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
39 lines
1.8 KiB
LLVM
39 lines
1.8 KiB
LLVM
; RUN: llc -mtriple=amdgcn < %s | FileCheck --check-prefixes=GCN,GCN-PROMOTE %s
|
|
; RUN: llc -mattr=-flat-for-global -mtriple=amdgcn--amdhsa -mcpu=kaveri < %s | FileCheck --check-prefixes=GCN,GCN-PROMOTE %s
|
|
; RUN: llc -disable-promote-alloca-to-vector -disable-promote-alloca-to-lds -mtriple=amdgcn < %s | FileCheck --check-prefixes=GCN,GCN-ALLOCA %s
|
|
; RUN: llc -disable-promote-alloca-to-vector -disable-promote-alloca-to-lds -mattr=-flat-for-global -mtriple=amdgcn-amdhsa -mcpu=kaveri < %s | FileCheck --check-prefixes=GCN,GCN-ALLOCA %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global < %s | FileCheck --check-prefixes=GCN,GCN-PROMOTE %s
|
|
; RUN: llc -disable-promote-alloca-to-vector -disable-promote-alloca-to-lds -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global < %s | FileCheck --check-prefixes=GCN,GCN-ALLOCA %s
|
|
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x() nounwind readnone
|
|
|
|
|
|
; Make sure we don't overwrite workitem information with private memory
|
|
|
|
; GCN-LABEL: {{^}}work_item_info:
|
|
; GCN-NOT: v0
|
|
; GCN: s_load_dword [[IN:s[0-9]+]]
|
|
; GCN-NOT: v0
|
|
|
|
; GCN-ALLOCA: v_add_{{[iu]}}32_e32 [[RESULT:v[0-9]+]], vcc, v{{[0-9]+}}, v0
|
|
|
|
; GCN-PROMOTE: s_cmp_eq_u32 [[IN]], 1
|
|
; GCN-PROMOTE-NEXT: s_cselect_b32 [[SCC:s[0-9]+]], 1, 0
|
|
; GCN-PROMOTE-NEXT: v_add_{{[iu]}}32_e32 [[RESULT:v[0-9]+]], vcc, [[SCC]], v0
|
|
|
|
; GCN: buffer_store_dword [[RESULT]]
|
|
define amdgpu_kernel void @work_item_info(ptr addrspace(1) %out, i32 %in) {
|
|
entry:
|
|
%0 = alloca [2 x i32], addrspace(5)
|
|
%1 = getelementptr [2 x i32], ptr addrspace(5) %0, i32 0, i32 1
|
|
store i32 0, ptr addrspace(5) %0
|
|
store i32 1, ptr addrspace(5) %1
|
|
%2 = getelementptr [2 x i32], ptr addrspace(5) %0, i32 0, i32 %in
|
|
%3 = load i32, ptr addrspace(5) %2
|
|
%4 = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%5 = add i32 %3, %4
|
|
store i32 %5, ptr addrspace(1) %out
|
|
ret void
|
|
}
|