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
62 lines
2.8 KiB
LLVM
62 lines
2.8 KiB
LLVM
; RUN: opt < %s -passes=amdgpu-sw-lower-lds -S -amdgpu-asan-instrument-lds=false -mtriple=amdgcn-amd-amdhsa | FileCheck %s
|
|
|
|
; Test that the sw-lower-lds pass moves constant-size allocas from the original
|
|
; entry block to the new entry block (WId), so they remain static allocas.
|
|
|
|
@lds = internal addrspace(3) global [64 x i32] poison, align 4
|
|
|
|
; Allocas clustered at the top of the entry block (common case).
|
|
define amdgpu_kernel void @kernel_allocas_at_top(i32 %n) sanitize_address {
|
|
; CHECK-LABEL: define amdgpu_kernel void @kernel_allocas_at_top(
|
|
; CHECK-SAME: i32 [[N:%.*]]) #[[ATTR0:[0-9]+]] {
|
|
; CHECK-NEXT: [[WID:.*]]:
|
|
; CHECK-NEXT: [[A:%.*]] = alloca i32, align 4, addrspace(5)
|
|
; CHECK-NEXT: [[B:%.*]] = alloca i32, align 4, addrspace(5)
|
|
; CHECK-NEXT: [[TMP0:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
|
|
; CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.amdgcn.workitem.id.y()
|
|
; CHECK-NEXT: [[TMP2:%.*]] = call i32 @llvm.amdgcn.workitem.id.z()
|
|
; CHECK-NEXT: [[TMP3:%.*]] = or i32 [[TMP0]], [[TMP1]]
|
|
; CHECK-NEXT: [[TMP4:%.*]] = or i32 [[TMP3]], [[TMP2]]
|
|
; CHECK-NEXT: [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 0
|
|
; CHECK-NEXT: br i1 [[TMP5]], label %[[MALLOC:.*]], label %[[BB18:.*]]
|
|
; CHECK: [[BB18]]:
|
|
; CHECK: store i32 [[N]], ptr addrspace(5) [[A]], align 4
|
|
; CHECK-NEXT: store i32 [[N]], ptr addrspace(5) [[B]], align 4
|
|
;
|
|
%a = alloca i32, align 4, addrspace(5)
|
|
%b = alloca i32, align 4, addrspace(5)
|
|
store i32 %n, ptr addrspace(5) %a, align 4
|
|
store i32 %n, ptr addrspace(5) %b, align 4
|
|
store i32 %n, ptr addrspace(3) @lds, align 4
|
|
ret void
|
|
}
|
|
|
|
; Allocas interleaved with non-alloca instructions.
|
|
define amdgpu_kernel void @kernel_allocas_scattered(i32 %n) sanitize_address {
|
|
; CHECK-LABEL: define amdgpu_kernel void @kernel_allocas_scattered(
|
|
; CHECK-SAME: i32 [[N:%.*]]) #[[ATTR0]] {
|
|
; CHECK-NEXT: [[WID:.*]]:
|
|
; CHECK-NEXT: [[A:%.*]] = alloca i32, align 4, addrspace(5)
|
|
; CHECK-NEXT: [[B:%.*]] = alloca i32, align 4, addrspace(5)
|
|
; CHECK-NEXT: [[TMP0:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
|
|
; CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.amdgcn.workitem.id.y()
|
|
; CHECK-NEXT: [[TMP2:%.*]] = call i32 @llvm.amdgcn.workitem.id.z()
|
|
; CHECK-NEXT: [[TMP3:%.*]] = or i32 [[TMP0]], [[TMP1]]
|
|
; CHECK-NEXT: [[TMP4:%.*]] = or i32 [[TMP3]], [[TMP2]]
|
|
; CHECK-NEXT: [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 0
|
|
; CHECK-NEXT: br i1 [[TMP5]], label %[[MALLOC:.*]], label %[[BB18:.*]]
|
|
; CHECK: [[BB18]]:
|
|
; CHECK: store i32 [[N]], ptr addrspace(5) [[A]], align 4
|
|
; CHECK-NEXT: store i32 [[N]], ptr addrspace(5) [[B]], align 4
|
|
;
|
|
%a = alloca i32, align 4, addrspace(5)
|
|
store i32 %n, ptr addrspace(5) %a, align 4
|
|
%b = alloca i32, align 4, addrspace(5)
|
|
store i32 %n, ptr addrspace(5) %b, align 4
|
|
store i32 %n, ptr addrspace(3) @lds, align 4
|
|
ret void
|
|
}
|
|
|
|
!llvm.module.flags = !{!0}
|
|
!0 = !{i32 4, !"nosanitize_address", i32 1}
|