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
71 lines
1.7 KiB
LLVM
71 lines
1.7 KiB
LLVM
; RUN: llc < %s -mtriple=nvptx -mcpu=sm_20 | FileCheck %s --check-prefix=PTX32
|
|
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_20 | FileCheck %s --check-prefix=PTX64
|
|
; RUN: %if ptxas-ptr32 %{ llc < %s -mtriple=nvptx -mcpu=sm_20 | %ptxas-verify %}
|
|
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_20 | %ptxas-verify %}
|
|
|
|
;; i8
|
|
|
|
define void @st_global_i8(ptr addrspace(0) %ptr, i8 %a) {
|
|
; PTX32: st.b8 [%r{{[0-9]+}}], %rs{{[0-9]+}}
|
|
; PTX32: ret
|
|
; PTX64: st.b8 [%rd{{[0-9]+}}], %rs{{[0-9]+}}
|
|
; PTX64: ret
|
|
store i8 %a, ptr addrspace(0) %ptr
|
|
ret void
|
|
}
|
|
|
|
;; i16
|
|
|
|
define void @st_global_i16(ptr addrspace(0) %ptr, i16 %a) {
|
|
; PTX32: st.b16 [%r{{[0-9]+}}], %rs{{[0-9]+}}
|
|
; PTX32: ret
|
|
; PTX64: st.b16 [%rd{{[0-9]+}}], %rs{{[0-9]+}}
|
|
; PTX64: ret
|
|
store i16 %a, ptr addrspace(0) %ptr
|
|
ret void
|
|
}
|
|
|
|
;; i32
|
|
|
|
define void @st_global_i32(ptr addrspace(0) %ptr, i32 %a) {
|
|
; PTX32: st.b32 [%r{{[0-9]+}}], %r{{[0-9]+}}
|
|
; PTX32: ret
|
|
; PTX64: st.b32 [%rd{{[0-9]+}}], %r{{[0-9]+}}
|
|
; PTX64: ret
|
|
store i32 %a, ptr addrspace(0) %ptr
|
|
ret void
|
|
}
|
|
|
|
;; i64
|
|
|
|
define void @st_global_i64(ptr addrspace(0) %ptr, i64 %a) {
|
|
; PTX32: st.b64 [%r{{[0-9]+}}], %rd{{[0-9]+}}
|
|
; PTX32: ret
|
|
; PTX64: st.b64 [%rd{{[0-9]+}}], %rd{{[0-9]+}}
|
|
; PTX64: ret
|
|
store i64 %a, ptr addrspace(0) %ptr
|
|
ret void
|
|
}
|
|
|
|
;; f32
|
|
|
|
define void @st_global_f32(ptr addrspace(0) %ptr, float %a) {
|
|
; PTX32: st.b32 [%r{{[0-9]+}}], %r{{[0-9]+}}
|
|
; PTX32: ret
|
|
; PTX64: st.b32 [%rd{{[0-9]+}}], %r{{[0-9]+}}
|
|
; PTX64: ret
|
|
store float %a, ptr addrspace(0) %ptr
|
|
ret void
|
|
}
|
|
|
|
;; f64
|
|
|
|
define void @st_global_f64(ptr addrspace(0) %ptr, double %a) {
|
|
; PTX32: st.b64 [%r{{[0-9]+}}], %rd{{[0-9]+}}
|
|
; PTX32: ret
|
|
; PTX64: st.b64 [%rd{{[0-9]+}}], %rd{{[0-9]+}}
|
|
; PTX64: ret
|
|
store double %a, ptr addrspace(0) %ptr
|
|
ret void
|
|
}
|