Skip to content

[SLP]Support revectorization of the previously vectorized scalars #133091

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Apr 1, 2025
Merged

[SLP]Support revectorization of the previously vectorized scalars #133091

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
90fa80e
[𝘀𝗽𝗿] initial version
alexey-bataev Mar 26, 2025
cae674e
Fix formatting
alexey-bataev Mar 26, 2025
1e555e9
Rebase, address comments
alexey-bataev Mar 27, 2025
ec7022b
Rebase, address comments
alexey-bataev Apr 1, 2025
60f0d25
Fix formatting
alexey-bataev Apr 1, 2025
e591029
address comments
alexey-bataev Apr 1, 2025
64f1f6c
Rebase, improve lookup time
alexey-bataev Apr 1, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
217 changes: 136 additions & 81 deletions llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
View file
Open in desktop

Large diffs are not rendered by default.

18 changes: 8 additions & 10 deletions llvm/test/Transforms/SLPVectorizer/AArch64/reused-scalar-repeated-in-node.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,28 +39,26 @@ define void @test() {
; CHECK: [[BB77]]:
; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <16 x float> [[TMP11]], <16 x float> poison, <8 x i32> <i32 poison, i32 poison, i32 poison, i32 poison, i32 14, i32 15, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP17:%.*]] = insertelement <8 x float> [[TMP12]], float [[I70]], i32 0
; CHECK-NEXT: [[TMP30:%.*]] = insertelement <2 x float> poison, float [[I68]], i32 0
; CHECK-NEXT: [[TMP31:%.*]] = insertelement <2 x float> [[TMP30]], float [[I66]], i32 1
; CHECK-NEXT: [[TMP14:%.*]] = insertelement <8 x float> poison, float [[I70]], i32 1
; CHECK-NEXT: [[TMP19:%.*]] = insertelement <8 x float> [[TMP14]], float [[I68]], i32 2
; CHECK-NEXT: [[TMP16:%.*]] = insertelement <8 x float> [[TMP19]], float [[I66]], i32 3
; CHECK-NEXT: [[TMP20:%.*]] = insertelement <8 x float> [[TMP16]], float [[I67]], i32 6
; CHECK-NEXT: [[TMP21:%.*]] = insertelement <8 x float> [[TMP20]], float [[I69]], i32 7
; CHECK-NEXT: [[TMP39:%.*]] = shufflevector <16 x float> [[TMP25]], <16 x float> poison, <16 x i32> <i32 poison, i32 poison, i32 3, i32 2, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <16 x float> [[TMP39]], <16 x float> [[TMP25]], <16 x i32> <i32 poison, i32 poison, i32 2, i32 3, i32 18, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 19, i32 poison, i32 poison>
; CHECK-NEXT: br label %[[BB78:.*]]
; CHECK: [[BB78]]:
; CHECK-NEXT: [[TMP15:%.*]] = phi <8 x float> [ [[TMP17]], %[[BB77]] ], [ [[TMP36:%.*]], %[[BB78]] ]
; CHECK-NEXT: [[TMP16:%.*]] = phi <2 x float> [ [[TMP31]], %[[BB77]] ], [ [[TMP37:%.*]], %[[BB78]] ]
; CHECK-NEXT: [[TMP22:%.*]] = phi <8 x float> [ [[TMP21]], %[[BB77]] ], [ [[TMP31:%.*]], %[[BB78]] ]
; CHECK-NEXT: [[TMP24:%.*]] = shufflevector <8 x float> [[TMP22]], <8 x float> poison, <16 x i32> <i32 0, i32 3, i32 1, i32 2, i32 3, i32 0, i32 2, i32 3, i32 2, i32 6, i32 2, i32 3, i32 0, i32 7, i32 6, i32 6>
; CHECK-NEXT: [[TMP38:%.*]] = shufflevector <8 x float> [[TMP15]], <8 x float> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 1, i32 0, i32 3, i32 1, i32 3, i32 5, i32 3, i32 1, i32 0, i32 4, i32 5, i32 5>
; CHECK-NEXT: [[TMP21:%.*]] = shufflevector <8 x float> [[TMP15]], <8 x float> poison, <16 x i32> <i32 2, i32 poison, i32 0, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP20:%.*]] = shufflevector <2 x float> [[TMP16]], <2 x float> poison, <16 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP23:%.*]] = shufflevector <16 x float> [[TMP21]], <16 x float> [[TMP20]], <16 x i32> <i32 0, i32 17, i32 2, i32 16, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP22:%.*]] = shufflevector <8 x float> [[TMP15]], <8 x float> poison, <16 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, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP40:%.*]] = shufflevector <16 x float> [[TMP23]], <16 x float> [[TMP22]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 18, i32 6, i32 7, i32 8, i32 20, i32 10, i32 11, i32 12, i32 21, i32 14, i32 15>
; CHECK-NEXT: [[TMP24:%.*]] = shufflevector <16 x float> [[TMP40]], <16 x float> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 1, i32 5, i32 3, i32 1, i32 3, i32 9, i32 3, i32 1, i32 5, i32 13, i32 9, i32 9>
; CHECK-NEXT: [[TMP18:%.*]] = fmul fast <16 x float> [[TMP24]], [[TMP13]]
; CHECK-NEXT: [[TMP26:%.*]] = fmul fast <16 x float> [[TMP38]], [[TMP25]]
; CHECK-NEXT: [[TMP27:%.*]] = fadd fast <16 x float> [[TMP26]], [[TMP18]]
; CHECK-NEXT: [[TMP28:%.*]] = fadd fast <16 x float> [[TMP27]], poison
; CHECK-NEXT: [[TMP29:%.*]] = fadd fast <16 x float> [[TMP28]], poison
; CHECK-NEXT: [[TMP36]] = shufflevector <16 x float> [[TMP29]], <16 x float> poison, <8 x i32> <i32 5, i32 11, i32 12, i32 10, i32 14, i32 15, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP37]] = shufflevector <16 x float> [[TMP29]], <16 x float> poison, <2 x i32> <i32 6, i32 7>
; CHECK-NEXT: [[TMP31]] = shufflevector <16 x float> [[TMP29]], <16 x float> poison, <8 x i32> <i32 12, i32 5, i32 6, i32 7, i32 poison, i32 poison, i32 14, i32 15>
; CHECK-NEXT: br i1 poison, label %[[BB78]], label %[[BB167]]
; CHECK: [[BB167]]:
; CHECK-NEXT: [[TMP32:%.*]] = phi <16 x float> [ [[TMP11]], %[[BB64]] ], [ [[TMP29]], %[[BB78]] ]
Expand Down
21 changes: 10 additions & 11 deletions llvm/test/Transforms/SLPVectorizer/AArch64/transpose-inseltpoison.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -123,18 +123,17 @@ define <4 x i32> @build_vec_v4i32_reuse_0(<2 x i32> %v0, <2 x i32> %v1) {

define <4 x i32> @build_vec_v4i32_reuse_1(<2 x i32> %v0, <2 x i32> %v1) {
; CHECK-LABEL: @build_vec_v4i32_reuse_1(
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <2 x i32> [[V0:%.*]], <2 x i32> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
; CHECK-NEXT: [[V0_1:%.*]] = extractelement <2 x i32> [[V0]], i64 1
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <2 x i32> [[V1:%.*]], <2 x i32> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
; CHECK-NEXT: [[V1_1:%.*]] = extractelement <2 x i32> [[V1]], i64 1
; CHECK-NEXT: [[TMP0_1:%.*]] = add i32 [[V0_1]], [[V1_1]]
; CHECK-NEXT: [[TMP3:%.*]] = add <4 x i32> [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[TMP4:%.*]] = xor <4 x i32> [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[V0:%.*]], <2 x i32> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <2 x i32> [[V1:%.*]], <2 x i32> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
; CHECK-NEXT: [[TMP3:%.*]] = add <4 x i32> [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[TMP4:%.*]] = xor <4 x i32> [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> [[TMP4]], <4 x i32> <i32 0, i32 1, i32 6, i32 7>
; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <4 x i32> [[TMP5]], <4 x i32> poison, <4 x i32> <i32 poison, i32 poison, i32 3, i32 2>
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <4 x i32> [[TMP6]], i32 [[TMP0_1]], i64 0
; CHECK-NEXT: [[TMP8:%.*]] = shufflevector <4 x i32> [[TMP7]], <4 x i32> poison, <4 x i32> <i32 0, i32 0, i32 2, i32 3>
; CHECK-NEXT: [[TMP9:%.*]] = sub <4 x i32> [[TMP5]], [[TMP8]]
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <2 x i32> [[V0]], <2 x i32> poison, <4 x i32> <i32 1, i32 1, i32 1, i32 0>
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <2 x i32> [[V1]], <2 x i32> poison, <4 x i32> <i32 1, i32 1, i32 1, i32 0>
; CHECK-NEXT: [[TMP8:%.*]] = add <4 x i32> [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[TMP11:%.*]] = xor <4 x i32> [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[TMP10:%.*]] = shufflevector <4 x i32> [[TMP8]], <4 x i32> [[TMP11]], <4 x i32> <i32 0, i32 1, i32 6, i32 7>
; CHECK-NEXT: [[TMP9:%.*]] = sub <4 x i32> [[TMP5]], [[TMP10]]
; CHECK-NEXT: ret <4 x i32> [[TMP9]]
;
%v0.0 = extractelement <2 x i32> %v0, i32 0
Expand Down
21 changes: 10 additions & 11 deletions llvm/test/Transforms/SLPVectorizer/AArch64/transpose.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -123,18 +123,17 @@ define <4 x i32> @build_vec_v4i32_reuse_0(<2 x i32> %v0, <2 x i32> %v1) {

define <4 x i32> @build_vec_v4i32_reuse_1(<2 x i32> %v0, <2 x i32> %v1) {
; CHECK-LABEL: @build_vec_v4i32_reuse_1(
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <2 x i32> [[V0:%.*]], <2 x i32> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
; CHECK-NEXT: [[V0_1:%.*]] = extractelement <2 x i32> [[V0]], i64 1
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <2 x i32> [[V1:%.*]], <2 x i32> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
; CHECK-NEXT: [[V1_1:%.*]] = extractelement <2 x i32> [[V1]], i64 1
; CHECK-NEXT: [[TMP0_1:%.*]] = add i32 [[V0_1]], [[V1_1]]
; CHECK-NEXT: [[TMP3:%.*]] = add <4 x i32> [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[TMP4:%.*]] = xor <4 x i32> [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[V0:%.*]], <2 x i32> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <2 x i32> [[V1:%.*]], <2 x i32> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
; CHECK-NEXT: [[TMP3:%.*]] = add <4 x i32> [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[TMP4:%.*]] = xor <4 x i32> [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> [[TMP4]], <4 x i32> <i32 0, i32 1, i32 6, i32 7>
; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <4 x i32> [[TMP5]], <4 x i32> poison, <4 x i32> <i32 poison, i32 poison, i32 3, i32 2>
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <4 x i32> [[TMP6]], i32 [[TMP0_1]], i64 0
; CHECK-NEXT: [[TMP8:%.*]] = shufflevector <4 x i32> [[TMP7]], <4 x i32> poison, <4 x i32> <i32 0, i32 0, i32 2, i32 3>
; CHECK-NEXT: [[TMP9:%.*]] = sub <4 x i32> [[TMP5]], [[TMP8]]
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <2 x i32> [[V0]], <2 x i32> poison, <4 x i32> <i32 1, i32 1, i32 1, i32 0>
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <2 x i32> [[V1]], <2 x i32> poison, <4 x i32> <i32 1, i32 1, i32 1, i32 0>
; CHECK-NEXT: [[TMP8:%.*]] = add <4 x i32> [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[TMP11:%.*]] = xor <4 x i32> [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[TMP10:%.*]] = shufflevector <4 x i32> [[TMP8]], <4 x i32> [[TMP11]], <4 x i32> <i32 0, i32 1, i32 6, i32 7>
; CHECK-NEXT: [[TMP9:%.*]] = sub <4 x i32> [[TMP5]], [[TMP10]]
; CHECK-NEXT: ret <4 x i32> [[TMP9]]
;
%v0.0 = extractelement <2 x i32> %v0, i32 0
Expand Down
4 changes: 2 additions & 2 deletions llvm/test/Transforms/SLPVectorizer/AArch64/vec3-reorder-reshuffle.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -206,15 +206,15 @@ define i32 @reorder_indices_1(float %0) {
; POW2-ONLY-SAME: float [[TMP0:%.*]]) {
; POW2-ONLY-NEXT: entry:
; POW2-ONLY-NEXT: [[NOR1:%.*]] = alloca [0 x [3 x float]], i32 0, align 4
; POW2-ONLY-NEXT: [[ARRAYIDX_I:%.*]] = getelementptr float, ptr [[NOR1]], i64 1
; POW2-ONLY-NEXT: [[ARRAYIDX2_I265:%.*]] = getelementptr float, ptr [[NOR1]], i64 2
; POW2-ONLY-NEXT: [[TMP1:%.*]] = load float, ptr [[ARRAYIDX2_I265]], align 4
; POW2-ONLY-NEXT: [[TMP7:%.*]] = load <2 x float>, ptr [[ARRAYIDX_I]], align 4
; POW2-ONLY-NEXT: [[TMP2:%.*]] = load <2 x float>, ptr [[NOR1]], align 4
; POW2-ONLY-NEXT: [[TMP3:%.*]] = extractelement <2 x float> [[TMP2]], i32 0
; POW2-ONLY-NEXT: [[TMP4:%.*]] = fneg float [[TMP3]]
; POW2-ONLY-NEXT: [[NEG11_I:%.*]] = fmul float [[TMP4]], [[TMP0]]
; POW2-ONLY-NEXT: [[TMP5:%.*]] = call float @llvm.fmuladd.f32(float [[TMP1]], float 0.000000e+00, float [[NEG11_I]])
; POW2-ONLY-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> poison, <2 x i32> <i32 1, i32 poison>
; POW2-ONLY-NEXT: [[TMP7:%.*]] = insertelement <2 x float> [[TMP6]], float [[TMP1]], i32 1
; POW2-ONLY-NEXT: [[TMP8:%.*]] = fneg <2 x float> [[TMP7]]
; POW2-ONLY-NEXT: [[TMP9:%.*]] = insertelement <2 x float> poison, float [[TMP0]], i32 0
; POW2-ONLY-NEXT: [[TMP10:%.*]] = shufflevector <2 x float> [[TMP9]], <2 x float> poison, <2 x i32> zeroinitializer
Expand Down
10 changes: 5 additions & 5 deletions llvm/test/Transforms/SLPVectorizer/X86/cast-operand-extracted.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,19 +8,19 @@ define void @test(ptr %0, i32 %add651) {
; CHECK-NEXT: [[PREDPEL11:%.*]] = alloca [0 x [0 x [25 x i32]]], i32 0, align 16
; CHECK-NEXT: [[ARRAYIDX469_6:%.*]] = getelementptr i8, ptr [[PREDPEL11]], i64 28
; CHECK-NEXT: [[ARRAYIDX469_7:%.*]] = getelementptr i8, ptr [[PREDPEL11]], i64 32
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr i8, ptr [[PREDPEL11]], i64 36
; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[ARRAYIDX469_7]], align 16
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr i8, ptr [[PREDPEL11]], i64 40
; CHECK-NEXT: [[TMP5:%.*]] = load i32, ptr [[TMP1]], align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <2 x i32>, ptr [[ARRAYIDX469_6]], align 4
; CHECK-NEXT: [[TMP7:%.*]] = load <2 x i32>, ptr [[ARRAYIDX469_7]], align 16
; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[ARRAYIDX469_7]], align 16
; CHECK-NEXT: [[CONV470_7:%.*]] = trunc i32 [[TMP2]] to i16
; CHECK-NEXT: store i16 [[CONV470_7]], ptr [[TMP0]], align 2
; CHECK-NEXT: [[TMP4:%.*]] = load ptr, ptr [[TMP0]], align 8
; CHECK-NEXT: [[ARRAYIDX660:%.*]] = getelementptr i8, ptr [[TMP4]], i64 7800
; CHECK-NEXT: [[ARRAYIDX689:%.*]] = getelementptr i8, ptr [[TMP4]], i64 7816
; CHECK-NEXT: [[TMP5:%.*]] = load <2 x i32>, ptr [[TMP1]], align 4
; CHECK-NEXT: [[TMP6:%.*]] = add <2 x i32> [[TMP3]], splat (i32 1)
; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <2 x i32> [[TMP3]], <2 x i32> [[TMP5]], <2 x i32> <i32 1, i32 2>
; CHECK-NEXT: [[TMP8:%.*]] = add <2 x i32> [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> <i32 1, i32 poison>, <2 x i32> <i32 2, i32 1>
; CHECK-NEXT: [[TMP9:%.*]] = insertelement <2 x i32> <i32 1, i32 poison>, i32 [[TMP5]], i32 1
; CHECK-NEXT: [[TMP10:%.*]] = add <2 x i32> [[TMP8]], [[TMP9]]
; CHECK-NEXT: [[TMP11:%.*]] = insertelement <4 x i32> poison, i32 [[ADD651]], i32 0
; CHECK-NEXT: [[TMP13:%.*]] = insertelement <4 x i32> [[TMP11]], i32 [[TMP2]], i32 1
Expand Down
7 changes: 3 additions & 4 deletions llvm/test/Transforms/SLPVectorizer/X86/scatter-vectorize-reorder.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,14 +8,13 @@ define void @test() {
; CHECK-NEXT: [[ARRAYIDX21_I:%.*]] = getelementptr inbounds [4 x float], ptr undef, i64 2
; CHECK-NEXT: br label [[BB1:%.*]]
; CHECK: bb1:
; CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[ARRAYIDX10_I_I86]], align 4
; CHECK-NEXT: [[TMP0:%.*]] = load <2 x float>, ptr undef, align 4
; CHECK-NEXT: [[TMP3:%.*]] = load <2 x float>, ptr undef, align 4
; CHECK-NEXT: [[TMP1:%.*]] = fsub <2 x float> zeroinitializer, [[TMP0]]
; CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[ARRAYIDX10_I_I86]], align 4
; CHECK-NEXT: [[TMP3:%.*]] = load float, ptr undef, align 4
; CHECK-NEXT: [[TMP4:%.*]] = insertelement <2 x float> <float 0.000000e+00, float poison>, float [[TMP2]], i32 1
; CHECK-NEXT: [[TMP5:%.*]] = insertelement <2 x float> [[TMP0]], float [[TMP3]], i32 0
; CHECK-NEXT: [[TMP6:%.*]] = insertelement <2 x float> <float poison, float 0.000000e+00>, float [[TMP2]], i32 0
; CHECK-NEXT: [[TMP7:%.*]] = call <2 x float> @llvm.fmuladd.v2f32(<2 x float> [[TMP4]], <2 x float> [[TMP5]], <2 x float> [[TMP6]])
; CHECK-NEXT: [[TMP7:%.*]] = call <2 x float> @llvm.fmuladd.v2f32(<2 x float> [[TMP4]], <2 x float> [[TMP3]], <2 x float> [[TMP6]])
; CHECK-NEXT: br i1 false, label [[BB2:%.*]], label [[BB3:%.*]]
; CHECK: bb2:
; CHECK-NEXT: [[TMP8:%.*]] = fmul <2 x float> [[TMP7]], zeroinitializer
Expand Down
4 changes: 2 additions & 2 deletions llvm/test/Transforms/SLPVectorizer/X86/vec3-reorder-reshuffle.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -205,15 +205,15 @@ define i32 @reorder_indices_1(float %0) {
; POW2-ONLY-SAME: float [[TMP0:%.*]]) {
; POW2-ONLY-NEXT: entry:
; POW2-ONLY-NEXT: [[NOR1:%.*]] = alloca [0 x [3 x float]], i32 0, align 4
; POW2-ONLY-NEXT: [[ARRAYIDX_I:%.*]] = getelementptr float, ptr [[NOR1]], i64 1
; POW2-ONLY-NEXT: [[ARRAYIDX2_I265:%.*]] = getelementptr float, ptr [[NOR1]], i64 2
; POW2-ONLY-NEXT: [[TMP1:%.*]] = load float, ptr [[ARRAYIDX2_I265]], align 4
; POW2-ONLY-NEXT: [[TMP7:%.*]] = load <2 x float>, ptr [[ARRAYIDX_I]], align 4
; POW2-ONLY-NEXT: [[TMP2:%.*]] = load <2 x float>, ptr [[NOR1]], align 4
; POW2-ONLY-NEXT: [[TMP3:%.*]] = extractelement <2 x float> [[TMP2]], i32 0
; POW2-ONLY-NEXT: [[TMP4:%.*]] = fneg float [[TMP3]]
; POW2-ONLY-NEXT: [[NEG11_I:%.*]] = fmul float [[TMP4]], [[TMP0]]
; POW2-ONLY-NEXT: [[TMP5:%.*]] = call float @llvm.fmuladd.f32(float [[TMP1]], float 0.000000e+00, float [[NEG11_I]])
; POW2-ONLY-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> poison, <2 x i32> <i32 1, i32 poison>
; POW2-ONLY-NEXT: [[TMP7:%.*]] = insertelement <2 x float> [[TMP6]], float [[TMP1]], i32 1
; POW2-ONLY-NEXT: [[TMP8:%.*]] = fneg <2 x float> [[TMP7]]
; POW2-ONLY-NEXT: [[TMP9:%.*]] = insertelement <2 x float> poison, float [[TMP0]], i32 0
; POW2-ONLY-NEXT: [[TMP10:%.*]] = shufflevector <2 x float> [[TMP9]], <2 x float> poison, <2 x i32> zeroinitializer
Expand Down
Loading