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
44 lines
1.8 KiB
LLVM
44 lines
1.8 KiB
LLVM
; RUN: llc -march=amdgcn -mcpu=SI < %s | FileCheck -check-prefix=SI %s
|
|
; RUN: llc -march=amdgcn -mcpu=tonga < %s | FileCheck -check-prefix=SI %s
|
|
|
|
declare float @llvm.AMDGPU.cvt.f32.ubyte0(i32) nounwind readnone
|
|
declare float @llvm.AMDGPU.cvt.f32.ubyte1(i32) nounwind readnone
|
|
declare float @llvm.AMDGPU.cvt.f32.ubyte2(i32) nounwind readnone
|
|
declare float @llvm.AMDGPU.cvt.f32.ubyte3(i32) nounwind readnone
|
|
|
|
; SI-LABEL: {{^}}test_unpack_byte0_to_float:
|
|
; SI: v_cvt_f32_ubyte0
|
|
define void @test_unpack_byte0_to_float(float addrspace(1)* %out, i32 addrspace(1)* %in) nounwind {
|
|
%val = load i32, i32 addrspace(1)* %in, align 4
|
|
%cvt = call float @llvm.AMDGPU.cvt.f32.ubyte0(i32 %val) nounwind readnone
|
|
store float %cvt, float addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; SI-LABEL: {{^}}test_unpack_byte1_to_float:
|
|
; SI: v_cvt_f32_ubyte1
|
|
define void @test_unpack_byte1_to_float(float addrspace(1)* %out, i32 addrspace(1)* %in) nounwind {
|
|
%val = load i32, i32 addrspace(1)* %in, align 4
|
|
%cvt = call float @llvm.AMDGPU.cvt.f32.ubyte1(i32 %val) nounwind readnone
|
|
store float %cvt, float addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; SI-LABEL: {{^}}test_unpack_byte2_to_float:
|
|
; SI: v_cvt_f32_ubyte2
|
|
define void @test_unpack_byte2_to_float(float addrspace(1)* %out, i32 addrspace(1)* %in) nounwind {
|
|
%val = load i32, i32 addrspace(1)* %in, align 4
|
|
%cvt = call float @llvm.AMDGPU.cvt.f32.ubyte2(i32 %val) nounwind readnone
|
|
store float %cvt, float addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; SI-LABEL: {{^}}test_unpack_byte3_to_float:
|
|
; SI: v_cvt_f32_ubyte3
|
|
define void @test_unpack_byte3_to_float(float addrspace(1)* %out, i32 addrspace(1)* %in) nounwind {
|
|
%val = load i32, i32 addrspace(1)* %in, align 4
|
|
%cvt = call float @llvm.AMDGPU.cvt.f32.ubyte3(i32 %val) nounwind readnone
|
|
store float %cvt, float addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|