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

[X86] When applying the shuffle-to-zero-extend transformation on floating point, bitcast to integer first. 

Fix issue described in PR34577.

Differential Revision: https://reviews.llvm.org/D37803

llvm-svn: 313256
This commit is contained in:
Ayman Musa 2017-09-14 12:06:38 +00:00
parent 5891060ff8
commit ab68449c53
2 changed files with 71 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -27153,13 +27153,18 @@ static bool matchUnaryVectorShuffle(MVT MaskVT, ArrayRef<int> Mask,
}
if (Match) {
unsigned SrcSize = std::max(128u, NumDstElts * MaskEltSize);
SrcVT = MVT::getVectorVT(MaskVT.getScalarType(), SrcSize / MaskEltSize);
if (SrcVT != MaskVT)
MVT ScalarTy = MaskVT.isInteger() ? MaskVT.getScalarType() :
MVT::getIntegerVT(MaskEltSize);
SrcVT = MVT::getVectorVT(ScalarTy, SrcSize / MaskEltSize);
if (SrcVT.getSizeInBits() != MaskVT.getSizeInBits()) {
V1 = extractSubVector(V1, 0, DAG, DL, SrcSize);
Shuffle = unsigned(X86ISD::VZEXT);
} else
Shuffle = unsigned(ISD::ZERO_EXTEND_VECTOR_INREG);
DstVT = MVT::getIntegerVT(Scale * MaskEltSize);
DstVT = MVT::getVectorVT(DstVT, NumDstElts);
Shuffle = SrcVT != MaskVT ? unsigned(X86ISD::VZEXT)
: unsigned(ISD::ZERO_EXTEND_VECTOR_INREG);
return true;
}
}

62
llvm/test/CodeGen/X86/vector-shuffle-combining-avx2.ll
View File

@ -897,3 +897,65 @@ define <32 x i8> @PR27320(<8 x i32> %a0) {
%3 = shufflevector <32 x i8> %2, <32 x i8> undef, <32 x i32> <i32 0, i32 1, i32 1, i32 2, i32 3, i32 4, i32 4, i32 5, i32 6, i32 7, i32 7, i32 8, i32 9, i32 10, i32 10, i32 11, i32 16, i32 17, i32 17, i32 18, i32 19, i32 20, i32 20, i32 21, i32 22, i32 23, i32 23, i32 24, i32 25, i32 26, i32 26, i32 27>
ret <32 x i8> %3
}
define internal fastcc <8 x float> @PR34577(<8 x float> %inp0, <8 x float> %inp1, <8 x float> %inp2) {
; X32-AVX2-LABEL: PR34577:
; X32-AVX2: # BB#0: # %entry
; X32-AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2
; X32-AVX2-NEXT: vpmovzxdq {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; X32-AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm2[0,1,2,3],ymm0[4,5,6,7]
; X32-AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <u,u,7,2,u,u,3,2>
; X32-AVX2-NEXT: vpermps %ymm1, %ymm2, %ymm1
; X32-AVX2-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3]
; X32-AVX2-NEXT: retl
;
; X32-AVX512-LABEL: PR34577:
; X32-AVX512: # BB#0: # %entry
; X32-AVX512-NEXT: vmovaps {{.*#+}} ymm3 = <1,u,u,u,2,u,5,0>
; X32-AVX512-NEXT: vpermps %ymm0, %ymm3, %ymm0
; X32-AVX512-NEXT: vmovaps {{.*#+}} ymm3 = <u,2,3,5,u,5,u,u>
; X32-AVX512-NEXT: vpermps %ymm2, %ymm3, %ymm2
; X32-AVX512-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm2[1,2,3],ymm0[4],ymm2[5],ymm0[6,7]
; X32-AVX512-NEXT: vxorps %xmm2, %xmm2, %xmm2
; X32-AVX512-NEXT: movb $86, %al
; X32-AVX512-NEXT: kmovw %eax, %k1
; X32-AVX512-NEXT: vblendmps %zmm0, %zmm2, %zmm0 {%k1}
; X32-AVX512-NEXT: vblendpd {{.*#+}} ymm0 = ymm2[0,1],ymm0[2,3]
; X32-AVX512-NEXT: vmovaps {{.*#+}} ymm2 = <u,u,7,2,u,u,3,2>
; X32-AVX512-NEXT: vpermps %ymm1, %ymm2, %ymm1
; X32-AVX512-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3]
; X32-AVX512-NEXT: retl
;
; X64-AVX2-LABEL: PR34577:
; X64-AVX2: # BB#0: # %entry
; X64-AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2
; X64-AVX2-NEXT: vpmovzxdq {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; X64-AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm2[0,1,2,3],ymm0[4,5,6,7]
; X64-AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <u,u,7,2,u,u,3,2>
; X64-AVX2-NEXT: vpermps %ymm1, %ymm2, %ymm1
; X64-AVX2-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3]
; X64-AVX2-NEXT: retq
;
; X64-AVX512-LABEL: PR34577:
; X64-AVX512: # BB#0: # %entry
; X64-AVX512-NEXT: vmovaps {{.*#+}} ymm3 = <1,u,u,u,2,u,5,0>
; X64-AVX512-NEXT: vpermps %ymm0, %ymm3, %ymm0
; X64-AVX512-NEXT: vmovaps {{.*#+}} ymm3 = <u,2,3,5,u,5,u,u>
; X64-AVX512-NEXT: vpermps %ymm2, %ymm3, %ymm2
; X64-AVX512-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm2[1,2,3],ymm0[4],ymm2[5],ymm0[6,7]
; X64-AVX512-NEXT: vxorps %xmm2, %xmm2, %xmm2
; X64-AVX512-NEXT: movb $86, %al
; X64-AVX512-NEXT: kmovw %eax, %k1
; X64-AVX512-NEXT: vblendmps %zmm0, %zmm2, %zmm0 {%k1}
; X64-AVX512-NEXT: vblendpd {{.*#+}} ymm0 = ymm2[0,1],ymm0[2,3]
; X64-AVX512-NEXT: vmovaps {{.*#+}} ymm2 = <u,u,7,2,u,u,3,2>
; X64-AVX512-NEXT: vpermps %ymm1, %ymm2, %ymm1
; X64-AVX512-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3]
; X64-AVX512-NEXT: retq
entry:
%shuf0 = shufflevector <8 x float> %inp0, <8 x float> %inp2, <8 x i32> <i32 1, i32 10, i32 11, i32 13, i32 2, i32 13, i32 5, i32 0>
%sel = select <8 x i1> <i1 false, i1 true, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false>, <8 x float> %shuf0, <8 x float> zeroinitializer
%shuf1 = shufflevector <8 x float> zeroinitializer, <8 x float> %sel, <8 x i32> <i32 6, i32 11, i32 6, i32 15, i32 12, i32 11, i32 1, i32 3>
%shuf2 = shufflevector <8 x float> %inp1, <8 x float> %shuf1, <8 x i32> <i32 15, i32 10, i32 7, i32 2, i32 12, i32 undef, i32 3, i32 2>
ret <8 x float> %shuf2
}