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
38 lines
1.7 KiB
LLVM
38 lines
1.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
|
|
;
|
|
; RUN: opt < %s -S -nvptx-lower-aggr-copies | FileCheck %s
|
|
|
|
target triple = "nvptx64-nvidia-cuda"
|
|
|
|
@global_data = global [256 x i8] zeroinitializer
|
|
|
|
declare void @llvm.memmove.p3.p0.i64(ptr addrspace(3) nocapture, ptr nocapture readonly, i64, i1)
|
|
declare void @llvm.memmove.p0.p3.i64(ptr nocapture, ptr addrspace(3) nocapture readonly, i64, i1)
|
|
|
|
; Test function that copies from alloca to shared memory, then from shared memory to global memory
|
|
define void @two_stage_copy() {
|
|
; CHECK-LABEL: define void @two_stage_copy() {
|
|
; CHECK-NEXT: [[ENTRY:.*:]]
|
|
; CHECK-NEXT: [[LOCAL_BUF:%.*]] = alloca [256 x i8], align 1
|
|
; CHECK-NEXT: [[SHARED_BUF:%.*]] = alloca [256 x i8], align 1, addrspace(3)
|
|
; CHECK-NEXT: [[LOCAL_PTR:%.*]] = getelementptr inbounds [256 x i8], ptr [[LOCAL_BUF]], i64 0, i64 0
|
|
; CHECK-NEXT: store i8 42, ptr [[LOCAL_PTR]], align 1
|
|
; CHECK-NEXT: call void @llvm.memmove.p3.p0.i64(ptr addrspace(3) [[SHARED_BUF]], ptr [[LOCAL_BUF]], i64 256, i1 false)
|
|
; CHECK-NEXT: call void @llvm.memmove.p0.p3.i64(ptr @global_data, ptr addrspace(3) [[SHARED_BUF]], i64 256, i1 false)
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%local_buf = alloca [256 x i8], align 1
|
|
%shared_buf = alloca [256 x i8], align 1, addrspace(3)
|
|
|
|
; Initialize local buffer
|
|
%local_ptr = getelementptr inbounds [256 x i8], ptr %local_buf, i64 0, i64 0
|
|
store i8 42, ptr %local_ptr, align 1
|
|
|
|
call void @llvm.memmove.p3.p0.i64(ptr addrspace(3) %shared_buf, ptr %local_buf, i64 256, i1 false)
|
|
|
|
call void @llvm.memmove.p0.p3.i64(ptr @global_data, ptr addrspace(3) %shared_buf, i64 256, i1 false)
|
|
|
|
ret void
|
|
}
|