[llvm] [VPlan] Omit zero add in VPWidenIntOrFpInductionRecipe (PR #119668)
via llvm-commits
llvm-commits at lists.llvm.org
Wed Dec 11 23:43:20 PST 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-vectorizers
Author: Luke Lau (lukel97)
<details>
<summary>Changes</summary>
I'm not sure if getStepVector was used for other things in the past where StartIdx was non-zero, but nowadays VPWidenIntOrFpInductionRecipe is the only user of it, and just passes zero to it. I presume InstCombine was already catching this so hopefully removing this won't affect codegen.
---
Patch is 43.49 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/119668.diff
17 Files Affected:
- (modified) llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp (+4-10)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/clamped-trip-count.ll (+2-4)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/divs-with-scalable-vfs.ll (+2-4)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/outer_loop_prefer_scalable.ll (+19-20)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/scalable-avoid-scalarization.ll (+1-2)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll (+1-2)
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/blocks-with-dead-instructions.ll (+7-14)
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/dead-ops-cost.ll (+4-8)
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/induction-costs.ll (+3-4)
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/mask-index-type.ll (+1-2)
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/masked_gather_scatter.ll (+2-4)
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/pr87378-vpinstruction-or-drop-poison-generating-flags.ll (+1-2)
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/strided-accesses.ll (+3-6)
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/uniform-load-store.ll (+5-10)
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cond-reduction.ll (+4-8)
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-interleave.ll (+1-2)
- (modified) llvm/test/Transforms/LoopVectorize/outer_loop_scalable.ll (+1-2)
``````````diff
diff --git a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
index e882368544e815..54392bcac4417f 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
@@ -1576,10 +1576,10 @@ InstructionCost VPHeaderPHIRecipe::computeCost(ElementCount VF,
}
/// This function adds
-/// (StartIdx * Step, (StartIdx + 1) * Step, (StartIdx + 2) * Step, ...)
+/// (0 * Step, 1 * Step, 2 * Step, ...)
/// to each vector element of Val. The sequence starts at StartIndex.
/// \p Opcode is relevant for FP induction variable.
-static Value *getStepVector(Value *Val, Value *StartIdx, Value *Step,
+static Value *getStepVector(Value *Val, Value *Step,
Instruction::BinaryOps BinOp, ElementCount VF,
IRBuilderBase &Builder) {
assert(VF.isVector() && "only vector VFs are supported");
@@ -1604,11 +1604,7 @@ static Value *getStepVector(Value *Val, Value *StartIdx, Value *Step,
}
Value *InitVec = Builder.CreateStepVector(InitVecValVTy);
- // Splat the StartIdx
- Value *StartIdxSplat = Builder.CreateVectorSplat(VLen, StartIdx);
-
if (STy->isIntegerTy()) {
- InitVec = Builder.CreateAdd(InitVec, StartIdxSplat);
Step = Builder.CreateVectorSplat(VLen, Step);
assert(Step->getType() == Val->getType() && "Invalid step vec");
// FIXME: The newly created binary instructions should contain nsw/nuw
@@ -1621,7 +1617,6 @@ static Value *getStepVector(Value *Val, Value *StartIdx, Value *Step,
assert((BinOp == Instruction::FAdd || BinOp == Instruction::FSub) &&
"Binary Opcode should be specified for FP induction");
InitVec = Builder.CreateUIToFP(InitVec, ValVTy);
- InitVec = Builder.CreateFAdd(InitVec, StartIdxSplat);
Step = Builder.CreateVectorSplat(VLen, Step);
Value *MulOp = Builder.CreateFMul(InitVec, Step);
@@ -1672,10 +1667,9 @@ void VPWidenIntOrFpInductionRecipe::execute(VPTransformState &State) {
Start = Builder.CreateCast(Instruction::Trunc, Start, TruncType);
}
- Value *Zero = getSignedIntOrFpConstant(Start->getType(), 0);
Value *SplatStart = Builder.CreateVectorSplat(State.VF, Start);
- Value *SteppedStart = getStepVector(
- SplatStart, Zero, Step, ID.getInductionOpcode(), State.VF, State.Builder);
+ Value *SteppedStart = getStepVector(SplatStart, Step, ID.getInductionOpcode(),
+ State.VF, State.Builder);
// We create vector phi nodes for both integer and floating-point induction
// variables. Here, we determine the kind of arithmetic we will perform.
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/clamped-trip-count.ll b/llvm/test/Transforms/LoopVectorize/AArch64/clamped-trip-count.ll
index 1948211858d446..ac7f1478cf68c3 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/clamped-trip-count.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/clamped-trip-count.ll
@@ -18,8 +18,7 @@ define void @clamped_tc_8(ptr nocapture %dst, i32 %n, i64 %val) vscale_range(1,1
; CHECK-NEXT: [[TMP6:%.*]] = mul i64 [[TMP5]], 8
; CHECK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 0, i64 8)
; CHECK-NEXT: [[TMP8:%.*]] = call <vscale x 8 x i64> @llvm.stepvector.nxv8i64()
-; CHECK-NEXT: [[TMP9:%.*]] = add <vscale x 8 x i64> [[TMP8]], zeroinitializer
-; CHECK-NEXT: [[TMP7:%.*]] = mul <vscale x 8 x i64> [[TMP9]], splat (i64 1)
+; CHECK-NEXT: [[TMP7:%.*]] = mul <vscale x 8 x i64> [[TMP8]], splat (i64 1)
; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 8 x i64> zeroinitializer, [[TMP7]]
; CHECK-NEXT: [[TMP12:%.*]] = mul i64 1, [[TMP6]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i64> poison, i64 [[TMP12]], i64 0
@@ -105,8 +104,7 @@ define void @clamped_tc_max_8(ptr nocapture %dst, i32 %n, i64 %val) vscale_range
; CHECK-NEXT: [[TMP6:%.*]] = mul i64 [[TMP5]], 8
; CHECK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 0, i64 [[WIDE_TRIP_COUNT]])
; CHECK-NEXT: [[TMP8:%.*]] = call <vscale x 8 x i64> @llvm.stepvector.nxv8i64()
-; CHECK-NEXT: [[TMP9:%.*]] = add <vscale x 8 x i64> [[TMP8]], zeroinitializer
-; CHECK-NEXT: [[TMP7:%.*]] = mul <vscale x 8 x i64> [[TMP9]], splat (i64 1)
+; CHECK-NEXT: [[TMP7:%.*]] = mul <vscale x 8 x i64> [[TMP8]], splat (i64 1)
; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 8 x i64> zeroinitializer, [[TMP7]]
; CHECK-NEXT: [[TMP12:%.*]] = mul i64 1, [[TMP6]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i64> poison, i64 [[TMP12]], i64 0
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/divs-with-scalable-vfs.ll b/llvm/test/Transforms/LoopVectorize/AArch64/divs-with-scalable-vfs.ll
index 5e7b4ca9d300b9..2da89120182c01 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/divs-with-scalable-vfs.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/divs-with-scalable-vfs.ll
@@ -125,8 +125,7 @@ define void @sdiv_feeding_gep_predicated(ptr %dst, i32 %x, i64 %M, i64 %conv6, i
; CHECK-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], i64 [[TMP12]], i64 0
; CHECK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 0, i64 [[N]])
; CHECK-NEXT: [[TMP15:%.*]] = call <vscale x 2 x i64> @llvm.stepvector.nxv2i64()
-; CHECK-NEXT: [[TMP16:%.*]] = add <vscale x 2 x i64> [[TMP15]], zeroinitializer
-; CHECK-NEXT: [[TMP17:%.*]] = mul <vscale x 2 x i64> [[TMP16]], splat (i64 1)
+; CHECK-NEXT: [[TMP17:%.*]] = mul <vscale x 2 x i64> [[TMP15]], splat (i64 1)
; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 2 x i64> zeroinitializer, [[TMP17]]
; CHECK-NEXT: [[TMP20:%.*]] = mul i64 1, [[TMP9]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP20]], i64 0
@@ -252,8 +251,7 @@ define void @udiv_urem_feeding_gep(i64 %x, ptr %dst, i64 %N) {
; CHECK-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], i64 [[TMP12]], i64 0
; CHECK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 0, i64 [[TMP0]])
; CHECK-NEXT: [[TMP15:%.*]] = call <vscale x 2 x i64> @llvm.stepvector.nxv2i64()
-; CHECK-NEXT: [[TMP16:%.*]] = add <vscale x 2 x i64> [[TMP15]], zeroinitializer
-; CHECK-NEXT: [[TMP17:%.*]] = mul <vscale x 2 x i64> [[TMP16]], splat (i64 1)
+; CHECK-NEXT: [[TMP17:%.*]] = mul <vscale x 2 x i64> [[TMP15]], splat (i64 1)
; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 2 x i64> zeroinitializer, [[TMP17]]
; CHECK-NEXT: [[TMP20:%.*]] = mul i64 1, [[TMP9]]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP20]], i64 0
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 0db4799a0a8fe8..3302103873bd33 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/outer_loop_prefer_scalable.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/outer_loop_prefer_scalable.ll
@@ -21,36 +21,35 @@ define void @foo() {
; CHECK-NEXT: [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP5:%.*]] = mul i64 [[TMP4]], 4
; CHECK-NEXT: [[TMP6:%.*]] = call <vscale x 4 x i64> @llvm.stepvector.nxv4i64()
-; CHECK-NEXT: [[TMP7:%.*]] = add <vscale x 4 x i64> [[TMP6]], zeroinitializer
-; CHECK-NEXT: [[TMP8:%.*]] = mul <vscale x 4 x i64> [[TMP7]], splat (i64 1)
-; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP8]]
-; CHECK-NEXT: [[TMP9:%.*]] = mul i64 1, [[TMP5]]
-; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP9]], i64 0
+; CHECK-NEXT: [[TMP7:%.*]] = mul <vscale x 4 x i64> [[TMP6]], splat (i64 1)
+; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP7]]
+; CHECK-NEXT: [[TMP8:%.*]] = mul i64 1, [[TMP5]]
+; 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:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_LATCH:%.*]] ]
; CHECK-NEXT: [[VEC_IND:%.*]] = phi <vscale x 4 x i64> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_LATCH]] ]
-; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds [1024 x float], ptr @A, i64 0, <vscale x 4 x i64> [[VEC_IND]]
-; CHECK-NEXT: [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x float> @llvm.masked.gather.nxv4f32.nxv4p0(<vscale x 4 x ptr> [[TMP10]], i32 4, <vscale x 4 x i1> splat (i1 true), <vscale x 4 x float> poison)
+; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1024 x float], ptr @A, i64 0, <vscale x 4 x i64> [[VEC_IND]]
+; CHECK-NEXT: [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x float> @llvm.masked.gather.nxv4f32.nxv4p0(<vscale x 4 x ptr> [[TMP9]], i32 4, <vscale x 4 x i1> splat (i1 true), <vscale x 4 x float> poison)
; CHECK-NEXT: br label [[INNER_LOOP1:%.*]]
; CHECK: inner_loop1:
-; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <vscale x 4 x i64> [ zeroinitializer, [[VECTOR_BODY]] ], [ [[TMP13:%.*]], [[INNER_LOOP1]] ]
-; CHECK-NEXT: [[VEC_PHI2:%.*]] = phi <vscale x 4 x float> [ [[WIDE_MASKED_GATHER]], [[VECTOR_BODY]] ], [ [[TMP12:%.*]], [[INNER_LOOP1]] ]
-; CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds [512 x float], ptr @B, i64 0, <vscale x 4 x i64> [[VEC_PHI]]
-; CHECK-NEXT: [[WIDE_MASKED_GATHER3:%.*]] = call <vscale x 4 x float> @llvm.masked.gather.nxv4f32.nxv4p0(<vscale x 4 x ptr> [[TMP11]], i32 4, <vscale x 4 x i1> splat (i1 true), <vscale x 4 x float> poison)
-; CHECK-NEXT: [[TMP12]] = fmul <vscale x 4 x float> [[VEC_PHI2]], [[WIDE_MASKED_GATHER3]]
-; CHECK-NEXT: [[TMP13]] = add nuw nsw <vscale x 4 x i64> [[VEC_PHI]], splat (i64 1)
-; CHECK-NEXT: [[TMP14:%.*]] = icmp eq <vscale x 4 x i64> [[TMP13]], splat (i64 512)
-; CHECK-NEXT: [[TMP15:%.*]] = extractelement <vscale x 4 x i1> [[TMP14]], i32 0
-; CHECK-NEXT: br i1 [[TMP15]], label [[VECTOR_LATCH]], label [[INNER_LOOP1]]
+; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <vscale x 4 x i64> [ zeroinitializer, [[VECTOR_BODY]] ], [ [[TMP12:%.*]], [[INNER_LOOP1]] ]
+; CHECK-NEXT: [[VEC_PHI2:%.*]] = phi <vscale x 4 x float> [ [[WIDE_MASKED_GATHER]], [[VECTOR_BODY]] ], [ [[TMP11:%.*]], [[INNER_LOOP1]] ]
+; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds [512 x float], ptr @B, i64 0, <vscale x 4 x i64> [[VEC_PHI]]
+; CHECK-NEXT: [[WIDE_MASKED_GATHER3:%.*]] = call <vscale x 4 x float> @llvm.masked.gather.nxv4f32.nxv4p0(<vscale x 4 x ptr> [[TMP10]], i32 4, <vscale x 4 x i1> splat (i1 true), <vscale x 4 x float> poison)
+; CHECK-NEXT: [[TMP11]] = fmul <vscale x 4 x float> [[VEC_PHI2]], [[WIDE_MASKED_GATHER3]]
+; CHECK-NEXT: [[TMP12]] = add nuw nsw <vscale x 4 x i64> [[VEC_PHI]], splat (i64 1)
+; CHECK-NEXT: [[TMP13:%.*]] = icmp eq <vscale x 4 x i64> [[TMP12]], splat (i64 512)
+; CHECK-NEXT: [[TMP14:%.*]] = extractelement <vscale x 4 x i1> [[TMP13]], i32 0
+; CHECK-NEXT: br i1 [[TMP14]], label [[VECTOR_LATCH]], label [[INNER_LOOP1]]
; CHECK: vector.latch:
-; CHECK-NEXT: [[VEC_PHI4:%.*]] = phi <vscale x 4 x float> [ [[TMP12]], [[INNER_LOOP1]] ]
-; CHECK-NEXT: call void @llvm.masked.scatter.nxv4f32.nxv4p0(<vscale x 4 x float> [[VEC_PHI4]], <vscale x 4 x ptr> [[TMP10]], i32 4, <vscale x 4 x i1> splat (i1 true))
+; CHECK-NEXT: [[VEC_PHI4:%.*]] = phi <vscale x 4 x float> [ [[TMP11]], [[INNER_LOOP1]] ]
+; CHECK-NEXT: call void @llvm.masked.scatter.nxv4f32.nxv4p0(<vscale x 4 x float> [[VEC_PHI4]], <vscale x 4 x ptr> [[TMP9]], i32 4, <vscale x 4 x i1> splat (i1 true))
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <vscale x 4 x i64> [[VEC_IND]], [[DOTSPLAT]]
-; CHECK-NEXT: [[TMP16:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT: br i1 [[TMP16]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK-NEXT: [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT: br i1 [[TMP15]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-avoid-scalarization.ll b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-avoid-scalarization.ll
index 41c92d61663325..a426cdf08062c8 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-avoid-scalarization.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-avoid-scalarization.ll
@@ -29,8 +29,7 @@ define void @test_no_scalarization(ptr %a, ptr noalias %b, i32 %idx, i32 %n) #0
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i32> poison, i32 [[IDX]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 2 x i32> [[DOTSPLATINSERT]], <vscale x 2 x i32> poison, <vscale x 2 x i32> zeroinitializer
; CHECK-NEXT: [[TMP8:%.*]] = call <vscale x 2 x i32> @llvm.stepvector.nxv2i32()
-; CHECK-NEXT: [[TMP9:%.*]] = add <vscale x 2 x i32> [[TMP8]], zeroinitializer
-; CHECK-NEXT: [[TMP10:%.*]] = mul <vscale x 2 x i32> [[TMP9]], splat (i32 1)
+; CHECK-NEXT: [[TMP10:%.*]] = mul <vscale x 2 x i32> [[TMP8]], splat (i32 1)
; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 2 x i32> [[DOTSPLAT]], [[TMP10]]
; CHECK-NEXT: [[TMP13:%.*]] = mul i32 1, [[TMP7]]
; CHECK-NEXT: [[DOTSPLATINSERT1:%.*]] = insertelement <vscale x 2 x i32> poison, i32 [[TMP13]], i64 0
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll
index 2850aca9185548..e5b9812604f164 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll
@@ -225,8 +225,7 @@ define void @copy_stride4(ptr noalias %dst, ptr noalias %src, i64 %n) #0 {
; CHECK-NEXT: [[TMP12:%.*]] = select i1 [[TMP11]], i64 [[TMP10]], i64 0
; CHECK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[TMP2]])
; CHECK-NEXT: [[TMP13:%.*]] = call <vscale x 4 x i64> @llvm.stepvector.nxv4i64()
-; CHECK-NEXT: [[TMP14:%.*]] = add <vscale x 4 x i64> [[TMP13]], zeroinitializer
-; CHECK-NEXT: [[TMP15:%.*]] = mul <vscale x 4 x i64> [[TMP14]], splat (i64 4)
+; CHECK-NEXT: [[TMP15:%.*]] = mul <vscale x 4 x i64> [[TMP13]], splat (i64 4)
; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP15]]
; CHECK-NEXT: [[TMP18:%.*]] = mul i64 4, [[TMP7]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP18]], i64 0
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/blocks-with-dead-instructions.ll b/llvm/test/Transforms/LoopVectorize/RISCV/blocks-with-dead-instructions.ll
index 2e0eee1f862927..00fc704a92b057 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/blocks-with-dead-instructions.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/blocks-with-dead-instructions.ll
@@ -26,8 +26,7 @@ define void @block_with_dead_inst_1(ptr %src, i64 %N) #0 {
; CHECK-NEXT: [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP10:%.*]] = mul i64 [[TMP9]], 8
; CHECK-NEXT: [[TMP11:%.*]] = call <vscale x 8 x i64> @llvm.stepvector.nxv8i64()
-; CHECK-NEXT: [[TMP12:%.*]] = add <vscale x 8 x i64> [[TMP11]], zeroinitializer
-; CHECK-NEXT: [[TMP13:%.*]] = mul <vscale x 8 x i64> [[TMP12]], splat (i64 3)
+; CHECK-NEXT: [[TMP13:%.*]] = mul <vscale x 8 x i64> [[TMP11]], splat (i64 3)
; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 8 x i64> zeroinitializer, [[TMP13]]
; CHECK-NEXT: [[TMP16:%.*]] = mul i64 3, [[TMP10]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i64> poison, i64 [[TMP16]], i64 0
@@ -121,8 +120,7 @@ define void @block_with_dead_inst_2(ptr %src) #0 {
; CHECK-NEXT: [[TMP6:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP7:%.*]] = mul i64 [[TMP6]], 4
; CHECK-NEXT: [[TMP8:%.*]] = call <vscale x 4 x i64> @llvm.stepvector.nxv4i64()
-; CHECK-NEXT: [[TMP9:%.*]] = add <vscale x 4 x i64> [[TMP8]], zeroinitializer
-; CHECK-NEXT: [[TMP10:%.*]] = mul <vscale x 4 x i64> [[TMP9]], splat (i64 3)
+; CHECK-NEXT: [[TMP10:%.*]] = mul <vscale x 4 x i64> [[TMP8]], splat (i64 3)
; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP10]]
; CHECK-NEXT: [[TMP13:%.*]] = mul i64 3, [[TMP7]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP13]], i64 0
@@ -216,8 +214,7 @@ define void @multiple_blocks_with_dead_insts_3(ptr %src) #0 {
; CHECK-NEXT: [[TMP6:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP7:%.*]] = mul i64 [[TMP6]], 4
; CHECK-NEXT: [[TMP8:%.*]] = call <vscale x 4 x i64> @llvm.stepvector.nxv4i64()
-; CHECK-NEXT: [[TMP9:%.*]] = add <vscale x 4 x i64> [[TMP8]], zeroinitializer
-; CHECK-NEXT: [[TMP10:%.*]] = mul <vscale x 4 x i64> [[TMP9]], splat (i64 3)
+; CHECK-NEXT: [[TMP10:%.*]] = mul <vscale x 4 x i64> [[TMP8]], splat (i64 3)
; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP10]]
; CHECK-NEXT: [[TMP13:%.*]] = mul i64 3, [[TMP7]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP13]], i64 0
@@ -321,8 +318,7 @@ define void @multiple_blocks_with_dead_insts_4(ptr %src, i64 %N) #0 {
; CHECK-NEXT: [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP10:%.*]] = mul i64 [[TMP9]], 8
; CHECK-NEXT: [[TMP11:%.*]] = call <vscale x 8 x i64> @llvm.stepvector.nxv8i64()
-; CHECK-NEXT: [[TMP12:%.*]] = add <vscale x 8 x i64> [[TMP11]], zeroinitializer
-; CHECK-NEXT: [[TMP13:%.*]] = mul <vscale x 8 x i64> [[TMP12]], splat (i64 3)
+; CHECK-NEXT: [[TMP13:%.*]] = mul <vscale x 8 x i64> [[TMP11]], splat (i64 3)
; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 8 x i64> zeroinitializer, [[TMP13]]
; CHECK-NEXT: [[TMP16:%.*]] = mul i64 3, [[TMP10]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i64> poison, i64 [[TMP16]], i64 0
@@ -428,8 +424,7 @@ define void @multiple_blocks_with_dead_inst_multiple_successors_5(ptr %src) #0 {
; CHECK-NEXT: [[TMP6:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP7:%.*]] = mul i64 [[TMP6]], 4
; CHECK-NEXT: [[TMP8:%.*]] = call <vscale x 4 x i64> @llvm.stepvector.nxv4i64()
-; CHECK-NEXT: [[TMP9:%.*]] = add <vscale x 4 x i64> [[TMP8]], zeroinitializer
-; CHECK-NEXT: [[TMP10:%.*]] = mul <vscale x 4 x i64> [[TMP9]], splat (i64 3)
+; CHECK-NEXT: [[TMP10:%.*]] = mul <vscale x 4 x i64> [[TMP8]], splat (i64 3)
; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP10]]
; CHECK-NEXT: [[TMP13:%.*]] = mul i64 3, [[TMP7]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP13]], i64 0
@@ -543,8 +538,7 @@ define void @multiple_blocks_with_dead_inst_multiple_successors_6(ptr %src, i1 %
; CHECK-NEXT: [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP10:%.*]] = mul i64 [[TMP9]], 8
; CHECK-NEXT: [[TMP11:%.*]] = call <vscale x 8 x i64> @llvm.stepvector.nxv8i64()
-; CHECK-NEXT: [[TMP12:%.*]] = add <vscale x 8 x i64> [[TMP11]], zeroinitializer
-; CHECK-NEXT: [[TMP13:%.*]] = mul <vscale x 8 x i64> [[TMP12]], splat (i64 3)
+; CHECK-NEXT: [[TMP13:%.*]] = mul <vscale x 8 x i64> [[TMP11]], splat (i64 3)
; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 8 x i64> zeroinitializer, [[TMP13]]
; CHECK-NEXT: [[TMP16:%.*]] = mul i64 3, [[TMP10]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i64> poison, i64 [[TMP16]], i64 0
@@ -861,8 +855,7 @@ define void @dead_load_in_block(ptr %dst, ptr %src, i8 %N, i64 %x) #0 {
; CHECK-NEXT: [[TMP16:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP17:%.*]] = mul i64 [[TMP16]], 2
; CHECK-NEXT: [[TMP18:%.*]] = call <vscale x 2 x i...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/119668
More information about the llvm-commits
mailing list