[llvm-branch-commits] [llvm] [SLP]Fix narrow-tree gate width and extract miscount (PR #217569)
via llvm-branch-commits
llvm-branch-commits at lists.llvm.org
Thu Aug 20 03:07:10 PDT 2026
llvmorg-github-actions[bot] wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-transforms
Author: Karthika Devi C (kartcq)
<details>
<summary>Changes</summary>
Measure the narrowness of in-loop trees by the actual vectorization width instead of the feeder-load width, and skip vector-typed scalars in the instruction count check to match the cost model.
Fixes #<!-- -->216715
Reviewers: efriedma-quic, bababuck, RKSimon, kartcq
Pull Request: https://github.com/llvm/llvm-project/pull/216797
---
Full diff: https://github.com/llvm/llvm-project/pull/217569.diff
5 Files Affected:
- (modified) llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp (+17-2)
- (added) llvm/test/Transforms/SLPVectorizer/AArch64/abs-mul-buildvector-in-loop.ll (+111)
- (modified) llvm/test/Transforms/SLPVectorizer/AArch64/long-non-power-of-2.ll (+4-2)
- (modified) llvm/test/Transforms/SLPVectorizer/X86/deleted-instructions-clear.ll (+5-5)
- (modified) llvm/test/Transforms/SLPVectorizer/X86/multi-parent-instr-copyable-regular.ll (+8-6)
``````````diff
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 80091308116f7..9bf48c489d949 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -13991,6 +13991,12 @@ unsigned BoUpSLP::getNumVectorInsts() const {
continue;
if (EU.User && EphValues.count(EU.User))
continue;
+ // Vector-typed scalars are consumed as whole vectors, no extract
+ // instruction is emitted for them.
+ if (isVectorizedTy(EU.Scalar->getType()) &&
+ (!SLPReVec ||
+ (EU.E.hasState() && EU.E.getOpcode() == Instruction::InsertElement)))
+ continue;
if (ExternalUsesAsOriginalScalar.contains(EU.Scalar))
continue;
if (!CountedExtracts.insert(EU.Scalar).second)
@@ -19457,8 +19463,17 @@ BoUpSLP::calculateTreeCostAndTrimNonProfitable(ArrayRef<Value *> VectorizedVals,
return Cost;
// The narrow non-profitable tree in loop? Skip, may cause regressions.
constexpr unsigned PartLimit = 2;
- const unsigned Sz =
- getVectorElementSize(VectorizableTree.front()->Scalars.front());
+ // Measure the narrowness by the width the tree is vectorized at.
+ const TreeEntry *RootTE = VectorizableTree.front().get();
+ unsigned Sz;
+ if (auto It = MinBWs.find(RootTE); It != MinBWs.end()) {
+ Sz = It->second.first;
+ } else {
+ Sz = std::max<unsigned>(
+ getVectorElementSize(RootTE->Scalars.front()),
+ DL->getTypeSizeInBits(
+ getValueType(RootTE->Scalars.front())->getScalarType()));
+ }
const unsigned MinVF = getMinVF(Sz);
if (Cost >= -SLPCostThreshold &&
VectorizableTree.front()->Scalars.size() * PartLimit <= MinVF &&
diff --git a/llvm/test/Transforms/SLPVectorizer/AArch64/abs-mul-buildvector-in-loop.ll b/llvm/test/Transforms/SLPVectorizer/AArch64/abs-mul-buildvector-in-loop.ll
new file mode 100644
index 0000000000000..1d1616698fc17
--- /dev/null
+++ b/llvm/test/Transforms/SLPVectorizer/AArch64/abs-mul-buildvector-in-loop.ll
@@ -0,0 +1,111 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
+; RUN: opt -S --passes=slp-vectorizer -mtriple=aarch64-linux-gnu -mcpu=cortex-a57 < %s | FileCheck %s
+
+ at lut = external constant [0 x i8]
+
+define void @test(ptr noalias %src, ptr noalias %descriptor, i32 %N) {
+; CHECK-LABEL: define void @test(
+; CHECK-SAME: ptr noalias [[SRC:%.*]], ptr noalias [[DESCRIPTOR:%.*]], i32 [[N:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT: [[ENTRY:.*]]:
+; CHECK-NEXT: [[CMP32:%.*]] = icmp sgt i32 [[N]], 0
+; CHECK-NEXT: br i1 [[CMP32]], label %[[FOR_BODY:.*]], label %[[FOR_COND_CLEANUP:.*]]
+; CHECK: [[FOR_COND_CLEANUP]]:
+; CHECK-NEXT: ret void
+; CHECK: [[FOR_BODY]]:
+; CHECK-NEXT: [[SRC_ADDR_035:%.*]] = phi ptr [ [[ARRAYIDX:%.*]], %[[FOR_BODY]] ], [ [[SRC]], %[[ENTRY]] ]
+; CHECK-NEXT: [[P_034:%.*]] = phi ptr [ [[INCDEC_PTR10:%.*]], %[[FOR_BODY]] ], [ @lut, %[[ENTRY]] ]
+; CHECK-NEXT: [[I_033:%.*]] = phi i32 [ [[INC:%.*]], %[[FOR_BODY]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT: [[ARRAYIDX]] = getelementptr inbounds nuw i8, ptr [[SRC_ADDR_035]], i64 1
+; CHECK-NEXT: [[TMP0:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
+; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[SRC_ADDR_035]], i64 -1
+; CHECK-NEXT: [[TMP1:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
+; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds nuw i8, ptr [[SRC_ADDR_035]], i64 17
+; CHECK-NEXT: [[TMP2:%.*]] = load i8, ptr [[ARRAYIDX3]], align 1
+; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i8, ptr [[SRC_ADDR_035]], i64 -17
+; CHECK-NEXT: [[TMP3:%.*]] = load i8, ptr [[ARRAYIDX5]], align 1
+; CHECK-NEXT: [[TMP4:%.*]] = load i8, ptr [[P_034]], align 1
+; CHECK-NEXT: [[CONV9:%.*]] = zext i8 [[TMP4]] to i32
+; CHECK-NEXT: [[INCDEC_PTR10]] = getelementptr inbounds nuw i8, ptr [[P_034]], i64 2
+; CHECK-NEXT: [[BIN:%.*]] = getelementptr inbounds nuw i8, ptr [[P_034]], i64 1
+; CHECK-NEXT: [[TMP5:%.*]] = load i8, ptr [[BIN]], align 1
+; CHECK-NEXT: [[IDX_EXT:%.*]] = zext i8 [[TMP5]] to i64
+; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds nuw [4 x i8], ptr [[DESCRIPTOR]], i64 [[IDX_EXT]]
+; CHECK-NEXT: [[CONV4:%.*]] = zext i8 [[TMP2]] to i32
+; CHECK-NEXT: [[CONV:%.*]] = zext i8 [[TMP0]] to i32
+; CHECK-NEXT: [[CONV6:%.*]] = zext i8 [[TMP3]] to i32
+; CHECK-NEXT: [[CONV2:%.*]] = zext i8 [[TMP1]] to i32
+; CHECK-NEXT: [[SUB7:%.*]] = sub nsw i32 [[CONV4]], [[CONV6]]
+; CHECK-NEXT: [[SUB:%.*]] = sub nsw i32 [[CONV]], [[CONV2]]
+; CHECK-NEXT: [[TMP6:%.*]] = insertelement <2 x i32> poison, i32 [[SUB]], i64 0
+; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x i32> [[TMP6]], i32 [[SUB7]], i64 1
+; CHECK-NEXT: [[TMP15:%.*]] = insertelement <2 x i32> poison, i32 [[CONV9]], i64 0
+; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <2 x i32> [[TMP15]], <2 x i32> poison, <2 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP10:%.*]] = mul nsw <2 x i32> [[TMP7]], [[TMP9]]
+; CHECK-NEXT: [[TMP11:%.*]] = call <2 x i32> @llvm.abs.v2i32(<2 x i32> [[TMP10]], i1 true)
+; CHECK-NEXT: [[TMP8:%.*]] = load <4 x i32>, ptr [[ADD_PTR]], align 4
+; CHECK-NEXT: [[TMP16:%.*]] = shufflevector <2 x i32> [[TMP10]], <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
+; CHECK-NEXT: [[TMP14:%.*]] = shufflevector <2 x i32> [[TMP11]], <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
+; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <4 x i32> [[TMP16]], <4 x i32> [[TMP14]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
+; CHECK-NEXT: [[TMP13:%.*]] = add nsw <4 x i32> [[TMP8]], [[TMP12]]
+; CHECK-NEXT: store <4 x i32> [[TMP13]], ptr [[ADD_PTR]], align 4
+; CHECK-NEXT: [[INC]] = add nuw nsw i32 [[I_033]], 1
+; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i32 [[INC]], [[N]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_COND_CLEANUP]], label %[[FOR_BODY]]
+;
+entry:
+ %cmp32 = icmp sgt i32 %N, 0
+ br i1 %cmp32, label %for.body, label %for.cond.cleanup
+
+for.cond.cleanup:
+ ret void
+
+for.body:
+ %src.addr.035 = phi ptr [ %arrayidx, %for.body ], [ %src, %entry ]
+ %p.034 = phi ptr [ %incdec.ptr10, %for.body ], [ @lut, %entry ]
+ %i.033 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
+ %arrayidx = getelementptr inbounds nuw i8, ptr %src.addr.035, i64 1
+ %0 = load i8, ptr %arrayidx, align 1
+ %conv = zext i8 %0 to i32
+ %arrayidx1 = getelementptr inbounds i8, ptr %src.addr.035, i64 -1
+ %1 = load i8, ptr %arrayidx1, align 1
+ %conv2 = zext i8 %1 to i32
+ %sub = sub nsw i32 %conv, %conv2
+ %arrayidx3 = getelementptr inbounds nuw i8, ptr %src.addr.035, i64 17
+ %2 = load i8, ptr %arrayidx3, align 1
+ %conv4 = zext i8 %2 to i32
+ %arrayidx5 = getelementptr inbounds i8, ptr %src.addr.035, i64 -17
+ %3 = load i8, ptr %arrayidx5, align 1
+ %conv6 = zext i8 %3 to i32
+ %sub7 = sub nsw i32 %conv4, %conv6
+ %4 = load i8, ptr %p.034, align 1
+ %conv9 = zext i8 %4 to i32
+ %incdec.ptr10 = getelementptr inbounds nuw i8, ptr %p.034, i64 2
+ %bin = getelementptr inbounds nuw i8, ptr %p.034, i64 1
+ %5 = load i8, ptr %bin, align 1
+ %idx.ext = zext i8 %5 to i64
+ %add.ptr = getelementptr inbounds nuw [4 x i8], ptr %descriptor, i64 %idx.ext
+ %mul = mul nsw i32 %sub, %conv9
+ %mul12 = mul nsw i32 %sub7, %conv9
+ %6 = load i32, ptr %add.ptr, align 4
+ %add = add nsw i32 %6, %mul
+ store i32 %add, ptr %add.ptr, align 4
+ %arrayidx14 = getelementptr inbounds nuw i8, ptr %add.ptr, i64 4
+ %7 = load i32, ptr %arrayidx14, align 4
+ %add15 = add nsw i32 %7, %mul12
+ store i32 %add15, ptr %arrayidx14, align 4
+ %8 = tail call i32 @llvm.abs.i32(i32 %mul, i1 true)
+ %arrayidx16 = getelementptr inbounds nuw i8, ptr %add.ptr, i64 8
+ %9 = load i32, ptr %arrayidx16, align 4
+ %add17 = add nsw i32 %9, %8
+ store i32 %add17, ptr %arrayidx16, align 4
+ %10 = tail call i32 @llvm.abs.i32(i32 %mul12, i1 true)
+ %arrayidx18 = getelementptr inbounds nuw i8, ptr %add.ptr, i64 12
+ %11 = load i32, ptr %arrayidx18, align 4
+ %add19 = add nsw i32 %11, %10
+ store i32 %add19, ptr %arrayidx18, align 4
+ %inc = add nuw nsw i32 %i.033, 1
+ %exitcond.not = icmp eq i32 %inc, %N
+ br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
+}
+
+declare i32 @llvm.abs.i32(i32, i1 immarg)
diff --git a/llvm/test/Transforms/SLPVectorizer/AArch64/long-non-power-of-2.ll b/llvm/test/Transforms/SLPVectorizer/AArch64/long-non-power-of-2.ll
index e1ca81edd2b39..c6489c2085000 100644
--- a/llvm/test/Transforms/SLPVectorizer/AArch64/long-non-power-of-2.ll
+++ b/llvm/test/Transforms/SLPVectorizer/AArch64/long-non-power-of-2.ll
@@ -7,6 +7,8 @@ define i1 @test(ptr %arg, ptr %arg1, i64 %arg2, ptr %arg3) {
; CHECK-NEXT: [[BB:.*:]]
; CHECK-NEXT: [[GETELEMENTPTR:%.*]] = getelementptr i8, ptr [[ARG1]], i64 [[ARG2]]
; CHECK-NEXT: [[GETELEMENTPTR4:%.*]] = getelementptr i8, ptr null, i64 0
+; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x ptr> <ptr null, ptr poison>, ptr [[ARG3]], i64 1
+; CHECK-NEXT: [[TMP1:%.*]] = getelementptr i8, <2 x ptr> [[TMP2]], <2 x i64> <i64 -32, i64 -432>
; CHECK-NEXT: [[GETELEMENTPTR5:%.*]] = getelementptr i8, ptr null, i64 -32
; CHECK-NEXT: [[TMP32:%.*]] = getelementptr i8, ptr [[ARG3]], i64 -440
; CHECK-NEXT: [[GETELEMENTPTR7:%.*]] = getelementptr i8, ptr [[ARG1]], i64 0
@@ -28,8 +30,8 @@ define i1 @test(ptr %arg, ptr %arg1, i64 %arg2, ptr %arg3) {
; CHECK-NEXT: [[AND25:%.*]] = and i1 false, [[ICMP24]]
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x ptr> <ptr poison, ptr poison, ptr null, ptr null>, ptr [[ARG]], i64 1
; CHECK-NEXT: [[TMP19:%.*]] = insertelement <4 x ptr> [[TMP0]], ptr [[GETELEMENTPTR7]], i64 0
-; CHECK-NEXT: [[TMP2:%.*]] = insertelement <4 x ptr> <ptr poison, ptr poison, ptr null, ptr null>, ptr [[GETELEMENTPTR5]], i64 0
-; CHECK-NEXT: [[TMP7:%.*]] = insertelement <4 x ptr> [[TMP2]], ptr [[GETELEMENTPTR8]], i64 1
+; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <2 x ptr> [[TMP1]], <2 x ptr> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
+; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <4 x ptr> <ptr poison, ptr poison, ptr null, ptr null>, <4 x ptr> [[TMP4]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; CHECK-NEXT: [[TMP20:%.*]] = icmp ult <4 x ptr> [[TMP19]], [[TMP7]]
; CHECK-NEXT: [[ICMP58:%.*]] = icmp ult ptr [[GETELEMENTPTR]], null
; CHECK-NEXT: [[ICMP62:%.*]] = icmp ult ptr [[GETELEMENTPTR]], null
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/deleted-instructions-clear.ll b/llvm/test/Transforms/SLPVectorizer/X86/deleted-instructions-clear.ll
index ae6da0913cc24..94631869b15fe 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/deleted-instructions-clear.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/deleted-instructions-clear.ll
@@ -7,7 +7,7 @@ define void @test(i32 %arg, i32 %arg1, i64 %arg2) {
; CHECK-NEXT: [[BB:.*]]:
; CHECK-NEXT: [[TMP11:%.*]] = insertelement <4 x i32> <i32 0, i32 0, i32 0, i32 poison>, i32 [[ARG]], i64 3
; CHECK-NEXT: [[TMP27:%.*]] = insertelement <2 x i32> poison, i32 [[ARG1]], i64 0
-; CHECK-NEXT: [[TMP28:%.*]] = shufflevector <2 x i32> [[TMP27]], <2 x i32> poison, <2 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP29:%.*]] = insertelement <2 x i32> <i32 0, i32 poison>, i32 [[ARG]], i64 1
; CHECK-NEXT: br label %[[BB3:.*]]
; CHECK: [[BB3]]:
; CHECK-NEXT: [[TMP3:%.*]] = phi i64 [ 0, %[[BB3]] ], [ 0, %[[BB]] ]
@@ -28,9 +28,9 @@ define void @test(i32 %arg, i32 %arg1, i64 %arg2) {
; CHECK-NEXT: [[OR11:%.*]] = or i32 [[TRUNC27]], 0
; CHECK-NEXT: [[TMP8:%.*]] = or <4 x i32> zeroinitializer, [[TMP2]]
; CHECK-NEXT: [[TMP9:%.*]] = mul <4 x i32> [[TMP5]], [[TMP8]]
-; CHECK-NEXT: [[XOR38:%.*]] = xor i32 [[ARG]], [[TRUNC28]]
-; CHECK-NEXT: [[TMP29:%.*]] = insertelement <2 x i32> <i32 poison, i32 0>, i32 [[TRUNC19]], i64 0
+; CHECK-NEXT: [[TMP28:%.*]] = insertelement <2 x i32> [[TMP27]], i32 [[TRUNC28]], i64 1
; CHECK-NEXT: [[TMP14:%.*]] = xor <2 x i32> [[TMP28]], [[TMP29]]
+; CHECK-NEXT: [[XOR31:%.*]] = xor i32 [[ARG1]], [[TRUNC19]]
; CHECK-NEXT: [[SHL:%.*]] = shl i32 0, 1
; CHECK-NEXT: [[TMP23:%.*]] = insertelement <4 x i32> poison, i32 [[SHL]], i64 0
; CHECK-NEXT: [[TMP31:%.*]] = insertelement <4 x i32> [[TMP23]], i32 [[TRUNC10]], i64 1
@@ -38,9 +38,9 @@ define void @test(i32 %arg, i32 %arg1, i64 %arg2) {
; CHECK-NEXT: [[TMP25:%.*]] = shufflevector <4 x i32> [[TMP13]], <4 x i32> poison, <4 x i32> <i32 0, i32 1, i32 0, i32 3>
; CHECK-NEXT: [[TMP26:%.*]] = xor <4 x i32> [[TMP11]], [[TMP25]]
; CHECK-NEXT: [[TMP24:%.*]] = shufflevector <4 x i32> [[TMP26]], <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
+; CHECK-NEXT: [[TMP32:%.*]] = insertelement <8 x i32> [[TMP24]], i32 [[XOR31]], i64 5
; CHECK-NEXT: [[TMP30:%.*]] = shufflevector <2 x i32> [[TMP14]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
-; CHECK-NEXT: [[TMP15:%.*]] = shufflevector <8 x i32> [[TMP24]], <8 x i32> [[TMP30]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 8, i32 9, i32 7>
-; CHECK-NEXT: [[TMP16:%.*]] = insertelement <8 x i32> [[TMP15]], i32 [[XOR38]], i64 7
+; CHECK-NEXT: [[TMP16:%.*]] = shufflevector <8 x i32> [[TMP32]], <8 x i32> [[TMP30]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; CHECK-NEXT: [[TMP17:%.*]] = shufflevector <8 x i32> [[TMP16]], <8 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 5, i32 6, i32 7>
; CHECK-NEXT: [[TMP18:%.*]] = shufflevector <8 x i32> [[TMP17]], <8 x i32> poison, <12 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP19:%.*]] = shufflevector <4 x i32> [[TMP9]], <4 x i32> poison, <12 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/multi-parent-instr-copyable-regular.ll b/llvm/test/Transforms/SLPVectorizer/X86/multi-parent-instr-copyable-regular.ll
index d7ba46ff439a6..239bc9ed64dc1 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/multi-parent-instr-copyable-regular.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/multi-parent-instr-copyable-regular.ll
@@ -9,21 +9,23 @@ define void @test(ptr %0, ptr %1, ptr %2, ptr %3, double %4, double %5) {
; CHECK-NEXT: [[TMP7:%.*]] = load double, ptr [[TMP1]], align 8
; CHECK-NEXT: [[TMP8:%.*]] = load double, ptr [[TMP0]], align 8
; CHECK-NEXT: [[TMP9:%.*]] = load double, ptr [[TMP2]], align 8
-; CHECK-NEXT: [[TMP15:%.*]] = fmul double [[TMP9]], 0.000000e+00
-; CHECK-NEXT: [[TMP16:%.*]] = fmul double [[TMP4]], 0.000000e+00
; CHECK-NEXT: [[TMP19:%.*]] = insertelement <4 x double> poison, double [[TMP4]], i64 0
; CHECK-NEXT: [[TMP11:%.*]] = insertelement <4 x double> [[TMP19]], double [[TMP5]], i64 1
; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <4 x double> [[TMP11]], <4 x double> poison, <4 x i32> <i32 0, i32 1, i32 1, i32 0>
; CHECK-NEXT: [[TMP13:%.*]] = insertelement <4 x double> <double 0.000000e+00, double 0.000000e+00, double 1.000000e+00, double poison>, double [[TMP4]], i64 3
; CHECK-NEXT: [[TMP14:%.*]] = fmul <4 x double> [[TMP12]], [[TMP13]]
-; CHECK-NEXT: [[TMP17:%.*]] = fmul double [[TMP15]], [[TMP8]]
-; CHECK-NEXT: [[TMP18:%.*]] = fmul double [[TMP9]], [[TMP16]]
+; CHECK-NEXT: [[TMP15:%.*]] = insertelement <2 x double> poison, double [[TMP4]], i64 0
+; CHECK-NEXT: [[TMP16:%.*]] = insertelement <2 x double> [[TMP15]], double [[TMP9]], i64 1
+; CHECK-NEXT: [[TMP17:%.*]] = fmul <2 x double> [[TMP16]], zeroinitializer
+; CHECK-NEXT: [[TMP18:%.*]] = insertelement <2 x double> poison, double [[TMP9]], i64 0
+; CHECK-NEXT: [[TMP35:%.*]] = insertelement <2 x double> [[TMP18]], double [[TMP8]], i64 1
+; CHECK-NEXT: [[TMP20:%.*]] = fmul <2 x double> [[TMP35]], [[TMP17]]
; CHECK-NEXT: [[TMP21:%.*]] = shufflevector <4 x double> [[TMP12]], <4 x double> <double 1.000000e+00, double 1.000000e+00, double poison, double poison>, <4 x i32> <i32 4, i32 5, i32 0, i32 0>
; CHECK-NEXT: [[TMP22:%.*]] = fmul <4 x double> [[TMP12]], [[TMP21]]
; CHECK-NEXT: [[TMP23:%.*]] = insertelement <4 x double> <double 0.000000e+00, double poison, double 1.000000e+00, double 0.000000e+00>, double [[TMP7]], i64 1
; CHECK-NEXT: [[TMP24:%.*]] = fmul <4 x double> [[TMP23]], [[TMP14]]
-; CHECK-NEXT: [[TMP25:%.*]] = insertelement <4 x double> [[TMP24]], double [[TMP18]], i64 0
-; CHECK-NEXT: [[TMP26:%.*]] = insertelement <4 x double> [[TMP25]], double [[TMP17]], i64 2
+; CHECK-NEXT: [[TMP25:%.*]] = shufflevector <2 x double> [[TMP20]], <2 x double> poison, <4 x i32> <i32 0, i32 poison, i32 1, i32 poison>
+; CHECK-NEXT: [[TMP26:%.*]] = shufflevector <4 x double> [[TMP24]], <4 x double> [[TMP25]], <4 x i32> <i32 4, i32 1, i32 6, i32 3>
; CHECK-NEXT: [[TMP27:%.*]] = shufflevector <4 x double> [[TMP26]], <4 x double> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 2>
; CHECK-NEXT: [[TMP28:%.*]] = fmul <4 x double> [[TMP27]], zeroinitializer
; CHECK-NEXT: [[TMP29:%.*]] = fmul <4 x double> [[TMP22]], <double 1.000000e+00, double 1.000000e+00, double 0.000000e+00, double 0.000000e+00>
``````````
</details>
https://github.com/llvm/llvm-project/pull/217569
More information about the llvm-branch-commits
mailing list