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

[X86][AVX] SimplifyDemandedVectorEltsForTargetNode - reduce width of X86ISD::VPERMILPV 

If we don't need the elements of the upper lanes, reduce the width of the X86ISD::VPERMILPV node.
This commit is contained in:
Simon Pilgrim 2020-06-27 14:43:03 +01:00
parent a43b99a1e3
commit d56c6475a6
2 changed files with 6 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -37122,7 +37122,8 @@ bool X86TargetLowering::SimplifyDemandedVectorEltsForTargetNode(
}
break;
}
// Target Shuffles.
// (Non-Lane Crossing) Target Shuffles.
case X86ISD::VPERMILPV:
case X86ISD::PSHUFB:
case X86ISD::UNPCKL:
case X86ISD::UNPCKH:

10
llvm/test/CodeGen/X86/var-permute-256.ll
View File

@ -1114,13 +1114,11 @@ define <4 x i32> @var_shuffle_v4i32_from_v8i32(<8 x i32> %v, <4 x i32> %indices)
;
; AVX1-LABEL: var_shuffle_v4i32_from_v8i32:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: # kill: def $xmm1 killed $xmm1 def $ymm1
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3,2,3]
; AVX1-NEXT: vpermilps %ymm1, %ymm2, %ymm2
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
; AVX1-NEXT: vpermilps %ymm1, %ymm0, %ymm0
; AVX1-NEXT: vpermilps %xmm1, %xmm0, %xmm2
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3]
; AVX1-NEXT: vpermilps %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpcmpgtd {{.*}}(%rip), %xmm1, %xmm1
; AVX1-NEXT: vblendvps %xmm1, %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vblendvps %xmm1, %xmm0, %xmm2, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;