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
45 lines
2.2 KiB
LLVM
45 lines
2.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: opt -mtriple amdgcn -passes=amdgpu-promote-alloca-to-vector -S < %s | FileCheck %s
|
|
|
|
; Skip promote-alloca in case of an index which is known to be out of bounds.
|
|
|
|
define amdgpu_kernel void @out_of_bounds() {
|
|
; CHECK-LABEL: define amdgpu_kernel void @out_of_bounds() {
|
|
; CHECK-NEXT: [[PTR:%.*]] = freeze <4 x float> poison
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x float> [[PTR]], <4 x float> poison, <4 x i32> <i32 poison, i32 poison, i32 2, i32 3>
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
%ptr = alloca [4 x float], align 4, addrspace(5)
|
|
%elem_ptr = getelementptr [4 x float], ptr addrspace(5) %ptr, i32 0, i32 42
|
|
call void @llvm.memcpy.p5.p5.i32(ptr addrspace(5) %ptr, ptr addrspace(5) %elem_ptr, i32 8, i1 false)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @memcpy_partially_out_of_bounds() {
|
|
; CHECK-LABEL: define amdgpu_kernel void @memcpy_partially_out_of_bounds() {
|
|
; CHECK-NEXT: [[PTR:%.*]] = freeze <3 x float> poison
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <3 x float> [[PTR]], <3 x float> poison, <3 x i32> <i32 2, i32 poison, i32 2>
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
%ptr = alloca [3 x float], align 4, addrspace(5)
|
|
%elem_ptr = getelementptr [3 x float], ptr addrspace(5) %ptr, i32 0, i32 2
|
|
call void @llvm.memcpy.p5.p5.i32(ptr addrspace(5) %ptr, ptr addrspace(5) %elem_ptr, i32 8, i1 false)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @in_bounds() {
|
|
; CHECK-LABEL: define amdgpu_kernel void @in_bounds() {
|
|
; CHECK-NEXT: [[PTR:%.*]] = freeze <4 x float> poison
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x float> [[PTR]], <4 x float> poison, <4 x i32> <i32 2, i32 3, i32 2, i32 3>
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
%ptr = alloca [4 x float], align 4, addrspace(5)
|
|
%elem_ptr = getelementptr [4 x float], ptr addrspace(5) %ptr, i32 0, i32 2
|
|
call void @llvm.memcpy.p5.p5.i32(ptr addrspace(5) %ptr, ptr addrspace(5) %elem_ptr, i32 8, i1 false)
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.memcpy.p5.p5.i32(ptr addrspace(5) writeonly captures(none), ptr addrspace(5) readonly captures(none), i32, i1 immarg) #0
|
|
|
|
attributes #0 = { nocallback nofree nounwind willreturn memory(argmem: readwrite) }
|