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
42 lines
1.6 KiB
LLVM
42 lines
1.6 KiB
LLVM
; RUN: opt < %s -S -nvptx-lower-alloca -infer-address-spaces | FileCheck %s
|
|
; RUN: opt < %s -S -nvptx-lower-alloca | FileCheck %s --check-prefix LOWERALLOCAONLY
|
|
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_35 | FileCheck %s --check-prefix PTX
|
|
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_35 | %ptxas-verify %}
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"
|
|
target triple = "nvptx64-unknown-unknown"
|
|
|
|
define ptx_kernel void @kernel() {
|
|
; LABEL: @lower_alloca
|
|
; PTX-LABEL: .visible .entry kernel(
|
|
%A = alloca i32
|
|
; CHECK: addrspacecast ptr %A to ptr addrspace(5)
|
|
; CHECK: store i32 0, ptr addrspace(5) {{%.+}}
|
|
; LOWERALLOCAONLY: [[V1:%.*]] = addrspacecast ptr %A to ptr addrspace(5)
|
|
; LOWERALLOCAONLY: [[V2:%.*]] = addrspacecast ptr addrspace(5) [[V1]] to ptr
|
|
; LOWERALLOCAONLY: store i32 0, ptr [[V2]], align 4
|
|
; PTX: st.local.b32 [{{%rd[0-9]+}}], 0
|
|
store i32 0, ptr %A
|
|
call void @callee(ptr %A)
|
|
ret void
|
|
}
|
|
|
|
define void @alloca_in_explicit_local_as() {
|
|
; LABEL: @lower_alloca_addrspace5
|
|
; PTX-LABEL: .visible .func alloca_in_explicit_local_as(
|
|
%A = alloca i32, addrspace(5)
|
|
; CHECK: store i32 0, ptr addrspace(5) {{%.+}}
|
|
; PTX: st.local.b32 [%SP], 0
|
|
; LOWERALLOCAONLY: [[V1:%.*]] = addrspacecast ptr addrspace(5) %A to ptr
|
|
; LOWERALLOCAONLY: store i32 0, ptr [[V1]], align 4
|
|
store i32 0, ptr addrspace(5) %A
|
|
call void @callee(ptr addrspace(5) %A)
|
|
ret void
|
|
}
|
|
|
|
declare void @callee(ptr)
|
|
declare void @callee_addrspace5(ptr addrspace(5))
|
|
|
|
!nvvm.annotations = !{!1}
|
|
!1 = !{ptr @alloca_in_explicit_local_as, !"alloca_in_explicit_local_as", i32 1}
|