RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-19 19:12:56 +02:00
Code Issues Projects Releases Wiki Activity

[X86][SSE] Regenerate vector blend commutation tests

Browse Source 
llvm-svn: 258091
This commit is contained in:
Simon Pilgrim 2016-01-18 21:46:46 +00:00
parent e1a6e6ae7f
commit 5bbdf4402d
2 changed files with 48 additions and 46 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

67
test/CodeGen/X86/commute-blend-avx2.ll
View File

@ -1,89 +1,90 @@
; RUN: llc -O3 -mtriple=x86_64-unknown -mcpu=core-avx2 -mattr=avx2 < %s | FileCheck %s
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx2 | FileCheck %s
define <8 x i16> @commute_fold_vpblendw_128(<8 x i16> %a, <8 x i16>* %b) #0 {
; CHECK-LABEL: commute_fold_vpblendw_128:
; CHECK: # BB#0:
; CHECK-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],mem[1,2,3],xmm0[4],mem[5,6,7]
; CHECK-NEXT: retq
%1 = load <8 x i16>, <8 x i16>* %b
%2 = call <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16> %1, <8 x i16> %a, i8 17)
ret <8 x i16> %2
;LABEL: commute_fold_vpblendw_128
;CHECK: vpblendw {{.*#+}} xmm0 = xmm0[0],mem[1,2,3],xmm0[4],mem[5,6,7]
;CHECK-NEXT: retq
}
declare <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16>, <8 x i16>, i8) nounwind readnone
define <16 x i16> @commute_fold_vpblendw_256(<16 x i16> %a, <16 x i16>* %b) #0 {
; CHECK-LABEL: commute_fold_vpblendw_256:
; CHECK: # BB#0:
; CHECK-NEXT: vpblendw {{.*#+}} ymm0 = ymm0[0],mem[1,2,3],ymm0[4],mem[5,6,7],ymm0[8],mem[9,10,11],ymm0[12],mem[13,14,15]
; CHECK-NEXT: retq
%1 = load <16 x i16>, <16 x i16>* %b
%2 = call <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16> %1, <16 x i16> %a, i8 17)
ret <16 x i16> %2
;LABEL: commute_fold_vpblendw_256
;CHECK: vpblendw {{.*#+}} ymm0 = ymm0[0],mem[1,2,3],ymm0[4],mem[5,6,7],ymm0[8],mem[9,10,11],ymm0[12],mem[13,14,15]
;CHECK-NEXT: retq
}
declare <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16>, <16 x i16>, i8) nounwind readnone
define <4 x i32> @commute_fold_vpblendd_128(<4 x i32> %a, <4 x i32>* %b) #0 {
; CHECK-LABEL: commute_fold_vpblendd_128:
; CHECK: # BB#0:
; CHECK-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],mem[1,2,3]
; CHECK-NEXT: retq
%1 = load <4 x i32>, <4 x i32>* %b
%2 = call <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32> %1, <4 x i32> %a, i8 1)
ret <4 x i32> %2
;LABEL: commute_fold_vpblendd_128
;CHECK: vpblendd {{.*#+}} xmm0 = xmm0[0],mem[1,2,3]
;CHECK-NEXT: retq
}
declare <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32>, <4 x i32>, i8) nounwind readnone
define <8 x i32> @commute_fold_vpblendd_256(<8 x i32> %a, <8 x i32>* %b) #0 {
; CHECK-LABEL: commute_fold_vpblendd_256:
; CHECK: # BB#0:
; CHECK-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0],mem[1,2,3,4,5,6],ymm0[7]
; CHECK-NEXT: retq
%1 = load <8 x i32>, <8 x i32>* %b
%2 = call <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32> %1, <8 x i32> %a, i8 129)
ret <8 x i32> %2
;LABEL: commute_fold_vpblendd_256
;CHECK: vpblendd {{.*#+}} ymm0 = ymm0[0],mem[1,2,3,4,5,6],ymm0[7]
;CHECK-NEXT: retq
}
declare <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32>, <8 x i32>, i8) nounwind readnone
define <4 x float> @commute_fold_vblendps_128(<4 x float> %a, <4 x float>* %b) #0 {
; CHECK-LABEL: commute_fold_vblendps_128:
; CHECK: # BB#0:
; CHECK-NEXT: vblendps {{.*#+}} xmm0 = xmm0[0],mem[1],xmm0[2],mem[3]
; CHECK-NEXT: retq
%1 = load <4 x float>, <4 x float>* %b
%2 = call <4 x float> @llvm.x86.sse41.blendps(<4 x float> %1, <4 x float> %a, i8 5)
ret <4 x float> %2
;LABEL: commute_fold_vblendps_128
;CHECK: vblendps {{.*#+}} xmm0 = xmm0[0],mem[1],xmm0[2],mem[3]
;CHECK-NEXT: retq
}
declare <4 x float> @llvm.x86.sse41.blendps(<4 x float>, <4 x float>, i8) nounwind readnone
define <8 x float> @commute_fold_vblendps_256(<8 x float> %a, <8 x float>* %b) #0 {
; CHECK-LABEL: commute_fold_vblendps_256:
; CHECK: # BB#0:
; CHECK-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1,2],mem[3,4,5,6,7]
; CHECK-NEXT: retq
%1 = load <8 x float>, <8 x float>* %b
%2 = call <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float> %1, <8 x float> %a, i8 7)
ret <8 x float> %2
;LABEL: commute_fold_vblendps_256
;CHECK: vblendps {{.*#+}} ymm0 = ymm0[0,1,2],mem[3,4,5,6,7]
;CHECK-NEXT: retq
}
declare <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float>, <8 x float>, i8) nounwind readnone
define <2 x double> @commute_fold_vblendpd_128(<2 x double> %a, <2 x double>* %b) #0 {
; CHECK-LABEL: commute_fold_vblendpd_128:
; CHECK: # BB#0:
; CHECK-NEXT: vblendpd {{.*#+}} xmm0 = xmm0[0],mem[1]
; CHECK-NEXT: retq
%1 = load <2 x double>, <2 x double>* %b
%2 = call <2 x double> @llvm.x86.sse41.blendpd(<2 x double> %1, <2 x double> %a, i8 1)
ret <2 x double> %2
;LABEL: commute_fold_vblendpd_128
;CHECK: vblendpd {{.*#+}} xmm0 = xmm0[0],mem[1]
;CHECK-NEXT: retq
}
declare <2 x double> @llvm.x86.sse41.blendpd(<2 x double>, <2 x double>, i8) nounwind readnone
define <4 x double> @commute_fold_vblendpd_256(<4 x double> %a, <4 x double>* %b) #0 {
; CHECK-LABEL: commute_fold_vblendpd_256:
; CHECK: # BB#0:
; CHECK-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0,1,2],mem[3]
; CHECK-NEXT: retq
%1 = load <4 x double>, <4 x double>* %b
%2 = call <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double> %1, <4 x double> %a, i8 7)
ret <4 x double> %2
;LABEL: commute_fold_vblendpd_256
;CHECK: vblendpd {{.*#+}} ymm0 = ymm0[0,1,2],mem[3]
;CHECK-NEXT: retq
}
declare <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double>, <4 x double>, i8) nounwind readnone

27
test/CodeGen/X86/commute-blend-sse41.ll
View File

@ -1,34 +1,35 @@
; RUN: llc -O3 -mtriple=x86_64-unknown -mcpu=corei7 < %s | FileCheck %s
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+sse4.1 | FileCheck %s
define <8 x i16> @commute_fold_pblendw(<8 x i16> %a, <8 x i16>* %b) #0 {
; CHECK-LABEL: commute_fold_pblendw:
; CHECK: # BB#0:
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0],mem[1,2,3],xmm0[4],mem[5,6,7]
; CHECK-NEXT: retq
%1 = load <8 x i16>, <8 x i16>* %b
%2 = call <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16> %1, <8 x i16> %a, i8 17)
ret <8 x i16> %2
;LABEL: commute_fold_pblendw
;CHECK: pblendw {{.*#+}} xmm0 = xmm0[0],mem[1,2,3],xmm0[4],mem[5,6,7]
;CHECK-NEXT: retq
}
declare <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16>, <8 x i16>, i8) nounwind readnone
define <4 x float> @commute_fold_blendps(<4 x float> %a, <4 x float>* %b) #0 {
; CHECK-LABEL: commute_fold_blendps:
; CHECK: # BB#0:
; CHECK-NEXT: blendps {{.*#+}} xmm0 = xmm0[0],mem[1],xmm0[2],mem[3]
; CHECK-NEXT: retq
%1 = load <4 x float>, <4 x float>* %b
%2 = call <4 x float> @llvm.x86.sse41.blendps(<4 x float> %1, <4 x float> %a, i8 5)
ret <4 x float> %2
;LABEL: commute_fold_blendps
;CHECK: blendps {{.*#+}} xmm0 = xmm0[0],mem[1],xmm0[2],mem[3]
;CHECK-NEXT: retq
}
declare <4 x float> @llvm.x86.sse41.blendps(<4 x float>, <4 x float>, i8) nounwind readnone
define <2 x double> @commute_fold_blendpd(<2 x double> %a, <2 x double>* %b) #0 {
; CHECK-LABEL: commute_fold_blendpd:
; CHECK: # BB#0:
; CHECK-NEXT: blendpd {{.*#+}} xmm0 = xmm0[0],mem[1]
; CHECK-NEXT: retq
%1 = load <2 x double>, <2 x double>* %b
%2 = call <2 x double> @llvm.x86.sse41.blendpd(<2 x double> %1, <2 x double> %a, i8 1)
ret <2 x double> %2
;LABEL: commute_fold_vblendpd
;CHECK: blendpd {{.*#+}} xmm0 = xmm0[0],mem[1]
;CHECK-NEXT: retq
}
declare <2 x double> @llvm.x86.sse41.blendpd(<2 x double>, <2 x double>, i8) nounwind readnone