mirror of
https://github.com/RPCSX/llvm.git
synced 2024-12-15 07:59:50 +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
44 lines
1.6 KiB
LLVM
44 lines
1.6 KiB
LLVM
; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a8 %s -o - | FileCheck %s
|
|
; Radar 7872877
|
|
|
|
define void @test(float* %fltp, i32 %packedValue, float* %table) nounwind {
|
|
entry:
|
|
%0 = load float, float* %fltp
|
|
%1 = insertelement <4 x float> undef, float %0, i32 0
|
|
%2 = shufflevector <4 x float> %1, <4 x float> undef, <4 x i32> zeroinitializer
|
|
%3 = shl i32 %packedValue, 16
|
|
%4 = ashr i32 %3, 30
|
|
%.sum = add i32 %4, 4
|
|
%5 = getelementptr inbounds float, float* %table, i32 %.sum
|
|
;CHECK: vldr s
|
|
%6 = load float, float* %5, align 4
|
|
%tmp11 = insertelement <4 x float> undef, float %6, i32 0
|
|
%7 = shl i32 %packedValue, 18
|
|
%8 = ashr i32 %7, 30
|
|
%.sum12 = add i32 %8, 4
|
|
%9 = getelementptr inbounds float, float* %table, i32 %.sum12
|
|
;CHECK: vldr s
|
|
%10 = load float, float* %9, align 4
|
|
%tmp9 = insertelement <4 x float> %tmp11, float %10, i32 1
|
|
%11 = shl i32 %packedValue, 20
|
|
%12 = ashr i32 %11, 30
|
|
%.sum13 = add i32 %12, 4
|
|
%13 = getelementptr inbounds float, float* %table, i32 %.sum13
|
|
;CHECK: vldr s
|
|
%14 = load float, float* %13, align 4
|
|
%tmp7 = insertelement <4 x float> %tmp9, float %14, i32 2
|
|
%15 = shl i32 %packedValue, 22
|
|
%16 = ashr i32 %15, 30
|
|
%.sum14 = add i32 %16, 4
|
|
%17 = getelementptr inbounds float, float* %table, i32 %.sum14
|
|
;CHECK: vldr s
|
|
%18 = load float, float* %17, align 4
|
|
%tmp5 = insertelement <4 x float> %tmp7, float %18, i32 3
|
|
%19 = fmul <4 x float> %tmp5, %2
|
|
%20 = bitcast float* %fltp to i8*
|
|
tail call void @llvm.arm.neon.vst1.v4f32(i8* %20, <4 x float> %19, i32 1)
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.arm.neon.vst1.v4f32(i8*, <4 x float>, i32) nounwind
|