llvm-6502/test/CodeGen/R600/fma.f64.ll
Tom Stellard 1f996fa36b R600/SI: Add a stub GCNTargetMachine
This is equivalent to the AMDGPUTargetMachine now, but it is the
starting point for separating R600 and GCN functionality into separate
targets.

It is recommened that users start using the gcn triple for GCN-based
GPUs, because using the r600 triple for these GPUs will be deprecated in
the future.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@225277 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-06 18:00:21 +00:00

47 lines
2.0 KiB
LLVM

; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
declare double @llvm.fma.f64(double, double, double) nounwind readnone
declare <2 x double> @llvm.fma.v2f64(<2 x double>, <2 x double>, <2 x double>) nounwind readnone
declare <4 x double> @llvm.fma.v4f64(<4 x double>, <4 x double>, <4 x double>) nounwind readnone
; FUNC-LABEL: {{^}}fma_f64:
; SI: v_fma_f64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\]}}
define void @fma_f64(double addrspace(1)* %out, double addrspace(1)* %in1,
double addrspace(1)* %in2, double addrspace(1)* %in3) {
%r0 = load double addrspace(1)* %in1
%r1 = load double addrspace(1)* %in2
%r2 = load double addrspace(1)* %in3
%r3 = tail call double @llvm.fma.f64(double %r0, double %r1, double %r2)
store double %r3, double addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}fma_v2f64:
; SI: v_fma_f64
; SI: v_fma_f64
define void @fma_v2f64(<2 x double> addrspace(1)* %out, <2 x double> addrspace(1)* %in1,
<2 x double> addrspace(1)* %in2, <2 x double> addrspace(1)* %in3) {
%r0 = load <2 x double> addrspace(1)* %in1
%r1 = load <2 x double> addrspace(1)* %in2
%r2 = load <2 x double> addrspace(1)* %in3
%r3 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %r0, <2 x double> %r1, <2 x double> %r2)
store <2 x double> %r3, <2 x double> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}fma_v4f64:
; SI: v_fma_f64
; SI: v_fma_f64
; SI: v_fma_f64
; SI: v_fma_f64
define void @fma_v4f64(<4 x double> addrspace(1)* %out, <4 x double> addrspace(1)* %in1,
<4 x double> addrspace(1)* %in2, <4 x double> addrspace(1)* %in3) {
%r0 = load <4 x double> addrspace(1)* %in1
%r1 = load <4 x double> addrspace(1)* %in2
%r2 = load <4 x double> addrspace(1)* %in3
%r3 = tail call <4 x double> @llvm.fma.v4f64(<4 x double> %r0, <4 x double> %r1, <4 x double> %r2)
store <4 x double> %r3, <4 x double> addrspace(1)* %out
ret void
}