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
48 lines
1.8 KiB
LLVM
48 lines
1.8 KiB
LLVM
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -passes=amdgpu-lower-module-lds -amdgpu-enable-object-linking < %s | FileCheck %s
|
|
|
|
source_filename = "source_a.hip"
|
|
|
|
; Internal-linkage LDS variables used by multiple kernels must be packed into a
|
|
; per-module struct with a module-unique name, rather than promoted individually
|
|
; to external linkage, to avoid cross-TU name collisions.
|
|
|
|
@a = internal addrspace(3) global [32 x i32] poison, align 16
|
|
@b = internal addrspace(3) global [16 x float] poison, align 4
|
|
|
|
; Per-module struct containing both internal multi-user variables.
|
|
; CHECK: @[[INTERN:__amdgpu_lds.__internal\.[a-f0-9]+]] = external {{(dso_local )?}}addrspace(3) global %[[INTERN]].t, align 16
|
|
|
|
; Original internal-linkage variables should be removed.
|
|
; CHECK-NOT: @a =
|
|
; CHECK-NOT: @b =
|
|
|
|
; Both kernels reference the struct.
|
|
; CHECK-LABEL: define amdgpu_kernel void @kernel1()
|
|
; CHECK: @[[INTERN]]
|
|
; CHECK: @[[INTERN]]
|
|
|
|
; CHECK-LABEL: define amdgpu_kernel void @kernel2()
|
|
; CHECK: @[[INTERN]]
|
|
; CHECK: @[[INTERN]]
|
|
|
|
; Metadata: struct entries for both kernels.
|
|
; CHECK: !amdgpu.lds.uses = !{{{![0-9]+, ![0-9]+}}}
|
|
; CHECK-DAG: !{ptr @kernel1, ptr addrspace(3) @[[INTERN]]}
|
|
; CHECK-DAG: !{ptr @kernel2, ptr addrspace(3) @[[INTERN]]}
|
|
|
|
define amdgpu_kernel void @kernel1() {
|
|
%gep_a = getelementptr [32 x i32], ptr addrspace(3) @a, i32 0, i32 0
|
|
store i32 1, ptr addrspace(3) %gep_a
|
|
%gep_b = getelementptr [16 x float], ptr addrspace(3) @b, i32 0, i32 0
|
|
store float 2.0, ptr addrspace(3) %gep_b
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @kernel2() {
|
|
%gep_a = getelementptr [32 x i32], ptr addrspace(3) @a, i32 0, i32 0
|
|
store i32 3, ptr addrspace(3) %gep_a
|
|
%gep_b = getelementptr [16 x float], ptr addrspace(3) @b, i32 0, i32 0
|
|
store float 4.0, ptr addrspace(3) %gep_b
|
|
ret void
|
|
}
|