8, v12, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv32i8( %a, %b, i32 63) @@ -702,7 +674,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e8, m8, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e8, m8, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e8, m8, ta, ma ; CHECK-NEXT: vslideup.vi v8, v16, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv64i8( %a, %b, i32 -1) @@ -718,7 +690,7 @@ ; CHECK-NEXT: li a1, 128 ; CHECK-NEXT: vsetvli zero, a1, e8, m8, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e8, m8, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e8, m8, ta, ma ; CHECK-NEXT: vslideup.vx v8, v16, a1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv64i8( %a, %b, i32 -128) @@ -734,7 +706,7 @@ ; CHECK-NEXT: li a1, 127 ; CHECK-NEXT: vsetvli zero, a0, e8, m8, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a1 -; CHECK-NEXT: vsetvli a1, zero, e8, m8, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e8, m8, ta, ma ; CHECK-NEXT: vslideup.vx v8, v16, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv64i8( %a, %b, i32 127) @@ -759,7 +731,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e16, mf4, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, mf4, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, mf4, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv1i16( %a, %b, i32 -1) @@ -774,7 +746,7 @@ ; CHECK-NEXT: addi a0, a0, -2 ; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, mf4, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, mf4, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 2 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv1i16( %a, %b, i32 -2) @@ -789,7 +761,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetvli zero, a0, e16, mf4, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 1 -; CHECK-NEXT: vsetvli a1, zero, e16, mf4, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e16, mf4, ta, ma ; CHECK-NEXT: vslideup.vx v8, v9, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv1i16( %a, %b, i32 1) @@ -814,7 +786,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e16, mf2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, mf2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, mf2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv2i16( %a, %b, i32 -1) @@ -829,7 +801,7 @@ ; CHECK-NEXT: addi a0, a0, -4 ; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, mf2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, mf2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 4 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv2i16( %a, %b, i32 -4) @@ -844,7 +816,7 @@ ; CHECK-NEXT: addi a0, a0, -3 ; CHECK-NEXT: vsetvli zero, a0, e16, mf2, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 3 -; CHECK-NEXT: vsetvli a1, zero, e16, mf2, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e16, mf2, ta, ma ; CHECK-NEXT: vslideup.vx v8, v9, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv2i16( %a, %b, i32 3) @@ -869,7 +841,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, m1, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, m1, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv4i16( %a, %b, i32 -1) @@ -884,7 +856,7 @@ ; CHECK-NEXT: addi a0, a0, -8 ; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, m1, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, m1, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 8 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv4i16( %a, %b, i32 -8) @@ -899,7 +871,7 @@ ; CHECK-NEXT: addi a0, a0, -7 ; CHECK-NEXT: vsetvli zero, a0, e16, m1, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 7 -; CHECK-NEXT: vsetvli a1, zero, e16, m1, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e16, m1, ta, ma ; CHECK-NEXT: vslideup.vx v8, v9, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv4i16( %a, %b, i32 7) @@ -923,7 +895,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e16, m2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, m2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, m2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v10, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv8i16( %a, %b, i32 -1) @@ -937,7 +909,7 @@ ; CHECK-NEXT: addi a0, a0, -16 ; CHECK-NEXT: vsetivli zero, 16, e16, m2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, m2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, m2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v10, 16 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv8i16( %a, %b, i32 -16) @@ -951,7 +923,7 @@ ; CHECK-NEXT: addi a0, a0, -15 ; CHECK-NEXT: vsetvli zero, a0, e16, m2, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 15 -; CHECK-NEXT: vsetvli a1, zero, e16, m2, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e16, m2, ta, ma ; CHECK-NEXT: vslideup.vx v8, v10, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv8i16( %a, %b, i32 15) @@ -976,7 +948,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e16, m4, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, m4, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, m4, ta, ma ; CHECK-NEXT: vslideup.vi v8, v12, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv16i16( %a, %b, i32 -1) @@ -992,7 +964,7 @@ ; CHECK-NEXT: li a1, 32 ; CHECK-NEXT: vsetvli zero, a1, e16, m4, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, m4, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, m4, ta, ma ; CHECK-NEXT: vslideup.vx v8, v12, a1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv16i16( %a, %b, i32 -32) @@ -1007,7 +979,7 @@ ; CHECK-NEXT: addi a0, a0, -31 ; CHECK-NEXT: vsetvli zero, a0, e16, m4, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 31 -; CHECK-NEXT: vsetvli a1, zero, e16, m4, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e16, m4, ta, ma ; CHECK-NEXT: vslideup.vx v8, v12, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv16i16( %a, %b, i32 31) @@ -1032,7 +1004,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e16, m8, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, m8, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, m8, ta, ma ; CHECK-NEXT: vslideup.vi v8, v16, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv32i16( %a, %b, i32 -1) @@ -1048,7 +1020,7 @@ ; CHECK-NEXT: li a1, 64 ; CHECK-NEXT: vsetvli zero, a1, e16, m8, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, m8, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, m8, ta, ma ; CHECK-NEXT: vslideup.vx v8, v16, a1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv32i16( %a, %b, i32 -64) @@ -1064,7 +1036,7 @@ ; CHECK-NEXT: li a1, 63 ; CHECK-NEXT: vsetvli zero, a0, e16, m8, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a1 -; CHECK-NEXT: vsetvli a1, zero, e16, m8, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e16, m8, ta, ma ; CHECK-NEXT: vslideup.vx v8, v16, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv32i16( %a, %b, i32 63) @@ -1089,7 +1061,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e32, mf2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e32, mf2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e32, mf2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv1i32( %a, %b, i32 -1) @@ -1104,7 +1076,7 @@ ; CHECK-NEXT: addi a0, a0, -2 ; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e32, mf2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e32, mf2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 2 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv1i32( %a, %b, i32 -2) @@ -1119,7 +1091,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetvli zero, a0, e32, mf2, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 1 -; CHECK-NEXT: vsetvli a1, zero, e32, mf2, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e32, mf2, ta, ma ; CHECK-NEXT: vslideup.vx v8, v9, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv1i32( %a, %b, i32 1) @@ -1144,7 +1116,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e32, m1, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e32, m1, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv2i32( %a, %b, i32 -1) @@ -1159,7 +1131,7 @@ ; CHECK-NEXT: addi a0, a0, -4 ; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e32, m1, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e32, m1, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 4 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv2i32( %a, %b, i32 -4) @@ -1174,7 +1146,7 @@ ; CHECK-NEXT: addi a0, a0, -3 ; CHECK-NEXT: vsetvli zero, a0, e32, m1, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 3 -; CHECK-NEXT: vsetvli a1, zero, e32, m1, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e32, m1, ta, ma ; CHECK-NEXT: vslideup.vx v8, v9, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv2i32( %a, %b, i32 3) @@ -1199,7 +1171,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e32, m2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e32, m2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e32, m2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v10, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv4i32( %a, %b, i32 -1) @@ -1214,7 +1186,7 @@ ; CHECK-NEXT: addi a0, a0, -8 ; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e32, m2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e32, m2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v10, 8 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv4i32( %a, %b, i32 -8) @@ -1229,7 +1201,7 @@ ; CHECK-NEXT: addi a0, a0, -7 ; CHECK-NEXT: vsetvli zero, a0, e32, m2, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 7 -; CHECK-NEXT: vsetvli a1, zero, e32, m2, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e32, m2, ta, ma ; CHECK-NEXT: vslideup.vx v8, v10, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv4i32( %a, %b, i32 7) @@ -1253,7 +1225,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e32, m4, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e32, m4, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e32, m4, ta, ma ; CHECK-NEXT: vslideup.vi v8, v12, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv8i32( %a, %b, i32 -1) @@ -1267,7 +1239,7 @@ ; CHECK-NEXT: addi a0, a0, -16 ; CHECK-NEXT: vsetivli zero, 16, e32, m4, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e32, m4, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e32, m4, ta, ma ; CHECK-NEXT: vslideup.vi v8, v12, 16 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv8i32( %a, %b, i32 -16) @@ -1281,7 +1253,7 @@ ; CHECK-NEXT: addi a0, a0, -15 ; CHECK-NEXT: vsetvli zero, a0, e32, m4, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 15 -; CHECK-NEXT: vsetvli a1, zero, e32, m4, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e32, m4, ta, ma ; CHECK-NEXT: vslideup.vx v8, v12, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv8i32( %a, %b, i32 15) @@ -1306,7 +1278,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e32, m8, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e32, m8, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e32, m8, ta, ma ; CHECK-NEXT: vslideup.vi v8, v16, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv16i32( %a, %b, i32 -1) @@ -1322,7 +1294,7 @@ ; CHECK-NEXT: li a1, 32 ; CHECK-NEXT: vsetvli zero, a1, e32, m8, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e32, m8, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e32, m8, ta, ma ; CHECK-NEXT: vslideup.vx v8, v16, a1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv16i32( %a, %b, i32 -32) @@ -1337,7 +1309,7 @@ ; CHECK-NEXT: addi a0, a0, -31 ; CHECK-NEXT: vsetvli zero, a0, e32, m8, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 31 -; CHECK-NEXT: vsetvli a1, zero, e32, m8, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e32, m8, ta, ma ; CHECK-NEXT: vslideup.vx v8, v16, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv16i32( %a, %b, i32 31) @@ -1362,7 +1334,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e64, m1, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e64, m1, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv1i64( %a, %b, i32 -1) @@ -1377,7 +1349,7 @@ ; CHECK-NEXT: addi a0, a0, -2 ; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e64, m1, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e64, m1, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 2 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv1i64( %a, %b, i32 -2) @@ -1392,7 +1364,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetvli zero, a0, e64, m1, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 1 -; CHECK-NEXT: vsetvli a1, zero, e64, m1, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e64, m1, ta, ma ; CHECK-NEXT: vslideup.vx v8, v9, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv1i64( %a, %b, i32 1) @@ -1417,7 +1389,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e64, m2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e64, m2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e64, m2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v10, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv2i64( %a, %b, i32 -1) @@ -1432,7 +1404,7 @@ ; CHECK-NEXT: addi a0, a0, -4 ; CHECK-NEXT: vsetivli zero, 4, e64, m2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e64, m2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e64, m2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v10, 4 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv2i64( %a, %b, i32 -4) @@ -1447,7 +1419,7 @@ ; CHECK-NEXT: addi a0, a0, -3 ; CHECK-NEXT: vsetvli zero, a0, e64, m2, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 3 -; CHECK-NEXT: vsetvli a1, zero, e64, m2, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e64, m2, ta, ma ; CHECK-NEXT: vslideup.vx v8, v10, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv2i64( %a, %b, i32 3) @@ -1472,7 +1444,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e64, m4, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e64, m4, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e64, m4, ta, ma ; CHECK-NEXT: vslideup.vi v8, v12, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv4i64( %a, %b, i32 -1) @@ -1487,7 +1459,7 @@ ; CHECK-NEXT: addi a0, a0, -8 ; CHECK-NEXT: vsetivli zero, 8, e64, m4, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e64, m4, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e64, m4, ta, ma ; CHECK-NEXT: vslideup.vi v8, v12, 8 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv4i64( %a, %b, i32 -8) @@ -1502,7 +1474,7 @@ ; CHECK-NEXT: addi a0, a0, -7 ; CHECK-NEXT: vsetvli zero, a0, e64, m4, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 7 -; CHECK-NEXT: vsetvli a1, zero, e64, m4, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e64, m4, ta, ma ; CHECK-NEXT: vslideup.vx v8, v12, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv4i64( %a, %b, i32 7) @@ -1526,7 +1498,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e64, m8, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e64, m8, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e64, m8, ta, ma ; CHECK-NEXT: vslideup.vi v8, v16, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv8i64( %a, %b, i32 -1) @@ -1540,7 +1512,7 @@ ; CHECK-NEXT: addi a0, a0, -16 ; CHECK-NEXT: vsetivli zero, 16, e64, m8, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e64, m8, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e64, m8, ta, ma ; CHECK-NEXT: vslideup.vi v8, v16, 16 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv8i64( %a, %b, i32 -16) @@ -1554,7 +1526,7 @@ ; CHECK-NEXT: addi a0, a0, -15 ; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 15 -; CHECK-NEXT: vsetvli a1, zero, e64, m8, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e64, m8, ta, ma ; CHECK-NEXT: vslideup.vx v8, v16, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv8i64( %a, %b, i32 15) @@ -1579,7 +1551,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e16, mf4, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, mf4, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, mf4, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv1f16( %a, %b, i32 -1) @@ -1594,7 +1566,7 @@ ; CHECK-NEXT: addi a0, a0, -2 ; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, mf4, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, mf4, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 2 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv1f16( %a, %b, i32 -2) @@ -1609,7 +1581,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetvli zero, a0, e16, mf4, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 1 -; CHECK-NEXT: vsetvli a1, zero, e16, mf4, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e16, mf4, ta, ma ; CHECK-NEXT: vslideup.vx v8, v9, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv1f16( %a, %b, i32 1) @@ -1634,7 +1606,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e16, mf2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, mf2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, mf2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv2f16( %a, %b, i32 -1) @@ -1649,7 +1621,7 @@ ; CHECK-NEXT: addi a0, a0, -4 ; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, mf2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, mf2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 4 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv2f16( %a, %b, i32 -4) @@ -1664,7 +1636,7 @@ ; CHECK-NEXT: addi a0, a0, -3 ; CHECK-NEXT: vsetvli zero, a0, e16, mf2, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 3 -; CHECK-NEXT: vsetvli a1, zero, e16, mf2, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e16, mf2, ta, ma ; CHECK-NEXT: vslideup.vx v8, v9, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv2f16( %a, %b, i32 3) @@ -1689,7 +1661,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, m1, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, m1, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv4f16( %a, %b, i32 -1) @@ -1704,7 +1676,7 @@ ; CHECK-NEXT: addi a0, a0, -8 ; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, m1, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, m1, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 8 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv4f16( %a, %b, i32 -8) @@ -1719,7 +1691,7 @@ ; CHECK-NEXT: addi a0, a0, -7 ; CHECK-NEXT: vsetvli zero, a0, e16, m1, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 7 -; CHECK-NEXT: vsetvli a1, zero, e16, m1, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e16, m1, ta, ma ; CHECK-NEXT: vslideup.vx v8, v9, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv4f16( %a, %b, i32 7) @@ -1743,7 +1715,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e16, m2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, m2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, m2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v10, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv8f16( %a, %b, i32 -1) @@ -1757,7 +1729,7 @@ ; CHECK-NEXT: addi a0, a0, -16 ; CHECK-NEXT: vsetivli zero, 16, e16, m2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, m2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, m2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v10, 16 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv8f16( %a, %b, i32 -16) @@ -1771,7 +1743,7 @@ ; CHECK-NEXT: addi a0, a0, -15 ; CHECK-NEXT: vsetvli zero, a0, e16, m2, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 15 -; CHECK-NEXT: vsetvli a1, zero, e16, m2, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e16, m2, ta, ma ; CHECK-NEXT: vslideup.vx v8, v10, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv8f16( %a, %b, i32 15) @@ -1796,7 +1768,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e16, m4, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, m4, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, m4, ta, ma ; CHECK-NEXT: vslideup.vi v8, v12, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv16f16( %a, %b, i32 -1) @@ -1812,7 +1784,7 @@ ; CHECK-NEXT: li a1, 32 ; CHECK-NEXT: vsetvli zero, a1, e16, m4, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, m4, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, m4, ta, ma ; CHECK-NEXT: vslideup.vx v8, v12, a1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv16f16( %a, %b, i32 -32) @@ -1827,7 +1799,7 @@ ; CHECK-NEXT: addi a0, a0, -31 ; CHECK-NEXT: vsetvli zero, a0, e16, m4, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 31 -; CHECK-NEXT: vsetvli a1, zero, e16, m4, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e16, m4, ta, ma ; CHECK-NEXT: vslideup.vx v8, v12, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv16f16( %a, %b, i32 31) @@ -1852,7 +1824,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e16, m8, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, m8, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, m8, ta, ma ; CHECK-NEXT: vslideup.vi v8, v16, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv32f16( %a, %b, i32 -1) @@ -1868,7 +1840,7 @@ ; CHECK-NEXT: li a1, 64 ; CHECK-NEXT: vsetvli zero, a1, e16, m8, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e16, m8, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e16, m8, ta, ma ; CHECK-NEXT: vslideup.vx v8, v16, a1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv32f16( %a, %b, i32 -64) @@ -1884,7 +1856,7 @@ ; CHECK-NEXT: li a1, 63 ; CHECK-NEXT: vsetvli zero, a0, e16, m8, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a1 -; CHECK-NEXT: vsetvli a1, zero, e16, m8, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e16, m8, ta, ma ; CHECK-NEXT: vslideup.vx v8, v16, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv32f16( %a, %b, i32 63) @@ -1909,7 +1881,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e32, mf2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e32, mf2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e32, mf2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv1f32( %a, %b, i32 -1) @@ -1924,7 +1896,7 @@ ; CHECK-NEXT: addi a0, a0, -2 ; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e32, mf2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e32, mf2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 2 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv1f32( %a, %b, i32 -2) @@ -1939,7 +1911,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetvli zero, a0, e32, mf2, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 1 -; CHECK-NEXT: vsetvli a1, zero, e32, mf2, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e32, mf2, ta, ma ; CHECK-NEXT: vslideup.vx v8, v9, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv1f32( %a, %b, i32 1) @@ -1964,7 +1936,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e32, m1, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e32, m1, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv2f32( %a, %b, i32 -1) @@ -1979,7 +1951,7 @@ ; CHECK-NEXT: addi a0, a0, -4 ; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e32, m1, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e32, m1, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 4 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv2f32( %a, %b, i32 -4) @@ -1994,7 +1966,7 @@ ; CHECK-NEXT: addi a0, a0, -3 ; CHECK-NEXT: vsetvli zero, a0, e32, m1, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 3 -; CHECK-NEXT: vsetvli a1, zero, e32, m1, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e32, m1, ta, ma ; CHECK-NEXT: vslideup.vx v8, v9, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv2f32( %a, %b, i32 3) @@ -2019,7 +1991,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e32, m2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e32, m2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e32, m2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v10, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv4f32( %a, %b, i32 -1) @@ -2034,7 +2006,7 @@ ; CHECK-NEXT: addi a0, a0, -8 ; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e32, m2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e32, m2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v10, 8 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv4f32( %a, %b, i32 -8) @@ -2049,7 +2021,7 @@ ; CHECK-NEXT: addi a0, a0, -7 ; CHECK-NEXT: vsetvli zero, a0, e32, m2, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 7 -; CHECK-NEXT: vsetvli a1, zero, e32, m2, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e32, m2, ta, ma ; CHECK-NEXT: vslideup.vx v8, v10, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv4f32( %a, %b, i32 7) @@ -2073,7 +2045,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e32, m4, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e32, m4, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e32, m4, ta, ma ; CHECK-NEXT: vslideup.vi v8, v12, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv8f32( %a, %b, i32 -1) @@ -2087,7 +2059,7 @@ ; CHECK-NEXT: addi a0, a0, -16 ; CHECK-NEXT: vsetivli zero, 16, e32, m4, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e32, m4, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e32, m4, ta, ma ; CHECK-NEXT: vslideup.vi v8, v12, 16 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv8f32( %a, %b, i32 -16) @@ -2101,7 +2073,7 @@ ; CHECK-NEXT: addi a0, a0, -15 ; CHECK-NEXT: vsetvli zero, a0, e32, m4, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 15 -; CHECK-NEXT: vsetvli a1, zero, e32, m4, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e32, m4, ta, ma ; CHECK-NEXT: vslideup.vx v8, v12, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv8f32( %a, %b, i32 15) @@ -2126,7 +2098,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e32, m8, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e32, m8, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e32, m8, ta, ma ; CHECK-NEXT: vslideup.vi v8, v16, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv16f32( %a, %b, i32 -1) @@ -2142,7 +2114,7 @@ ; CHECK-NEXT: li a1, 32 ; CHECK-NEXT: vsetvli zero, a1, e32, m8, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e32, m8, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e32, m8, ta, ma ; CHECK-NEXT: vslideup.vx v8, v16, a1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv16f32( %a, %b, i32 -32) @@ -2157,7 +2129,7 @@ ; CHECK-NEXT: addi a0, a0, -31 ; CHECK-NEXT: vsetvli zero, a0, e32, m8, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 31 -; CHECK-NEXT: vsetvli a1, zero, e32, m8, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e32, m8, ta, ma ; CHECK-NEXT: vslideup.vx v8, v16, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv16f32( %a, %b, i32 31) @@ -2182,7 +2154,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e64, m1, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e64, m1, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv1f64( %a, %b, i32 -1) @@ -2197,7 +2169,7 @@ ; CHECK-NEXT: addi a0, a0, -2 ; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e64, m1, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e64, m1, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 2 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv1f64( %a, %b, i32 -2) @@ -2212,7 +2184,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetvli zero, a0, e64, m1, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 1 -; CHECK-NEXT: vsetvli a1, zero, e64, m1, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e64, m1, ta, ma ; CHECK-NEXT: vslideup.vx v8, v9, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv1f64( %a, %b, i32 1) @@ -2237,7 +2209,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e64, m2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e64, m2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e64, m2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v10, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv2f64( %a, %b, i32 -1) @@ -2252,7 +2224,7 @@ ; CHECK-NEXT: addi a0, a0, -4 ; CHECK-NEXT: vsetivli zero, 4, e64, m2, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e64, m2, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e64, m2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v10, 4 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv2f64( %a, %b, i32 -4) @@ -2267,7 +2239,7 @@ ; CHECK-NEXT: addi a0, a0, -3 ; CHECK-NEXT: vsetvli zero, a0, e64, m2, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 3 -; CHECK-NEXT: vsetvli a1, zero, e64, m2, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e64, m2, ta, ma ; CHECK-NEXT: vslideup.vx v8, v10, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv2f64( %a, %b, i32 3) @@ -2292,7 +2264,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e64, m4, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e64, m4, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e64, m4, ta, ma ; CHECK-NEXT: vslideup.vi v8, v12, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv4f64( %a, %b, i32 -1) @@ -2307,7 +2279,7 @@ ; CHECK-NEXT: addi a0, a0, -8 ; CHECK-NEXT: vsetivli zero, 8, e64, m4, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e64, m4, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e64, m4, ta, ma ; CHECK-NEXT: vslideup.vi v8, v12, 8 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv4f64( %a, %b, i32 -8) @@ -2322,7 +2294,7 @@ ; CHECK-NEXT: addi a0, a0, -7 ; CHECK-NEXT: vsetvli zero, a0, e64, m4, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 7 -; CHECK-NEXT: vsetvli a1, zero, e64, m4, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e64, m4, ta, ma ; CHECK-NEXT: vslideup.vx v8, v12, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv4f64( %a, %b, i32 7) @@ -2346,7 +2318,7 @@ ; CHECK-NEXT: addi a0, a0, -1 ; CHECK-NEXT: vsetivli zero, 1, e64, m8, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e64, m8, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e64, m8, ta, ma ; CHECK-NEXT: vslideup.vi v8, v16, 1 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv8f64( %a, %b, i32 -1) @@ -2360,7 +2332,7 @@ ; CHECK-NEXT: addi a0, a0, -16 ; CHECK-NEXT: vsetivli zero, 16, e64, m8, ta, ma ; CHECK-NEXT: vslidedown.vx v8, v8, a0 -; CHECK-NEXT: vsetvli a0, zero, e64, m8, tu, ma +; CHECK-NEXT: vsetvli a0, zero, e64, m8, ta, ma ; CHECK-NEXT: vslideup.vi v8, v16, 16 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv8f64( %a, %b, i32 -16) @@ -2374,7 +2346,7 @@ ; CHECK-NEXT: addi a0, a0, -15 ; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v8, 15 -; CHECK-NEXT: vsetvli a1, zero, e64, m8, tu, ma +; CHECK-NEXT: vsetvli a1, zero, e64, m8, ta, ma ; CHECK-NEXT: vslideup.vx v8, v16, a0 ; CHECK-NEXT: ret %res = call @llvm.experimental.vector.splice.nxv8f64( %a, %b, i32 15) diff --git a/llvm/test/CodeGen/RISCV/shuffle-reverse.ll b/llvm/test/CodeGen/RISCV/shuffle-reverse.ll --- a/llvm/test/CodeGen/RISCV/shuffle-reverse.ll +++ b/llvm/test/CodeGen/RISCV/shuffle-reverse.ll @@ -7,7 +7,7 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e8, mf8, ta, ma ; CHECK-NEXT: vslidedown.vi v9, v8, 1 -; CHECK-NEXT: vsetivli zero, 2, e8, mf8, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e8, mf8, ta, ma ; CHECK-NEXT: vslideup.vi v9, v8, 1 ; CHECK-NEXT: vmv1r.v v8, v9 ; CHECK-NEXT: ret @@ -20,11 +20,11 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e8, mf8, ta, ma ; CHECK-NEXT: vslidedown.vi v10, v8, 1 -; CHECK-NEXT: vsetivli zero, 2, e8, mf8, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e8, mf8, ta, ma ; CHECK-NEXT: vslideup.vi v10, v8, 1 ; CHECK-NEXT: vsetivli zero, 1, e8, mf8, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v9, 1 -; CHECK-NEXT: vsetivli zero, 2, e8, mf8, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e8, mf8, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 1 ; CHECK-NEXT: vsetivli zero, 4, e8, mf4, tu, ma ; CHECK-NEXT: vslideup.vi v8, v10, 2 @@ -159,7 +159,7 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e16, mf4, ta, ma ; CHECK-NEXT: vslidedown.vi v9, v8, 1 -; CHECK-NEXT: vsetivli zero, 2, e16, mf4, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma ; CHECK-NEXT: vslideup.vi v9, v8, 1 ; CHECK-NEXT: vmv1r.v v8, v9 ; CHECK-NEXT: ret @@ -172,11 +172,11 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e16, mf4, ta, ma ; CHECK-NEXT: vslidedown.vi v10, v8, 1 -; CHECK-NEXT: vsetivli zero, 2, e16, mf4, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma ; CHECK-NEXT: vslideup.vi v10, v8, 1 ; CHECK-NEXT: vsetivli zero, 1, e16, mf4, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v9, 1 -; CHECK-NEXT: vsetivli zero, 2, e16, mf4, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 1 ; CHECK-NEXT: vsetivli zero, 4, e16, mf2, tu, ma ; CHECK-NEXT: vslideup.vi v8, v10, 2 @@ -311,7 +311,7 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e32, mf2, ta, ma ; CHECK-NEXT: vslidedown.vi v9, v8, 1 -; CHECK-NEXT: vsetivli zero, 2, e32, mf2, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma ; CHECK-NEXT: vslideup.vi v9, v8, 1 ; CHECK-NEXT: vmv1r.v v8, v9 ; CHECK-NEXT: ret @@ -324,11 +324,11 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e32, mf2, ta, ma ; CHECK-NEXT: vslidedown.vi v10, v8, 1 -; CHECK-NEXT: vsetivli zero, 2, e32, mf2, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma ; CHECK-NEXT: vslideup.vi v10, v8, 1 ; CHECK-NEXT: vsetivli zero, 1, e32, mf2, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v9, 1 -; CHECK-NEXT: vsetivli zero, 2, e32, mf2, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 1 ; CHECK-NEXT: vsetivli zero, 4, e32, m1, tu, ma ; CHECK-NEXT: vslideup.vi v8, v10, 2 @@ -463,9 +463,9 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma ; CHECK-NEXT: vslidedown.vi v9, v8, 1 -; CHECK-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-NEXT: vslideup.vi v9, v8, 1 -; CHECK-NEXT: vmv1r.v v8, v9 +; CHECK-NEXT: vmv.v.v v8, v9 ; CHECK-NEXT: ret %v2i64 = shufflevector <2 x i64> %a, <2 x i64> undef, <2 x i32> ret <2 x i64> %v2i64 @@ -476,11 +476,11 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma ; CHECK-NEXT: vslidedown.vi v12, v8, 1 -; CHECK-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-NEXT: vslideup.vi v12, v8, 1 ; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma ; CHECK-NEXT: vslidedown.vi v10, v9, 1 -; CHECK-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-NEXT: vslideup.vi v10, v9, 1 ; CHECK-NEXT: vsetivli zero, 4, e64, m2, tu, ma ; CHECK-NEXT: vslideup.vi v10, v12, 2 @@ -555,7 +555,7 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e16, mf4, ta, ma ; CHECK-NEXT: vslidedown.vi v9, v8, 1 -; CHECK-NEXT: vsetivli zero, 2, e16, mf4, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma ; CHECK-NEXT: vslideup.vi v9, v8, 1 ; CHECK-NEXT: vmv1r.v v8, v9 ; CHECK-NEXT: ret @@ -568,11 +568,11 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e16, mf4, ta, ma ; CHECK-NEXT: vslidedown.vi v10, v8, 1 -; CHECK-NEXT: vsetivli zero, 2, e16, mf4, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma ; CHECK-NEXT: vslideup.vi v10, v8, 1 ; CHECK-NEXT: vsetivli zero, 1, e16, mf4, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v9, 1 -; CHECK-NEXT: vsetivli zero, 2, e16, mf4, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 1 ; CHECK-NEXT: vsetivli zero, 4, e16, mf2, tu, ma ; CHECK-NEXT: vslideup.vi v8, v10, 2 @@ -680,7 +680,7 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e32, mf2, ta, ma ; CHECK-NEXT: vslidedown.vi v9, v8, 1 -; CHECK-NEXT: vsetivli zero, 2, e32, mf2, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma ; CHECK-NEXT: vslideup.vi v9, v8, 1 ; CHECK-NEXT: vmv1r.v v8, v9 ; CHECK-NEXT: ret @@ -693,11 +693,11 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e32, mf2, ta, ma ; CHECK-NEXT: vslidedown.vi v10, v8, 1 -; CHECK-NEXT: vsetivli zero, 2, e32, mf2, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma ; CHECK-NEXT: vslideup.vi v10, v8, 1 ; CHECK-NEXT: vsetivli zero, 1, e32, mf2, ta, ma ; CHECK-NEXT: vslidedown.vi v8, v9, 1 -; CHECK-NEXT: vsetivli zero, 2, e32, mf2, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma ; CHECK-NEXT: vslideup.vi v8, v9, 1 ; CHECK-NEXT: vsetivli zero, 4, e32, m1, tu, ma ; CHECK-NEXT: vslideup.vi v8, v10, 2 @@ -775,9 +775,9 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma ; CHECK-NEXT: vslidedown.vi v9, v8, 1 -; CHECK-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-NEXT: vslideup.vi v9, v8, 1 -; CHECK-NEXT: vmv1r.v v8, v9 +; CHECK-NEXT: vmv.v.v v8, v9 ; CHECK-NEXT: ret %v2f64 = shufflevector <2 x double> %a, <2 x double> undef, <2 x i32> ret <2 x double> %v2f64 @@ -788,11 +788,11 @@ ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma ; CHECK-NEXT: vslidedown.vi v12, v8, 1 -; CHECK-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-NEXT: vslideup.vi v12, v8, 1 ; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma ; CHECK-NEXT: vslidedown.vi v10, v9, 1 -; CHECK-NEXT: vsetivli zero, 2, e64, m1, tu, ma +; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-NEXT: vslideup.vi v10, v9, 1 ; CHECK-NEXT: vsetivli zero, 4, e64, m2, tu, ma ; CHECK-NEXT: vslideup.vi v10, v12, 2