mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-24 06:30:19 +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
43 lines
2.2 KiB
LLVM
43 lines
2.2 KiB
LLVM
; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs -mattr=+load-store-opt -enable-misched < %s | FileCheck --check-prefix=CHECK %s
|
|
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs -mattr=+load-store-opt -enable-misched < %s | FileCheck --check-prefix=CHECK %s
|
|
|
|
; This test is for a bug in the machine scheduler where stores without
|
|
; an underlying object would be moved across the barrier. In this
|
|
; test, the <2 x i8> store will be split into two i8 stores, so they
|
|
; won't have an underlying object.
|
|
|
|
; CHECK-LABEL: {{^}}test:
|
|
; CHECK: ds_write_b8
|
|
; CHECK: ds_write_b8
|
|
; CHECK: s_barrier
|
|
; CHECK: s_endpgm
|
|
; Function Attrs: nounwind
|
|
define void @test(<2 x i8> addrspace(3)* nocapture %arg, <2 x i8> addrspace(1)* nocapture readonly %arg1, i32 addrspace(1)* nocapture readonly %arg2, <2 x i8> addrspace(1)* nocapture %arg3, i32 %arg4, i64 %tmp9) {
|
|
bb:
|
|
%tmp10 = getelementptr inbounds i32, i32 addrspace(1)* %arg2, i64 %tmp9
|
|
%tmp13 = load i32, i32 addrspace(1)* %tmp10, align 2
|
|
%tmp14 = getelementptr inbounds <2 x i8>, <2 x i8> addrspace(3)* %arg, i32 %tmp13
|
|
%tmp15 = load <2 x i8>, <2 x i8> addrspace(3)* %tmp14, align 2
|
|
%tmp16 = add i32 %tmp13, 1
|
|
%tmp17 = getelementptr inbounds <2 x i8>, <2 x i8> addrspace(3)* %arg, i32 %tmp16
|
|
store <2 x i8> %tmp15, <2 x i8> addrspace(3)* %tmp17, align 2
|
|
tail call void @llvm.AMDGPU.barrier.local() #2
|
|
%tmp25 = load i32, i32 addrspace(1)* %tmp10, align 4
|
|
%tmp26 = sext i32 %tmp25 to i64
|
|
%tmp27 = sext i32 %arg4 to i64
|
|
%tmp28 = getelementptr inbounds <2 x i8>, <2 x i8> addrspace(3)* %arg, i32 %tmp25, i32 %arg4
|
|
%tmp29 = load i8, i8 addrspace(3)* %tmp28, align 1
|
|
%tmp30 = getelementptr inbounds <2 x i8>, <2 x i8> addrspace(1)* %arg3, i64 %tmp26, i64 %tmp27
|
|
store i8 %tmp29, i8 addrspace(1)* %tmp30, align 1
|
|
%tmp32 = getelementptr inbounds <2 x i8>, <2 x i8> addrspace(3)* %arg, i32 %tmp25, i32 0
|
|
%tmp33 = load i8, i8 addrspace(3)* %tmp32, align 1
|
|
%tmp35 = getelementptr inbounds <2 x i8>, <2 x i8> addrspace(1)* %arg3, i64 %tmp26, i64 0
|
|
store i8 %tmp33, i8 addrspace(1)* %tmp35, align 1
|
|
ret void
|
|
}
|
|
|
|
; Function Attrs: noduplicate nounwind
|
|
declare void @llvm.AMDGPU.barrier.local() #2
|
|
|
|
attributes #2 = { noduplicate nounwind }
|