[llvm] 214f99b - Revert "[SLP]Do not emit extra shuffle for insertelements vectorization."
Alexey Bataev via llvm-commits
llvm-commits at lists.llvm.org
Wed Aug 4 11:30:20 PDT 2021
Author: Alexey Bataev
Date: 2021-08-04T11:28:59-07:00
New Revision: 214f99b27c009c815884d82fded65c4d006b532e
URL: https://github.com/llvm/llvm-project/commit/214f99b27c009c815884d82fded65c4d006b532e
DIFF: https://github.com/llvm/llvm-project/commit/214f99b27c009c815884d82fded65c4d006b532e.diff
LOG: Revert "[SLP]Do not emit extra shuffle for insertelements vectorization."
This reverts commit 871ea69803b1f231254ab0c560795a33b6ed0c77 to fix the
problem if the first vector is not just undef.
Added:
Modified:
llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
llvm/test/Transforms/SLPVectorizer/AArch64/vectorize-free-extracts-inserts.ll
llvm/test/Transforms/SLPVectorizer/X86/arith-fp-inseltpoison.ll
llvm/test/Transforms/SLPVectorizer/X86/arith-fp.ll
llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector-inseltpoison.ll
llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll
llvm/test/Transforms/SLPVectorizer/X86/load-merge-inseltpoison.ll
llvm/test/Transforms/SLPVectorizer/X86/load-merge.ll
llvm/test/Transforms/SLPVectorizer/X86/sitofp-inseltpoison.ll
llvm/test/Transforms/SLPVectorizer/X86/sitofp.ll
llvm/test/Transforms/SLPVectorizer/X86/value-bug-inseltpoison.ll
Removed:
################################################################################
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 212d73f2c9fa..eb9d5ab6059e 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -5251,7 +5251,7 @@ Value *BoUpSLP::vectorizeTree(TreeEntry *E) {
if (!IsIdentity || NumElts != NumScalars)
V = Builder.CreateShuffleVector(V, Mask);
- if ((!IsIdentity || Offset != 0) && NumElts != NumScalars) {
+ if (NumElts != NumScalars) {
SmallVector<int> InsertMask(NumElts);
std::iota(InsertMask.begin(), InsertMask.end(), 0);
for (unsigned I = 0; I < NumElts; I++) {
diff --git a/llvm/test/Transforms/SLPVectorizer/AArch64/vectorize-free-extracts-inserts.ll b/llvm/test/Transforms/SLPVectorizer/AArch64/vectorize-free-extracts-inserts.ll
index d7ef813d6b72..067049c26293 100644
--- a/llvm/test/Transforms/SLPVectorizer/AArch64/vectorize-free-extracts-inserts.ll
+++ b/llvm/test/Transforms/SLPVectorizer/AArch64/vectorize-free-extracts-inserts.ll
@@ -105,9 +105,10 @@ define void @noop_extract_second_2_lanes(<4 x double>* %ptr.1, <4 x double>* %pt
; CHECK-NEXT: [[TMP3:%.*]] = insertelement <2 x double> [[TMP2]], double [[V2_LANE_2]], i32 1
; CHECK-NEXT: [[TMP4:%.*]] = fmul <2 x double> [[TMP1]], [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <2 x double> [[TMP4]], <2 x double> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
+; CHECK-NEXT: [[A_INS_11:%.*]] = shufflevector <4 x double> undef, <4 x double> [[TMP5]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; CHECK-NEXT: call void @use(double [[V1_LANE_2]])
; CHECK-NEXT: call void @use(double [[V1_LANE_3]])
-; CHECK-NEXT: store <4 x double> [[TMP5]], <4 x double>* [[PTR_1]], align 8
+; CHECK-NEXT: store <4 x double> [[A_INS_11]], <4 x double>* [[PTR_1]], align 8
; CHECK-NEXT: ret void
;
bb:
@@ -185,9 +186,10 @@ define void @extract_lanes_1_and_2(<4 x double>* %ptr.1, <4 x double>* %ptr.2) {
; CHECK-NEXT: [[TMP3:%.*]] = insertelement <2 x double> [[TMP2]], double [[V2_LANE_2]], i32 1
; CHECK-NEXT: [[TMP4:%.*]] = fmul <2 x double> [[TMP1]], [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <2 x double> [[TMP4]], <2 x double> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
+; CHECK-NEXT: [[A_INS_11:%.*]] = shufflevector <4 x double> undef, <4 x double> [[TMP5]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; CHECK-NEXT: call void @use(double [[V1_LANE_1]])
; CHECK-NEXT: call void @use(double [[V1_LANE_2]])
-; CHECK-NEXT: store <4 x double> [[TMP5]], <4 x double>* [[PTR_1]], align 8
+; CHECK-NEXT: store <4 x double> [[A_INS_11]], <4 x double>* [[PTR_1]], align 8
; CHECK-NEXT: ret void
;
bb:
@@ -235,11 +237,12 @@ define void @noop_extracts_existing_vector_4_lanes(<9 x double>* %ptr.1, <4 x do
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x double> [[TMP5]], <4 x double> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
; CHECK-NEXT: [[TMP6:%.*]] = fmul <4 x double> [[TMP3]], [[SHUFFLE]]
; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <4 x double> [[TMP6]], <4 x double> poison, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+; CHECK-NEXT: [[A_INS_31:%.*]] = shufflevector <9 x double> undef, <9 x double> [[TMP7]], <9 x i32> <i32 9, i32 10, i32 11, i32 12, i32 4, i32 5, i32 6, i32 7, i32 8>
; CHECK-NEXT: call void @use(double [[V1_LANE_0]])
; CHECK-NEXT: call void @use(double [[V1_LANE_1]])
; CHECK-NEXT: call void @use(double [[V1_LANE_2]])
; CHECK-NEXT: call void @use(double [[V1_LANE_3]])
-; CHECK-NEXT: store <9 x double> [[TMP7]], <9 x double>* [[PTR_1]], align 8
+; CHECK-NEXT: store <9 x double> [[A_INS_31]], <9 x double>* [[PTR_1]], align 8
; CHECK-NEXT: ret void
;
bb:
@@ -355,11 +358,12 @@ define void @noop_extracts_9_lanes(<9 x double>* %ptr.1, <4 x double>* %ptr.2) {
; CHECK-NEXT: [[TMP8:%.*]] = insertelement <8 x double> poison, double [[V2_LANE_0]], i32 0
; CHECK-NEXT: [[TMP9:%.*]] = insertelement <8 x double> [[TMP8]], double [[V2_LANE_2]], i32 1
; CHECK-NEXT: [[TMP10:%.*]] = insertelement <8 x double> [[TMP9]], double [[V2_LANE_1]], i32 2
-; CHECK-NEXT: [[SHUFFLE1:%.*]] = shufflevector <8 x double> [[TMP10]], <8 x double> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 0, i32 1, i32 0, i32 1, i32 2>
-; CHECK-NEXT: [[TMP11:%.*]] = fmul <8 x double> [[TMP7]], [[SHUFFLE1]]
+; CHECK-NEXT: [[SHUFFLE2:%.*]] = shufflevector <8 x double> [[TMP10]], <8 x double> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 0, i32 1, i32 0, i32 1, i32 2>
+; CHECK-NEXT: [[TMP11:%.*]] = fmul <8 x double> [[TMP7]], [[SHUFFLE2]]
; CHECK-NEXT: [[A_LANE_8:%.*]] = fmul double [[V1_LANE_2]], [[V2_LANE_0]]
; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <8 x double> [[TMP11]], <8 x double> poison, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef>
-; CHECK-NEXT: [[A_INS_8:%.*]] = insertelement <9 x double> [[TMP12]], double [[A_LANE_8]], i32 8
+; CHECK-NEXT: [[A_INS_73:%.*]] = shufflevector <9 x double> undef, <9 x double> [[TMP12]], <9 x i32> <i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 8>
+; CHECK-NEXT: [[A_INS_8:%.*]] = insertelement <9 x double> [[A_INS_73]], double [[A_LANE_8]], i32 8
; CHECK-NEXT: [[TMP13:%.*]] = insertelement <8 x double> poison, double [[V1_LANE_6]], i32 0
; CHECK-NEXT: [[TMP14:%.*]] = insertelement <8 x double> [[TMP13]], double [[V1_LANE_7]], i32 1
; CHECK-NEXT: [[TMP15:%.*]] = insertelement <8 x double> [[TMP14]], double [[V1_LANE_8]], i32 2
@@ -375,7 +379,8 @@ define void @noop_extracts_9_lanes(<9 x double>* %ptr.1, <4 x double>* %ptr.2) {
; CHECK-NEXT: [[TMP24:%.*]] = fmul <8 x double> [[TMP20]], [[SHUFFLE]]
; CHECK-NEXT: [[B_LANE_8:%.*]] = fmul double [[V1_LANE_5]], [[V2_LANE_0]]
; CHECK-NEXT: [[TMP25:%.*]] = shufflevector <8 x double> [[TMP24]], <8 x double> poison, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef>
-; CHECK-NEXT: [[B_INS_8:%.*]] = insertelement <9 x double> [[TMP25]], double [[B_LANE_8]], i32 8
+; CHECK-NEXT: [[B_INS_71:%.*]] = shufflevector <9 x double> undef, <9 x double> [[TMP25]], <9 x i32> <i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 8>
+; CHECK-NEXT: [[B_INS_8:%.*]] = insertelement <9 x double> [[B_INS_71]], double [[B_LANE_8]], i32 8
; CHECK-NEXT: [[RES:%.*]] = fsub <9 x double> [[A_INS_8]], [[B_INS_8]]
; CHECK-NEXT: store <9 x double> [[RES]], <9 x double>* [[PTR_1]], align 8
; CHECK-NEXT: ret void
@@ -472,11 +477,12 @@ define void @first_mul_chain_jumbled(<9 x double>* %ptr.1, <4 x double>* %ptr.2)
; CHECK-NEXT: [[TMP8:%.*]] = insertelement <8 x double> poison, double [[V2_LANE_1]], i32 0
; CHECK-NEXT: [[TMP9:%.*]] = insertelement <8 x double> [[TMP8]], double [[V2_LANE_0]], i32 1
; CHECK-NEXT: [[TMP10:%.*]] = insertelement <8 x double> [[TMP9]], double [[V2_LANE_2]], i32 2
-; CHECK-NEXT: [[SHUFFLE1:%.*]] = shufflevector <8 x double> [[TMP10]], <8 x double> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 1, i32 2, i32 0, i32 1, i32 2>
-; CHECK-NEXT: [[TMP11:%.*]] = fmul <8 x double> [[TMP7]], [[SHUFFLE1]]
+; CHECK-NEXT: [[SHUFFLE2:%.*]] = shufflevector <8 x double> [[TMP10]], <8 x double> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 1, i32 2, i32 0, i32 1, i32 2>
+; CHECK-NEXT: [[TMP11:%.*]] = fmul <8 x double> [[TMP7]], [[SHUFFLE2]]
; CHECK-NEXT: [[A_LANE_8:%.*]] = fmul double [[V1_LANE_2]], [[V2_LANE_1]]
; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <8 x double> [[TMP11]], <8 x double> poison, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef>
-; CHECK-NEXT: [[A_INS_8:%.*]] = insertelement <9 x double> [[TMP12]], double [[A_LANE_8]], i32 8
+; CHECK-NEXT: [[A_INS_73:%.*]] = shufflevector <9 x double> undef, <9 x double> [[TMP12]], <9 x i32> <i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 8>
+; CHECK-NEXT: [[A_INS_8:%.*]] = insertelement <9 x double> [[A_INS_73]], double [[A_LANE_8]], i32 8
; CHECK-NEXT: [[TMP13:%.*]] = insertelement <8 x double> poison, double [[V1_LANE_6]], i32 0
; CHECK-NEXT: [[TMP14:%.*]] = insertelement <8 x double> [[TMP13]], double [[V1_LANE_7]], i32 1
; CHECK-NEXT: [[TMP15:%.*]] = insertelement <8 x double> [[TMP14]], double [[V1_LANE_8]], i32 2
@@ -485,10 +491,11 @@ define void @first_mul_chain_jumbled(<9 x double>* %ptr.1, <4 x double>* %ptr.2)
; CHECK-NEXT: [[TMP18:%.*]] = insertelement <8 x double> [[TMP17]], double [[V1_LANE_2]], i32 5
; CHECK-NEXT: [[TMP19:%.*]] = insertelement <8 x double> [[TMP18]], double [[V1_LANE_3]], i32 6
; CHECK-NEXT: [[TMP20:%.*]] = insertelement <8 x double> [[TMP19]], double [[V1_LANE_4]], i32 7
-; CHECK-NEXT: [[TMP21:%.*]] = fmul <8 x double> [[TMP20]], [[SHUFFLE1]]
+; CHECK-NEXT: [[TMP21:%.*]] = fmul <8 x double> [[TMP20]], [[SHUFFLE2]]
; CHECK-NEXT: [[B_LANE_8:%.*]] = fmul double [[V1_LANE_5]], [[V2_LANE_0]]
; CHECK-NEXT: [[TMP22:%.*]] = shufflevector <8 x double> [[TMP21]], <8 x double> poison, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef>
-; CHECK-NEXT: [[B_INS_8:%.*]] = insertelement <9 x double> [[TMP22]], double [[B_LANE_8]], i32 8
+; CHECK-NEXT: [[B_INS_71:%.*]] = shufflevector <9 x double> undef, <9 x double> [[TMP22]], <9 x i32> <i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 8>
+; CHECK-NEXT: [[B_INS_8:%.*]] = insertelement <9 x double> [[B_INS_71]], double [[B_LANE_8]], i32 8
; CHECK-NEXT: [[RES:%.*]] = fsub <9 x double> [[A_INS_8]], [[B_INS_8]]
; CHECK-NEXT: store <9 x double> [[RES]], <9 x double>* [[PTR_1]], align 8
; CHECK-NEXT: ret void
@@ -585,11 +592,12 @@ define void @first_and_second_mul_chain_jumbled(<9 x double>* %ptr.1, <4 x doubl
; CHECK-NEXT: [[TMP8:%.*]] = insertelement <8 x double> poison, double [[V2_LANE_0]], i32 0
; CHECK-NEXT: [[TMP9:%.*]] = insertelement <8 x double> [[TMP8]], double [[V2_LANE_2]], i32 1
; CHECK-NEXT: [[TMP10:%.*]] = insertelement <8 x double> [[TMP9]], double [[V2_LANE_1]], i32 2
-; CHECK-NEXT: [[SHUFFLE1:%.*]] = shufflevector <8 x double> [[TMP10]], <8 x double> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 1, i32 2, i32 0, i32 1, i32 2>
-; CHECK-NEXT: [[TMP11:%.*]] = fmul <8 x double> [[TMP7]], [[SHUFFLE1]]
+; CHECK-NEXT: [[SHUFFLE2:%.*]] = shufflevector <8 x double> [[TMP10]], <8 x double> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 1, i32 2, i32 0, i32 1, i32 2>
+; CHECK-NEXT: [[TMP11:%.*]] = fmul <8 x double> [[TMP7]], [[SHUFFLE2]]
; CHECK-NEXT: [[A_LANE_8:%.*]] = fmul double [[V1_LANE_2]], [[V2_LANE_0]]
; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <8 x double> [[TMP11]], <8 x double> poison, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef>
-; CHECK-NEXT: [[A_INS_8:%.*]] = insertelement <9 x double> [[TMP12]], double [[A_LANE_8]], i32 8
+; CHECK-NEXT: [[A_INS_73:%.*]] = shufflevector <9 x double> undef, <9 x double> [[TMP12]], <9 x i32> <i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 8>
+; CHECK-NEXT: [[A_INS_8:%.*]] = insertelement <9 x double> [[A_INS_73]], double [[A_LANE_8]], i32 8
; CHECK-NEXT: [[TMP13:%.*]] = insertelement <8 x double> poison, double [[V1_LANE_7]], i32 0
; CHECK-NEXT: [[TMP14:%.*]] = insertelement <8 x double> [[TMP13]], double [[V1_LANE_6]], i32 1
; CHECK-NEXT: [[TMP15:%.*]] = insertelement <8 x double> [[TMP14]], double [[V1_LANE_8]], i32 2
@@ -605,7 +613,8 @@ define void @first_and_second_mul_chain_jumbled(<9 x double>* %ptr.1, <4 x doubl
; CHECK-NEXT: [[TMP24:%.*]] = fmul <8 x double> [[TMP20]], [[SHUFFLE]]
; CHECK-NEXT: [[B_LANE_8:%.*]] = fmul double [[V1_LANE_4]], [[V2_LANE_2]]
; CHECK-NEXT: [[TMP25:%.*]] = shufflevector <8 x double> [[TMP24]], <8 x double> poison, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef>
-; CHECK-NEXT: [[B_INS_8:%.*]] = insertelement <9 x double> [[TMP25]], double [[B_LANE_8]], i32 8
+; CHECK-NEXT: [[B_INS_71:%.*]] = shufflevector <9 x double> undef, <9 x double> [[TMP25]], <9 x i32> <i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 8>
+; CHECK-NEXT: [[B_INS_8:%.*]] = insertelement <9 x double> [[B_INS_71]], double [[B_LANE_8]], i32 8
; CHECK-NEXT: [[RES:%.*]] = fsub <9 x double> [[A_INS_8]], [[B_INS_8]]
; CHECK-NEXT: store <9 x double> [[RES]], <9 x double>* [[PTR_1]], align 8
; CHECK-NEXT: ret void
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/arith-fp-inseltpoison.ll b/llvm/test/Transforms/SLPVectorizer/X86/arith-fp-inseltpoison.ll
index d059b32c7217..1e9e435e855a 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/arith-fp-inseltpoison.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/arith-fp-inseltpoison.ll
@@ -644,13 +644,14 @@ define <8 x double> @buildvector_div_8f64(<8 x double> %a, <8 x double> %b) {
; SLM-NEXT: [[TMP19:%.*]] = insertelement <2 x double> [[TMP18]], double [[B7]], i32 1
; SLM-NEXT: [[TMP20:%.*]] = fdiv <2 x double> [[TMP17]], [[TMP19]]
; SLM-NEXT: [[TMP21:%.*]] = shufflevector <2 x double> [[TMP5]], <2 x double> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+; SLM-NEXT: [[R11:%.*]] = shufflevector <8 x double> poison, <8 x double> [[TMP21]], <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; SLM-NEXT: [[TMP22:%.*]] = shufflevector <2 x double> [[TMP10]], <2 x double> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
-; SLM-NEXT: [[R31:%.*]] = shufflevector <8 x double> [[TMP21]], <8 x double> [[TMP22]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; SLM-NEXT: [[R32:%.*]] = shufflevector <8 x double> [[R11]], <8 x double> [[TMP22]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
; SLM-NEXT: [[TMP23:%.*]] = shufflevector <2 x double> [[TMP15]], <2 x double> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
-; SLM-NEXT: [[R52:%.*]] = shufflevector <8 x double> [[R31]], <8 x double> [[TMP23]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
+; SLM-NEXT: [[R53:%.*]] = shufflevector <8 x double> [[R32]], <8 x double> [[TMP23]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
; SLM-NEXT: [[TMP24:%.*]] = shufflevector <2 x double> [[TMP20]], <2 x double> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
-; SLM-NEXT: [[R73:%.*]] = shufflevector <8 x double> [[R52]], <8 x double> [[TMP24]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
-; SLM-NEXT: ret <8 x double> [[R73]]
+; SLM-NEXT: [[R74:%.*]] = shufflevector <8 x double> [[R53]], <8 x double> [[TMP24]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
+; SLM-NEXT: ret <8 x double> [[R74]]
;
; AVX-LABEL: @buildvector_div_8f64(
; AVX-NEXT: [[TMP1:%.*]] = fdiv <8 x double> [[A:%.*]], [[B:%.*]]
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/arith-fp.ll b/llvm/test/Transforms/SLPVectorizer/X86/arith-fp.ll
index 70e55d760b03..733f3ede42a3 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/arith-fp.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/arith-fp.ll
@@ -644,13 +644,14 @@ define <8 x double> @buildvector_div_8f64(<8 x double> %a, <8 x double> %b) {
; SLM-NEXT: [[TMP19:%.*]] = insertelement <2 x double> [[TMP18]], double [[B7]], i32 1
; SLM-NEXT: [[TMP20:%.*]] = fdiv <2 x double> [[TMP17]], [[TMP19]]
; SLM-NEXT: [[TMP21:%.*]] = shufflevector <2 x double> [[TMP5]], <2 x double> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+; SLM-NEXT: [[R11:%.*]] = shufflevector <8 x double> undef, <8 x double> [[TMP21]], <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; SLM-NEXT: [[TMP22:%.*]] = shufflevector <2 x double> [[TMP10]], <2 x double> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
-; SLM-NEXT: [[R31:%.*]] = shufflevector <8 x double> [[TMP21]], <8 x double> [[TMP22]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; SLM-NEXT: [[R32:%.*]] = shufflevector <8 x double> [[R11]], <8 x double> [[TMP22]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
; SLM-NEXT: [[TMP23:%.*]] = shufflevector <2 x double> [[TMP15]], <2 x double> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
-; SLM-NEXT: [[R52:%.*]] = shufflevector <8 x double> [[R31]], <8 x double> [[TMP23]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
+; SLM-NEXT: [[R53:%.*]] = shufflevector <8 x double> [[R32]], <8 x double> [[TMP23]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
; SLM-NEXT: [[TMP24:%.*]] = shufflevector <2 x double> [[TMP20]], <2 x double> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
-; SLM-NEXT: [[R73:%.*]] = shufflevector <8 x double> [[R52]], <8 x double> [[TMP24]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
-; SLM-NEXT: ret <8 x double> [[R73]]
+; SLM-NEXT: [[R74:%.*]] = shufflevector <8 x double> [[R53]], <8 x double> [[TMP24]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
+; SLM-NEXT: ret <8 x double> [[R74]]
;
; AVX-LABEL: @buildvector_div_8f64(
; AVX-NEXT: [[TMP1:%.*]] = fdiv <8 x double> [[A:%.*]], [[B:%.*]]
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector-inseltpoison.ll b/llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector-inseltpoison.ll
index 0250292b3503..fb7af465f015 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector-inseltpoison.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector-inseltpoison.ll
@@ -300,6 +300,7 @@ define <4 x float> @simple_select_no_users(<4 x float> %a, <4 x float> %b, <4 x
; CHECK-NEXT: [[TMP15:%.*]] = insertelement <2 x float> [[TMP14]], float [[B3]], i32 1
; CHECK-NEXT: [[TMP16:%.*]] = select <2 x i1> [[TMP6]], <2 x float> [[TMP13]], <2 x float> [[TMP15]]
; CHECK-NEXT: [[TMP17:%.*]] = shufflevector <2 x float> [[TMP11]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
+; CHECK-NEXT: [[RB2:%.*]] = shufflevector <4 x float> poison, <4 x float> [[TMP17]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; CHECK-NEXT: [[TMP18:%.*]] = shufflevector <2 x float> [[TMP16]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
; CHECK-NEXT: [[RD1:%.*]] = shufflevector <4 x float> poison, <4 x float> [[TMP18]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; CHECK-NEXT: ret <4 x float> [[RD1]]
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll b/llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll
index fe3e86d142f5..7101ed2bb409 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll
@@ -335,6 +335,7 @@ define <4 x float> @simple_select_no_users(<4 x float> %a, <4 x float> %b, <4 x
; CHECK-NEXT: [[TMP15:%.*]] = insertelement <2 x float> [[TMP14]], float [[B3]], i32 1
; CHECK-NEXT: [[TMP16:%.*]] = select <2 x i1> [[TMP6]], <2 x float> [[TMP13]], <2 x float> [[TMP15]]
; CHECK-NEXT: [[TMP17:%.*]] = shufflevector <2 x float> [[TMP11]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
+; CHECK-NEXT: [[RB2:%.*]] = shufflevector <4 x float> undef, <4 x float> [[TMP17]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; CHECK-NEXT: [[TMP18:%.*]] = shufflevector <2 x float> [[TMP16]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
; CHECK-NEXT: [[RD1:%.*]] = shufflevector <4 x float> undef, <4 x float> [[TMP18]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; CHECK-NEXT: ret <4 x float> [[RD1]]
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/load-merge-inseltpoison.ll b/llvm/test/Transforms/SLPVectorizer/X86/load-merge-inseltpoison.ll
index f9a5434b0400..c1e578c9f402 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/load-merge-inseltpoison.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/load-merge-inseltpoison.ll
@@ -58,7 +58,8 @@ define <4 x float> @PR16739_byref(<4 x float>* nocapture readonly dereferenceabl
; CHECK-NEXT: [[TMP2:%.*]] = load <2 x float>, <2 x float>* [[TMP1]], align 4
; CHECK-NEXT: [[X2:%.*]] = load float, float* [[GEP2]], align 4
; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
-; CHECK-NEXT: [[I2:%.*]] = insertelement <4 x float> [[TMP3]], float [[X2]], i32 2
+; CHECK-NEXT: [[I11:%.*]] = shufflevector <4 x float> poison, <4 x float> [[TMP3]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
+; CHECK-NEXT: [[I2:%.*]] = insertelement <4 x float> [[I11]], float [[X2]], i32 2
; CHECK-NEXT: [[I3:%.*]] = insertelement <4 x float> [[I2]], float [[X2]], i32 3
; CHECK-NEXT: ret <4 x float> [[I3]]
;
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/load-merge.ll b/llvm/test/Transforms/SLPVectorizer/X86/load-merge.ll
index a8c83781d3aa..0c8e916c7f04 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/load-merge.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/load-merge.ll
@@ -58,7 +58,8 @@ define <4 x float> @PR16739_byref(<4 x float>* nocapture readonly dereferenceabl
; CHECK-NEXT: [[TMP2:%.*]] = load <2 x float>, <2 x float>* [[TMP1]], align 4
; CHECK-NEXT: [[X2:%.*]] = load float, float* [[GEP2]], align 4
; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
-; CHECK-NEXT: [[I2:%.*]] = insertelement <4 x float> [[TMP3]], float [[X2]], i32 2
+; CHECK-NEXT: [[I11:%.*]] = shufflevector <4 x float> undef, <4 x float> [[TMP3]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
+; CHECK-NEXT: [[I2:%.*]] = insertelement <4 x float> [[I11]], float [[X2]], i32 2
; CHECK-NEXT: [[I3:%.*]] = insertelement <4 x float> [[I2]], float [[X2]], i32 3
; CHECK-NEXT: ret <4 x float> [[I3]]
;
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/sitofp-inseltpoison.ll b/llvm/test/Transforms/SLPVectorizer/X86/sitofp-inseltpoison.ll
index 0188dd74f7a0..3418b6e01696 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/sitofp-inseltpoison.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/sitofp-inseltpoison.ll
@@ -1072,9 +1072,10 @@ define <4 x double> @sitofp_4xi32_4f64(i32 %a0, i32 %a1, i32 %a2, i32 %a3) #0 {
; SSE-NEXT: [[TMP5:%.*]] = insertelement <2 x i32> [[TMP4]], i32 [[A3:%.*]], i32 1
; SSE-NEXT: [[TMP6:%.*]] = sitofp <2 x i32> [[TMP5]] to <2 x double>
; SSE-NEXT: [[TMP7:%.*]] = shufflevector <2 x double> [[TMP3]], <2 x double> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
+; SSE-NEXT: [[RES11:%.*]] = shufflevector <4 x double> poison, <4 x double> [[TMP7]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; SSE-NEXT: [[TMP8:%.*]] = shufflevector <2 x double> [[TMP6]], <2 x double> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
-; SSE-NEXT: [[RES31:%.*]] = shufflevector <4 x double> [[TMP7]], <4 x double> [[TMP8]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
-; SSE-NEXT: ret <4 x double> [[RES31]]
+; SSE-NEXT: [[RES32:%.*]] = shufflevector <4 x double> [[RES11]], <4 x double> [[TMP8]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
+; SSE-NEXT: ret <4 x double> [[RES32]]
;
; AVX-LABEL: @sitofp_4xi32_4f64(
; AVX-NEXT: [[TMP1:%.*]] = insertelement <4 x i32> poison, i32 [[A0:%.*]], i32 0
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/sitofp.ll b/llvm/test/Transforms/SLPVectorizer/X86/sitofp.ll
index 4939d79c5c6d..5cec75d85fea 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/sitofp.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/sitofp.ll
@@ -1072,9 +1072,10 @@ define <4 x double> @sitofp_4xi32_4f64(i32 %a0, i32 %a1, i32 %a2, i32 %a3) #0 {
; SSE-NEXT: [[TMP5:%.*]] = insertelement <2 x i32> [[TMP4]], i32 [[A3:%.*]], i32 1
; SSE-NEXT: [[TMP6:%.*]] = sitofp <2 x i32> [[TMP5]] to <2 x double>
; SSE-NEXT: [[TMP7:%.*]] = shufflevector <2 x double> [[TMP3]], <2 x double> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
+; SSE-NEXT: [[RES11:%.*]] = shufflevector <4 x double> undef, <4 x double> [[TMP7]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; SSE-NEXT: [[TMP8:%.*]] = shufflevector <2 x double> [[TMP6]], <2 x double> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
-; SSE-NEXT: [[RES31:%.*]] = shufflevector <4 x double> [[TMP7]], <4 x double> [[TMP8]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
-; SSE-NEXT: ret <4 x double> [[RES31]]
+; SSE-NEXT: [[RES32:%.*]] = shufflevector <4 x double> [[RES11]], <4 x double> [[TMP8]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
+; SSE-NEXT: ret <4 x double> [[RES32]]
;
; AVX-LABEL: @sitofp_4xi32_4f64(
; AVX-NEXT: [[TMP1:%.*]] = insertelement <4 x i32> poison, i32 [[A0:%.*]], i32 0
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/value-bug-inseltpoison.ll b/llvm/test/Transforms/SLPVectorizer/X86/value-bug-inseltpoison.ll
index 5aaa4dad4e97..fc41ec9e9386 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/value-bug-inseltpoison.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/value-bug-inseltpoison.ll
@@ -91,7 +91,7 @@ exit:
define <4 x double> @constant_folding() {
; CHECK-LABEL: @constant_folding(
; CHECK-NEXT: entry:
-; CHECK-NEXT: ret <4 x double> <double 2.000000e+00, double 1.000000e+00, double undef, double undef>
+; CHECK-NEXT: ret <4 x double> <double 2.000000e+00, double 1.000000e+00, double poison, double poison>
;
entry:
%t0 = fadd double 1.000000e+00 , 0.000000e+00
More information about the llvm-commits
mailing list