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

[AVX-512] Add tests demonstrating failure to generated masked instructions for VSHUFF32x4 and VSHUFI32x4 due to shuffle lowering widening elements. 

llvm-svn: 287897
This commit is contained in:
Craig Topper 2016-11-24 18:24:46 +00:00
parent 403512cf29
commit 00758090ca
1 changed files with 44 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
llvm/test/CodeGen/X86/vector-shuffle-512-v16.ll
View File

@ -424,3 +424,47 @@ define <16 x i32> @test_vshufi32x4_512(<16 x i32> %x, <16 x i32> %x1) nounwind {
%res = shufflevector <16 x i32> %x, <16 x i32> %x1, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 20, i32 21, i32 22, i32 23, i32 16, i32 17, i32 18, i32 19>
ret <16 x i32> %res
}
define <16 x float> @test_vshuff32x4_512_mask(<16 x float> %x, <16 x float> %x1, <16 x float> %y, <16 x i1> %mask) nounwind {
; AVX512F-LABEL: test_vshuff32x4_512_mask:
; AVX512F: # BB#0:
; AVX512F-NEXT: vpmovsxbd %xmm3, %zmm3
; AVX512F-NEXT: vpslld $31, %zmm3, %zmm3
; AVX512F-NEXT: vptestmd %zmm3, %zmm3, %k1
; AVX512F-NEXT: vshuff64x2 {{.*#+}} zmm0 = zmm0[0,1,2,3],zmm1[2,3,0,1]
; AVX512F-NEXT: vblendmps %zmm0, %zmm2, %zmm0 {%k1}
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: test_vshuff32x4_512_mask:
; AVX512BW: # BB#0:
; AVX512BW-NEXT: vpsllw $7, %xmm3, %xmm3
; AVX512BW-NEXT: vpmovb2m %zmm3, %k1
; AVX512BW-NEXT: vshuff64x2 {{.*#+}} zmm0 = zmm0[0,1,2,3],zmm1[2,3,0,1]
; AVX512BW-NEXT: vblendmps %zmm0, %zmm2, %zmm0 {%k1}
; AVX512BW-NEXT: retq
%x2 = shufflevector <16 x float> %x, <16 x float> %x1, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 20, i32 21, i32 22, i32 23, i32 16, i32 17, i32 18, i32 19>
%res = select <16 x i1> %mask, <16 x float> %x2, <16 x float> %y
ret <16 x float> %res
}
define <16 x i32> @test_vshufi32x4_512_mask(<16 x i32> %x, <16 x i32> %x1, <16 x i32> %y, <16 x i1> %mask) nounwind {
; AVX512F-LABEL: test_vshufi32x4_512_mask:
; AVX512F: # BB#0:
; AVX512F-NEXT: vpmovsxbd %xmm3, %zmm3
; AVX512F-NEXT: vpslld $31, %zmm3, %zmm3
; AVX512F-NEXT: vptestmd %zmm3, %zmm3, %k1
; AVX512F-NEXT: vshufi64x2 {{.*#+}} zmm0 = zmm0[0,1,2,3],zmm1[2,3,0,1]
; AVX512F-NEXT: vpblendmd %zmm0, %zmm2, %zmm0 {%k1}
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: test_vshufi32x4_512_mask:
; AVX512BW: # BB#0:
; AVX512BW-NEXT: vpsllw $7, %xmm3, %xmm3
; AVX512BW-NEXT: vpmovb2m %zmm3, %k1
; AVX512BW-NEXT: vshufi64x2 {{.*#+}} zmm0 = zmm0[0,1,2,3],zmm1[2,3,0,1]
; AVX512BW-NEXT: vpblendmd %zmm0, %zmm2, %zmm0 {%k1}
; AVX512BW-NEXT: retq
%x2 = shufflevector <16 x i32> %x, <16 x i32> %x1, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 20, i32 21, i32 22, i32 23, i32 16, i32 17, i32 18, i32 19>
%res = select <16 x i1> %mask, <16 x i32> %x2, <16 x i32> %y
ret <16 x i32> %res
}