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

[X86][AVX] combineX86ShufflesRecursively - peekThroughOneUseBitcasts subvector before widening. 

This matches what we do for the full sized vector ops at the start of combineX86ShufflesRecursively, and helps getFauxShuffleMask extract more INSERT_SUBVECTOR patterns.
This commit is contained in:
Simon Pilgrim 2020-05-31 19:58:15 +01:00
parent 0cf5ef176b
commit 8f2f613a6e
2 changed files with 36 additions and 76 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -35047,7 +35047,8 @@ static SDValue combineX86ShufflesRecursively(
for (SDValue &Op : OpInputs)
if (Op.getValueSizeInBits() < RootSizeInBits)
Op = widenSubVector(Op, false, Subtarget, DAG, SDLoc(Op), RootSizeInBits);
Op = widenSubVector(peekThroughOneUseBitcasts(Op), false, Subtarget, DAG,
SDLoc(Op), RootSizeInBits);
SmallVector<int, 64> Mask;
SmallVector<SDValue, 16> Ops;

109
llvm/test/CodeGen/X86/vector-reduce-mul.ll
View File

@ -1970,18 +1970,13 @@ define i8 @test_v32i8(<32 x i8> %a0) {
; AVX2-NEXT: vpmullw %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpand %xmm3, %xmm0, %xmm1
; AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX2-NEXT: vpackuswb %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[1,1,2,3]
; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
; AVX2-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[2,3,2,3,6,7,6,7]
; AVX2-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpand %xmm3, %xmm0, %xmm1
; AVX2-NEXT: vpackuswb %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpsrld $16, %xmm1, %xmm1
; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
; AVX2-NEXT: vpshufb {{.*#+}} xmm1 = xmm0[4],zero,xmm0[6],zero,zero,zero,zero,zero,xmm0[12],zero,xmm0[14],zero,zero,zero,zero,zero
; AVX2-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpand %xmm3, %xmm0, %xmm0
; AVX2-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpsrlw $8, %xmm0, %xmm1
; AVX2-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vmovd %xmm0, %eax
@ -2058,18 +2053,13 @@ define i8 @test_v32i8(<32 x i8> %a0) {
; AVX512DQ-NEXT: vpmullw %xmm2, %xmm1, %xmm1
; AVX512DQ-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512DQ-NEXT: vpand %xmm3, %xmm0, %xmm1
; AVX512DQ-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX512DQ-NEXT: vpackuswb %xmm2, %xmm1, %xmm1
; AVX512DQ-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[1,1,2,3]
; AVX512DQ-NEXT: vpmovzxbw {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
; AVX512DQ-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[2,3,2,3,6,7,6,7]
; AVX512DQ-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512DQ-NEXT: vpand %xmm3, %xmm0, %xmm1
; AVX512DQ-NEXT: vpackuswb %xmm2, %xmm1, %xmm1
; AVX512DQ-NEXT: vpsrld $16, %xmm1, %xmm1
; AVX512DQ-NEXT: vpmovzxbw {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
; AVX512DQ-NEXT: vpshufb {{.*#+}} xmm1 = xmm0[4],zero,xmm0[6],zero,zero,zero,zero,zero,xmm0[12],zero,xmm0[14],zero,zero,zero,zero,zero
; AVX512DQ-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512DQ-NEXT: vpand %xmm3, %xmm0, %xmm0
; AVX512DQ-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX512DQ-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512DQ-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX512DQ-NEXT: vpsrlw $8, %xmm0, %xmm1
; AVX512DQ-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512DQ-NEXT: vmovd %xmm0, %eax
@ -2090,18 +2080,13 @@ define i8 @test_v32i8(<32 x i8> %a0) {
; AVX512DQVL-NEXT: vpmullw %xmm2, %xmm1, %xmm1
; AVX512DQVL-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512DQVL-NEXT: vpand %xmm3, %xmm0, %xmm1
; AVX512DQVL-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX512DQVL-NEXT: vpackuswb %xmm2, %xmm1, %xmm1
; AVX512DQVL-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[1,1,2,3]
; AVX512DQVL-NEXT: vpmovzxbw {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
; AVX512DQVL-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[2,3,2,3,6,7,6,7]
; AVX512DQVL-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512DQVL-NEXT: vpand %xmm3, %xmm0, %xmm1
; AVX512DQVL-NEXT: vpackuswb %xmm2, %xmm1, %xmm1
; AVX512DQVL-NEXT: vpsrld $16, %xmm1, %xmm1
; AVX512DQVL-NEXT: vpmovzxbw {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
; AVX512DQVL-NEXT: vpshufb {{.*#+}} xmm1 = xmm0[4],zero,xmm0[6],zero,zero,zero,zero,zero,xmm0[12],zero,xmm0[14],zero,zero,zero,zero,zero
; AVX512DQVL-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512DQVL-NEXT: vpand %xmm3, %xmm0, %xmm0
; AVX512DQVL-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX512DQVL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512DQVL-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX512DQVL-NEXT: vpsrlw $8, %xmm0, %xmm1
; AVX512DQVL-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512DQVL-NEXT: vmovd %xmm0, %eax
@ -2254,18 +2239,13 @@ define i8 @test_v64i8(<64 x i8> %a0) {
; AVX2-NEXT: vpmullw %xmm0, %xmm3, %xmm0
; AVX2-NEXT: vpmullw %xmm0, %xmm2, %xmm0
; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm2
; AVX2-NEXT: vpxor %xmm3, %xmm3, %xmm3
; AVX2-NEXT: vpackuswb %xmm3, %xmm2, %xmm2
; AVX2-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[1,1,2,3]
; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero,xmm2[4],zero,xmm2[5],zero,xmm2[6],zero,xmm2[7],zero
; AVX2-NEXT: vpshufd {{.*#+}} ymm2 = ymm2[2,3,2,3,6,7,6,7]
; AVX2-NEXT: vpmullw %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm2
; AVX2-NEXT: vpackuswb %xmm3, %xmm2, %xmm2
; AVX2-NEXT: vpsrld $16, %xmm2, %xmm2
; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero,xmm2[4],zero,xmm2[5],zero,xmm2[6],zero,xmm2[7],zero
; AVX2-NEXT: vpshufb {{.*#+}} xmm2 = xmm0[4],zero,xmm0[6],zero,zero,zero,zero,zero,xmm0[12],zero,xmm0[14],zero,zero,zero,zero,zero
; AVX2-NEXT: vpmullw %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpackuswb %xmm3, %xmm0, %xmm0
; AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpsrlw $8, %xmm0, %xmm1
; AVX2-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vmovd %xmm0, %eax
@ -2295,18 +2275,13 @@ define i8 @test_v64i8(<64 x i8> %a0) {
; AVX512BW-NEXT: vpmullw %xmm2, %xmm1, %xmm1
; AVX512BW-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512BW-NEXT: vpand %xmm3, %xmm0, %xmm1
; AVX512BW-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX512BW-NEXT: vpackuswb %xmm2, %xmm1, %xmm1
; AVX512BW-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[1,1,2,3]
; AVX512BW-NEXT: vpmovzxbw {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
; AVX512BW-NEXT: vpshufd {{.*#+}} zmm1 = zmm1[2,3,2,3,6,7,6,7,10,11,10,11,14,15,14,15]
; AVX512BW-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512BW-NEXT: vpand %xmm3, %xmm0, %xmm1
; AVX512BW-NEXT: vpackuswb %xmm2, %xmm1, %xmm1
; AVX512BW-NEXT: vpsrld $16, %xmm1, %xmm1
; AVX512BW-NEXT: vpmovzxbw {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm1 = xmm0[4],zero,xmm0[6],zero,zero,zero,zero,zero,xmm0[12],zero,xmm0[14],zero,zero,zero,zero,zero
; AVX512BW-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512BW-NEXT: vpand %xmm3, %xmm0, %xmm0
; AVX512BW-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX512BW-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512BW-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX512BW-NEXT: vpsrlw $8, %xmm0, %xmm1
; AVX512BW-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512BW-NEXT: vmovd %xmm0, %eax
@ -2336,13 +2311,10 @@ define i8 @test_v64i8(<64 x i8> %a0) {
; AVX512BWVL-NEXT: vpunpckhbw {{.*#+}} xmm2 = xmm2[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; AVX512BWVL-NEXT: vpmullw %xmm2, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512BWVL-NEXT: vpmovwb %ymm0, %xmm1
; AVX512BWVL-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[1,1,2,3]
; AVX512BWVL-NEXT: vpmovzxbw {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
; AVX512BWVL-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm1
; AVX512BWVL-NEXT: vpshufd {{.*#+}} zmm1 = zmm1[2,3,2,3,6,7,6,7,10,11,10,11,14,15,14,15]
; AVX512BWVL-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512BWVL-NEXT: vpmovwb %ymm0, %xmm1
; AVX512BWVL-NEXT: vpsrld $16, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpmovzxbw {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
; AVX512BWVL-NEXT: vpshufb {{.*#+}} xmm1 = xmm0[4],zero,xmm0[6],zero,zero,zero,zero,zero,xmm0[12],zero,xmm0[14],zero,zero,zero,zero,zero
; AVX512BWVL-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512BWVL-NEXT: vpmovwb %ymm0, %xmm0
; AVX512BWVL-NEXT: vpsrlw $8, %xmm0, %xmm1
@ -2637,18 +2609,13 @@ define i8 @test_v128i8(<128 x i8> %a0) {
; AVX2-NEXT: vpmullw %xmm1, %xmm3, %xmm1
; AVX2-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpand %xmm2, %xmm0, %xmm1
; AVX2-NEXT: vpxor %xmm3, %xmm3, %xmm3
; AVX2-NEXT: vpackuswb %xmm3, %xmm1, %xmm1
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[1,1,2,3]
; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
; AVX2-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[2,3,2,3,6,7,6,7]
; AVX2-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpand %xmm2, %xmm0, %xmm1
; AVX2-NEXT: vpackuswb %xmm3, %xmm1, %xmm1
; AVX2-NEXT: vpsrld $16, %xmm1, %xmm1
; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
; AVX2-NEXT: vpshufb {{.*#+}} xmm1 = xmm0[4],zero,xmm0[6],zero,zero,zero,zero,zero,xmm0[12],zero,xmm0[14],zero,zero,zero,zero,zero
; AVX2-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpand %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpackuswb %xmm3, %xmm0, %xmm0
; AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpsrlw $8, %xmm0, %xmm1
; AVX2-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vmovd %xmm0, %eax
@ -2681,18 +2648,13 @@ define i8 @test_v128i8(<128 x i8> %a0) {
; AVX512BW-NEXT: vpmullw %xmm0, %xmm1, %xmm0
; AVX512BW-NEXT: vpmullw %xmm0, %xmm2, %xmm0
; AVX512BW-NEXT: vpand %xmm3, %xmm0, %xmm1
; AVX512BW-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX512BW-NEXT: vpackuswb %xmm2, %xmm1, %xmm1
; AVX512BW-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[1,1,2,3]
; AVX512BW-NEXT: vpmovzxbw {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
; AVX512BW-NEXT: vpshufd {{.*#+}} zmm1 = zmm1[2,3,2,3,6,7,6,7,10,11,10,11,14,15,14,15]
; AVX512BW-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512BW-NEXT: vpand %xmm3, %xmm0, %xmm1
; AVX512BW-NEXT: vpackuswb %xmm2, %xmm1, %xmm1
; AVX512BW-NEXT: vpsrld $16, %xmm1, %xmm1
; AVX512BW-NEXT: vpmovzxbw {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm1 = xmm0[4],zero,xmm0[6],zero,zero,zero,zero,zero,xmm0[12],zero,xmm0[14],zero,zero,zero,zero,zero
; AVX512BW-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512BW-NEXT: vpand %xmm3, %xmm0, %xmm0
; AVX512BW-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX512BW-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512BW-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX512BW-NEXT: vpsrlw $8, %xmm0, %xmm1
; AVX512BW-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512BW-NEXT: vmovd %xmm0, %eax
@ -2725,13 +2687,10 @@ define i8 @test_v128i8(<128 x i8> %a0) {
; AVX512BWVL-NEXT: vpunpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; AVX512BWVL-NEXT: vpmullw %xmm0, %xmm1, %xmm0
; AVX512BWVL-NEXT: vpmullw %xmm0, %xmm2, %xmm0
; AVX512BWVL-NEXT: vpmovwb %ymm0, %xmm1
; AVX512BWVL-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[1,1,2,3]
; AVX512BWVL-NEXT: vpmovzxbw {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
; AVX512BWVL-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm1
; AVX512BWVL-NEXT: vpshufd {{.*#+}} zmm1 = zmm1[2,3,2,3,6,7,6,7,10,11,10,11,14,15,14,15]
; AVX512BWVL-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512BWVL-NEXT: vpmovwb %ymm0, %xmm1
; AVX512BWVL-NEXT: vpsrld $16, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpmovzxbw {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
; AVX512BWVL-NEXT: vpshufb {{.*#+}} xmm1 = xmm0[4],zero,xmm0[6],zero,zero,zero,zero,zero,xmm0[12],zero,xmm0[14],zero,zero,zero,zero,zero
; AVX512BWVL-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512BWVL-NEXT: vpmovwb %ymm0, %xmm0
; AVX512BWVL-NEXT: vpsrlw $8, %xmm0, %xmm1