mirror of
https://github.com/RPCS3/llvm.git
synced 2024-12-13 23:18:58 +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
42 lines
1.8 KiB
LLVM
42 lines
1.8 KiB
LLVM
; RUN: llc -mtriple=arm-eabi -mattr=+neon -mcpu=cortex-a9 %s -o /dev/null
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @foo(i8* nocapture %pBuffer, i32 %numItems) nounwind {
|
|
%1 = ptrtoint i8* %pBuffer to i32
|
|
|
|
%lsr.iv2641 = inttoptr i32 %1 to float*
|
|
%tmp29 = add i32 %1, 4
|
|
%tmp2930 = inttoptr i32 %tmp29 to float*
|
|
%tmp31 = add i32 %1, 8
|
|
%tmp3132 = inttoptr i32 %tmp31 to float*
|
|
%tmp33 = add i32 %1, 12
|
|
%tmp3334 = inttoptr i32 %tmp33 to float*
|
|
%tmp35 = add i32 %1, 16
|
|
%tmp3536 = inttoptr i32 %tmp35 to float*
|
|
%tmp37 = add i32 %1, 20
|
|
%tmp3738 = inttoptr i32 %tmp37 to float*
|
|
%tmp39 = add i32 %1, 24
|
|
%tmp3940 = inttoptr i32 %tmp39 to float*
|
|
%2 = load float, float* %lsr.iv2641, align 4
|
|
%3 = load float, float* %tmp2930, align 4
|
|
%4 = load float, float* %tmp3132, align 4
|
|
%5 = load float, float* %tmp3334, align 4
|
|
%6 = load float, float* %tmp3536, align 4
|
|
%7 = load float, float* %tmp3738, align 4
|
|
%8 = load float, float* %tmp3940, align 4
|
|
%9 = insertelement <4 x float> undef, float %6, i32 0
|
|
%10 = shufflevector <4 x float> %9, <4 x float> undef, <4 x i32> zeroinitializer
|
|
%11 = insertelement <4 x float> %10, float %7, i32 1
|
|
%12 = insertelement <4 x float> %11, float %8, i32 2
|
|
%13 = insertelement <4 x float> undef, float %2, i32 0
|
|
%14 = shufflevector <4 x float> %13, <4 x float> undef, <4 x i32> zeroinitializer
|
|
%15 = insertelement <4 x float> %14, float %3, i32 1
|
|
%16 = insertelement <4 x float> %15, float %4, i32 2
|
|
%17 = insertelement <4 x float> %16, float %5, i32 3
|
|
%18 = fsub <4 x float> zeroinitializer, %12
|
|
%19 = shufflevector <4 x float> %18, <4 x float> undef, <4 x i32> zeroinitializer
|
|
%20 = shufflevector <4 x float> %17, <4 x float> undef, <2 x i32> <i32 0, i32 1>
|
|
%21 = shufflevector <2 x float> %20, <2 x float> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
|
|
|
|
ret <4 x float> %21
|
|
}
|