mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-23 21:13:02 +02:00
342e72a308
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. llvm-svn: 225277
46 lines
1.3 KiB
LLVM
46 lines
1.3 KiB
LLVM
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -check-prefix=CI -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
|
|
; FUNC-LABEL: {{^}}rint_f64:
|
|
; CI: v_rndne_f64_e32
|
|
|
|
; SI-DAG: v_add_f64
|
|
; SI-DAG: v_add_f64
|
|
; SI-DAG v_cmp_gt_f64_e64
|
|
; SI: v_cndmask_b32
|
|
; SI: v_cndmask_b32
|
|
; SI: s_endpgm
|
|
define void @rint_f64(double addrspace(1)* %out, double %in) {
|
|
entry:
|
|
%0 = call double @llvm.rint.f64(double %in)
|
|
store double %0, double addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}rint_v2f64:
|
|
; CI: v_rndne_f64_e32
|
|
; CI: v_rndne_f64_e32
|
|
define void @rint_v2f64(<2 x double> addrspace(1)* %out, <2 x double> %in) {
|
|
entry:
|
|
%0 = call <2 x double> @llvm.rint.v2f64(<2 x double> %in)
|
|
store <2 x double> %0, <2 x double> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}rint_v4f64:
|
|
; CI: v_rndne_f64_e32
|
|
; CI: v_rndne_f64_e32
|
|
; CI: v_rndne_f64_e32
|
|
; CI: v_rndne_f64_e32
|
|
define void @rint_v4f64(<4 x double> addrspace(1)* %out, <4 x double> %in) {
|
|
entry:
|
|
%0 = call <4 x double> @llvm.rint.v4f64(<4 x double> %in)
|
|
store <4 x double> %0, <4 x double> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
|
|
declare double @llvm.rint.f64(double) #0
|
|
declare <2 x double> @llvm.rint.v2f64(<2 x double>) #0
|
|
declare <4 x double> @llvm.rint.v4f64(<4 x double>) #0
|