Files
archived-llvm/test/CodeGen/AMDGPU/fmax3.f64.ll
Matt Arsenault d019e8638a 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>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@292982 91177308-0d34-0410-b5e6-96231b3b80d8
2017-01-24 22:02:15 +00:00

25 lines
1.4 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 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 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
}