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
76 lines
4.8 KiB
LLVM
76 lines
4.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -passes=amdgpu-promote-alloca %s -o - | FileCheck %s
|
|
|
|
declare ptr @llvm.invariant.start.p5(i64, ptr addrspace(5) nocapture)
|
|
declare void @llvm.invariant.end.p5(ptr, i64, ptr addrspace(5) nocapture)
|
|
declare ptr addrspace(5) @llvm.launder.invariant.group.p5(ptr addrspace(5))
|
|
declare ptr addrspace(5) @llvm.strip.invariant.group.p5(ptr addrspace(5))
|
|
|
|
define amdgpu_kernel void @use_invariant_start_and_end() {
|
|
; CHECK-LABEL: define amdgpu_kernel void @use_invariant_start_and_end() {
|
|
; CHECK-NEXT: [[BB:.*:]]
|
|
; CHECK-NEXT: [[TMP0:%.*]] = call noalias nonnull dereferenceable(64) ptr addrspace(4) @llvm.amdgcn.dispatch.ptr()
|
|
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i32, ptr addrspace(4) [[TMP0]], i64 1
|
|
; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr addrspace(4) [[TMP1]], align 4, !invariant.load [[META0:![0-9]+]]
|
|
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds i32, ptr addrspace(4) [[TMP0]], i64 2
|
|
; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(4) [[TMP3]], align 4, !range [[RNG1:![0-9]+]], !invariant.load [[META0]]
|
|
; CHECK-NEXT: [[TMP5:%.*]] = lshr i32 [[TMP2]], 16
|
|
; CHECK-NEXT: [[TMP6:%.*]] = call range(i32 0, 1024) i32 @llvm.amdgcn.workitem.id.x()
|
|
; CHECK-NEXT: [[TMP7:%.*]] = call range(i32 0, 1024) i32 @llvm.amdgcn.workitem.id.y()
|
|
; CHECK-NEXT: [[TMP8:%.*]] = call range(i32 0, 1024) i32 @llvm.amdgcn.workitem.id.z()
|
|
; CHECK-NEXT: [[TMP9:%.*]] = mul nuw nsw i32 [[TMP5]], [[TMP4]]
|
|
; CHECK-NEXT: [[TMP10:%.*]] = mul i32 [[TMP9]], [[TMP6]]
|
|
; CHECK-NEXT: [[TMP11:%.*]] = mul nuw nsw i32 [[TMP7]], [[TMP4]]
|
|
; CHECK-NEXT: [[TMP12:%.*]] = add i32 [[TMP10]], [[TMP11]]
|
|
; CHECK-NEXT: [[TMP13:%.*]] = add i32 [[TMP12]], [[TMP8]]
|
|
; CHECK-NEXT: [[TMP14:%.*]] = getelementptr inbounds [1024 x i32], ptr addrspace(3) @use_invariant_start_and_end.alloca, i32 0, i32 [[TMP13]]
|
|
; CHECK-NEXT: [[INVARIANT1:%.*]] = call ptr @llvm.invariant.start.p3(i64 0, ptr addrspace(3) [[TMP14]])
|
|
; CHECK-NEXT: store <2 x i1> zeroinitializer, ptr [[INVARIANT1]], align 1
|
|
; CHECK-NEXT: call void @llvm.invariant.end.p3(ptr [[INVARIANT1]], i64 0, ptr addrspace(3) [[TMP14]])
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
bb:
|
|
%alloca = alloca i32, align 4, addrspace(5)
|
|
%invariant = call ptr @llvm.invariant.start.p5(i64 0, ptr addrspace(5) %alloca)
|
|
store <2 x i1> zeroinitializer, ptr %invariant, align 1
|
|
call void @llvm.invariant.end.p5(ptr %invariant, i64 0, ptr addrspace(5) %alloca)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @use_invariant_group_and_strip() {
|
|
; CHECK-LABEL: define amdgpu_kernel void @use_invariant_group_and_strip() {
|
|
; CHECK-NEXT: [[BB:.*:]]
|
|
; CHECK-NEXT: [[TMP0:%.*]] = call noalias nonnull dereferenceable(64) ptr addrspace(4) @llvm.amdgcn.dispatch.ptr()
|
|
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i32, ptr addrspace(4) [[TMP0]], i64 1
|
|
; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr addrspace(4) [[TMP1]], align 4, !invariant.load [[META0]]
|
|
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds i32, ptr addrspace(4) [[TMP0]], i64 2
|
|
; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(4) [[TMP3]], align 4, !range [[RNG1]], !invariant.load [[META0]]
|
|
; CHECK-NEXT: [[TMP5:%.*]] = lshr i32 [[TMP2]], 16
|
|
; CHECK-NEXT: [[TMP6:%.*]] = call range(i32 0, 1024) i32 @llvm.amdgcn.workitem.id.x()
|
|
; CHECK-NEXT: [[TMP7:%.*]] = call range(i32 0, 1024) i32 @llvm.amdgcn.workitem.id.y()
|
|
; CHECK-NEXT: [[TMP8:%.*]] = call range(i32 0, 1024) i32 @llvm.amdgcn.workitem.id.z()
|
|
; CHECK-NEXT: [[TMP9:%.*]] = mul nuw nsw i32 [[TMP5]], [[TMP4]]
|
|
; CHECK-NEXT: [[TMP10:%.*]] = mul i32 [[TMP9]], [[TMP6]]
|
|
; CHECK-NEXT: [[TMP11:%.*]] = mul nuw nsw i32 [[TMP7]], [[TMP4]]
|
|
; CHECK-NEXT: [[TMP12:%.*]] = add i32 [[TMP10]], [[TMP11]]
|
|
; CHECK-NEXT: [[TMP13:%.*]] = add i32 [[TMP12]], [[TMP8]]
|
|
; CHECK-NEXT: [[TMP14:%.*]] = getelementptr inbounds [1024 x i32], ptr addrspace(3) @use_invariant_group_and_strip.alloca, i32 0, i32 [[TMP13]]
|
|
; CHECK-NEXT: [[INVARIANT2:%.*]] = call ptr addrspace(3) @llvm.launder.invariant.group.p3(ptr addrspace(3) [[TMP14]])
|
|
; CHECK-NEXT: store <2 x i1> zeroinitializer, ptr addrspace(3) [[INVARIANT2]], align 1
|
|
; CHECK-NEXT: [[STRIP1:%.*]] = call ptr addrspace(3) @llvm.strip.invariant.group.p3(ptr addrspace(3) [[TMP14]])
|
|
; CHECK-NEXT: store <2 x i1> zeroinitializer, ptr addrspace(3) [[STRIP1]], align 1
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
bb:
|
|
%alloca = alloca i32, align 4, addrspace(5)
|
|
%invariant = call ptr addrspace(5) @llvm.launder.invariant.group.p5(ptr addrspace(5) %alloca)
|
|
store <2 x i1> zeroinitializer, ptr addrspace(5) %invariant, align 1
|
|
%strip = call ptr addrspace(5) @llvm.strip.invariant.group.p5(ptr addrspace(5) %alloca)
|
|
store <2 x i1> zeroinitializer, ptr addrspace(5) %strip, align 1
|
|
ret void
|
|
}
|
|
;.
|
|
; CHECK: [[META0]] = !{}
|
|
; CHECK: [[RNG1]] = !{i32 0, i32 1025}
|
|
;.
|