mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-15 04:30:12 +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
46 lines
2.0 KiB
LLVM
46 lines
2.0 KiB
LLVM
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs -mattr=+load-store-opt -enable-misched < %s | FileCheck -strict-whitespace -check-prefix=SI %s
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs -mattr=+load-store-opt -enable-misched < %s | FileCheck -strict-whitespace -check-prefix=SI %s
|
|
|
|
; XFAIL: *
|
|
|
|
@lds = addrspace(3) global [512 x float] undef, align 4
|
|
|
|
; SI-LABEL: {{^}}offset_order:
|
|
|
|
; SI: ds_read_b32 v{{[0-9]+}}, v{{[0-9]+}} offset:56
|
|
; SI: ds_read2st64_b32 v[{{[0-9]+}}:{{[0-9]+}}], v{{[0-9]+}} offset0:0 offset1:4
|
|
; SI: ds_read2_b32 v[{{[0-9]+}}:{{[0-9]+}}], v{{[0-9]+}} offset0:2 offset1:3
|
|
; SI: ds_read2_b32 v[{{[0-9]+}}:{{[0-9]+}}], v{{[0-9]+}} offset0:11 offset1:1
|
|
|
|
define void @offset_order(float addrspace(1)* %out) {
|
|
entry:
|
|
%ptr0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 0
|
|
%val0 = load float, float addrspace(3)* %ptr0
|
|
|
|
%ptr1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 256
|
|
%val1 = load float, float addrspace(3)* %ptr1
|
|
%add1 = fadd float %val0, %val1
|
|
|
|
%ptr2 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 3
|
|
%val2 = load float, float addrspace(3)* %ptr2
|
|
%add2 = fadd float %add1, %val2
|
|
|
|
%ptr3 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 2
|
|
%val3 = load float, float addrspace(3)* %ptr3
|
|
%add3 = fadd float %add2, %val3
|
|
|
|
%ptr4 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 12
|
|
%val4 = load float, float addrspace(3)* %ptr4
|
|
%add4 = fadd float %add3, %val4
|
|
|
|
%ptr5 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 14
|
|
%val5 = load float, float addrspace(3)* %ptr5
|
|
%add5 = fadd float %add4, %val5
|
|
|
|
%ptr6 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 11
|
|
%val6 = load float, float addrspace(3)* %ptr6
|
|
%add6 = fadd float %add5, %val6
|
|
store float %add6, float addrspace(1)* %out
|
|
ret void
|
|
}
|