[llvm] [VPlan] Add VPValue for VF, use it for VPWidenIntOrFpInductionRecipe. (PR #95305)
via llvm-commits
llvm-commits at lists.llvm.org
Wed Jun 12 13:39:49 PDT 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-transforms
Author: Florian Hahn (fhahn)
<details>
<summary>Changes</summary>
Similar to VFxUF, also add a VF VPValue to VPlan and use it to get the runtime VF in VPWidenIntOrFpInductionRecipe. Code for VF is only generated if there are users of VF, to avoid unnecessary test changes.
Note: some tests still need updating, will do once we converge on a final version of the patch.
---
Patch is 32.69 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/95305.diff
12 Files Affected:
- (modified) llvm/lib/Transforms/Vectorize/LoopVectorize.cpp (+5-2)
- (modified) llvm/lib/Transforms/Vectorize/VPlan.cpp (+16-2)
- (modified) llvm/lib/Transforms/Vectorize/VPlan.h (+10-4)
- (modified) llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp (+2-2)
- (modified) llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp (+2-1)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/outer_loop_prefer_scalable.ll (+1-3)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions-unusual-types.ll (+4-2)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/sve-interleaved-accesses.ll (+13-29)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/sve-interleaved-masked-accesses.ll (+3-9)
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/pr87378-vpinstruction-or-drop-poison-generating-flags.ll (+1-3)
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/uniform-load-store.ll (+2-6)
- (modified) llvm/test/Transforms/LoopVectorize/scalable-inductions.ll (+4-6)
``````````diff
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 7edf83a76faaa..07191235009ce 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -8069,10 +8069,12 @@ createWidenInductionRecipes(PHINode *Phi, Instruction *PhiOrTrunc,
VPValue *Step =
vputils::getOrCreateVPValueForSCEVExpr(Plan, IndDesc.getStep(), SE);
if (auto *TruncI = dyn_cast<TruncInst>(PhiOrTrunc)) {
- return new VPWidenIntOrFpInductionRecipe(Phi, Start, Step, IndDesc, TruncI);
+ return new VPWidenIntOrFpInductionRecipe(Phi, Start, Step, Plan.getVF(),
+ IndDesc, TruncI);
}
assert(isa<PHINode>(PhiOrTrunc) && "must be a phi node here");
- return new VPWidenIntOrFpInductionRecipe(Phi, Start, Step, IndDesc);
+ return new VPWidenIntOrFpInductionRecipe(Phi, Start, Step, Plan.getVF(),
+ IndDesc);
}
VPHeaderPHIRecipe *VPRecipeBuilder::tryToOptimizeInductionPHI(
@@ -8487,6 +8489,7 @@ static void addCanonicalIVRecipes(VPlan &Plan, Type *IdxTy, bool HasNUW,
VPBasicBlock *Header = TopRegion->getEntryBasicBlock();
Header->insert(CanonicalIVPHI, Header->begin());
+ VPBuilder PhBuilder(cast<VPBasicBlock>(TopRegion->getSinglePredecessor()));
VPBuilder Builder(TopRegion->getExitingBasicBlock());
// Add a VPInstruction to increment the scalar canonical IV by VF * UF.
auto *CanonicalIVIncrement = Builder.createOverflowingOp(
diff --git a/llvm/lib/Transforms/Vectorize/VPlan.cpp b/llvm/lib/Transforms/Vectorize/VPlan.cpp
index f17be451e6846..5806a5141f9a2 100644
--- a/llvm/lib/Transforms/Vectorize/VPlan.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlan.cpp
@@ -814,8 +814,21 @@ void VPlan::prepareToExecute(Value *TripCountV, Value *VectorTripCountV,
IRBuilder<> Builder(State.CFG.PrevBB->getTerminator());
// FIXME: Model VF * UF computation completely in VPlan.
- VFxUF.setUnderlyingValue(
- createStepForVF(Builder, TripCountV->getType(), State.VF, State.UF));
+ Value *RuntimeVF = nullptr;
+ if (VF.getNumUsers()) {
+ RuntimeVF = createStepForVF(Builder, TripCountV->getType(), State.VF, 1);
+ VF.setUnderlyingValue(RuntimeVF);
+ }
+ if (RuntimeVF) {
+ VFxUF.setUnderlyingValue(
+ State.UF > 1 ? Builder.CreateMul(
+ VF.getLiveInIRValue(),
+ ConstantInt::get(TripCountV->getType(), State.UF))
+ : VF.getLiveInIRValue());
+ } else {
+ VFxUF.setUnderlyingValue(
+ createStepForVF(Builder, TripCountV->getType(), State.VF, State.UF));
+ }
// When vectorizing the epilogue loop, the canonical induction start value
// needs to be changed from zero to the value after the main vector loop.
@@ -1067,6 +1080,7 @@ VPlan *VPlan::duplicate() {
}
Old2NewVPValues[&VectorTripCount] = &NewPlan->VectorTripCount;
Old2NewVPValues[&VFxUF] = &NewPlan->VFxUF;
+ Old2NewVPValues[&VF] = &NewPlan->VF;
if (BackedgeTakenCount) {
NewPlan->BackedgeTakenCount = new VPValue();
Old2NewVPValues[BackedgeTakenCount] = NewPlan->BackedgeTakenCount;
diff --git a/llvm/lib/Transforms/Vectorize/VPlan.h b/llvm/lib/Transforms/Vectorize/VPlan.h
index 5bb88e4a57dc3..566a5244c5abc 100644
--- a/llvm/lib/Transforms/Vectorize/VPlan.h
+++ b/llvm/lib/Transforms/Vectorize/VPlan.h
@@ -1705,25 +1705,27 @@ class VPWidenIntOrFpInductionRecipe : public VPHeaderPHIRecipe {
public:
VPWidenIntOrFpInductionRecipe(PHINode *IV, VPValue *Start, VPValue *Step,
- const InductionDescriptor &IndDesc)
+ VPValue *VF, const InductionDescriptor &IndDesc)
: VPHeaderPHIRecipe(VPDef::VPWidenIntOrFpInductionSC, IV, Start), IV(IV),
Trunc(nullptr), IndDesc(IndDesc) {
addOperand(Step);
+ addOperand(VF);
}
VPWidenIntOrFpInductionRecipe(PHINode *IV, VPValue *Start, VPValue *Step,
- const InductionDescriptor &IndDesc,
+ VPValue *VF, const InductionDescriptor &IndDesc,
TruncInst *Trunc)
: VPHeaderPHIRecipe(VPDef::VPWidenIntOrFpInductionSC, Trunc, Start),
IV(IV), Trunc(Trunc), IndDesc(IndDesc) {
addOperand(Step);
+ addOperand(VF);
}
~VPWidenIntOrFpInductionRecipe() override = default;
VPWidenIntOrFpInductionRecipe *clone() override {
- return new VPWidenIntOrFpInductionRecipe(IV, getStartValue(),
- getStepValue(), IndDesc, Trunc);
+ return new VPWidenIntOrFpInductionRecipe(
+ IV, getStartValue(), getStepValue(), getOperand(2), IndDesc, Trunc);
}
VP_CLASSOF_IMPL(VPDef::VPWidenIntOrFpInductionSC)
@@ -3142,6 +3144,8 @@ class VPlan {
/// Represents the vector trip count.
VPValue VectorTripCount;
+ VPValue VF;
+
/// Represents the loop-invariant VF * UF of the vector loop region.
VPValue VFxUF;
@@ -3233,6 +3237,8 @@ class VPlan {
/// Returns VF * UF of the vector loop region.
VPValue &getVFxUF() { return VFxUF; }
+ VPValue *getVF() { return &VF; };
+
void addVF(ElementCount VF) { VFs.insert(VF); }
void setVF(ElementCount VF) {
diff --git a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
index 7a482455473e4..7165d77c1033b 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
@@ -1217,11 +1217,11 @@ void VPWidenIntOrFpInductionRecipe::execute(VPTransformState &State) {
// Multiply the vectorization factor by the step using integer or
// floating-point arithmetic as appropriate.
Type *StepType = Step->getType();
- Value *RuntimeVF;
+ Value *RuntimeVF = State.get(getOperand(2), {0, 0});
if (Step->getType()->isFloatingPointTy())
RuntimeVF = getRuntimeVFAsFloat(Builder, StepType, State.VF);
else
- RuntimeVF = getRuntimeVF(Builder, StepType, State.VF);
+ RuntimeVF = Builder.CreateZExtOrTrunc(RuntimeVF, StepType);
Value *Mul = Builder.CreateBinOp(MulOp, Step, RuntimeVF);
// Create a vector splat to use in the induction update.
diff --git a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
index 8ec67eb2f54bd..c2b8502af058a 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
@@ -55,7 +55,8 @@ void VPlanTransforms::VPInstructionsToVPRecipes(
VPValue *Start = Plan->getOrAddLiveIn(II->getStartValue());
VPValue *Step =
vputils::getOrCreateVPValueForSCEVExpr(*Plan, II->getStep(), SE);
- NewRecipe = new VPWidenIntOrFpInductionRecipe(Phi, Start, Step, *II);
+ NewRecipe = new VPWidenIntOrFpInductionRecipe(Phi, Start, Step,
+ Plan->getVF(), *II);
} else {
assert(isa<VPInstruction>(&Ingredient) &&
"only VPInstructions expected here");
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/outer_loop_prefer_scalable.ll b/llvm/test/Transforms/LoopVectorize/AArch64/outer_loop_prefer_scalable.ll
index 59a1e108b92f0..0d1298b909976 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/outer_loop_prefer_scalable.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/outer_loop_prefer_scalable.ll
@@ -24,9 +24,7 @@ define void @foo() {
; CHECK-NEXT: [[TMP5:%.*]] = add <vscale x 4 x i64> [[TMP4]], zeroinitializer
; CHECK-NEXT: [[TMP6:%.*]] = mul <vscale x 4 x i64> [[TMP5]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP6]]
-; CHECK-NEXT: [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP8:%.*]] = mul i64 [[TMP7]], 4
-; CHECK-NEXT: [[TMP9:%.*]] = mul i64 1, [[TMP8]]
+; CHECK-NEXT: [[TMP9:%.*]] = mul i64 1, [[TMP19]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP9]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions-unusual-types.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions-unusual-types.ll
index 3217f508f0adc..5d131e9c94727 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions-unusual-types.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions-unusual-types.ll
@@ -13,7 +13,8 @@ define void @induction_i7(ptr %dst) #0 {
; CHECK: vector.ph:
; CHECK: %ind.end = trunc i64 %n.vec to i7
; CHECK-NEXT: [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP5:%.*]] = mul i64 [[TMP4]], 4
+; CHECK-NEXT: [[TMP40:%.*]] = mul i64 [[TMP4]], 2
+; CHECK-NEXT: [[TMP5:%.*]] = mul i64 [[TMP40]], 2
; CHECK-NEXT: [[TMP6:%.*]] = call <vscale x 2 x i8> @llvm.experimental.stepvector.nxv2i8()
; CHECK-NEXT: [[TMP7:%.*]] = trunc <vscale x 2 x i8> [[TMP6]] to <vscale x 2 x i7>
; CHECK-NEXT: [[TMP8:%.*]] = add <vscale x 2 x i7> [[TMP7]], zeroinitializer
@@ -73,7 +74,8 @@ define void @induction_i3_zext(ptr %dst) #0 {
; CHECK: vector.ph:
; CHECK: %ind.end = trunc i64 %n.vec to i3
; CHECK-NEXT: [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP5:%.*]] = mul i64 [[TMP4]], 4
+; CHECK-NEXT: [[TMP40:%.*]] = mul i64 [[TMP4]], 2
+; CHECK-NEXT: [[TMP5:%.*]] = mul i64 [[TMP40]], 2
; CHECK-NEXT: [[TMP6:%.*]] = call <vscale x 2 x i8> @llvm.experimental.stepvector.nxv2i8()
; CHECK-NEXT: [[TMP7:%.*]] = trunc <vscale x 2 x i8> [[TMP6]] to <vscale x 2 x i3>
; CHECK-NEXT: [[TMP8:%.*]] = add <vscale x 2 x i3> [[TMP7]], zeroinitializer
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-interleaved-accesses.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-interleaved-accesses.ll
index 3a25ffe26cc03..501243672ea4f 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-interleaved-accesses.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-interleaved-accesses.ll
@@ -110,8 +110,7 @@ define void @test_array_load2_i16_store2(i32 %C, i32 %D) #1 {
; CHECK-NEXT: [[TMP1:%.*]] = shl nuw nsw i64 [[TMP0]], 2
; CHECK-NEXT: [[TMP2:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
; CHECK-NEXT: [[TMP3:%.*]] = shl <vscale x 4 x i64> [[TMP2]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
-; CHECK-NEXT: [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP5:%.*]] = shl nuw nsw i64 [[TMP4]], 3
+; CHECK-NEXT: [[TMP5:%.*]] = shl nuw nsw i64 [[TMP0]], 3
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP5]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[C:%.*]], i64 0
@@ -201,8 +200,7 @@ define void @test_array_load2_store2_i16(i32 noundef %C, i32 noundef %D) #1 {
; CHECK-NEXT: [[TMP1:%.*]] = shl nuw nsw i64 [[TMP0]], 2
; CHECK-NEXT: [[TMP2:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
; CHECK-NEXT: [[TMP3:%.*]] = shl <vscale x 4 x i64> [[TMP2]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
-; CHECK-NEXT: [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP5:%.*]] = shl nuw nsw i64 [[TMP4]], 3
+; CHECK-NEXT: [[TMP5:%.*]] = shl nuw nsw i64 [[TMP0]], 3
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP5]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[C:%.*]], i64 0
@@ -280,9 +278,7 @@ define i32 @test_struct_load6(ptr %S) #1 {
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = shl nuw nsw i64 [[TMP0]], 2
; CHECK-NEXT: [[TMP2:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
-; CHECK-NEXT: [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP4:%.*]] = shl nuw nsw i64 [[TMP3]], 2
-; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP4]], i64 0
+; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP1]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
@@ -385,8 +381,8 @@ define void @test_reversed_load2_store2(ptr noalias nocapture readonly %A, ptr n
; CHECK-NEXT: [[TMP1:%.*]] = shl nuw nsw i64 [[TMP0]], 2
; CHECK-NEXT: [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.experimental.stepvector.nxv4i32()
; CHECK-NEXT: [[INDUCTION:%.*]] = sub <vscale x 4 x i32> shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1023, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer), [[TMP2]]
-; CHECK-NEXT: [[TMP3:%.*]] = call i32 @llvm.vscale.i32()
-; CHECK-NEXT: [[DOTNEG:%.*]] = mul nsw i32 [[TMP3]], -4
+; CHECK-NEXT: [[TMP3:%.*]] = trunc nuw nsw i64 [[TMP1]] to i32
+; CHECK-NEXT: [[DOTNEG:%.*]] = sub nsw i32 0, [[TMP3]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[DOTNEG]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
@@ -644,8 +640,7 @@ define void @load_gap_reverse(ptr noalias nocapture readonly %P1, ptr noalias no
; CHECK-NEXT: [[TMP1:%.*]] = shl nuw nsw i64 [[TMP0]], 2
; CHECK-NEXT: [[TMP2:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
; CHECK-NEXT: [[INDUCTION:%.*]] = sub <vscale x 4 x i64> shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1023, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer), [[TMP2]]
-; CHECK-NEXT: [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[DOTNEG:%.*]] = mul nsw i64 [[TMP3]], -4
+; CHECK-NEXT: [[DOTNEG:%.*]] = sub nsw i64 0, [[TMP1]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[DOTNEG]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[X:%.*]], i64 0
@@ -895,9 +890,7 @@ define void @PR27626_0(ptr %p, i32 %z, i64 %n) #1 {
; CHECK-NEXT: [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP8:%.*]] = shl nuw nsw i64 [[TMP7]], 2
; CHECK-NEXT: [[TMP9:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
-; CHECK-NEXT: [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP11:%.*]] = shl nuw nsw i64 [[TMP10]], 2
-; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP11]], i64 0
+; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP8]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[Z:%.*]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
@@ -982,9 +975,7 @@ define i32 @PR27626_1(ptr %p, i64 %n) #1 {
; CHECK-NEXT: [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP8:%.*]] = shl nuw nsw i64 [[TMP7]], 2
; CHECK-NEXT: [[TMP9:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
-; CHECK-NEXT: [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP11:%.*]] = shl nuw nsw i64 [[TMP10]], 2
-; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP11]], i64 0
+; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP8]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
@@ -1077,9 +1068,7 @@ define void @PR27626_2(ptr %p, i64 %n, i32 %z) #1 {
; CHECK-NEXT: [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP8:%.*]] = shl nuw nsw i64 [[TMP7]], 2
; CHECK-NEXT: [[TMP9:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
-; CHECK-NEXT: [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP11:%.*]] = shl nuw nsw i64 [[TMP10]], 2
-; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP11]], i64 0
+; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP8]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[Z:%.*]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
@@ -1167,9 +1156,7 @@ define i32 @PR27626_3(ptr %p, i64 %n, i32 %z) #1 {
; CHECK-NEXT: [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP8:%.*]] = shl nuw nsw i64 [[TMP7]], 2
; CHECK-NEXT: [[TMP9:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
-; CHECK-NEXT: [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP11:%.*]] = shl nuw nsw i64 [[TMP10]], 2
-; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP11]], i64 0
+; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP8]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
@@ -1271,8 +1258,7 @@ define void @PR27626_4(ptr %a, i32 %x, i32 %y, i32 %z, i64 %n) #1 {
; CHECK-NEXT: [[TMP7:%.*]] = shl nuw nsw i64 [[TMP6]], 2
; CHECK-NEXT: [[TMP8:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
; CHECK-NEXT: [[TMP9:%.*]] = shl <vscale x 4 x i64> [[TMP8]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
-; CHECK-NEXT: [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP11:%.*]] = shl nuw nsw i64 [[TMP10]], 3
+; CHECK-NEXT: [[TMP11:%.*]] = shl nuw nsw i64 [[TMP6]], 3
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP11]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[X:%.*]], i64 0
@@ -1368,8 +1354,7 @@ define void @PR27626_5(ptr %a, i32 %x, i32 %y, i32 %z, i64 %n) #1 {
; CHECK-NEXT: [[TMP9:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
; CHECK-NEXT: [[TMP10:%.*]] = shl <vscale x 4 x i64> [[TMP9]], shufflevector (<vscale x 4 x i64> insertelement (<vscal...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/95305
More information about the llvm-commits
mailing list