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

AVX512: Add extract_subvector patterns v8i1->v4i1 , v4i1->v2i1. 

Differential Revision: http://reviews.llvm.org/D17953

llvm-svn: 262929
This commit is contained in:
Igor Breger 2016-03-08 15:21:25 +00:00
parent 28cc4dde49
commit 999ac754f2
2 changed files with 31 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
llvm/lib/Target/X86/X86InstrAVX512.td
View File

@ -2512,6 +2512,14 @@ defm : operation_subvector_mask_lowering<VK16, v16i1, VK64, v64i1>;
defm : operation_subvector_mask_lowering<VK32, v32i1, VK64, v64i1>;
def : Pat<(v2i1 (extract_subvector (v4i1 VK4:$src), (iPTR 2))),
(v2i1 (COPY_TO_REGCLASS
(KSHIFTRWri (COPY_TO_REGCLASS VK4:$src, VK16), (i8 2)),
VK2))>;
def : Pat<(v4i1 (extract_subvector (v8i1 VK8:$src), (iPTR 4))),
(v4i1 (COPY_TO_REGCLASS
(KSHIFTRWri (COPY_TO_REGCLASS VK8:$src, VK16), (i8 4)),
VK4))>;
def : Pat<(v8i1 (extract_subvector (v16i1 VK16:$src), (iPTR 8))),
(v8i1 (COPY_TO_REGCLASS (KSHIFTRWri VK16:$src, (i8 8)), VK8))>;
def : Pat<(v16i1 (extract_subvector (v32i1 VK32:$src), (iPTR 16))),

23
llvm/test/CodeGen/X86/avx512-skx-insert-subvec.ll
View File

@ -145,3 +145,26 @@ define <64 x i1> @test8(<8 x i1> %a, <8 x i1>%b) {
ret <64 x i1> %res
}
define <4 x i1> @test9(<8 x i1> %a, <8 x i1> %b) {
; CHECK-LABEL: test9:
; CHECK: # BB#0:
; CHECK-NEXT: vpsllw $15, %xmm0, %xmm0
; CHECK-NEXT: vpmovw2m %xmm0, %k0
; CHECK-NEXT: kshiftrw $4, %k0, %k0
; CHECK-NEXT: vpmovm2d %k0, %xmm0
; CHECK-NEXT: retq
%res = shufflevector <8 x i1> %a, <8 x i1> %b, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
ret <4 x i1> %res
}
define <2 x i1> @test10(<4 x i1> %a, <4 x i1> %b) {
; CHECK-LABEL: test10:
; CHECK: # BB#0:
; CHECK-NEXT: vpslld $31, %xmm0, %xmm0
; CHECK-NEXT: vptestmd %xmm0, %xmm0, %k0
; CHECK-NEXT: kshiftrw $2, %k0, %k0
; CHECK-NEXT: vpmovm2q %k0, %xmm0
; CHECK-NEXT: retq
%res = shufflevector <4 x i1> %a, <4 x i1> %b, <2 x i32> <i32 2, i32 3>
ret <2 x i1> %res
}