mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-22 18:54:02 +01:00
dd9ab77318
Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
51 lines
1.4 KiB
LLVM
51 lines
1.4 KiB
LLVM
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck %s -check-prefix=R600 -check-prefix=FUNC
|
|
|
|
; FUNC-LABEL: {{^}}rint_f32:
|
|
; R600: RNDNE
|
|
|
|
; SI: v_rndne_f32_e32
|
|
define amdgpu_kernel void @rint_f32(float addrspace(1)* %out, float %in) {
|
|
entry:
|
|
%0 = call float @llvm.rint.f32(float %in) #0
|
|
store float %0, float addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}rint_v2f32:
|
|
; R600: RNDNE
|
|
; R600: RNDNE
|
|
|
|
; SI: v_rndne_f32_e32
|
|
; SI: v_rndne_f32_e32
|
|
define amdgpu_kernel void @rint_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %in) {
|
|
entry:
|
|
%0 = call <2 x float> @llvm.rint.v2f32(<2 x float> %in) #0
|
|
store <2 x float> %0, <2 x float> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}rint_v4f32:
|
|
; R600: RNDNE
|
|
; R600: RNDNE
|
|
; R600: RNDNE
|
|
; R600: RNDNE
|
|
|
|
; SI: v_rndne_f32_e32
|
|
; SI: v_rndne_f32_e32
|
|
; SI: v_rndne_f32_e32
|
|
; SI: v_rndne_f32_e32
|
|
define amdgpu_kernel void @rint_v4f32(<4 x float> addrspace(1)* %out, <4 x float> %in) {
|
|
entry:
|
|
%0 = call <4 x float> @llvm.rint.v4f32(<4 x float> %in) #0
|
|
store <4 x float> %0, <4 x float> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
declare float @llvm.rint.f32(float) #0
|
|
declare <2 x float> @llvm.rint.v2f32(<2 x float>) #0
|
|
declare <4 x float> @llvm.rint.v4f32(<4 x float>) #0
|
|
|
|
attributes #0 = { nounwind readnone }
|