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
49 lines
1.7 KiB
LLVM
49 lines
1.7 KiB
LLVM
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -check-prefix=CI -check-prefix=FUNC %s
|
|
|
|
@local_memory.local_mem = internal unnamed_addr addrspace(3) global [128 x i32] undef, align 4
|
|
|
|
; FUNC-LABEL: {{^}}local_memory:
|
|
|
|
; Check that the LDS size emitted correctly
|
|
; EG: .long 166120
|
|
; EG-NEXT: .long 128
|
|
; SI: .long 47180
|
|
; SI-NEXT: .long 71560
|
|
; CI: .long 47180
|
|
; CI-NEXT: .long 38792
|
|
|
|
; EG: LDS_WRITE
|
|
; SI-NOT: s_wqm_b64
|
|
; SI: ds_write_b32
|
|
|
|
; GROUP_BARRIER must be the last instruction in a clause
|
|
; EG: GROUP_BARRIER
|
|
; EG-NEXT: ALU clause
|
|
; SI: s_barrier
|
|
|
|
; EG: LDS_READ_RET
|
|
; SI: ds_read_b32 {{v[0-9]+}},
|
|
|
|
define void @local_memory(i32 addrspace(1)* %out) {
|
|
entry:
|
|
%y.i = call i32 @llvm.r600.read.tidig.x() #0
|
|
%arrayidx = getelementptr inbounds [128 x i32], [128 x i32] addrspace(3)* @local_memory.local_mem, i32 0, i32 %y.i
|
|
store i32 %y.i, i32 addrspace(3)* %arrayidx, align 4
|
|
%add = add nsw i32 %y.i, 1
|
|
%cmp = icmp eq i32 %add, 16
|
|
%.add = select i1 %cmp, i32 0, i32 %add
|
|
call void @llvm.AMDGPU.barrier.local()
|
|
%arrayidx1 = getelementptr inbounds [128 x i32], [128 x i32] addrspace(3)* @local_memory.local_mem, i32 0, i32 %.add
|
|
%0 = load i32, i32 addrspace(3)* %arrayidx1, align 4
|
|
%arrayidx2 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 %y.i
|
|
store i32 %0, i32 addrspace(1)* %arrayidx2, align 4
|
|
ret void
|
|
}
|
|
|
|
declare i32 @llvm.r600.read.tidig.x() #0
|
|
declare void @llvm.AMDGPU.barrier.local()
|
|
|
|
attributes #0 = { readnone }
|