1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 19:23:23 +01:00
llvm-mirror/test/CodeGen/AMDGPU/fmax3.f64.ll
Matt Arsenault 5dfc642fbd AMDGPU: Cleanup subtarget features
Try to avoid mutually exclusive features. Don't use
a real default GPU, and use a fake "generic". The goal
is to make it easier to see which set of features are
incompatible between feature strings.

Most of the test changes are due to random scheduling changes
from not having a default fullspeed model.

llvm-svn: 310258
2017-08-07 14:58:04 +00:00

25 lines
1.4 KiB
LLVM

; RUN: llc -march=amdgcn -mcpu=tahiti -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 double @llvm.maxnum.f64(double, double) nounwind readnone
; SI-LABEL: {{^}}test_fmax3_f64:
; SI-DAG: buffer_load_dwordx2 [[REGA:v\[[0-9]+:[0-9]+\]]], off, s[{{[0-9]+:[0-9]+}}], 0{{$}}
; SI-DAG: buffer_load_dwordx2 [[REGB:v\[[0-9]+:[0-9]+\]]], off, s[{{[0-9]+:[0-9]+}}], 0 offset:8
; SI: v_max_f64 [[REGA]], [[REGA]], [[REGB]]
; SI: buffer_load_dwordx2 [[REGC:v\[[0-9]+:[0-9]+\]]], off, s[{{[0-9]+:[0-9]+}}], 0 offset:16
; SI: v_max_f64 [[RESULT:v\[[0-9]+:[0-9]+\]]], [[REGA]], [[REGC]]
; SI: buffer_store_dwordx2 [[RESULT]],
; SI: s_endpgm
define amdgpu_kernel void @test_fmax3_f64(double addrspace(1)* %out, double addrspace(1)* %aptr) nounwind {
%bptr = getelementptr double, double addrspace(1)* %aptr, i32 1
%cptr = getelementptr double, double addrspace(1)* %aptr, i32 2
%a = load volatile double, double addrspace(1)* %aptr, align 8
%b = load volatile double, double addrspace(1)* %bptr, align 8
%c = load volatile double, double addrspace(1)* %cptr, align 8
%f0 = call double @llvm.maxnum.f64(double %a, double %b) nounwind readnone
%f1 = call double @llvm.maxnum.f64(double %f0, double %c) nounwind readnone
store double %f1, double addrspace(1)* %out, align 8
ret void
}