mirror of
https://github.com/RPCS3/llvm.git
synced 2025-05-23 13:56:06 +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
41 lines
2.1 KiB
LLVM
41 lines
2.1 KiB
LLVM
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
|
|
|
|
declare float @llvm.minnum.f32(float, float) nounwind readnone
|
|
|
|
; SI-LABEL: {{^}}test_fmin3_olt_0:
|
|
; SI: buffer_load_dword [[REGC:v[0-9]+]]
|
|
; SI: buffer_load_dword [[REGB:v[0-9]+]]
|
|
; SI: buffer_load_dword [[REGA:v[0-9]+]]
|
|
; SI: v_min3_f32 [[RESULT:v[0-9]+]], [[REGC]], [[REGB]], [[REGA]]
|
|
; SI: buffer_store_dword [[RESULT]],
|
|
; SI: s_endpgm
|
|
define amdgpu_kernel void @test_fmin3_olt_0(float addrspace(1)* %out, float addrspace(1)* %aptr, float addrspace(1)* %bptr, float addrspace(1)* %cptr) nounwind {
|
|
%a = load volatile float, float addrspace(1)* %aptr, align 4
|
|
%b = load volatile float, float addrspace(1)* %bptr, align 4
|
|
%c = load volatile float, float addrspace(1)* %cptr, align 4
|
|
%f0 = call float @llvm.minnum.f32(float %a, float %b) nounwind readnone
|
|
%f1 = call float @llvm.minnum.f32(float %f0, float %c) nounwind readnone
|
|
store float %f1, float addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; Commute operand of second fmin
|
|
; SI-LABEL: {{^}}test_fmin3_olt_1:
|
|
; SI: buffer_load_dword [[REGB:v[0-9]+]]
|
|
; SI: buffer_load_dword [[REGA:v[0-9]+]]
|
|
; SI: buffer_load_dword [[REGC:v[0-9]+]]
|
|
; SI: v_min3_f32 [[RESULT:v[0-9]+]], [[REGC]], [[REGB]], [[REGA]]
|
|
; SI: buffer_store_dword [[RESULT]],
|
|
; SI: s_endpgm
|
|
define amdgpu_kernel void @test_fmin3_olt_1(float addrspace(1)* %out, float addrspace(1)* %aptr, float addrspace(1)* %bptr, float addrspace(1)* %cptr) nounwind {
|
|
%a = load volatile float, float addrspace(1)* %aptr, align 4
|
|
%b = load volatile float, float addrspace(1)* %bptr, align 4
|
|
%c = load volatile float, float addrspace(1)* %cptr, align 4
|
|
%f0 = call float @llvm.minnum.f32(float %a, float %b) nounwind readnone
|
|
%f1 = call float @llvm.minnum.f32(float %c, float %f0) nounwind readnone
|
|
store float %f1, float addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|