mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 11:13:28 +01:00
ab043ff680
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
llvm-svn: 230794
61 lines
2.5 KiB
LLVM
61 lines
2.5 KiB
LLVM
; RUN: llc -O3 -disable-peephole -mcpu=corei7-avx -mattr=+avx < %s | FileCheck %s
|
|
|
|
target datalayout = "e-i64:64-f80:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-apple-macosx10.9.0"
|
|
|
|
; Function Attrs: nounwind ssp uwtable
|
|
define void @test1(float* %A, float* %C) #0 {
|
|
%tmp1 = bitcast float* %A to <8 x float>*
|
|
%tmp2 = load <8 x float>, <8 x float>* %tmp1, align 32
|
|
%tmp3 = bitcast <8 x float> %tmp2 to <8 x i32>
|
|
%tmp4 = and <8 x i32> %tmp3, <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>
|
|
%tmp5 = bitcast <8 x i32> %tmp4 to <8 x float>
|
|
%tmp6 = extractelement <8 x float> %tmp5, i32 0
|
|
store float %tmp6, float* %C
|
|
ret void
|
|
|
|
; CHECK: vandps LCPI0_0(%rip), %ymm0, %ymm0
|
|
}
|
|
|
|
; Function Attrs: nounwind ssp uwtable
|
|
define void @test2(float* %A, float* %C) #0 {
|
|
%tmp1 = bitcast float* %A to <8 x float>*
|
|
%tmp2 = load <8 x float>, <8 x float>* %tmp1, align 32
|
|
%tmp3 = bitcast <8 x float> %tmp2 to <8 x i32>
|
|
%tmp4 = or <8 x i32> %tmp3, <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>
|
|
%tmp5 = bitcast <8 x i32> %tmp4 to <8 x float>
|
|
%tmp6 = extractelement <8 x float> %tmp5, i32 0
|
|
store float %tmp6, float* %C
|
|
ret void
|
|
|
|
; CHECK: vorps LCPI1_0(%rip), %ymm0, %ymm0
|
|
}
|
|
|
|
; Function Attrs: nounwind ssp uwtable
|
|
define void @test3(float* %A, float* %C) #0 {
|
|
%tmp1 = bitcast float* %A to <8 x float>*
|
|
%tmp2 = load <8 x float>, <8 x float>* %tmp1, align 32
|
|
%tmp3 = bitcast <8 x float> %tmp2 to <8 x i32>
|
|
%tmp4 = xor <8 x i32> %tmp3, <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>
|
|
%tmp5 = bitcast <8 x i32> %tmp4 to <8 x float>
|
|
%tmp6 = extractelement <8 x float> %tmp5, i32 0
|
|
store float %tmp6, float* %C
|
|
ret void
|
|
|
|
; CHECK: vxorps LCPI2_0(%rip), %ymm0, %ymm0
|
|
}
|
|
|
|
define void @test4(float* %A, float* %C) #0 {
|
|
%tmp1 = bitcast float* %A to <8 x float>*
|
|
%tmp2 = load <8 x float>, <8 x float>* %tmp1, align 32
|
|
%tmp3 = bitcast <8 x float> %tmp2 to <8 x i32>
|
|
%tmp4 = xor <8 x i32> %tmp3, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
|
|
%tmp5 = and <8 x i32> %tmp4, <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>
|
|
%tmp6 = bitcast <8 x i32> %tmp5 to <8 x float>
|
|
%tmp7 = extractelement <8 x float> %tmp6, i32 0
|
|
store float %tmp7, float * %C
|
|
ret void
|
|
|
|
;CHECK: vandnps LCPI3_0(%rip), %ymm0, %ymm0
|
|
}
|