mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-19 11:02:59 +02:00
81a9bfe915
This switches to the workaround that HSA defaults to for the mesa path. This should be applied to the 4.0 branch. Patch by Vedran Miletić <vedran@miletic.net> llvm-svn: 292982
40 lines
1.9 KiB
LLVM
40 lines
1.9 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
|
|
|
|
declare float @llvm.maxnum.f32(float, float) nounwind readnone
|
|
|
|
; SI-LABEL: {{^}}test_fmax3_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_max3_f32 [[RESULT:v[0-9]+]], [[REGC]], [[REGB]], [[REGA]]
|
|
; SI: buffer_store_dword [[RESULT]],
|
|
; SI: s_endpgm
|
|
define void @test_fmax3_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.maxnum.f32(float %a, float %b) nounwind readnone
|
|
%f1 = call float @llvm.maxnum.f32(float %f0, float %c) nounwind readnone
|
|
store float %f1, float addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; Commute operand of second fmax
|
|
; SI-LABEL: {{^}}test_fmax3_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_max3_f32 [[RESULT:v[0-9]+]], [[REGC]], [[REGB]], [[REGA]]
|
|
; SI: buffer_store_dword [[RESULT]],
|
|
; SI: s_endpgm
|
|
define void @test_fmax3_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.maxnum.f32(float %a, float %b) nounwind readnone
|
|
%f1 = call float @llvm.maxnum.f32(float %c, float %f0) nounwind readnone
|
|
store float %f1, float addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|