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

[X86] Simplify vector-shuffle-v48 test. NFC. 

llvm-svn: 305670
This commit is contained in:
Guy Blank 2017-06-19 08:58:13 +00:00
parent 9c6e848989
commit f4a09e55a6
1 changed files with 39 additions and 42 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

81
llvm/test/CodeGen/X86/vector-shuffle-v48.ll
View File

@ -1,49 +1,46 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=x86_64-pc-linux -mattr=+avx2 < %s | FileCheck %s ; RUN: llc -mtriple=x86_64-pc-linux -mattr=+avx2 < %s | FileCheck %s
define <16 x i8> @foo(<48 x i8>* %x0, <16 x i32> %x1, <16 x i32> %x2) { define <32 x i8> @foo(<48 x i8>* %x0, <16 x i32> %x1, <16 x i32> %x2) {
; CHECK-LABEL: foo: ; CHECK-LABEL: foo:
; CHECK: # BB#0: ; CHECK: # BB#0:
; CHECK-NEXT: vmovdqu (%rdi), %ymm4 ; CHECK-NEXT: vmovdqu 32(%rdi), %xmm0
; CHECK-NEXT: vmovdqu 32(%rdi), %xmm5 ; CHECK-NEXT: vmovdqu (%rdi), %ymm1
; CHECK-NEXT: vpextrb $13, %xmm5, %eax ; CHECK-NEXT: vextracti128 $1, %ymm1, %xmm2
; CHECK-NEXT: vpextrb $10, %xmm5, %ecx ; CHECK-NEXT: vpextrb $0, %xmm2, %eax
; CHECK-NEXT: vpextrb $7, %xmm5, %edx ; CHECK-NEXT: vpshufb {{.*#+}} xmm1 = xmm1[0,1,3,4,6,7,9,10,12,13,15],zero,zero,zero,zero,zero
; CHECK-NEXT: vpextrb $4, %xmm5, %esi ; CHECK-NEXT: vpinsrb $11, %eax, %xmm1, %xmm1
; CHECK-NEXT: vpextrb $1, %xmm5, %edi ; CHECK-NEXT: vpextrb $2, %xmm2, %eax
; CHECK-NEXT: vextracti128 $1, %ymm4, %xmm5 ; CHECK-NEXT: vpinsrb $12, %eax, %xmm1, %xmm1
; CHECK-NEXT: vpshufb {{.*#+}} xmm6 = xmm5[2,2,5,5,5,5,3,3,4,4,5,5,6,6,7,7] ; CHECK-NEXT: vpextrb $3, %xmm2, %eax
; CHECK-NEXT: vpshufb {{.*#+}} xmm7 = xmm4[12,12,13,13,15,15,15,15,12,12,13,13,14,14,15,15] ; CHECK-NEXT: vpinsrb $13, %eax, %xmm1, %xmm1
; CHECK-NEXT: vpunpcklqdq {{.*#+}} xmm6 = xmm7[0],xmm6[0] ; CHECK-NEXT: vpextrb $5, %xmm2, %eax
; CHECK-NEXT: vpshufb {{.*#+}} xmm4 = xmm4[0,0,1,1,3,3,3,3,6,6,9,9,9,9,7,7] ; CHECK-NEXT: vpinsrb $14, %eax, %xmm1, %xmm1
; CHECK-NEXT: vinserti128 $1, %xmm6, %ymm4, %ymm4 ; CHECK-NEXT: vpextrb $6, %xmm2, %eax
; CHECK-NEXT: vpand {{.*}}(%rip), %ymm4, %ymm4 ; CHECK-NEXT: vpinsrb $15, %eax, %xmm1, %xmm1
; CHECK-NEXT: vpshufb {{.*#+}} xmm5 = xmm5[8,11,14],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero ; CHECK-NEXT: vpextrb $1, %xmm0, %eax
; CHECK-NEXT: vpinsrb $3, %edi, %xmm5, %xmm5 ; CHECK-NEXT: vpshufb {{.*#+}} xmm2 = xmm2[8,9,11,12,14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; CHECK-NEXT: vpinsrb $4, %esi, %xmm5, %xmm5 ; CHECK-NEXT: vpinsrb $6, %eax, %xmm2, %xmm2
; CHECK-NEXT: vpinsrb $5, %edx, %xmm5, %xmm5 ; CHECK-NEXT: vpextrb $2, %xmm0, %eax
; CHECK-NEXT: vpinsrb $6, %ecx, %xmm5, %xmm5 ; CHECK-NEXT: vpinsrb $7, %eax, %xmm2, %xmm2
; CHECK-NEXT: vpinsrb $7, %eax, %xmm5, %xmm5 ; CHECK-NEXT: vpextrb $4, %xmm0, %eax
; CHECK-NEXT: vpmovzxbd {{.*#+}} ymm5 = xmm5[0],zero,zero,zero,xmm5[1],zero,zero,zero,xmm5[2],zero,zero,zero,xmm5[3],zero,zero,zero,xmm5[4],zero,zero,zero,xmm5[5],zero,zero,zero,xmm5[6],zero,zero,zero,xmm5[7],zero,zero,zero ; CHECK-NEXT: vpinsrb $8, %eax, %xmm2, %xmm2
; CHECK-NEXT: vpmulld %ymm0, %ymm4, %ymm0 ; CHECK-NEXT: vpextrb $5, %xmm0, %eax
; CHECK-NEXT: vpmulld %ymm1, %ymm5, %ymm1 ; CHECK-NEXT: vpinsrb $9, %eax, %xmm2, %xmm2
; CHECK-NEXT: vpsrlvd %ymm2, %ymm0, %ymm0 ; CHECK-NEXT: vpextrb $7, %xmm0, %eax
; CHECK-NEXT: vpsrlvd %ymm3, %ymm1, %ymm1 ; CHECK-NEXT: vpinsrb $10, %eax, %xmm2, %xmm2
; CHECK-NEXT: vmovdqa {{.*#+}} ymm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31] ; CHECK-NEXT: vpextrb $8, %xmm0, %eax
; CHECK-NEXT: vpshufb %ymm2, %ymm0, %ymm0 ; CHECK-NEXT: vpinsrb $11, %eax, %xmm2, %xmm2
; CHECK-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3] ; CHECK-NEXT: vpextrb $10, %xmm0, %eax
; CHECK-NEXT: vmovdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u> ; CHECK-NEXT: vpinsrb $12, %eax, %xmm2, %xmm2
; CHECK-NEXT: vpshufb %xmm3, %xmm0, %xmm0 ; CHECK-NEXT: vpextrb $11, %xmm0, %eax
; CHECK-NEXT: vpshufb %ymm2, %ymm1, %ymm1 ; CHECK-NEXT: vpinsrb $13, %eax, %xmm2, %xmm2
; CHECK-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3] ; CHECK-NEXT: vpextrb $13, %xmm0, %eax
; CHECK-NEXT: vpshufb %xmm3, %xmm1, %xmm1 ; CHECK-NEXT: vpinsrb $14, %eax, %xmm2, %xmm2
; CHECK-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0] ; CHECK-NEXT: vpextrb $14, %xmm0, %eax
; CHECK-NEXT: vzeroupper ; CHECK-NEXT: vpinsrb $15, %eax, %xmm2, %xmm0
; CHECK-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; CHECK-NEXT: retq ; CHECK-NEXT: retq
%1 = load <48 x i8>, <48 x i8>* %x0, align 1 %1 = load <48 x i8>, <48 x i8>* %x0, align 1
%2 = shufflevector <48 x i8> %1, <48 x i8> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45> %2 = shufflevector <48 x i8> %1, <48 x i8> undef, <32 x i32> <i32 0, i32 1, i32 3, i32 4, i32 6, i32 7, i32 9, i32 10, i32 12, i32 13, i32 15, i32 16, i32 18, i32 19, i32 21, i32 22, i32 24, i32 25, i32 27, i32 28, i32 30, i32 31, i32 33, i32 34, i32 36, i32 37, i32 39, i32 40, i32 42, i32 43, i32 45, i32 46>
%3 = zext <16 x i8> %2 to <16 x i32> ret <32 x i8> %2
%4 = mul <16 x i32> %3, %x1
%5 = lshr <16 x i32> %4, %x2
%6 = trunc <16 x i32> %5 to <16 x i8>
ret <16 x i8> %6
} }