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
32 lines
1.2 KiB
LLVM
32 lines
1.2 KiB
LLVM
; RUN: llc < %s | FileCheck %s
|
|
; RUN: %if ptxas %{ llc < %s | %ptxas-verify %}
|
|
|
|
target triple = "nvptx64-nvidia-cuda"
|
|
|
|
; CHECK-LABEL: test1
|
|
; CHECK: ld.global.v2.b32
|
|
; CHECK: ld.global.v2.b32
|
|
; CHECK: st.global.v2.b32
|
|
; CHECK: st.global.v2.b32
|
|
define void @test1(ptr addrspace(1) noalias align 8 %in, ptr addrspace(1) noalias align 8 %out) {
|
|
%in.1 = getelementptr float, ptr addrspace(1) %in, i32 1
|
|
%in.2 = getelementptr float, ptr addrspace(1) %in, i32 2
|
|
%in.3 = getelementptr float, ptr addrspace(1) %in, i32 3
|
|
%v0 = load float, ptr addrspace(1) %in, align 8
|
|
%v1 = load float, ptr addrspace(1) %in.1, align 4
|
|
%v2 = load float, ptr addrspace(1) %in.2, align 8
|
|
%v3 = load float, ptr addrspace(1) %in.3, align 4
|
|
%sum0 = fadd float %v0, %v1
|
|
%sum1 = fadd float %v1, %v2
|
|
%sum2 = fadd float %v3, %v1
|
|
%sum3 = fadd float %v2, %v3
|
|
%out.1 = getelementptr float, ptr addrspace(1) %out, i32 1
|
|
%out.2 = getelementptr float, ptr addrspace(1) %out, i32 2
|
|
%out.3 = getelementptr float, ptr addrspace(1) %out, i32 3
|
|
store float %sum0, ptr addrspace(1) %out, align 8
|
|
store float %sum1, ptr addrspace(1) %out.1, align 4
|
|
store float %sum2, ptr addrspace(1) %out.2, align 8
|
|
store float %sum3, ptr addrspace(1) %out.3, align 4
|
|
ret void
|
|
}
|