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

[X86] Adding a test for vector shuffle extractions. 

When both the vector inputs of the shuffle vector is comprising of same vector or shuffle mask is accessing elements from only one operand vector (like in PR33758 test already present).

Committed on behalf of @jbhateja (Jatin Bhateja)

Differential Revision: https://reviews.llvm.org/D36271

llvm-svn: 309963
This commit is contained in:
Simon Pilgrim 2017-08-03 17:04:59 +00:00
parent 869fa74d4b
commit 99d0ab38bc
1 changed files with 114 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

114
llvm/test/CodeGen/X86/shuffle-vs-trunc-512.ll
View File

@ -227,3 +227,117 @@ define void @trunc_v8i64_to_v8i8(<64 x i8>* %L, <8 x i8>* %S) nounwind {
store <8 x i8> %strided.vec, <8 x i8>* %S
ret void
}
define <16 x i8> @trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62(<64 x i8> %x) {
; AVX512F-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62:
; AVX512F: # BB#0:
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm3 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512F-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512F-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512F-NEXT: vpshufb {{.*#+}} xmm2 = xmm2[u,u,u,u,1,5,9,14,u,u,u,u,u,u,u,u]
; AVX512F-NEXT: vpshufb {{.*#+}} xmm1 = xmm1[u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u]
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512F-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62:
; AVX512VL: # BB#0:
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VL-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512VL-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512VL-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512VL-NEXT: vpshufb {{.*#+}} xmm2 = xmm2[u,u,u,u,1,5,9,14,u,u,u,u,u,u,u,u]
; AVX512VL-NEXT: vpshufb {{.*#+}} xmm1 = xmm1[u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u]
; AVX512VL-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512VL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62:
; AVX512BW: # BB#0:
; AVX512BW-NEXT: vpextrb $5, %xmm0, %eax
; AVX512BW-NEXT: vpextrb $1, %xmm0, %ecx
; AVX512BW-NEXT: vmovd %ecx, %xmm1
; AVX512BW-NEXT: vpinsrb $1, %eax, %xmm1, %xmm1
; AVX512BW-NEXT: vpextrb $9, %xmm0, %eax
; AVX512BW-NEXT: vpinsrb $2, %eax, %xmm1, %xmm1
; AVX512BW-NEXT: vpextrb $13, %xmm0, %eax
; AVX512BW-NEXT: vpinsrb $3, %eax, %xmm1, %xmm1
; AVX512BW-NEXT: vextracti32x4 $1, %zmm0, %xmm2
; AVX512BW-NEXT: vpextrb $1, %xmm2, %eax
; AVX512BW-NEXT: vpinsrb $4, %eax, %xmm1, %xmm1
; AVX512BW-NEXT: vpextrb $5, %xmm2, %eax
; AVX512BW-NEXT: vpinsrb $5, %eax, %xmm1, %xmm1
; AVX512BW-NEXT: vpextrb $9, %xmm2, %eax
; AVX512BW-NEXT: vpinsrb $6, %eax, %xmm1, %xmm1
; AVX512BW-NEXT: vpextrb $13, %xmm2, %eax
; AVX512BW-NEXT: vpinsrb $7, %eax, %xmm1, %xmm1
; AVX512BW-NEXT: vextracti32x4 $2, %zmm0, %xmm2
; AVX512BW-NEXT: vpextrb $1, %xmm2, %eax
; AVX512BW-NEXT: vpinsrb $8, %eax, %xmm1, %xmm1
; AVX512BW-NEXT: vpextrb $5, %xmm2, %eax
; AVX512BW-NEXT: vpinsrb $9, %eax, %xmm1, %xmm1
; AVX512BW-NEXT: vpextrb $9, %xmm2, %eax
; AVX512BW-NEXT: vpinsrb $10, %eax, %xmm1, %xmm1
; AVX512BW-NEXT: vpextrb $13, %xmm2, %eax
; AVX512BW-NEXT: vpinsrb $11, %eax, %xmm1, %xmm1
; AVX512BW-NEXT: vextracti32x4 $3, %zmm0, %xmm0
; AVX512BW-NEXT: vpextrb $1, %xmm0, %eax
; AVX512BW-NEXT: vpinsrb $12, %eax, %xmm1, %xmm1
; AVX512BW-NEXT: vpextrb $5, %xmm0, %eax
; AVX512BW-NEXT: vpinsrb $13, %eax, %xmm1, %xmm1
; AVX512BW-NEXT: vpextrb $9, %xmm0, %eax
; AVX512BW-NEXT: vpinsrb $14, %eax, %xmm1, %xmm1
; AVX512BW-NEXT: vpextrb $14, %xmm0, %eax
; AVX512BW-NEXT: vpinsrb $15, %eax, %xmm1, %xmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62:
; AVX512BWVL: # BB#0:
; AVX512BWVL-NEXT: vpextrb $5, %xmm0, %eax
; AVX512BWVL-NEXT: vpextrb $1, %xmm0, %ecx
; AVX512BWVL-NEXT: vmovd %ecx, %xmm1
; AVX512BWVL-NEXT: vpinsrb $1, %eax, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpextrb $9, %xmm0, %eax
; AVX512BWVL-NEXT: vpinsrb $2, %eax, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpextrb $13, %xmm0, %eax
; AVX512BWVL-NEXT: vpinsrb $3, %eax, %xmm1, %xmm1
; AVX512BWVL-NEXT: vextracti32x4 $1, %zmm0, %xmm2
; AVX512BWVL-NEXT: vpextrb $1, %xmm2, %eax
; AVX512BWVL-NEXT: vpinsrb $4, %eax, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpextrb $5, %xmm2, %eax
; AVX512BWVL-NEXT: vpinsrb $5, %eax, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpextrb $9, %xmm2, %eax
; AVX512BWVL-NEXT: vpinsrb $6, %eax, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpextrb $13, %xmm2, %eax
; AVX512BWVL-NEXT: vpinsrb $7, %eax, %xmm1, %xmm1
; AVX512BWVL-NEXT: vextracti32x4 $2, %zmm0, %xmm2
; AVX512BWVL-NEXT: vpextrb $1, %xmm2, %eax
; AVX512BWVL-NEXT: vpinsrb $8, %eax, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpextrb $5, %xmm2, %eax
; AVX512BWVL-NEXT: vpinsrb $9, %eax, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpextrb $9, %xmm2, %eax
; AVX512BWVL-NEXT: vpinsrb $10, %eax, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpextrb $13, %xmm2, %eax
; AVX512BWVL-NEXT: vpinsrb $11, %eax, %xmm1, %xmm1
; AVX512BWVL-NEXT: vextracti32x4 $3, %zmm0, %xmm0
; AVX512BWVL-NEXT: vpextrb $1, %xmm0, %eax
; AVX512BWVL-NEXT: vpinsrb $12, %eax, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpextrb $5, %xmm0, %eax
; AVX512BWVL-NEXT: vpinsrb $13, %eax, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpextrb $9, %xmm0, %eax
; AVX512BWVL-NEXT: vpinsrb $14, %eax, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpextrb $14, %xmm0, %eax
; AVX512BWVL-NEXT: vpinsrb $15, %eax, %xmm1, %xmm0
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
%res = shufflevector <64 x i8> %x, <64 x i8> %x, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 62>
ret <16 x i8> %res
}