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

[DAG] SimplifyDemandedVectorElts - add MULHS/MULHU handling to existing MUL/AND handling 

Allows to determine known zero elements, which particularly helps simplification of DIV/REM by constant patterns
This commit is contained in:
Simon Pilgrim 2022-09-19 12:44:36 +01:00
parent f51789ce5e
commit 8206044183
7 changed files with 26 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
View File

@ -3383,6 +3383,8 @@ bool TargetLowering::SimplifyDemandedVectorElts(
break;
}
case ISD::MUL:
case ISD::MULHU:
case ISD::MULHS:
case ISD::AND: {
SDValue Op0 = Op.getOperand(0);
SDValue Op1 = Op.getOperand(1);

30
llvm/test/CodeGen/RISCV/rvv/fixed-vectors-extract.ll
View File

@ -766,18 +766,11 @@ define i32 @extractelt_sdiv_v4i32(<4 x i32> %x) {
define i32 @extractelt_udiv_v4i32(<4 x i32> %x) {
; RV32NOM-LABEL: extractelt_udiv_v4i32:
; RV32NOM: # %bb.0:
; RV32NOM-NEXT: li a0, 1
; RV32NOM-NEXT: vsetivli zero, 4, e32, m1, ta, mu
; RV32NOM-NEXT: vmv.s.x v9, a0
; RV32NOM-NEXT: vmv.v.i v10, 0
; RV32NOM-NEXT: vsetvli zero, zero, e32, m1, tu, mu
; RV32NOM-NEXT: vslideup.vi v10, v9, 3
; RV32NOM-NEXT: vsetvli zero, zero, e32, m1, ta, mu
; RV32NOM-NEXT: lui a0, %hi(.LCPI39_0)
; RV32NOM-NEXT: addi a0, a0, %lo(.LCPI39_0)
; RV32NOM-NEXT: vle32.v v9, (a0)
; RV32NOM-NEXT: vsrl.vv v8, v8, v10
; RV32NOM-NEXT: vmulhu.vv v8, v8, v9
; RV32NOM-NEXT: vsrl.vi v8, v8, 0
; RV32NOM-NEXT: lui a0, 322639
; RV32NOM-NEXT: addi a0, a0, -945
; RV32NOM-NEXT: vmulhu.vx v8, v8, a0
; RV32NOM-NEXT: vsetivli zero, 1, e32, m1, ta, mu
; RV32NOM-NEXT: vslidedown.vi v8, v8, 2
; RV32NOM-NEXT: vmv.x.s a0, v8
@ -797,18 +790,11 @@ define i32 @extractelt_udiv_v4i32(<4 x i32> %x) {
;
; RV64-LABEL: extractelt_udiv_v4i32:
; RV64: # %bb.0:
; RV64-NEXT: li a0, 1
; RV64-NEXT: vsetivli zero, 4, e32, m1, ta, mu
; RV64-NEXT: vmv.s.x v9, a0
; RV64-NEXT: vmv.v.i v10, 0
; RV64-NEXT: vsetvli zero, zero, e32, m1, tu, mu
; RV64-NEXT: vslideup.vi v10, v9, 3
; RV64-NEXT: vsetvli zero, zero, e32, m1, ta, mu
; RV64-NEXT: lui a0, %hi(.LCPI39_0)
; RV64-NEXT: addi a0, a0, %lo(.LCPI39_0)
; RV64-NEXT: vle32.v v9, (a0)
; RV64-NEXT: vsrl.vv v8, v8, v10
; RV64-NEXT: vmulhu.vv v8, v8, v9
; RV64-NEXT: vsrl.vi v8, v8, 0
; RV64-NEXT: lui a0, 322639
; RV64-NEXT: addiw a0, a0, -945
; RV64-NEXT: vmulhu.vx v8, v8, a0
; RV64-NEXT: vsrl.vi v8, v8, 2
; RV64-NEXT: vsetivli zero, 1, e32, m1, ta, mu
; RV64-NEXT: vslidedown.vi v8, v8, 2

2
llvm/test/CodeGen/X86/combine-sdiv.ll
View File

@ -2678,7 +2678,7 @@ define <8 x i16> @combine_vec_sdiv_nonuniform5(<8 x i16> %x) {
; SSE41-NEXT: pmullw %xmm0, %xmm1
; SSE41-NEXT: pmulhw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; SSE41-NEXT: paddw %xmm1, %xmm0
; SSE41-NEXT: movdqa {{.*#+}} xmm1 = <256,16384,4096,u,u,32768,512,256>
; SSE41-NEXT: movdqa {{.*#+}} xmm1 = <256,16384,4096,u,u,u,512,256>
; SSE41-NEXT: pmulhw %xmm0, %xmm1
; SSE41-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0,1,2],xmm0[3,4],xmm1[5,6,7]
; SSE41-NEXT: movdqa %xmm0, %xmm2

20
llvm/test/CodeGen/X86/combine-udiv.ll
View File

@ -688,18 +688,20 @@ define <16 x i8> @combine_vec_udiv_nonuniform4(<16 x i8> %x) {
define <8 x i16> @pr38477(<8 x i16> %a0) {
; SSE2-LABEL: pr38477:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [0,4957,57457,4103,16385,35545,2048,2115]
; SSE2-NEXT: pmulhuw %xmm0, %xmm2
; SSE2-NEXT: movdqa {{.*#+}} xmm1 = [0,4957,57457,4103,16385,35545,2048,2115]
; SSE2-NEXT: pmulhuw %xmm0, %xmm1
; SSE2-NEXT: movdqa %xmm0, %xmm2
; SSE2-NEXT: psubw %xmm1, %xmm2
; SSE2-NEXT: pmulhuw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm2
; SSE2-NEXT: paddw %xmm1, %xmm2
; SSE2-NEXT: movdqa {{.*#+}} xmm1 = [65535,65535,65535,65535,65535,65535,0,65535]
; SSE2-NEXT: pandn %xmm2, %xmm1
; SSE2-NEXT: pmulhuw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm2
; SSE2-NEXT: por %xmm1, %xmm2
; SSE2-NEXT: movdqa {{.*#+}} xmm1 = [0,65535,65535,65535,65535,65535,65535,65535]
; SSE2-NEXT: pand %xmm1, %xmm2
; SSE2-NEXT: pandn %xmm0, %xmm1
; SSE2-NEXT: psubw %xmm2, %xmm0
; SSE2-NEXT: pmulhuw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; SSE2-NEXT: paddw %xmm2, %xmm0
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [65535,65535,65535,65535,65535,65535,0,65535]
; SSE2-NEXT: pandn %xmm0, %xmm2
; SSE2-NEXT: pmulhuw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; SSE2-NEXT: por %xmm2, %xmm1
; SSE2-NEXT: por %xmm0, %xmm1
; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: retq
;

8
llvm/test/CodeGen/X86/pmulh.ll
View File

@ -55,10 +55,9 @@ define <4 x i16> @and_mulhuw_v4i16(<4 x i64> %a, <4 x i64> %b) {
;
; AVX2-LABEL: and_mulhuw_v4i16:
; AVX2: # %bb.0:
; AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX2-NEXT: vpblendw {{.*#+}} ymm0 = ymm0[0],ymm2[1,2,3],ymm0[4],ymm2[5,6,7],ymm0[8],ymm2[9,10,11],ymm0[12],ymm2[13,14,15]
; AVX2-NEXT: vpblendw {{.*#+}} ymm1 = ymm1[0],ymm2[1,2,3],ymm1[4],ymm2[5,6,7],ymm1[8],ymm2[9,10,11],ymm1[12],ymm2[13,14,15]
; AVX2-NEXT: vpmulhuw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX2-NEXT: vpblendw {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7],ymm0[8],ymm1[9,10,11],ymm0[12],ymm1[13,14,15]
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpackusdw %xmm0, %xmm0, %xmm0
@ -67,9 +66,6 @@ define <4 x i16> @and_mulhuw_v4i16(<4 x i64> %a, <4 x i64> %b) {
;
; AVX512-LABEL: and_mulhuw_v4i16:
; AVX512: # %bb.0:
; AVX512-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX512-NEXT: vpblendw {{.*#+}} ymm0 = ymm0[0],ymm2[1,2,3],ymm0[4],ymm2[5,6,7],ymm0[8],ymm2[9,10,11],ymm0[12],ymm2[13,14,15]
; AVX512-NEXT: vpblendw {{.*#+}} ymm1 = ymm1[0],ymm2[1,2,3],ymm1[4],ymm2[5,6,7],ymm1[8],ymm2[9,10,11],ymm1[12],ymm2[13,14,15]
; AVX512-NEXT: vpmulhuw %ymm1, %ymm0, %ymm0
; AVX512-NEXT: vpmovqw %zmm0, %xmm0
; AVX512-NEXT: vzeroupper

2
llvm/test/CodeGen/X86/vector-shift-ashr-128.ll
View File

@ -1398,7 +1398,7 @@ define <8 x i16> @constant_shift_v8i16(<8 x i16> %a) nounwind {
;
; SSE41-LABEL: constant_shift_v8i16:
; SSE41: # %bb.0:
; SSE41-NEXT: movdqa {{.*#+}} xmm1 = <u,32768,16384,8192,4096,2048,1024,512>
; SSE41-NEXT: movdqa {{.*#+}} xmm1 = <u,u,16384,8192,4096,2048,1024,512>
; SSE41-NEXT: pmulhw %xmm0, %xmm1
; SSE41-NEXT: pblendw {{.*#+}} xmm1 = xmm0[0],xmm1[1,2,3,4,5,6,7]
; SSE41-NEXT: psraw $1, %xmm0

2
llvm/test/CodeGen/X86/vector-shift-ashr-sub128.ll
View File

@ -1790,7 +1790,7 @@ define <4 x i16> @constant_shift_v4i16(<4 x i16> %a) nounwind {
;
; SSE41-LABEL: constant_shift_v4i16:
; SSE41: # %bb.0:
; SSE41-NEXT: movdqa {{.*#+}} xmm1 = <u,32768,16384,8192,u,u,u,u>
; SSE41-NEXT: movdqa {{.*#+}} xmm1 = <u,u,16384,8192,u,u,u,u>
; SSE41-NEXT: pmulhw %xmm0, %xmm1
; SSE41-NEXT: pblendw {{.*#+}} xmm1 = xmm0[0],xmm1[1,2,3,4,5,6,7]
; SSE41-NEXT: psraw $1, %xmm0