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
28 lines
1.4 KiB
LLVM
28 lines
1.4 KiB
LLVM
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -passes=amdgpu-promote-alloca -disable-promote-alloca-to-vector < %s | FileCheck %s
|
|
|
|
; This kernel starts with the amdgpu-no-workitem-id-* attributes, but
|
|
; need to be removed when these intrinsic uses are introduced.
|
|
|
|
; CHECK-LABEL: define amdgpu_kernel void @promote_to_lds(ptr addrspace(1) %out, i32 %in) #0 {
|
|
; CHECK: call noalias nonnull dereferenceable(64) ptr addrspace(4) @llvm.amdgcn.dispatch.ptr()
|
|
; CHECK: call range(i32 0, 256) i32 @llvm.amdgcn.workitem.id.x()
|
|
; CHECK: call range(i32 0, 256) i32 @llvm.amdgcn.workitem.id.y()
|
|
; CHECK: call range(i32 0, 256) i32 @llvm.amdgcn.workitem.id.z()
|
|
define amdgpu_kernel void @promote_to_lds(ptr addrspace(1) %out, i32 %in) #0 {
|
|
entry:
|
|
%tmp = alloca [2 x i32], addrspace(5)
|
|
%tmp2 = getelementptr inbounds [2 x i32], ptr addrspace(5) %tmp, i32 0, i32 1
|
|
store i32 0, ptr addrspace(5) %tmp
|
|
store i32 1, ptr addrspace(5) %tmp2
|
|
%tmp3 = getelementptr inbounds [2 x i32], ptr addrspace(5) %tmp, i32 0, i32 %in
|
|
%tmp4 = load i32, ptr addrspace(5) %tmp3
|
|
%tmp5 = load volatile i32, ptr addrspace(1) poison
|
|
%tmp6 = add i32 %tmp4, %tmp5
|
|
store i32 %tmp6, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { "amdgpu-flat-work-group-size"="256,256" "amdgpu-waves-per-eu"="1,5" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-no-dispatch-ptr" }
|
|
|
|
; CHECK: attributes #0 = { "amdgpu-flat-work-group-size"="256,256" "amdgpu-waves-per-eu"="1,5" }
|