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
44 lines
1.7 KiB
LLVM
44 lines
1.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -S -passes=memcpyopt -verify-memoryssa | FileCheck %s
|
|
target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64"
|
|
|
|
declare void @llvm.memcpy.p0.p0.i64(ptr nocapture, ptr nocapture, i64, i1) nounwind
|
|
declare void @llvm.memset.p0.i64(ptr nocapture, i8, i64, i1) nounwind
|
|
|
|
; The resulting memset is only 4-byte aligned, despite containing
|
|
; a 16-byte aligned store in the middle.
|
|
|
|
define void @foo(ptr %p) {
|
|
; CHECK-LABEL: @foo(
|
|
; CHECK-NEXT: [[A1:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 1
|
|
; CHECK-NEXT: [[A2:%.*]] = getelementptr i32, ptr [[P]], i64 2
|
|
; CHECK-NEXT: [[A3:%.*]] = getelementptr i32, ptr [[P]], i64 3
|
|
; CHECK-NEXT: call void @llvm.memset.p0.i64(ptr align 4 [[P]], i8 0, i64 16, i1 false)
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
store i32 0, ptr %p, align 4
|
|
%a1 = getelementptr i32, ptr %p, i64 1
|
|
store i32 0, ptr %a1, align 16
|
|
%a2 = getelementptr i32, ptr %p, i64 2
|
|
store i32 0, ptr %a2, align 4
|
|
%a3 = getelementptr i32, ptr %p, i64 3
|
|
store i32 0, ptr %a3, align 4
|
|
ret void
|
|
}
|
|
|
|
; Replacing %a8 with %a4 in the memset requires boosting the alignment of %a4.
|
|
|
|
define void @bar() {
|
|
; CHECK-LABEL: @bar(
|
|
; CHECK-NEXT: [[A4:%.*]] = alloca i32, align 8
|
|
; CHECK-NEXT: [[A8:%.*]] = alloca i32, align 8
|
|
; CHECK-NEXT: call void @llvm.memset.p0.i64(ptr align 8 [[A4]], i8 0, i64 4, i1 false)
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
%a4 = alloca i32, align 4
|
|
%a8 = alloca i32, align 8
|
|
call void @llvm.memset.p0.i64(ptr align 8 %a8, i8 0, i64 4, i1 false)
|
|
call void @llvm.memcpy.p0.p0.i64(ptr align 4 %a4, ptr align 4 %a8, i64 4, i1 false)
|
|
ret void
|
|
}
|