derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
58 lines
2.2 KiB
LLVM
58 lines
2.2 KiB
LLVM
; RUN: llc -mtriple=amdgcn < %s | FileCheck -check-prefix=FUNC %s
|
|
; RUN: llc -mtriple=amdgcn-amdhsa -mcpu=kaveri < %s | FileCheck -check-prefix=FUNC %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global < %s | FileCheck -check-prefix=FUNC %s
|
|
; RUN: llc -mtriple=r600 -mcpu=redwood < %s | FileCheck --check-prefixes=EG,FUNC %s
|
|
|
|
; FIXME: This seems to not ever actually become an extload
|
|
; FUNC-LABEL: {{^}}global_anyext_load_i8:
|
|
; GCN: buffer_load_dword v{{[0-9]+}}
|
|
; GCN: buffer_store_dword v{{[0-9]+}}
|
|
|
|
; EG: MEM_RAT_CACHELESS STORE_RAW [[VAL:T[0-9]+.[XYZW]]],
|
|
; EG: VTX_READ_32 [[VAL]]
|
|
define amdgpu_kernel void @global_anyext_load_i8(ptr addrspace(1) nocapture noalias %out, ptr addrspace(1) nocapture noalias %src) nounwind {
|
|
%load = load i32, ptr addrspace(1) %src
|
|
%x = bitcast i32 %load to <4 x i8>
|
|
store <4 x i8> %x, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}global_anyext_load_i16:
|
|
; GCN: buffer_load_dword v{{[0-9]+}}
|
|
; GCN: buffer_store_dword v{{[0-9]+}}
|
|
|
|
; EG: MEM_RAT_CACHELESS STORE_RAW [[VAL:T[0-9]+.[XYZW]]],
|
|
; EG: VTX_READ_32 [[VAL]]
|
|
define amdgpu_kernel void @global_anyext_load_i16(ptr addrspace(1) nocapture noalias %out, ptr addrspace(1) nocapture noalias %src) nounwind {
|
|
%load = load i32, ptr addrspace(1) %src
|
|
%x = bitcast i32 %load to <2 x i16>
|
|
store <2 x i16> %x, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}local_anyext_load_i8:
|
|
; GCN: ds_read_b32 v{{[0-9]+}}
|
|
; GCN: ds_write_b32 v{{[0-9]+}}
|
|
|
|
; EG: LDS_READ_RET {{.*}}, [[VAL:T[0-9]+.[XYZW]]]
|
|
; EG: LDS_WRITE * [[VAL]]
|
|
define amdgpu_kernel void @local_anyext_load_i8(ptr addrspace(3) nocapture noalias %out, ptr addrspace(3) nocapture noalias %src) nounwind {
|
|
%load = load i32, ptr addrspace(3) %src
|
|
%x = bitcast i32 %load to <4 x i8>
|
|
store <4 x i8> %x, ptr addrspace(3) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}local_anyext_load_i16:
|
|
; GCN: ds_read_b32 v{{[0-9]+}}
|
|
; GCN: ds_write_b32 v{{[0-9]+}}
|
|
|
|
; EG: LDS_READ_RET {{.*}}, [[VAL:T[0-9]+.[XYZW]]]
|
|
; EG: LDS_WRITE * [[VAL]]
|
|
define amdgpu_kernel void @local_anyext_load_i16(ptr addrspace(3) nocapture noalias %out, ptr addrspace(3) nocapture noalias %src) nounwind {
|
|
%load = load i32, ptr addrspace(3) %src
|
|
%x = bitcast i32 %load to <2 x i16>
|
|
store <2 x i16> %x, ptr addrspace(3) %out
|
|
ret void
|
|
}
|