mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-16 11:30:51 +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
12 lines
554 B
LLVM
12 lines
554 B
LLVM
; RUN: llc -march=r600 -mcpu=redwood -verify-machineinstrs < %s
|
|
|
|
declare float @llvm.AMDGPU.dp4(<4 x float>, <4 x float>) nounwind readnone
|
|
|
|
define void @test_dp4(float addrspace(1)* %out, <4 x float> addrspace(1)* %a, <4 x float> addrspace(1)* %b) nounwind {
|
|
%src0 = load <4 x float>, <4 x float> addrspace(1)* %a, align 16
|
|
%src1 = load <4 x float>, <4 x float> addrspace(1)* %b, align 16
|
|
%dp4 = call float @llvm.AMDGPU.dp4(<4 x float> %src0, <4 x float> %src1) nounwind readnone
|
|
store float %dp4, float addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|