mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-09-30 04:56:49 +00:00
7c9c6ed761
Essentially the same as the GEP change in r230786.
A similar migration script can be used to update test cases, though a few more
test case improvements/changes were required this time around: (r229269-r229278)
import fileinput
import sys
import re
pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)")
for line in sys.stdin:
sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line))
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7649
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230794 91177308-0d34-0410-b5e6-96231b3b80d8
90 lines
3.6 KiB
LLVM
90 lines
3.6 KiB
LLVM
; RUN: llc -O3 -mtriple=x86_64-unknown -mcpu=core-avx2 -mattr=avx2 < %s | FileCheck %s
|
|
|
|
define <8 x i16> @commute_fold_vpblendw_128(<8 x i16> %a, <8 x i16>* %b) #0 {
|
|
%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 {
|
|
%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 {
|
|
%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 {
|
|
%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 {
|
|
%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 3)
|
|
ret <4 x float> %2
|
|
|
|
;LABEL: commute_fold_vblendps_128
|
|
;CHECK: vblendps {{.*#+}} xmm0 = xmm0[0,1],mem[2,3]
|
|
;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 {
|
|
%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 {
|
|
%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 {
|
|
%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
|