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
69 lines
3.3 KiB
LLVM
69 lines
3.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -S -passes=memcpyopt < %s | FileCheck %s
|
|
|
|
define void @test_copy_uninit(ptr %arg) {
|
|
; CHECK-LABEL: @test_copy_uninit(
|
|
; CHECK-NEXT: start:
|
|
; CHECK-NEXT: [[ALLOCA:%.*]] = alloca [1000 x i32], align 4
|
|
; CHECK-NEXT: [[END:%.*]] = getelementptr inbounds [1000 x [1000 x i32]], ptr [[ARG:%.*]], i64 0, i64 1000
|
|
; CHECK-NEXT: br label [[LOOP:%.*]]
|
|
; CHECK: loop:
|
|
; CHECK-NEXT: [[CURRENT:%.*]] = phi ptr [ [[ARG]], [[START:%.*]] ], [ [[NEXT:%.*]], [[LOOP]] ]
|
|
; CHECK-NEXT: [[NEXT]] = getelementptr inbounds [1000 x i32], ptr [[CURRENT]], i64 1
|
|
; CHECK-NEXT: [[COND:%.*]] = icmp eq ptr [[NEXT]], [[END]]
|
|
; CHECK-NEXT: br i1 [[COND]], label [[EXIT:%.*]], label [[LOOP]]
|
|
; CHECK: exit:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
start:
|
|
%alloca = alloca [1000 x i32], align 4
|
|
%end = getelementptr inbounds [1000 x [1000 x i32]], ptr %arg, i64 0, i64 1000
|
|
br label %loop
|
|
|
|
loop: ; preds = %loop, %start
|
|
%current = phi ptr [ %arg, %start ], [ %next, %loop ]
|
|
call void @llvm.memcpy.p0.p0.i64(ptr nonnull align 4 dereferenceable(4000) %current, ptr nonnull align 4 dereferenceable(4000) %alloca, i64 4000, i1 false)
|
|
%next = getelementptr inbounds [1000 x i32], ptr %current, i64 1
|
|
%cond = icmp eq ptr %next, %end
|
|
br i1 %cond, label %exit, label %loop
|
|
|
|
exit: ; preds = %loop
|
|
ret void
|
|
}
|
|
|
|
define void @test_copy_zero(ptr %arg) {
|
|
; CHECK-LABEL: @test_copy_zero(
|
|
; CHECK-NEXT: start:
|
|
; CHECK-NEXT: [[ALLOCA:%.*]] = alloca [1000 x i32], align 4
|
|
; CHECK-NEXT: call void @llvm.memset.p0.i64(ptr nonnull align 4 dereferenceable(4000) [[ALLOCA]], i8 0, i64 4000, i1 false)
|
|
; CHECK-NEXT: [[END:%.*]] = getelementptr inbounds [1000 x [1000 x i32]], ptr [[ARG:%.*]], i64 0, i64 1000
|
|
; CHECK-NEXT: br label [[LOOP:%.*]]
|
|
; CHECK: loop:
|
|
; CHECK-NEXT: [[CURRENT:%.*]] = phi ptr [ [[ARG]], [[START:%.*]] ], [ [[NEXT:%.*]], [[LOOP]] ]
|
|
; CHECK-NEXT: call void @llvm.memset.p0.i64(ptr align 4 [[CURRENT]], i8 0, i64 4000, i1 false)
|
|
; CHECK-NEXT: [[NEXT]] = getelementptr inbounds [1000 x i32], ptr [[CURRENT]], i64 1
|
|
; CHECK-NEXT: [[COND:%.*]] = icmp eq ptr [[NEXT]], [[END]]
|
|
; CHECK-NEXT: br i1 [[COND]], label [[EXIT:%.*]], label [[LOOP]]
|
|
; CHECK: exit:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
start:
|
|
%alloca = alloca [1000 x i32], align 4
|
|
call void @llvm.memset.p0.i64(ptr nonnull align 4 dereferenceable(4000) %alloca, i8 0, i64 4000, i1 false)
|
|
%end = getelementptr inbounds [1000 x [1000 x i32]], ptr %arg, i64 0, i64 1000
|
|
br label %loop
|
|
|
|
loop: ; preds = %loop, %start
|
|
%current = phi ptr [ %arg, %start ], [ %next, %loop ]
|
|
call void @llvm.memcpy.p0.p0.i64(ptr nonnull align 4 dereferenceable(4000) %current, ptr nonnull align 4 dereferenceable(4000) %alloca, i64 4000, i1 false)
|
|
%next = getelementptr inbounds [1000 x i32], ptr %current, i64 1
|
|
%cond = icmp eq ptr %next, %end
|
|
br i1 %cond, label %exit, label %loop
|
|
|
|
exit: ; preds = %loop
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.memset.p0.i64(ptr nocapture writeonly, i8, i64, i1 immarg)
|
|
declare void @llvm.memcpy.p0.p0.i64(ptr noalias nocapture writeonly, ptr noalias nocapture readonly, i64, i1 immarg)
|