1 ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-NOHSA -check-prefix=FUNC -check-prefix=SI-NOHSA %s
2 ; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn-amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-HSA -check-prefix=FUNC -check-prefix=GCNX3-HSA %s
3 ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-NOHSA -check-prefix=FUNC -check-prefix=GCNX3-NOHSA %s
5 ; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=R600 -check-prefix=FUNC %s
6 ; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=cayman < %s | FileCheck -check-prefix=R600 -check-prefix=FUNC %s
8 ; FUNC-LABEL: {{^}}global_load_f32:
9 ; GCN-NOHSA: buffer_load_dword v{{[0-9]+}}
10 ; GCN-HSA: flat_load_dword
12 ; R600: VTX_READ_32 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0
13 define amdgpu_kernel void @global_load_f32(float addrspace(1)* %out, float addrspace(1)* %in) #0 {
15 %tmp0 = load float, float addrspace(1)* %in
16 store float %tmp0, float addrspace(1)* %out
20 ; FUNC-LABEL: {{^}}global_load_v2f32:
21 ; GCN-NOHSA: buffer_load_dwordx2
22 ; GCN-HSA: flat_load_dwordx2
25 define amdgpu_kernel void @global_load_v2f32(<2 x float> addrspace(1)* %out, <2 x float> addrspace(1)* %in) #0 {
27 %tmp0 = load <2 x float>, <2 x float> addrspace(1)* %in
28 store <2 x float> %tmp0, <2 x float> addrspace(1)* %out
32 ; FUNC-LABEL: {{^}}global_load_v3f32:
33 ; SI-NOHSA: buffer_load_dwordx4
34 ; GCNX3-NOHSA: buffer_load_dwordx3
35 ; GCNX3-HSA: flat_load_dwordx3
38 define amdgpu_kernel void @global_load_v3f32(<3 x float> addrspace(1)* %out, <3 x float> addrspace(1)* %in) #0 {
40 %tmp0 = load <3 x float>, <3 x float> addrspace(1)* %in
41 store <3 x float> %tmp0, <3 x float> addrspace(1)* %out
45 ; FUNC-LABEL: {{^}}global_load_v4f32:
46 ; GCN-NOHSA: buffer_load_dwordx4
47 ; GCN-HSA: flat_load_dwordx4
50 define amdgpu_kernel void @global_load_v4f32(<4 x float> addrspace(1)* %out, <4 x float> addrspace(1)* %in) #0 {
52 %tmp0 = load <4 x float>, <4 x float> addrspace(1)* %in
53 store <4 x float> %tmp0, <4 x float> addrspace(1)* %out
57 ; FUNC-LABEL: {{^}}global_load_v8f32:
58 ; GCN-NOHSA: buffer_load_dwordx4
59 ; GCN-NOHSA: buffer_load_dwordx4
60 ; GCN-HSA: flat_load_dwordx4
61 ; GCN-HSA: flat_load_dwordx4
65 define amdgpu_kernel void @global_load_v8f32(<8 x float> addrspace(1)* %out, <8 x float> addrspace(1)* %in) #0 {
67 %tmp0 = load <8 x float>, <8 x float> addrspace(1)* %in
68 store <8 x float> %tmp0, <8 x float> addrspace(1)* %out
72 ; FUNC-LABEL: {{^}}global_load_v16f32:
73 ; GCN-NOHSA: buffer_load_dwordx4
74 ; GCN-NOHSA: buffer_load_dwordx4
75 ; GCN-NOHSA: buffer_load_dwordx4
76 ; GCN-NOHSA: buffer_load_dwordx4
78 ; GCN-HSA: flat_load_dwordx4
79 ; GCN-HSA: flat_load_dwordx4
80 ; GCN-HSA: flat_load_dwordx4
81 ; GCN-HSA: flat_load_dwordx4
87 define amdgpu_kernel void @global_load_v16f32(<16 x float> addrspace(1)* %out, <16 x float> addrspace(1)* %in) #0 {
89 %tmp0 = load <16 x float>, <16 x float> addrspace(1)* %in
90 store <16 x float> %tmp0, <16 x float> addrspace(1)* %out
94 attributes #0 = { nounwind }