diff options
Diffstat (limited to 'llvm/test')
5 files changed, 384 insertions, 52 deletions
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/jumbled-load-multiuse.ll b/llvm/test/Transforms/SLPVectorizer/X86/jumbled-load-multiuse.ll index 557a83a7562..4def8ce561c 100644 --- a/llvm/test/Transforms/SLPVectorizer/X86/jumbled-load-multiuse.ll +++ b/llvm/test/Transforms/SLPVectorizer/X86/jumbled-load-multiuse.ll @@ -11,20 +11,16 @@ define i32 @fn1() { ; CHECK-LABEL: @fn1( ; CHECK-NEXT: entry: -; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* getelementptr inbounds ([4 x i32], [4 x i32]* @b, i64 0, i32 0), align 4 -; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* getelementptr inbounds ([4 x i32], [4 x i32]* @b, i64 0, i32 1), align 4 -; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* getelementptr inbounds ([4 x i32], [4 x i32]* @b, i64 0, i32 2), align 4 -; CHECK-NEXT: [[TMP3:%.*]] = load i32, i32* getelementptr inbounds ([4 x i32], [4 x i32]* @b, i64 0, i32 3), align 4 -; CHECK-NEXT: [[TMP4:%.*]] = insertelement <4 x i32> undef, i32 [[TMP1]], i32 0 -; CHECK-NEXT: [[TMP5:%.*]] = insertelement <4 x i32> [[TMP4]], i32 [[TMP2]], i32 1 -; CHECK-NEXT: [[TMP6:%.*]] = insertelement <4 x i32> [[TMP5]], i32 [[TMP3]], i32 2 -; CHECK-NEXT: [[TMP7:%.*]] = insertelement <4 x i32> [[TMP6]], i32 [[TMP0]], i32 3 -; CHECK-NEXT: [[TMP8:%.*]] = icmp sgt <4 x i32> [[TMP7]], zeroinitializer -; CHECK-NEXT: [[TMP9:%.*]] = insertelement <4 x i32> [[TMP4]], i32 ptrtoint (i32 ()* @fn1 to i32), i32 1 -; CHECK-NEXT: [[TMP10:%.*]] = insertelement <4 x i32> [[TMP9]], i32 ptrtoint (i32 ()* @fn1 to i32), i32 2 -; CHECK-NEXT: [[TMP11:%.*]] = insertelement <4 x i32> [[TMP10]], i32 8, i32 3 -; CHECK-NEXT: [[TMP12:%.*]] = select <4 x i1> [[TMP8]], <4 x i32> [[TMP11]], <4 x i32> <i32 6, i32 0, i32 0, i32 0> -; CHECK-NEXT: store <4 x i32> [[TMP12]], <4 x i32>* bitcast ([4 x i32]* @a to <4 x i32>*), align 4 +; CHECK-NEXT: [[TMP0:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([4 x i32]* @b to <4 x i32>*), align 4 +; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> undef, <4 x i32> <i32 1, i32 2, i32 3, i32 0> +; CHECK-NEXT: [[TMP2:%.*]] = icmp sgt <4 x i32> [[TMP1]], zeroinitializer +; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x i32> [[TMP0]], i32 1 +; CHECK-NEXT: [[TMP4:%.*]] = insertelement <4 x i32> undef, i32 [[TMP3]], i32 0 +; CHECK-NEXT: [[TMP5:%.*]] = insertelement <4 x i32> [[TMP4]], i32 ptrtoint (i32 ()* @fn1 to i32), i32 1 +; CHECK-NEXT: [[TMP6:%.*]] = insertelement <4 x i32> [[TMP5]], i32 ptrtoint (i32 ()* @fn1 to i32), i32 2 +; CHECK-NEXT: [[TMP7:%.*]] = insertelement <4 x i32> [[TMP6]], i32 8, i32 3 +; CHECK-NEXT: [[TMP8:%.*]] = select <4 x i1> [[TMP2]], <4 x i32> [[TMP7]], <4 x i32> <i32 6, i32 0, i32 0, i32 0> +; CHECK-NEXT: store <4 x i32> [[TMP8]], <4 x i32>* bitcast ([4 x i32]* @a to <4 x i32>*), align 4 ; CHECK-NEXT: ret i32 0 ; entry: diff --git a/llvm/test/Transforms/SLPVectorizer/X86/jumbled-load-shuffle-placement.ll b/llvm/test/Transforms/SLPVectorizer/X86/jumbled-load-shuffle-placement.ll new file mode 100644 index 00000000000..5fc0298b6ce --- /dev/null +++ b/llvm/test/Transforms/SLPVectorizer/X86/jumbled-load-shuffle-placement.ll @@ -0,0 +1,125 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py +; RUN: opt < %s -S -mtriple=x86_64-unknown -mattr=+avx -slp-vectorizer | FileCheck %s + + +;void jumble (int * restrict A, int * restrict B) { + ; int tmp0 = A[10]*A[0]; + ; int tmp1 = A[11]*A[1]; + ; int tmp2 = A[12]*A[3]; + ; int tmp3 = A[13]*A[2]; + ; B[0] = tmp0; + ; B[1] = tmp1; + ; B[2] = tmp2; + ; B[3] = tmp3; + ;} + + + ; Function Attrs: norecurse nounwind uwtable + define void @jumble1(i32* noalias nocapture readonly %A, i32* noalias nocapture %B) { +; CHECK-LABEL: @jumble1( +; CHECK-NEXT: entry: +; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 10 +; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 11 +; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 1 +; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 12 +; CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 3 +; CHECK-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 13 +; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[ARRAYIDX]] to <4 x i32>* +; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4 +; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 2 +; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[A]] to <4 x i32>* +; CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP2]], align 4 +; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> undef, <4 x i32> <i32 0, i32 1, i32 3, i32 2> +; CHECK-NEXT: [[TMP5:%.*]] = mul nsw <4 x i32> [[TMP1]], [[TMP4]] +; CHECK-NEXT: [[ARRAYIDX12:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 1 +; CHECK-NEXT: [[ARRAYIDX13:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 2 +; CHECK-NEXT: [[ARRAYIDX14:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 3 +; CHECK-NEXT: [[TMP6:%.*]] = bitcast i32* [[B]] to <4 x i32>* +; CHECK-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP6]], align 4 +; CHECK-NEXT: ret void +; +entry: + %arrayidx = getelementptr inbounds i32, i32* %A, i64 10 + %0 = load i32, i32* %arrayidx, align 4 + %1 = load i32, i32* %A, align 4 + %mul = mul nsw i32 %0, %1 + %arrayidx2 = getelementptr inbounds i32, i32* %A, i64 11 + %2 = load i32, i32* %arrayidx2, align 4 + %arrayidx3 = getelementptr inbounds i32, i32* %A, i64 1 + %3 = load i32, i32* %arrayidx3, align 4 + %mul4 = mul nsw i32 %2, %3 + %arrayidx5 = getelementptr inbounds i32, i32* %A, i64 12 + %4 = load i32, i32* %arrayidx5, align 4 + %arrayidx6 = getelementptr inbounds i32, i32* %A, i64 3 + %5 = load i32, i32* %arrayidx6, align 4 + %mul7 = mul nsw i32 %4, %5 + %arrayidx8 = getelementptr inbounds i32, i32* %A, i64 13 + %6 = load i32, i32* %arrayidx8, align 4 + %arrayidx9 = getelementptr inbounds i32, i32* %A, i64 2 + %7 = load i32, i32* %arrayidx9, align 4 + %mul10 = mul nsw i32 %6, %7 + store i32 %mul, i32* %B, align 4 + %arrayidx12 = getelementptr inbounds i32, i32* %B, i64 1 + store i32 %mul4, i32* %arrayidx12, align 4 + %arrayidx13 = getelementptr inbounds i32, i32* %B, i64 2 + store i32 %mul7, i32* %arrayidx13, align 4 + %arrayidx14 = getelementptr inbounds i32, i32* %B, i64 3 + store i32 %mul10, i32* %arrayidx14, align 4 + ret void + } + +;Reversing the operand of MUL + ; Function Attrs: norecurse nounwind uwtable + define void @jumble2(i32* noalias nocapture readonly %A, i32* noalias nocapture %B) { +; CHECK-LABEL: @jumble2( +; CHECK-NEXT: entry: +; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 10 +; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 11 +; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 1 +; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 12 +; CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 3 +; CHECK-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 13 +; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[ARRAYIDX]] to <4 x i32>* +; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4 +; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 2 +; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[A]] to <4 x i32>* +; CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP2]], align 4 +; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> undef, <4 x i32> <i32 0, i32 1, i32 3, i32 2> +; CHECK-NEXT: [[TMP5:%.*]] = mul nsw <4 x i32> [[TMP4]], [[TMP1]] +; CHECK-NEXT: [[ARRAYIDX12:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 1 +; CHECK-NEXT: [[ARRAYIDX13:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 2 +; CHECK-NEXT: [[ARRAYIDX14:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 3 +; CHECK-NEXT: [[TMP6:%.*]] = bitcast i32* [[B]] to <4 x i32>* +; CHECK-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP6]], align 4 +; CHECK-NEXT: ret void +; +entry: + %arrayidx = getelementptr inbounds i32, i32* %A, i64 10 + %0 = load i32, i32* %arrayidx, align 4 + %1 = load i32, i32* %A, align 4 + %mul = mul nsw i32 %1, %0 + %arrayidx2 = getelementptr inbounds i32, i32* %A, i64 11 + %2 = load i32, i32* %arrayidx2, align 4 + %arrayidx3 = getelementptr inbounds i32, i32* %A, i64 1 + %3 = load i32, i32* %arrayidx3, align 4 + %mul4 = mul nsw i32 %3, %2 + %arrayidx5 = getelementptr inbounds i32, i32* %A, i64 12 + %4 = load i32, i32* %arrayidx5, align 4 + %arrayidx6 = getelementptr inbounds i32, i32* %A, i64 3 + %5 = load i32, i32* %arrayidx6, align 4 + %mul7 = mul nsw i32 %5, %4 + %arrayidx8 = getelementptr inbounds i32, i32* %A, i64 13 + %6 = load i32, i32* %arrayidx8, align 4 + %arrayidx9 = getelementptr inbounds i32, i32* %A, i64 2 + %7 = load i32, i32* %arrayidx9, align 4 + %mul10 = mul nsw i32 %7, %6 + store i32 %mul, i32* %B, align 4 + %arrayidx12 = getelementptr inbounds i32, i32* %B, i64 1 + store i32 %mul4, i32* %arrayidx12, align 4 + %arrayidx13 = getelementptr inbounds i32, i32* %B, i64 2 + store i32 %mul7, i32* %arrayidx13, align 4 + %arrayidx14 = getelementptr inbounds i32, i32* %B, i64 3 + store i32 %mul10, i32* %arrayidx14, align 4 + ret void + } + diff --git a/llvm/test/Transforms/SLPVectorizer/X86/jumbled-load-used-in-phi.ll b/llvm/test/Transforms/SLPVectorizer/X86/jumbled-load-used-in-phi.ll new file mode 100644 index 00000000000..568fd9f3ac7 --- /dev/null +++ b/llvm/test/Transforms/SLPVectorizer/X86/jumbled-load-used-in-phi.ll @@ -0,0 +1,225 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py +; RUN: opt < %s -S -mtriple=x86_64-unknown -mattr=+avx -slp-vectorizer | FileCheck %s + +;void phiUsingLoads(int *restrict A, int *restrict B) { +; int tmp0, tmp1, tmp2, tmp3; +; for (int i = 0; i < 100; i++) { +; if (A[0] == 0) { +; tmp0 = A[i + 0]; +; tmp1 = A[i + 1]; +; tmp2 = A[i + 2]; +; tmp3 = A[i + 3]; +; } else if (A[25] == 0) { +; tmp0 = A[i + 0]; +; tmp1 = A[i + 1]; +; tmp2 = A[i + 2]; +; tmp3 = A[i + 3]; +; } else if (A[50] == 0) { +; tmp0 = A[i + 0]; +; tmp1 = A[i + 1]; +; tmp2 = A[i + 2]; +; tmp3 = A[i + 3]; +; } else if (A[75] == 0) { +; tmp0 = A[i + 0]; +; tmp1 = A[i + 1]; +; tmp2 = A[i + 3]; +; tmp3 = A[i + 2]; +; } +; } +; B[0] = tmp0; +; B[1] = tmp1; +; B[2] = tmp2; +; B[3] = tmp3; +;} + + +; Function Attrs: norecurse nounwind uwtable +define void @phiUsingLoads(i32* noalias nocapture readonly %A, i32* noalias nocapture %B) local_unnamed_addr #0 { +; CHECK-LABEL: @phiUsingLoads( +; CHECK-NEXT: entry: +; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[A:%.*]], align 4 +; CHECK-NEXT: [[CMP1:%.*]] = icmp eq i32 [[TMP0]], 0 +; CHECK-NEXT: [[ARRAYIDX12:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 25 +; CHECK-NEXT: [[ARRAYIDX28:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 50 +; CHECK-NEXT: [[ARRAYIDX44:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 75 +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.cond.cleanup: +; CHECK-NEXT: [[ARRAYIDX64:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 1 +; CHECK-NEXT: [[ARRAYIDX65:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 2 +; CHECK-NEXT: [[ARRAYIDX66:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 3 +; CHECK-NEXT: [[TMP1:%.*]] = bitcast i32* [[B]] to <4 x i32>* +; CHECK-NEXT: store <4 x i32> [[TMP27:%.*]], <4 x i32>* [[TMP1]], align 4 +; CHECK-NEXT: ret void +; CHECK: for.body: +; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ] +; CHECK-NEXT: [[TMP2:%.*]] = phi <4 x i32> [ undef, [[ENTRY]] ], [ [[TMP27]], [[FOR_INC]] ] +; CHECK-NEXT: br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]] +; CHECK: if.then: +; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[INDVARS_IV]] +; CHECK-NEXT: [[TMP3:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 1 +; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP3]] +; CHECK-NEXT: [[TMP4:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 2 +; CHECK-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP4]] +; CHECK-NEXT: [[TMP5:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 3 +; CHECK-NEXT: [[ARRAYIDX11:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP5]] +; CHECK-NEXT: [[TMP6:%.*]] = bitcast i32* [[ARRAYIDX2]] to <4 x i32>* +; CHECK-NEXT: [[TMP7:%.*]] = load <4 x i32>, <4 x i32>* [[TMP6]], align 4 +; CHECK-NEXT: br label [[FOR_INC]] +; CHECK: if.else: +; CHECK-NEXT: [[TMP8:%.*]] = load i32, i32* [[ARRAYIDX12]], align 4 +; CHECK-NEXT: [[CMP13:%.*]] = icmp eq i32 [[TMP8]], 0 +; CHECK-NEXT: br i1 [[CMP13]], label [[IF_THEN14:%.*]], label [[IF_ELSE27:%.*]] +; CHECK: if.then14: +; CHECK-NEXT: [[ARRAYIDX17:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[INDVARS_IV]] +; CHECK-NEXT: [[TMP9:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 1 +; CHECK-NEXT: [[ARRAYIDX20:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP9]] +; CHECK-NEXT: [[TMP10:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 2 +; CHECK-NEXT: [[ARRAYIDX23:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP10]] +; CHECK-NEXT: [[TMP11:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 3 +; CHECK-NEXT: [[ARRAYIDX26:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP11]] +; CHECK-NEXT: [[TMP12:%.*]] = bitcast i32* [[ARRAYIDX17]] to <4 x i32>* +; CHECK-NEXT: [[TMP13:%.*]] = load <4 x i32>, <4 x i32>* [[TMP12]], align 4 +; CHECK-NEXT: br label [[FOR_INC]] +; CHECK: if.else27: +; CHECK-NEXT: [[TMP14:%.*]] = load i32, i32* [[ARRAYIDX28]], align 4 +; CHECK-NEXT: [[CMP29:%.*]] = icmp eq i32 [[TMP14]], 0 +; CHECK-NEXT: br i1 [[CMP29]], label [[IF_THEN30:%.*]], label [[IF_ELSE43:%.*]] +; CHECK: if.then30: +; CHECK-NEXT: [[ARRAYIDX33:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[INDVARS_IV]] +; CHECK-NEXT: [[TMP15:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 1 +; CHECK-NEXT: [[ARRAYIDX36:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP15]] +; CHECK-NEXT: [[TMP16:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 2 +; CHECK-NEXT: [[ARRAYIDX39:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP16]] +; CHECK-NEXT: [[TMP17:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 3 +; CHECK-NEXT: [[ARRAYIDX42:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP17]] +; CHECK-NEXT: [[TMP18:%.*]] = bitcast i32* [[ARRAYIDX33]] to <4 x i32>* +; CHECK-NEXT: [[TMP19:%.*]] = load <4 x i32>, <4 x i32>* [[TMP18]], align 4 +; CHECK-NEXT: br label [[FOR_INC]] +; CHECK: if.else43: +; CHECK-NEXT: [[TMP20:%.*]] = load i32, i32* [[ARRAYIDX44]], align 4 +; CHECK-NEXT: [[CMP45:%.*]] = icmp eq i32 [[TMP20]], 0 +; CHECK-NEXT: br i1 [[CMP45]], label [[IF_THEN46:%.*]], label [[FOR_INC]] +; CHECK: if.then46: +; CHECK-NEXT: [[ARRAYIDX49:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[INDVARS_IV]] +; CHECK-NEXT: [[TMP21:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 1 +; CHECK-NEXT: [[ARRAYIDX52:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP21]] +; CHECK-NEXT: [[TMP22:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 3 +; CHECK-NEXT: [[ARRAYIDX55:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP22]] +; CHECK-NEXT: [[TMP23:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 2 +; CHECK-NEXT: [[ARRAYIDX58:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP23]] +; CHECK-NEXT: [[TMP24:%.*]] = bitcast i32* [[ARRAYIDX49]] to <4 x i32>* +; CHECK-NEXT: [[TMP25:%.*]] = load <4 x i32>, <4 x i32>* [[TMP24]], align 4 +; CHECK-NEXT: [[TMP26:%.*]] = shufflevector <4 x i32> [[TMP25]], <4 x i32> undef, <4 x i32> <i32 0, i32 1, i32 3, i32 2> +; CHECK-NEXT: br label [[FOR_INC]] +; CHECK: for.inc: +; CHECK-NEXT: [[TMP27]] = phi <4 x i32> [ [[TMP7]], [[IF_THEN]] ], [ [[TMP13]], [[IF_THEN14]] ], [ [[TMP19]], [[IF_THEN30]] ], [ [[TMP26]], [[IF_THEN46]] ], [ [[TMP2]], [[IF_ELSE43]] ] +; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1 +; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 100 +; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]] +; +entry: + %0 = load i32, i32* %A, align 4 + %cmp1 = icmp eq i32 %0, 0 + %arrayidx12 = getelementptr inbounds i32, i32* %A, i64 25 + %arrayidx28 = getelementptr inbounds i32, i32* %A, i64 50 + %arrayidx44 = getelementptr inbounds i32, i32* %A, i64 75 + br label %for.body + +for.cond.cleanup: ; preds = %for.inc + store i32 %tmp0.1, i32* %B, align 4 + %arrayidx64 = getelementptr inbounds i32, i32* %B, i64 1 + store i32 %tmp1.1, i32* %arrayidx64, align 4 + %arrayidx65 = getelementptr inbounds i32, i32* %B, i64 2 + store i32 %tmp2.1, i32* %arrayidx65, align 4 + %arrayidx66 = getelementptr inbounds i32, i32* %B, i64 3 + store i32 %tmp3.1, i32* %arrayidx66, align 4 + ret void + +for.body: ; preds = %for.inc, %entry + %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.inc ] + %tmp3.0111 = phi i32 [ undef, %entry ], [ %tmp3.1, %for.inc ] + %tmp2.0110 = phi i32 [ undef, %entry ], [ %tmp2.1, %for.inc ] + %tmp1.0109 = phi i32 [ undef, %entry ], [ %tmp1.1, %for.inc ] + %tmp0.0108 = phi i32 [ undef, %entry ], [ %tmp0.1, %for.inc ] + br i1 %cmp1, label %if.then, label %if.else + +if.then: ; preds = %for.body + %arrayidx2 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv + %1 = load i32, i32* %arrayidx2, align 4 + %2 = add nuw nsw i64 %indvars.iv, 1 + %arrayidx5 = getelementptr inbounds i32, i32* %A, i64 %2 + %3 = load i32, i32* %arrayidx5, align 4 + %4 = add nuw nsw i64 %indvars.iv, 2 + %arrayidx8 = getelementptr inbounds i32, i32* %A, i64 %4 + %5 = load i32, i32* %arrayidx8, align 4 + %6 = add nuw nsw i64 %indvars.iv, 3 + %arrayidx11 = getelementptr inbounds i32, i32* %A, i64 %6 + %7 = load i32, i32* %arrayidx11, align 4 + br label %for.inc + +if.else: ; preds = %for.body + %8 = load i32, i32* %arrayidx12, align 4 + %cmp13 = icmp eq i32 %8, 0 + br i1 %cmp13, label %if.then14, label %if.else27 + +if.then14: ; preds = %if.else + %arrayidx17 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv + %9 = load i32, i32* %arrayidx17, align 4 + %10 = add nuw nsw i64 %indvars.iv, 1 + %arrayidx20 = getelementptr inbounds i32, i32* %A, i64 %10 + %11 = load i32, i32* %arrayidx20, align 4 + %12 = add nuw nsw i64 %indvars.iv, 2 + %arrayidx23 = getelementptr inbounds i32, i32* %A, i64 %12 + %13 = load i32, i32* %arrayidx23, align 4 + %14 = add nuw nsw i64 %indvars.iv, 3 + %arrayidx26 = getelementptr inbounds i32, i32* %A, i64 %14 + %15 = load i32, i32* %arrayidx26, align 4 + br label %for.inc + +if.else27: ; preds = %if.else + %16 = load i32, i32* %arrayidx28, align 4 + %cmp29 = icmp eq i32 %16, 0 + br i1 %cmp29, label %if.then30, label %if.else43 + +if.then30: ; preds = %if.else27 + %arrayidx33 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv + %17 = load i32, i32* %arrayidx33, align 4 + %18 = add nuw nsw i64 %indvars.iv, 1 + %arrayidx36 = getelementptr inbounds i32, i32* %A, i64 %18 + %19 = load i32, i32* %arrayidx36, align 4 + %20 = add nuw nsw i64 %indvars.iv, 2 + %arrayidx39 = getelementptr inbounds i32, i32* %A, i64 %20 + %21 = load i32, i32* %arrayidx39, align 4 + %22 = add nuw nsw i64 %indvars.iv, 3 + %arrayidx42 = getelementptr inbounds i32, i32* %A, i64 %22 + %23 = load i32, i32* %arrayidx42, align 4 + br label %for.inc + +if.else43: ; preds = %if.else27 + %24 = load i32, i32* %arrayidx44, align 4 + %cmp45 = icmp eq i32 %24, 0 + br i1 %cmp45, label %if.then46, label %for.inc + +if.then46: ; preds = %if.else43 + %arrayidx49 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv + %25 = load i32, i32* %arrayidx49, align 4 + %26 = add nuw nsw i64 %indvars.iv, 1 + %arrayidx52 = getelementptr inbounds i32, i32* %A, i64 %26 + %27 = load i32, i32* %arrayidx52, align 4 + %28 = add nuw nsw i64 %indvars.iv, 3 + %arrayidx55 = getelementptr inbounds i32, i32* %A, i64 %28 + %29 = load i32, i32* %arrayidx55, align 4 + %30 = add nuw nsw i64 %indvars.iv, 2 + %arrayidx58 = getelementptr inbounds i32, i32* %A, i64 %30 + %31 = load i32, i32* %arrayidx58, align 4 + br label %for.inc + +for.inc: ; preds = %if.then, %if.then30, %if.else43, %if.then46, %if.then14 + %tmp0.1 = phi i32 [ %1, %if.then ], [ %9, %if.then14 ], [ %17, %if.then30 ], [ %25, %if.then46 ], [ %tmp0.0108, %if.else43 ] + %tmp1.1 = phi i32 [ %3, %if.then ], [ %11, %if.then14 ], [ %19, %if.then30 ], [ %27, %if.then46 ], [ %tmp1.0109, %if.else43 ] + %tmp2.1 = phi i32 [ %5, %if.then ], [ %13, %if.then14 ], [ %21, %if.then30 ], [ %29, %if.then46 ], [ %tmp2.0110, %if.else43 ] + %tmp3.1 = phi i32 [ %7, %if.then ], [ %15, %if.then14 ], [ %23, %if.then30 ], [ %31, %if.then46 ], [ %tmp3.0111, %if.else43 ] + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 + %exitcond = icmp eq i64 %indvars.iv.next, 100 + br i1 %exitcond, label %for.cond.cleanup, label %for.body +} diff --git a/llvm/test/Transforms/SLPVectorizer/X86/jumbled-load.ll b/llvm/test/Transforms/SLPVectorizer/X86/jumbled-load.ll index 06e051a90b0..be58521ed89 100644 --- a/llvm/test/Transforms/SLPVectorizer/X86/jumbled-load.ll +++ b/llvm/test/Transforms/SLPVectorizer/X86/jumbled-load.ll @@ -5,34 +5,27 @@ define i32 @jumbled-load(i32* noalias nocapture %in, i32* noalias nocapture %inn, i32* noalias nocapture %out) { ; CHECK-LABEL: @jumbled-load( -; CHECK-NEXT: [[IN_ADDR:%.*]] = getelementptr inbounds i32, i32* %in, i64 0 -; CHECK-NEXT: [[LOAD_1:%.*]] = load i32, i32* [[IN_ADDR]], align 4 +; CHECK-NEXT: [[IN_ADDR:%.*]] = getelementptr inbounds i32, i32* [[IN:%.*]], i64 0 ; CHECK-NEXT: [[GEP_1:%.*]] = getelementptr inbounds i32, i32* [[IN_ADDR]], i64 3 -; CHECK-NEXT: [[LOAD_2:%.*]] = load i32, i32* [[GEP_1]], align 4 ; CHECK-NEXT: [[GEP_2:%.*]] = getelementptr inbounds i32, i32* [[IN_ADDR]], i64 1 -; CHECK-NEXT: [[LOAD_3:%.*]] = load i32, i32* [[GEP_2]], align 4 ; CHECK-NEXT: [[GEP_3:%.*]] = getelementptr inbounds i32, i32* [[IN_ADDR]], i64 2 -; CHECK-NEXT: [[LOAD_4:%.*]] = load i32, i32* [[GEP_3]], align 4 -; CHECK-NEXT: [[INN_ADDR:%.*]] = getelementptr inbounds i32, i32* %inn, i64 0 -; CHECK-NEXT: [[LOAD_5:%.*]] = load i32, i32* [[INN_ADDR]], align 4 +; CHECK-NEXT: [[TMP1:%.*]] = bitcast i32* [[IN_ADDR]] to <4 x i32>* +; CHECK-NEXT: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP1]], align 4 +; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> undef, <4 x i32> <i32 1, i32 3, i32 2, i32 0> +; CHECK-NEXT: [[INN_ADDR:%.*]] = getelementptr inbounds i32, i32* [[INN:%.*]], i64 0 ; CHECK-NEXT: [[GEP_4:%.*]] = getelementptr inbounds i32, i32* [[INN_ADDR]], i64 2 -; CHECK-NEXT: [[LOAD_6:%.*]] = load i32, i32* [[GEP_4]], align 4 ; CHECK-NEXT: [[GEP_5:%.*]] = getelementptr inbounds i32, i32* [[INN_ADDR]], i64 3 -; CHECK-NEXT: [[LOAD_7:%.*]] = load i32, i32* [[GEP_5]], align 4 ; CHECK-NEXT: [[GEP_6:%.*]] = getelementptr inbounds i32, i32* [[INN_ADDR]], i64 1 -; CHECK-NEXT: [[LOAD_8:%.*]] = load i32, i32* [[GEP_6]], align 4 -; CHECK-NEXT: [[MUL_1:%.*]] = mul i32 [[LOAD_3]], [[LOAD_5]] -; CHECK-NEXT: [[MUL_2:%.*]] = mul i32 [[LOAD_2]], [[LOAD_8]] -; CHECK-NEXT: [[MUL_3:%.*]] = mul i32 [[LOAD_4]], [[LOAD_7]] -; CHECK-NEXT: [[MUL_4:%.*]] = mul i32 [[LOAD_1]], [[LOAD_6]] -; CHECK-NEXT: [[GEP_7:%.*]] = getelementptr inbounds i32, i32* %out, i64 0 -; CHECK-NEXT: store i32 [[MUL_1]], i32* [[GEP_7]], align 4 -; CHECK-NEXT: [[GEP_8:%.*]] = getelementptr inbounds i32, i32* %out, i64 1 -; CHECK-NEXT: store i32 [[MUL_2]], i32* [[GEP_8]], align 4 -; CHECK-NEXT: [[GEP_9:%.*]] = getelementptr inbounds i32, i32* %out, i64 2 -; CHECK-NEXT: store i32 [[MUL_3]], i32* [[GEP_9]], align 4 -; CHECK-NEXT: [[GEP_10:%.*]] = getelementptr inbounds i32, i32* %out, i64 3 -; CHECK-NEXT: store i32 [[MUL_4]], i32* [[GEP_10]], align 4 +; CHECK-NEXT: [[TMP4:%.*]] = bitcast i32* [[INN_ADDR]] to <4 x i32>* +; CHECK-NEXT: [[TMP5:%.*]] = load <4 x i32>, <4 x i32>* [[TMP4]], align 4 +; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <4 x i32> [[TMP5]], <4 x i32> undef, <4 x i32> <i32 0, i32 1, i32 3, i32 2> +; CHECK-NEXT: [[TMP7:%.*]] = mul <4 x i32> [[TMP3]], [[TMP6]] +; CHECK-NEXT: [[GEP_7:%.*]] = getelementptr inbounds i32, i32* [[OUT:%.*]], i64 0 +; CHECK-NEXT: [[GEP_8:%.*]] = getelementptr inbounds i32, i32* [[OUT]], i64 1 +; CHECK-NEXT: [[GEP_9:%.*]] = getelementptr inbounds i32, i32* [[OUT]], i64 2 +; CHECK-NEXT: [[GEP_10:%.*]] = getelementptr inbounds i32, i32* [[OUT]], i64 3 +; CHECK-NEXT: [[TMP8:%.*]] = bitcast i32* [[GEP_7]] to <4 x i32>* +; CHECK-NEXT: store <4 x i32> [[TMP7]], <4 x i32>* [[TMP8]], align 4 ; CHECK-NEXT: ret i32 undef ; %in.addr = getelementptr inbounds i32, i32* %in, i64 0 diff --git a/llvm/test/Transforms/SLPVectorizer/X86/store-jumbled.ll b/llvm/test/Transforms/SLPVectorizer/X86/store-jumbled.ll index 1b2c76384e0..6ae76352001 100644 --- a/llvm/test/Transforms/SLPVectorizer/X86/store-jumbled.ll +++ b/llvm/test/Transforms/SLPVectorizer/X86/store-jumbled.ll @@ -6,33 +6,26 @@ define i32 @jumbled-load(i32* noalias nocapture %in, i32* noalias nocapture %inn, i32* noalias nocapture %out) { ; CHECK-LABEL: @jumbled-load( ; CHECK-NEXT: [[IN_ADDR:%.*]] = getelementptr inbounds i32, i32* [[IN:%.*]], i64 0 -; CHECK-NEXT: [[LOAD_1:%.*]] = load i32, i32* [[IN_ADDR]], align 4 ; CHECK-NEXT: [[GEP_1:%.*]] = getelementptr inbounds i32, i32* [[IN_ADDR]], i64 1 -; CHECK-NEXT: [[LOAD_2:%.*]] = load i32, i32* [[GEP_1]], align 4 ; CHECK-NEXT: [[GEP_2:%.*]] = getelementptr inbounds i32, i32* [[IN_ADDR]], i64 2 -; CHECK-NEXT: [[LOAD_3:%.*]] = load i32, i32* [[GEP_2]], align 4 ; CHECK-NEXT: [[GEP_3:%.*]] = getelementptr inbounds i32, i32* [[IN_ADDR]], i64 3 -; CHECK-NEXT: [[LOAD_4:%.*]] = load i32, i32* [[GEP_3]], align 4 +; CHECK-NEXT: [[TMP1:%.*]] = bitcast i32* [[IN_ADDR]] to <4 x i32>* +; CHECK-NEXT: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP1]], align 4 +; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> undef, <4 x i32> <i32 1, i32 3, i32 0, i32 2> ; CHECK-NEXT: [[INN_ADDR:%.*]] = getelementptr inbounds i32, i32* [[INN:%.*]], i64 0 -; CHECK-NEXT: [[LOAD_5:%.*]] = load i32, i32* [[INN_ADDR]], align 4 ; CHECK-NEXT: [[GEP_4:%.*]] = getelementptr inbounds i32, i32* [[INN_ADDR]], i64 1 -; CHECK-NEXT: [[LOAD_6:%.*]] = load i32, i32* [[GEP_4]], align 4 ; CHECK-NEXT: [[GEP_5:%.*]] = getelementptr inbounds i32, i32* [[INN_ADDR]], i64 2 -; CHECK-NEXT: [[LOAD_7:%.*]] = load i32, i32* [[GEP_5]], align 4 ; CHECK-NEXT: [[GEP_6:%.*]] = getelementptr inbounds i32, i32* [[INN_ADDR]], i64 3 -; CHECK-NEXT: [[LOAD_8:%.*]] = load i32, i32* [[GEP_6]], align 4 -; CHECK-NEXT: [[MUL_1:%.*]] = mul i32 [[LOAD_1]], [[LOAD_5]] -; CHECK-NEXT: [[MUL_2:%.*]] = mul i32 [[LOAD_2]], [[LOAD_6]] -; CHECK-NEXT: [[MUL_3:%.*]] = mul i32 [[LOAD_3]], [[LOAD_7]] -; CHECK-NEXT: [[MUL_4:%.*]] = mul i32 [[LOAD_4]], [[LOAD_8]] +; CHECK-NEXT: [[TMP4:%.*]] = bitcast i32* [[INN_ADDR]] to <4 x i32>* +; CHECK-NEXT: [[TMP5:%.*]] = load <4 x i32>, <4 x i32>* [[TMP4]], align 4 +; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <4 x i32> [[TMP5]], <4 x i32> undef, <4 x i32> <i32 1, i32 3, i32 0, i32 2> +; CHECK-NEXT: [[TMP7:%.*]] = mul <4 x i32> [[TMP3]], [[TMP6]] ; CHECK-NEXT: [[GEP_7:%.*]] = getelementptr inbounds i32, i32* [[OUT:%.*]], i64 0 ; CHECK-NEXT: [[GEP_8:%.*]] = getelementptr inbounds i32, i32* [[OUT]], i64 1 ; CHECK-NEXT: [[GEP_9:%.*]] = getelementptr inbounds i32, i32* [[OUT]], i64 2 ; CHECK-NEXT: [[GEP_10:%.*]] = getelementptr inbounds i32, i32* [[OUT]], i64 3 -; CHECK-NEXT: store i32 [[MUL_1]], i32* [[GEP_9]], align 4 -; CHECK-NEXT: store i32 [[MUL_2]], i32* [[GEP_7]], align 4 -; CHECK-NEXT: store i32 [[MUL_3]], i32* [[GEP_10]], align 4 -; CHECK-NEXT: store i32 [[MUL_4]], i32* [[GEP_8]], align 4 +; CHECK-NEXT: [[TMP8:%.*]] = bitcast i32* [[GEP_7]] to <4 x i32>* +; CHECK-NEXT: store <4 x i32> [[TMP7]], <4 x i32>* [[TMP8]], align 4 ; CHECK-NEXT: ret i32 undef ; %in.addr = getelementptr inbounds i32, i32* %in, i64 0 |
