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
52 lines
2.0 KiB
LLVM
52 lines
2.0 KiB
LLVM
; RUN: llc -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=None < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=None < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=None < %s | FileCheck -check-prefixes=GCN,GFX9,FUNC %s
|
|
; RUN: llc -mtriple=r600 -mcpu=redwood -amdgpu-atomic-optimizer-strategy=None < %s | FileCheck -check-prefixes=R600,FUNC %s
|
|
|
|
; FUNC-LABEL: {{^}}atomic_add_local:
|
|
; SICIVI: s_mov_b32 m0
|
|
; GFX9-NOT: m0
|
|
; R600: LDS_ADD *
|
|
; GCN: ds_add_u32
|
|
define amdgpu_kernel void @atomic_add_local(ptr addrspace(3) %local) {
|
|
%unused = atomicrmw volatile add ptr addrspace(3) %local, i32 5 seq_cst
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}atomic_add_local_const_offset:
|
|
; SICIVI: s_mov_b32 m0
|
|
; GFX9-NOT: m0
|
|
|
|
; R600: LDS_ADD *
|
|
; GCN: ds_add_u32 v{{[0-9]+}}, v{{[0-9]+}} offset:16
|
|
define amdgpu_kernel void @atomic_add_local_const_offset(ptr addrspace(3) %local) {
|
|
%gep = getelementptr i32, ptr addrspace(3) %local, i32 4
|
|
%val = atomicrmw volatile add ptr addrspace(3) %gep, i32 5 seq_cst
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}atomic_add_ret_local:
|
|
; SICIVI: s_mov_b32 m0
|
|
; GFX9-NOT: m0
|
|
|
|
; R600: LDS_ADD_RET *
|
|
; GCN: ds_add_rtn_u32
|
|
define amdgpu_kernel void @atomic_add_ret_local(ptr addrspace(1) %out, ptr addrspace(3) %local) {
|
|
%val = atomicrmw volatile add ptr addrspace(3) %local, i32 5 seq_cst
|
|
store i32 %val, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}atomic_add_ret_local_const_offset:
|
|
; SICIVI: s_mov_b32 m0
|
|
; GFX9-NOT: m0
|
|
|
|
; R600: LDS_ADD_RET *
|
|
; GCN: ds_add_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} offset:20
|
|
define amdgpu_kernel void @atomic_add_ret_local_const_offset(ptr addrspace(1) %out, ptr addrspace(3) %local) {
|
|
%gep = getelementptr i32, ptr addrspace(3) %local, i32 5
|
|
%val = atomicrmw volatile add ptr addrspace(3) %gep, i32 5 seq_cst
|
|
store i32 %val, ptr addrspace(1) %out
|
|
ret void
|
|
}
|