maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[x86] In the new vector shuffle lowering, when trying to do another 

layer of tie-breaking sorting, it really helps to check that you're in
a tie first. =] Otherwise the whole thing cycles infinitely. Test case
added, another one found through fuzz testing.

llvm-svn: 218523
This commit is contained in:
Chandler Carruth 2014-09-26 17:24:26 +00:00
parent 5afd4c2603
commit 0c9ee10d01
2 changed files with 35 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -9959,17 +9959,18 @@ static SDValue lowerVectorShuffle(SDValue Op, const X86Subtarget *Subtarget,
++LowV2Elements;
else if (M >= 0)
++LowV1Elements;
if (LowV2Elements > LowV1Elements)
return DAG.getCommutedVectorShuffle(*SVOp);
int SumV1Indices = 0, SumV2Indices = 0;
for (int i = 0, Size = SVOp->getMask().size(); i < Size; ++i)
if (SVOp->getMask()[i] >= NumElements)
SumV2Indices += i;
else if (SVOp->getMask()[i] >= 0)
SumV1Indices += i;
if (SumV2Indices < SumV1Indices)
if (LowV2Elements > LowV1Elements) {
return DAG.getCommutedVectorShuffle(*SVOp);
} else if (LowV2Elements == LowV1Elements) {
int SumV1Indices = 0, SumV2Indices = 0;
for (int i = 0, Size = SVOp->getMask().size(); i < Size; ++i)
if (SVOp->getMask()[i] >= NumElements)
SumV2Indices += i;
else if (SVOp->getMask()[i] >= 0)
SumV1Indices += i;
if (SumV2Indices < SumV1Indices)
return DAG.getCommutedVectorShuffle(*SVOp);
}
}
// For each vector width, delegate to a specialized lowering routine.

24
llvm/test/CodeGen/X86/vector-shuffle-256-v8.ll
View File

@ -669,6 +669,30 @@ define <8 x float> @shuffle_v8f32_c348cda0(<8 x float> %a, <8 x float> %b) {
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_f511235a(<8 x float> %a, <8 x float> %b) {
; AVX1-LABEL: @shuffle_v8f32_f511235a
; AVX1: # BB#0:
; AVX1-NEXT: vperm2f128 {{.*}} # ymm2 = ymm0[2,3,0,1]
; AVX1-NEXT: vpermilps {{.*}} # ymm2 = ymm2[u,1,u,u,6,7,u,u]
; AVX1-NEXT: vpermilps {{.*}} # ymm0 = ymm0[0,1,1,1,4,5,5,5]
; AVX1-NEXT: vblendps {{.*}} # ymm0 = ymm0[0],ymm2[1],ymm0[2,3],ymm2[4,5],ymm0[6,7]
; AVX1-NEXT: vperm2f128 {{.*}} # ymm1 = ymm1[2,3,0,1]
; AVX1-NEXT: vpermilps {{.*}} # ymm1 = ymm1[3,1,2,2,7,5,6,6]
; AVX1-NEXT: vblendps {{.*}} # ymm0 = ymm1[0],ymm0[1,2,3,4,5,6],ymm1[7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: @shuffle_v8f32_f511235a
; AVX2: # BB#0:
; AVX2-NEXT: vmovaps {{.*}} # ymm2 = <7,u,u,u,u,u,u,2>
; AVX2-NEXT: vpermps %ymm1, %ymm2, %ymm1
; AVX2-NEXT: vmovaps {{.*}} # ymm2 = <u,5,1,1,2,3,5,u>
; AVX2-NEXT: vpermps %ymm0, %ymm2, %ymm0
; AVX2-NEXT: vblendps {{.*}} # ymm0 = ymm1[0],ymm0[1,2,3,4,5,6],ymm1[7]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 15, i32 5, i32 1, i32 1, i32 2, i32 3, i32 5, i32 10>
ret <8 x float> %shuffle
}
define <8 x i32> @shuffle_v8i32_00000000(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: @shuffle_v8i32_00000000
; AVX1: # BB#0: