mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-07-21 02:29:22 +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
39 lines
2.0 KiB
LLVM
39 lines
2.0 KiB
LLVM
; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -march=r600 -mcpu=cayman -verify-machineinstrs < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
|
|
; RUN: llc -march=r600 -mcpu=redwood -verify-machineinstrs < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
|
|
; XUN: llc -march=r600 -mcpu=r600 -verify-machineinstrs < %s | FileCheck -check-prefix=R600 -check-prefix=FUNC %s
|
|
; XUN: llc -march=r600 -mcpu=rv770 -verify-machineinstrs < %s | FileCheck -check-prefix=R600 -check-prefix=FUNC %s
|
|
|
|
declare i32 @llvm.AMDGPU.umad24(i32, i32, i32) nounwind readnone
|
|
declare i32 @llvm.r600.read.tidig.x() nounwind readnone
|
|
|
|
; FUNC-LABEL: {{^}}test_umad24:
|
|
; SI: v_mad_u32_u24
|
|
; EG: MULADD_UINT24
|
|
; R600: MULLO_UINT
|
|
; R600: ADD_INT
|
|
define void @test_umad24(i32 addrspace(1)* %out, i32 %src0, i32 %src1, i32 %src2) nounwind {
|
|
%mad = call i32 @llvm.AMDGPU.umad24(i32 %src0, i32 %src1, i32 %src2) nounwind readnone
|
|
store i32 %mad, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}commute_umad24:
|
|
; SI-DAG: buffer_load_dword [[SRC0:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64{{$}}
|
|
; SI-DAG: buffer_load_dword [[SRC2:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:4
|
|
; SI: v_mad_u32_u24 [[RESULT:v[0-9]+]], 4, [[SRC0]], [[SRC2]]
|
|
; SI: buffer_store_dword [[RESULT]]
|
|
define void @commute_umad24(i32 addrspace(1)* %out, i32 addrspace(1)* %in) nounwind {
|
|
%tid = call i32 @llvm.r600.read.tidig.x() nounwind readnone
|
|
%out.gep = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
|
|
%src0.gep = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
|
|
%src2.gep = getelementptr i32, i32 addrspace(1)* %src0.gep, i32 1
|
|
|
|
%src0 = load i32, i32 addrspace(1)* %src0.gep, align 4
|
|
%src2 = load i32, i32 addrspace(1)* %src2.gep, align 4
|
|
%mad = call i32 @llvm.AMDGPU.umad24(i32 %src0, i32 4, i32 %src2) nounwind readnone
|
|
store i32 %mad, i32 addrspace(1)* %out.gep, align 4
|
|
ret void
|
|
}
|
|
|