maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/fmax3.ll

40 lines
1.9 KiB
LLVM
Raw Normal View History

Enable FeatureFlatForGlobal on Volcanic Islands 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
2017-01-25 06:02:15 +08:00
; 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
R600/SI: Combine min3/max3 instructions llvm-svn: 222032
2014-11-15 04:08:52 +08:00
declare float @llvm.maxnum.f32(float, float) nounwind readnone
; SI-LABEL: {{^}}test_fmax3_olt_0:
; SI: buffer_load_dword [[REGC:v[0-9]+]]
R600/SI: Define a schedule model and enable the generic machine scheduler The schedule model is not complete yet, and could be improved. llvm-svn: 227461
2015-01-30 00:55:25 +08:00
; SI: buffer_load_dword [[REGB:v[0-9]+]]
; SI: buffer_load_dword [[REGA:v[0-9]+]]
R600/SI: Combine min3/max3 instructions llvm-svn: 222032
2014-11-15 04:08:52 +08:00
; SI: v_max3_f32 [[RESULT:v[0-9]+]], [[REGC]], [[REGB]], [[REGA]]
; SI: buffer_store_dword [[RESULT]],
; SI: s_endpgm
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_fmax3_olt_0(float addrspace(1)* %out, float addrspace(1)* %aptr, float addrspace(1)* %bptr, float addrspace(1)* %cptr) nounwind {
AMDGPU/SI: Enable load-store-opt by default. Summary: Enable load-store-opt by default, and update LIT tests. Reviewers: arsenm Differential Revision: http://reviews.llvm.org/D20694 llvm-svn: 270894
2016-05-27 03:35:29 +08:00
%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
R600/SI: Combine min3/max3 instructions llvm-svn: 222032
2014-11-15 04:08:52 +08:00
%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]+]]
R600/SI: Define a schedule model and enable the generic machine scheduler The schedule model is not complete yet, and could be improved. llvm-svn: 227461
2015-01-30 00:55:25 +08:00
; SI: buffer_load_dword [[REGA:v[0-9]+]]
R600/SI: Combine min3/max3 instructions llvm-svn: 222032
2014-11-15 04:08:52 +08:00
; 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
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_fmax3_olt_1(float addrspace(1)* %out, float addrspace(1)* %aptr, float addrspace(1)* %bptr, float addrspace(1)* %cptr) nounwind {
AMDGPU/SI: Enable load-store-opt by default. Summary: Enable load-store-opt by default, and update LIT tests. Reviewers: arsenm Differential Revision: http://reviews.llvm.org/D20694 llvm-svn: 270894
2016-05-27 03:35:29 +08:00
%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
R600/SI: Combine min3/max3 instructions llvm-svn: 222032
2014-11-15 04:08:52 +08:00
%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
}