1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 18:54:02 +01:00
llvm-mirror/test/CodeGen/AMDGPU/load-global-i64.ll
Carl Ritson 9a5c628361 [AMDGPU] Add 224-bit vector types and link 192-bit types to MVTs
Add SReg_224, VReg_224, AReg_224, etc.
Link 224-bit types with v7i32/v7f32.
Link existing 192-bit types to newly added v3i64/v3f64/v6i32/v6f32.

Reviewed By: rampitec

Differential Revision: https://reviews.llvm.org/D104622
2021-06-24 12:41:22 +09:00

123 lines
3.9 KiB
LLVM

; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN-NOHSA,FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN-HSA,FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN-NOHSA,FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=redwood < %s | FileCheck --check-prefixes=EG,FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=cayman < %s | FileCheck --check-prefixes=EG,FUNC %s
; FUNC-LABEL: {{^}}global_load_i64:
; GCN-NOHSA: buffer_load_dwordx2 [[VAL:v\[[0-9]+:[0-9]+\]]]
; GCN-NOHSA: buffer_store_dwordx2 [[VAL]]
; GCN-HSA: flat_load_dwordx2 [[VAL:v\[[0-9]+:[0-9]+\]]]
; GCN-HSA: flat_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, [[VAL]]
; EG: VTX_READ_64
define amdgpu_kernel void @global_load_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %in) #0 {
%ld = load i64, i64 addrspace(1)* %in
store i64 %ld, i64 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_load_v2i64:
; GCN-NOHSA: buffer_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; EG: VTX_READ_128
define amdgpu_kernel void @global_load_v2i64(<2 x i64> addrspace(1)* %out, <2 x i64> addrspace(1)* %in) #0 {
entry:
%ld = load <2 x i64>, <2 x i64> addrspace(1)* %in
store <2 x i64> %ld, <2 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_load_v3i64:
; GCN-NOHSA-DAG: buffer_load_dwordx4
; GCN-NOHSA-DAG: buffer_load_dwordx2
; GCN-HSA-DAG: flat_load_dwordx4
; GCN-HSA-DAG: flat_load_dwordx2
; EG: VTX_READ_128
; EG: VTX_READ_128
define amdgpu_kernel void @global_load_v3i64(<3 x i64> addrspace(1)* %out, <3 x i64> addrspace(1)* %in) #0 {
entry:
%ld = load <3 x i64>, <3 x i64> addrspace(1)* %in
store <3 x i64> %ld, <3 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_load_v4i64:
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; EG: VTX_READ_128
; EG: VTX_READ_128
define amdgpu_kernel void @global_load_v4i64(<4 x i64> addrspace(1)* %out, <4 x i64> addrspace(1)* %in) #0 {
entry:
%ld = load <4 x i64>, <4 x i64> addrspace(1)* %in
store <4 x i64> %ld, <4 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_load_v8i64:
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; EG: VTX_READ_128
; EG: VTX_READ_128
; EG: VTX_READ_128
; EG: VTX_READ_128
define amdgpu_kernel void @global_load_v8i64(<8 x i64> addrspace(1)* %out, <8 x i64> addrspace(1)* %in) #0 {
entry:
%ld = load <8 x i64>, <8 x i64> addrspace(1)* %in
store <8 x i64> %ld, <8 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_load_v16i64:
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; EG: VTX_READ_128
; EG: VTX_READ_128
; EG: VTX_READ_128
; EG: VTX_READ_128
; EG: VTX_READ_128
; EG: VTX_READ_128
; EG: VTX_READ_128
; EG: VTX_READ_128
define amdgpu_kernel void @global_load_v16i64(<16 x i64> addrspace(1)* %out, <16 x i64> addrspace(1)* %in) #0 {
entry:
%ld = load <16 x i64>, <16 x i64> addrspace(1)* %in
store <16 x i64> %ld, <16 x i64> addrspace(1)* %out
ret void
}
attributes #0 = { nounwind }