llvm/test/CodeGen/AMDGPU/fmax3.ll
Changpeng Fang faf7289db3 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

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@270894 91177308-0d34-0410-b5e6-96231b3b80d8
2016-05-26 19:35:29 +00:00

40 lines
1.9 KiB
LLVM

; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
; RUN: llc -march=amdgcn -mcpu=tonga -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
}