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

[X86][SSE] Attempt to combine 64-bit and 32-bit shuffles to unary shuffles before bit shifts 

We are combining shuffles to bit shifts before unary permutes, which means we can't fold loads plus the destination register is destructive

llvm-svn: 306978
This commit is contained in:
Simon Pilgrim 2017-07-02 14:16:25 +00:00
parent 4cb5613c38
commit 8971b2904e
3 changed files with 23 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -27156,6 +27156,26 @@ static bool matchUnaryPermuteVectorShuffle(MVT MaskVT, ArrayRef<int> Mask,
}
}
// Handle PSHUFD/VPERMILPI vXi32/vXf32 repeated patterns.
// AVX introduced the VPERMILPD/VPERMILPS float permutes, before then we
// had to use 2-input SHUFPD/SHUFPS shuffles (not handled here).
if ((MaskScalarSizeInBits == 64 || MaskScalarSizeInBits == 32) &&
!ContainsZeros && (AllowIntDomain || Subtarget.hasAVX())) {
SmallVector<int, 4> RepeatedMask;
if (is128BitLaneRepeatedShuffleMask(MaskEltVT, Mask, RepeatedMask)) {
// Narrow the repeated mask to create 32-bit element permutes.
SmallVector<int, 4> WordMask = RepeatedMask;
if (MaskScalarSizeInBits == 64)
scaleShuffleMask(2, RepeatedMask, WordMask);
Shuffle = (AllowIntDomain ? X86ISD::PSHUFD : X86ISD::VPERMILPI);
ShuffleVT = (AllowIntDomain ? MVT::i32 : MVT::f32);
ShuffleVT = MVT::getVectorVT(ShuffleVT, InputSizeInBits / 32);
PermuteImm = getV4X86ShuffleImm(WordMask);
return true;
}
}
// Handle PSHUFLW/PSHUFHW vXi16 repeated patterns.
if (!ContainsZeros && AllowIntDomain && MaskScalarSizeInBits == 16) {
SmallVector<int, 4> RepeatedMask;
@ -27201,38 +27221,7 @@ static bool matchUnaryPermuteVectorShuffle(MVT MaskVT, ArrayRef<int> Mask,
}
}
// Ensure we don't contain any zero elements.
if (ContainsZeros)
return false;
assert(llvm::all_of(Mask, [&](int M) {
return SM_SentinelUndef <= M && M < (int)NumMaskElts;
}) && "Expected unary shuffle");
// We only support permutation of 32/64 bit elements after this.
if (MaskScalarSizeInBits != 32 && MaskScalarSizeInBits != 64)
return false;
// AVX introduced the VPERMILPD/VPERMILPS float permutes, before then we
// had to use 2-input SHUFPD/SHUFPS shuffles (not handled here).
if ((AllowFloatDomain && !AllowIntDomain) && !Subtarget.hasAVX())
return false;
// We need a repeating shuffle mask for VPERMILPS/PSHUFD.
SmallVector<int, 4> RepeatedMask;
if (!is128BitLaneRepeatedShuffleMask(MaskEltVT, Mask, RepeatedMask))
return false;
// Narrow the repeated mask for 32-bit element permutes.
SmallVector<int, 4> WordMask = RepeatedMask;
if (MaskScalarSizeInBits == 64)
scaleShuffleMask(2, RepeatedMask, WordMask);
Shuffle = (AllowFloatDomain ? X86ISD::VPERMILPI : X86ISD::PSHUFD);
ShuffleVT = (AllowFloatDomain ? MVT::f32 : MVT::i32);
ShuffleVT = MVT::getVectorVT(ShuffleVT, InputSizeInBits / 32);
PermuteImm = getV4X86ShuffleImm(WordMask);
return true;
return false;
}
// Attempt to match a combined unary shuffle mask against supported binary

2
llvm/test/CodeGen/X86/cast-vsel.ll
View File

@ -148,7 +148,7 @@ define <4 x double> @fpext(<4 x double> %a, <4 x double> %b, <4 x float> %c, <4
; SSE2-NEXT: andnps %xmm5, %xmm0
; SSE2-NEXT: orps %xmm4, %xmm0
; SSE2-NEXT: cvtps2pd %xmm0, %xmm2
; SSE2-NEXT: psrldq {{.*#+}} xmm0 = xmm0[8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero,zero,zero
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,2,3]
; SSE2-NEXT: cvtps2pd %xmm0, %xmm1
; SSE2-NEXT: movaps %xmm2, %xmm0
; SSE2-NEXT: retq

2
llvm/test/CodeGen/X86/extract-store.ll
View File

@ -345,7 +345,7 @@ define void @extract_i64_1(i64* nocapture %dst, <2 x i64> %foo) nounwind {
; SSE-X32-LABEL: extract_i64_1:
; SSE-X32: # BB#0:
; SSE-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE-X32-NEXT: psrldq {{.*#+}} xmm0 = xmm0[8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero,zero,zero
; SSE-X32-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,2,3]
; SSE-X32-NEXT: movq %xmm0, (%eax)
; SSE-X32-NEXT: retl
;