1 ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-NOHSA -check-prefix=FUNC %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 %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 %s 4 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 7 8 ; FUNC-LABEL: {{^}}global_load_f32: 9 ; GCN-NOHSA: buffer_load_dword v{{[0-9]+}} 10 ; GCN-HSA: flat_load_dword 11 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 { 14 entry: 15 %tmp0 = load float, float addrspace(1)* %in 16 store float %tmp0, float addrspace(1)* %out 17 ret void 18 } 19 20 ; FUNC-LABEL: {{^}}global_load_v2f32: 21 ; GCN-NOHSA: buffer_load_dwordx2 22 ; GCN-HSA: flat_load_dwordx2 23 24 ; R600: VTX_READ_64 25 define amdgpu_kernel void @global_load_v2f32(<2 x float> addrspace(1)* %out, <2 x float> addrspace(1)* %in) #0 { 26 entry: 27 %tmp0 = load <2 x float>, <2 x float> addrspace(1)* %in 28 store <2 x float> %tmp0, <2 x float> addrspace(1)* %out 29 ret void 30 } 31 32 ; FUNC-LABEL: {{^}}global_load_v3f32: 33 ; GCN-NOHSA: buffer_load_dwordx4 34 ; GCN-HSA: flat_load_dwordx4 35 36 ; R600: VTX_READ_128 37 define amdgpu_kernel void @global_load_v3f32(<3 x float> addrspace(1)* %out, <3 x float> addrspace(1)* %in) #0 { 38 entry: 39 %tmp0 = load <3 x float>, <3 x float> addrspace(1)* %in 40 store <3 x float> %tmp0, <3 x float> addrspace(1)* %out 41 ret void 42 } 43 44 ; FUNC-LABEL: {{^}}global_load_v4f32: 45 ; GCN-NOHSA: buffer_load_dwordx4 46 ; GCN-HSA: flat_load_dwordx4 47 48 ; R600: VTX_READ_128 49 define amdgpu_kernel void @global_load_v4f32(<4 x float> addrspace(1)* %out, <4 x float> addrspace(1)* %in) #0 { 50 entry: 51 %tmp0 = load <4 x float>, <4 x float> addrspace(1)* %in 52 store <4 x float> %tmp0, <4 x float> addrspace(1)* %out 53 ret void 54 } 55 56 ; FUNC-LABEL: {{^}}global_load_v8f32: 57 ; GCN-NOHSA: buffer_load_dwordx4 58 ; GCN-NOHSA: buffer_load_dwordx4 59 ; GCN-HSA: flat_load_dwordx4 60 ; GCN-HSA: flat_load_dwordx4 61 62 ; R600: VTX_READ_128 63 ; R600: VTX_READ_128 64 define amdgpu_kernel void @global_load_v8f32(<8 x float> addrspace(1)* %out, <8 x float> addrspace(1)* %in) #0 { 65 entry: 66 %tmp0 = load <8 x float>, <8 x float> addrspace(1)* %in 67 store <8 x float> %tmp0, <8 x float> addrspace(1)* %out 68 ret void 69 } 70 71 ; FUNC-LABEL: {{^}}global_load_v16f32: 72 ; GCN-NOHSA: buffer_load_dwordx4 73 ; GCN-NOHSA: buffer_load_dwordx4 74 ; GCN-NOHSA: buffer_load_dwordx4 75 ; GCN-NOHSA: buffer_load_dwordx4 76 77 ; GCN-HSA: flat_load_dwordx4 78 ; GCN-HSA: flat_load_dwordx4 79 ; GCN-HSA: flat_load_dwordx4 80 ; GCN-HSA: flat_load_dwordx4 81 82 ; R600: VTX_READ_128 83 ; R600: VTX_READ_128 84 ; R600: VTX_READ_128 85 ; R600: VTX_READ_128 86 define amdgpu_kernel void @global_load_v16f32(<16 x float> addrspace(1)* %out, <16 x float> addrspace(1)* %in) #0 { 87 entry: 88 %tmp0 = load <16 x float>, <16 x float> addrspace(1)* %in 89 store <16 x float> %tmp0, <16 x float> addrspace(1)* %out 90 ret void 91 } 92 93 attributes #0 = { nounwind } 94
