mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-15 20:29:48 +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
36 lines
1.2 KiB
LLVM
36 lines
1.2 KiB
LLVM
; RUN: llc < %s -march=amdgcn -mcpu=SI -verify-machineinstrs | FileCheck %s
|
|
; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s
|
|
|
|
@lds = external addrspace(3) global [64 x float]
|
|
|
|
; CHECK-LABEL: {{^}}main:
|
|
; CHECK-NOT: v_readlane_b32 m0
|
|
define void @main(<16 x i8> addrspace(2)* inreg, <16 x i8> addrspace(2)* inreg, <32 x i8> addrspace(2)* inreg, i32 inreg) "ShaderType"="0" {
|
|
main_body:
|
|
%4 = call float @llvm.SI.fs.constant(i32 0, i32 0, i32 %3)
|
|
%cmp = fcmp ueq float 0.0, %4
|
|
br i1 %cmp, label %if, label %else
|
|
|
|
if:
|
|
%lds_ptr = getelementptr [64 x float], [64 x float] addrspace(3)* @lds, i32 0, i32 0
|
|
%lds_data = load float, float addrspace(3)* %lds_ptr
|
|
br label %endif
|
|
|
|
else:
|
|
%interp = call float @llvm.SI.fs.constant(i32 0, i32 0, i32 %3)
|
|
br label %endif
|
|
|
|
endif:
|
|
%export = phi float [%lds_data, %if], [%interp, %else]
|
|
%5 = call i32 @llvm.SI.packf16(float %export, float %export)
|
|
%6 = bitcast i32 %5 to float
|
|
call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %6, float %6, float %6, float %6)
|
|
ret void
|
|
}
|
|
|
|
declare float @llvm.SI.fs.constant(i32, i32, i32) readnone
|
|
|
|
declare i32 @llvm.SI.packf16(float, float) readnone
|
|
|
|
declare void @llvm.SI.export(i32, i32, i32, i32, i32, float, float, float, float)
|