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

[X86][SSE] Use bitmasks instead of shuffles where possible. 

VPAND is a lot faster than VPSHUFB and VPBLENDVB - this patch ensures we attempt to lower to a basic bitmask before lowering to the slower byte shuffle/blend instructions.

Split off from D11518.

Differential Revision: http://reviews.llvm.org/D11541

llvm-svn: 243395
This commit is contained in:
Simon Pilgrim 2015-07-28 08:54:41 +00:00
parent 74da38706e
commit df984f58ad
4 changed files with 27 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -6663,6 +6663,10 @@ static SDValue lowerVectorShuffleAsBlend(SDLoc DL, MVT VT, SDValue V1,
assert((VT.getSizeInBits() == 128 || Subtarget->hasAVX2()) &&
"256-bit byte-blends require AVX2 support!");
// Attempt to lower to a bitmask if we can. VPAND is faster than VPBLENDVB.
if (SDValue Masked = lowerVectorShuffleAsBitMask(DL, VT, V1, V2, Mask, DAG))
return Masked;
// Scale the blend by the number of bytes per element.
int Scale = VT.getScalarSizeInBits() / 8;
@ -9071,6 +9075,10 @@ static SDValue lowerV16I8VectorShuffle(SDValue Op, SDValue V1, SDValue V2,
return V;
}
if (SDValue Masked =
lowerVectorShuffleAsBitMask(DL, MVT::v16i8, V1, V2, Mask, DAG))
return Masked;
// Use dedicated unpack instructions for masks that match their pattern.
if (isShuffleEquivalent(V1, V2, Mask, {// Low half.
0, 16, 1, 17, 2, 18, 3, 19,

24
llvm/test/CodeGen/X86/vector-shuffle-128-v16.ll
View File

@ -470,28 +470,14 @@ define <16 x i8> @shuffle_v16i8_00_01_02_19_04_05_06_23_08_09_10_27_12_13_14_31(
}
define <16 x i8> @shuffle_v16i8_00_01_02_zz_04_05_06_zz_08_09_10_zz_12_13_14_zz(<16 x i8> %a) {
; SSE2-LABEL: shuffle_v16i8_00_01_02_zz_04_05_06_zz_08_09_10_zz_12_13_14_zz:
; SSE2: # BB#0:
; SSE2-NEXT: xorps %xmm1, %xmm1
; SSE2-NEXT: movaps {{.*#+}} xmm2 = [255,255,255,0,255,255,255,0,255,255,255,0,255,255,255,0]
; SSE2-NEXT: andps %xmm2, %xmm0
; SSE2-NEXT: andnps %xmm1, %xmm2
; SSE2-NEXT: orps %xmm2, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: shuffle_v16i8_00_01_02_zz_04_05_06_zz_08_09_10_zz_12_13_14_zz:
; SSSE3: # BB#0:
; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,1,2],zero,xmm0[4,5,6],zero,xmm0[8,9,10],zero,xmm0[12,13,14],zero
; SSSE3-NEXT: retq
;
; SSE41-LABEL: shuffle_v16i8_00_01_02_zz_04_05_06_zz_08_09_10_zz_12_13_14_zz:
; SSE41: # BB#0:
; SSE41-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,1,2],zero,xmm0[4,5,6],zero,xmm0[8,9,10],zero,xmm0[12,13,14],zero
; SSE41-NEXT: retq
; SSE-LABEL: shuffle_v16i8_00_01_02_zz_04_05_06_zz_08_09_10_zz_12_13_14_zz:
; SSE: # BB#0:
; SSE-NEXT: andps {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: shuffle_v16i8_00_01_02_zz_04_05_06_zz_08_09_10_zz_12_13_14_zz:
; AVX: # BB#0:
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,2],zero,xmm0[4,5,6],zero,xmm0[8,9,10],zero,xmm0[12,13,14],zero
; AVX-NEXT: vandps {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
%shuffle = shufflevector <16 x i8> %a, <16 x i8> zeroinitializer, <16 x i32> <i32 0, i32 1, i32 2, i32 19, i32 4, i32 5, i32 6, i32 23, i32 8, i32 9, i32 10, i32 27, i32 12, i32 13, i32 14, i32 31>
ret <16 x i8> %shuffle

10
llvm/test/CodeGen/X86/vector-shuffle-256-v32.ll
View File

@ -951,17 +951,15 @@ define <32 x i8> @shuffle_v32i8_zz_01_zz_03_zz_05_zz_07_zz_09_zz_11_zz_13_zz_15_
; AVX1-LABEL: shuffle_v32i8_zz_01_zz_03_zz_05_zz_07_zz_09_zz_11_zz_13_zz_15_zz_17_zz_19_zz_21_zz_23_zz_25_zz_27_zz_29_zz_31:
; AVX1: # BB#0:
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [128,1,128,3,128,5,128,7,128,9,128,11,128,13,128,15]
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vmovaps {{.*#+}} xmm2 = [0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255]
; AVX1-NEXT: vandps %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vandps %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v32i8_zz_01_zz_03_zz_05_zz_07_zz_09_zz_11_zz_13_zz_15_zz_17_zz_19_zz_21_zz_23_zz_25_zz_27_zz_29_zz_31:
; AVX2: # BB#0:
; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
; AVX2-NEXT: vpxor %ymm2, %ymm2, %ymm2
; AVX2-NEXT: vpblendvb %ymm1, %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vandps {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: retq
%shuffle = shufflevector <32 x i8> %a, <32 x i8> zeroinitializer, <32 x i32> <i32 32, i32 1, i32 34, i32 3, i32 36, i32 5, i32 38, i32 7, i32 40, i32 9, i32 42, i32 11, i32 44, i32 13, i32 46, i32 15, i32 48, i32 17, i32 50, i32 19, i32 52, i32 21, i32 54, i32 23, i32 56, i32 25, i32 58, i32 27, i32 60, i32 29, i32 62, i32 31>
ret <32 x i8> %shuffle

21
llvm/test/CodeGen/X86/vector-zext.ll
View File

@ -1092,17 +1092,16 @@ entry:
define <8 x i32> @shuf_zext_8i8_to_8i32(<8 x i8> %A) {
; SSE2-LABEL: shuf_zext_8i8_to_8i32:
; SSE2: # BB#0: # %entry
; SSE2-NEXT: pand {{.*}}(%rip), %xmm0
; SSE2-NEXT: packuswb %xmm0, %xmm0
; SSE2-NEXT: pxor %xmm1, %xmm1
; SSE2-NEXT: movdqa %xmm0, %xmm2
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3],xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
; SSE2-NEXT: movdqa {{.*#+}} xmm1 = [0,255,255,255,0,255,255,255,0,255,255,255,0,255,255,255]
; SSE2-NEXT: pandn %xmm0, %xmm1
; SSE2-NEXT: movdqa %xmm2, %xmm0
; SSE2-NEXT: movdqa %xmm0, %xmm1
; SSE2-NEXT: pand {{.*}}(%rip), %xmm1
; SSE2-NEXT: packuswb %xmm1, %xmm1
; SSE2-NEXT: pxor %xmm2, %xmm2
; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4,4,5,5,6,6,7,7]
; SSE2-NEXT: pand {{.*}}(%rip), %xmm1
; SSE2-NEXT: retq
;
; SSSE3-LABEL: shuf_zext_8i8_to_8i32: