summaryrefslogtreecommitdiffstats
path: root/llvm/test/Transforms/SLPVectorizer/X86
diff options
context:
space:
mode:
authorHaojian Wu <hokein.wu@gmail.com>2019-10-31 10:21:24 +0100
committerHaojian Wu <hokein.wu@gmail.com>2019-10-31 10:21:24 +0100
commite65ddcafee547eddb72aa63b1d49f76e46acdd9a (patch)
tree2d5fc60abf28c5ca11d1d3e98ddd7b65a25a8969 /llvm/test/Transforms/SLPVectorizer/X86
parent9d4bbe88915a3a878d8501369f2ce8093a194921 (diff)
downloadbcm5719-llvm-e65ddcafee547eddb72aa63b1d49f76e46acdd9a.tar.gz
bcm5719-llvm-e65ddcafee547eddb72aa63b1d49f76e46acdd9a.zip
Revert "[SLP] Vectorize jumbled stores."
This reverts commit 21d498c9c0f32dcab5bc89ac593aa813b533b43a. This commit causes some crashes on some targets.
Diffstat (limited to 'llvm/test/Transforms/SLPVectorizer/X86')
-rw-r--r--llvm/test/Transforms/SLPVectorizer/X86/store-jumbled.ll7
-rw-r--r--llvm/test/Transforms/SLPVectorizer/X86/stores_vectorize.ll9
2 files changed, 9 insertions, 7 deletions
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/store-jumbled.ll b/llvm/test/Transforms/SLPVectorizer/X86/store-jumbled.ll
index e99864205bf..2255a12342f 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/store-jumbled.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/store-jumbled.ll
@@ -11,20 +11,21 @@ define i32 @jumbled-load(i32* noalias nocapture %in, i32* noalias nocapture %inn
; CHECK-NEXT: [[GEP_3:%.*]] = getelementptr inbounds i32, i32* [[IN_ADDR]], i64 3
; 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: [[REORDER_SHUFFLE:%.*]] = 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: [[GEP_4:%.*]] = getelementptr inbounds i32, i32* [[INN_ADDR]], i64 1
; CHECK-NEXT: [[GEP_5:%.*]] = getelementptr inbounds i32, i32* [[INN_ADDR]], i64 2
; CHECK-NEXT: [[GEP_6:%.*]] = getelementptr inbounds i32, i32* [[INN_ADDR]], i64 3
; CHECK-NEXT: [[TMP3:%.*]] = bitcast i32* [[INN_ADDR]] to <4 x i32>*
; CHECK-NEXT: [[TMP4:%.*]] = load <4 x i32>, <4 x i32>* [[TMP3]], align 4
-; CHECK-NEXT: [[TMP5:%.*]] = mul <4 x i32> [[TMP2]], [[TMP4]]
+; CHECK-NEXT: [[REORDER_SHUFFLE1:%.*]] = shufflevector <4 x i32> [[TMP4]], <4 x i32> undef, <4 x i32> <i32 1, i32 3, i32 0, i32 2>
+; CHECK-NEXT: [[TMP5:%.*]] = mul <4 x i32> [[REORDER_SHUFFLE]], [[REORDER_SHUFFLE1]]
; 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: [[REORDER_SHUFFLE:%.*]] = shufflevector <4 x i32> [[TMP5]], <4 x i32> undef, <4 x i32> <i32 1, i32 3, i32 0, i32 2>
; CHECK-NEXT: [[TMP6:%.*]] = bitcast i32* [[GEP_7]] to <4 x i32>*
-; CHECK-NEXT: store <4 x i32> [[REORDER_SHUFFLE]], <4 x i32>* [[TMP6]], align 4
+; CHECK-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP6]], align 4
; CHECK-NEXT: ret i32 undef
;
%in.addr = getelementptr inbounds i32, i32* %in, i64 0
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/stores_vectorize.ll b/llvm/test/Transforms/SLPVectorizer/X86/stores_vectorize.ll
index fd697f1a7ca..425f3e63416 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/stores_vectorize.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/stores_vectorize.ll
@@ -92,14 +92,15 @@ define void @store_reverse(i64* %p3) {
; CHECK-NEXT: [[ARRAYIDX11:%.*]] = getelementptr inbounds i64, i64* [[P3]], i64 3
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i64* [[P3]] to <4 x i64>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i64>, <4 x i64>* [[TMP0]], align 8
+; CHECK-NEXT: [[REORDER_SHUFFLE:%.*]] = shufflevector <4 x i64> [[TMP1]], <4 x i64> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT: [[ARRAYIDX12:%.*]] = getelementptr inbounds i64, i64* [[P3]], i64 11
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i64* [[ARRAYIDX1]] to <4 x i64>*
; CHECK-NEXT: [[TMP3:%.*]] = load <4 x i64>, <4 x i64>* [[TMP2]], align 8
-; CHECK-NEXT: [[TMP4:%.*]] = shl <4 x i64> [[TMP1]], [[TMP3]]
+; CHECK-NEXT: [[REORDER_SHUFFLE1:%.*]] = shufflevector <4 x i64> [[TMP3]], <4 x i64> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+; CHECK-NEXT: [[TMP4:%.*]] = shl <4 x i64> [[REORDER_SHUFFLE]], [[REORDER_SHUFFLE1]]
; CHECK-NEXT: [[ARRAYIDX14:%.*]] = getelementptr inbounds i64, i64* [[P3]], i64 4
-; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <4 x i64> [[TMP4]], <4 x i64> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
-; CHECK-NEXT: [[TMP6:%.*]] = bitcast i64* [[ARRAYIDX14]] to <4 x i64>*
-; CHECK-NEXT: store <4 x i64> [[TMP5]], <4 x i64>* [[TMP6]], align 8
+; CHECK-NEXT: [[TMP5:%.*]] = bitcast i64* [[ARRAYIDX14]] to <4 x i64>*
+; CHECK-NEXT: store <4 x i64> [[TMP4]], <4 x i64>* [[TMP5]], align 8
; CHECK-NEXT: ret void
;
entry:
OpenPOWER on IntegriCloud