mirror of
https://github.com/RPCSX/llvm.git
synced 2025-04-12 21:18:23 +00:00
d706d030af
Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@298444 91177308-0d34-0410-b5e6-96231b3b80d8
21 lines
981 B
LLVM
21 lines
981 B
LLVM
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=FUNC %s
|
|
; RUN: llc -march=r600 -mcpu=cypress -verify-machineinstrs < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
|
|
|
|
declare i16 @llvm.convert.to.fp16.f32(float) nounwind readnone
|
|
|
|
; FUNC-LABEL: {{^}}test_convert_fp32_to_fp16:
|
|
; GCN: buffer_load_dword [[VAL:v[0-9]+]]
|
|
; GCN: v_cvt_f16_f32_e32 [[RESULT:v[0-9]+]], [[VAL]]
|
|
; GCN: buffer_store_short [[RESULT]]
|
|
|
|
; EG: MEM_RAT MSKOR
|
|
; EG: VTX_READ_32
|
|
; EG: FLT32_TO_FLT16
|
|
define amdgpu_kernel void @test_convert_fp32_to_fp16(i16 addrspace(1)* noalias %out, float addrspace(1)* noalias %in) nounwind {
|
|
%val = load float, float addrspace(1)* %in, align 4
|
|
%cvt = call i16 @llvm.convert.to.fp16.f32(float %val) nounwind readnone
|
|
store i16 %cvt, i16 addrspace(1)* %out, align 2
|
|
ret void
|
|
}
|