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

[X86][SSE] Improved blend+zero target shuffle combining to use combined shuffle mask directly 

We currently only combine to blend+zero if the target value type has 8 elements or less, but this was missing a lot of cases where the combined mask had been widened.

This change makes it so we use the combined mask to determine the blend value type, allowing us to catch more widened cases.

llvm-svn: 272003
This commit is contained in:
Simon Pilgrim 2016-06-07 12:20:14 +00:00
parent 53298a1808
commit ca1da1bf07
4 changed files with 59 additions and 38 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -24602,23 +24602,27 @@ static bool combineX86ShuffleChain(SDValue Input, SDValue Root,
}
// Attempt to blend with zero.
if (VT.getVectorNumElements() <= 8 &&
if (NumMaskElts <= 8 &&
((Subtarget.hasSSE41() && VT.is128BitVector()) ||
(Subtarget.hasAVX() && VT.is256BitVector()))) {
// Convert VT to a type compatible with X86ISD::BLENDI.
// TODO - add 16i16 support (requires lane duplication).
MVT ShuffleVT = VT;
bool FloatDomain = VT.isFloatingPoint();
MVT ShuffleVT = FloatDomain ? MVT::getFloatingPointVT(MaskEltSizeInBits)
: MVT::getIntegerVT(MaskEltSizeInBits);
ShuffleVT = MVT::getVectorVT(ShuffleVT, NumMaskElts);
if (Subtarget.hasAVX2()) {
if (VT == MVT::v4i64)
if (ShuffleVT == MVT::v4i64)
ShuffleVT = MVT::v8i32;
else if (VT == MVT::v2i64)
else if (ShuffleVT == MVT::v2i64)
ShuffleVT = MVT::v4i32;
} else {
if (VT == MVT::v2i64 || VT == MVT::v4i32)
if (ShuffleVT == MVT::v2i64 || ShuffleVT == MVT::v4i32)
ShuffleVT = MVT::v8i16;
else if (VT == MVT::v4i64)
else if (ShuffleVT == MVT::v4i64)
ShuffleVT = MVT::v4f64;
else if (VT == MVT::v8i32)
else if (ShuffleVT == MVT::v8i32)
ShuffleVT = MVT::v8f32;
}

15
llvm/test/CodeGen/X86/clear_upper_vector_element_bits.ll
View File

@ -347,16 +347,11 @@ define <4 x i32> @_clearupper4xi32b(<4 x i32>) nounwind {
; SSE-NEXT: pinsrw $7, %eax, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: _clearupper4xi32b:
; AVX1: # BB#0:
; AVX1-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: _clearupper4xi32b:
; AVX2: # BB#0:
; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1],zero,zero,xmm0[4,5],zero,zero,xmm0[8,9],zero,zero,xmm0[12,13],zero,zero
; AVX2-NEXT: retq
; AVX-LABEL: _clearupper4xi32b:
; AVX: # BB#0:
; AVX-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7]
; AVX-NEXT: retq
%x16 = bitcast <4 x i32> %0 to <8 x i16>
%r0 = insertelement <8 x i16> %x16, i16 zeroinitializer, i32 1
%r1 = insertelement <8 x i16> %r0, i16 zeroinitializer, i32 3

3
llvm/test/CodeGen/X86/vector-shuffle-combining-xop.ll
View File

@ -107,7 +107,8 @@ define <16 x i8> @combine_vpperm_identity_bitcast(<16 x i8> %a0, <16 x i8> %a1)
define <16 x i8> @combine_vpperm_as_blend_with_zero(<16 x i8> %a0, <16 x i8> %a1) {
; CHECK-LABEL: combine_vpperm_as_blend_with_zero:
; CHECK: # BB#0:
; CHECK-NEXT: vpperm {{.*#+}} xmm0 = xmm0[0,1],zero,zero,xmm0[4,5,6,7],zero,zero,zero,zero,zero,zero,zero,zero
; CHECK-NEXT: vpxor %xmm1, %xmm1, %xmm1
; CHECK-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3],xmm1[4,5,6,7]
; CHECK-NEXT: retq
%res0 = call <16 x i8> @llvm.x86.xop.vpperm(<16 x i8> %a0, <16 x i8> %a1, <16 x i8> <i8 0, i8 1, i8 128, i8 129, i8 4, i8 5, i8 6, i8 7, i8 130, i8 131, i8 132, i8 133, i8 134, i8 135, i8 136, i8 137>)
ret <16 x i8> %res0

61
llvm/test/CodeGen/X86/vector-shuffle-variable-128.ll
View File

@ -1182,26 +1182,47 @@ define <8 x i16> @var_shuffle_v8i16_v8i16_xyxyxy00_i16(<8 x i16> %x, <8 x i16> %
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1,2,3,4,5],xmm0[6,7]
; SSE41-NEXT: retq
;
; AVX-LABEL: var_shuffle_v8i16_v8i16_xyxyxy00_i16:
; AVX: # BB#0:
; AVX-NEXT: movswq %di, %r10
; AVX-NEXT: movswq %si, %r11
; AVX-NEXT: movswq %dx, %rdx
; AVX-NEXT: movswq %cx, %rcx
; AVX-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; AVX-NEXT: movswq %r8w, %rdi
; AVX-NEXT: vmovdqa %xmm1, -{{[0-9]+}}(%rsp)
; AVX-NEXT: movswq %r9w, %rax
; AVX-NEXT: movzwl -40(%rsp,%r10,2), %esi
; AVX-NEXT: vmovd %esi, %xmm0
; AVX-NEXT: vpinsrw $1, -24(%rsp,%r11,2), %xmm0, %xmm0
; AVX-NEXT: vpinsrw $2, -40(%rsp,%rdx,2), %xmm0, %xmm0
; AVX-NEXT: vpinsrw $3, -24(%rsp,%rcx,2), %xmm0, %xmm0
; AVX-NEXT: vpinsrw $4, -40(%rsp,%rdi,2), %xmm0, %xmm0
; AVX-NEXT: vpinsrw $5, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,5],xmm1[6,7]
; AVX-NEXT: retq
; AVX1-LABEL: var_shuffle_v8i16_v8i16_xyxyxy00_i16:
; AVX1: # BB#0:
; AVX1-NEXT: movswq %di, %r10
; AVX1-NEXT: movswq %si, %r11
; AVX1-NEXT: movswq %dx, %rdx
; AVX1-NEXT: movswq %cx, %rcx
; AVX1-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: movswq %r8w, %rdi
; AVX1-NEXT: vmovdqa %xmm1, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: movswq %r9w, %rax
; AVX1-NEXT: movzwl -40(%rsp,%r10,2), %esi
; AVX1-NEXT: vmovd %esi, %xmm0
; AVX1-NEXT: vpinsrw $1, -24(%rsp,%r11,2), %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $2, -40(%rsp,%rdx,2), %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $3, -24(%rsp,%rcx,2), %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $4, -40(%rsp,%rdi,2), %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $5, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,5],xmm1[6,7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: var_shuffle_v8i16_v8i16_xyxyxy00_i16:
; AVX2: # BB#0:
; AVX2-NEXT: movswq %di, %r10
; AVX2-NEXT: movswq %si, %r11
; AVX2-NEXT: movswq %dx, %rdx
; AVX2-NEXT: movswq %cx, %rcx
; AVX2-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: movswq %r8w, %rdi
; AVX2-NEXT: vmovdqa %xmm1, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: movswq %r9w, %rax
; AVX2-NEXT: movzwl -40(%rsp,%r10,2), %esi
; AVX2-NEXT: vmovd %esi, %xmm0
; AVX2-NEXT: vpinsrw $1, -24(%rsp,%r11,2), %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $2, -40(%rsp,%rdx,2), %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $3, -24(%rsp,%rcx,2), %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $4, -40(%rsp,%rdi,2), %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $5, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX2-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[3]
; AVX2-NEXT: retq
%x0 = extractelement <8 x i16> %x, i16 %i0
%y1 = extractelement <8 x i16> %y, i16 %i1
%x2 = extractelement <8 x i16> %x, i16 %i2