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
127 lines
5.8 KiB
LLVM
127 lines
5.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
|
|
; RUN: opt -passes="loop-idiom" < %s -S | FileCheck %s
|
|
|
|
define void @looper(ptr nocapture %out) {
|
|
; CHECK-LABEL: define void @looper(
|
|
; CHECK-SAME: ptr captures(none) [[OUT:%.*]]) {
|
|
; CHECK-NEXT: [[ENTRY:.*]]:
|
|
; CHECK-NEXT: [[M:%.*]] = getelementptr double, ptr [[OUT]], i32 16
|
|
; CHECK-NEXT: call void @llvm.memmove.p0.p0.i64(ptr align 8 [[OUT]], ptr align 8 [[M]], i64 256, i1 false), !tbaa [[DOUBLE_TBAA0:![0-9]+]]
|
|
; CHECK-NEXT: br label %[[FOR_BODY4:.*]]
|
|
; CHECK: [[FOR_BODY4]]:
|
|
; CHECK-NEXT: [[J_020:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[INC:%.*]], %[[FOR_BODY4]] ]
|
|
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds double, ptr [[M]], i64 [[J_020]]
|
|
; CHECK-NEXT: [[A0:%.*]] = load double, ptr [[ARRAYIDX]], align 8, !tbaa [[DOUBLE_TBAA0]]
|
|
; CHECK-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds double, ptr [[OUT]], i64 [[J_020]]
|
|
; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[J_020]], 1
|
|
; CHECK-NEXT: [[CMP2:%.*]] = icmp ult i64 [[J_020]], 31
|
|
; CHECK-NEXT: br i1 [[CMP2]], label %[[FOR_BODY4]], label %[[FOR_COND_CLEANUP:.*]]
|
|
; CHECK: [[FOR_COND_CLEANUP]]:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%M = getelementptr double, ptr %out, i32 16
|
|
br label %for.body4
|
|
|
|
for.body4: ; preds = %for.cond1.preheader, %for.body4
|
|
%j.020 = phi i64 [ 0, %entry ], [ %inc, %for.body4 ]
|
|
%arrayidx = getelementptr inbounds double, ptr %M, i64 %j.020
|
|
%a0 = load double, ptr %arrayidx, align 8, !tbaa !5
|
|
%arrayidx8 = getelementptr inbounds double, ptr %out, i64 %j.020
|
|
store double %a0, ptr %arrayidx8, align 8, !tbaa !5
|
|
%inc = add nuw nsw i64 %j.020, 1
|
|
%cmp2 = icmp ult i64 %j.020, 31
|
|
br i1 %cmp2, label %for.body4, label %for.cond.cleanup
|
|
|
|
for.cond.cleanup: ; preds = %for.cond.cleanup3
|
|
ret void
|
|
}
|
|
|
|
|
|
define void @looperBadMerge(ptr nocapture %out) {
|
|
; CHECK-LABEL: define void @looperBadMerge(
|
|
; CHECK-SAME: ptr captures(none) [[OUT:%.*]]) {
|
|
; CHECK-NEXT: [[ENTRY:.*]]:
|
|
; CHECK-NEXT: [[M:%.*]] = getelementptr double, ptr [[OUT]], i32 16
|
|
; CHECK-NEXT: call void @llvm.memmove.p0.p0.i64(ptr align 8 [[OUT]], ptr align 8 [[M]], i64 256, i1 false), !tbaa [[CHAR_TBAA4:![0-9]+]]
|
|
; CHECK-NEXT: br label %[[FOR_BODY4:.*]]
|
|
; CHECK: [[FOR_BODY4]]:
|
|
; CHECK-NEXT: [[J_020:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[INC:%.*]], %[[FOR_BODY4]] ]
|
|
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds double, ptr [[M]], i64 [[J_020]]
|
|
; CHECK-NEXT: [[A0:%.*]] = load double, ptr [[ARRAYIDX]], align 8, !tbaa [[DOUBLE_TBAA0]]
|
|
; CHECK-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds double, ptr [[OUT]], i64 [[J_020]]
|
|
; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[J_020]], 1
|
|
; CHECK-NEXT: [[CMP2:%.*]] = icmp ult i64 [[J_020]], 31
|
|
; CHECK-NEXT: br i1 [[CMP2]], label %[[FOR_BODY4]], label %[[FOR_COND_CLEANUP:.*]]
|
|
; CHECK: [[FOR_COND_CLEANUP]]:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%M = getelementptr double, ptr %out, i32 16
|
|
br label %for.body4
|
|
|
|
for.body4: ; preds = %for.cond1.preheader, %for.body4
|
|
%j.020 = phi i64 [ 0, %entry ], [ %inc, %for.body4 ]
|
|
%arrayidx = getelementptr inbounds double, ptr %M, i64 %j.020
|
|
%a0 = load double, ptr %arrayidx, align 8, !tbaa !5
|
|
%arrayidx8 = getelementptr inbounds double, ptr %out, i64 %j.020
|
|
store double %a0, ptr %arrayidx8, align 8, !tbaa !3
|
|
%inc = add nuw nsw i64 %j.020, 1
|
|
%cmp2 = icmp ult i64 %j.020, 31
|
|
br i1 %cmp2, label %for.body4, label %for.cond.cleanup
|
|
|
|
for.cond.cleanup: ; preds = %for.cond.cleanup3
|
|
ret void
|
|
}
|
|
|
|
define void @looperGoodMerge(ptr nocapture %out) {
|
|
; CHECK-LABEL: define void @looperGoodMerge(
|
|
; CHECK-SAME: ptr captures(none) [[OUT:%.*]]) {
|
|
; CHECK-NEXT: [[ENTRY:.*]]:
|
|
; CHECK-NEXT: [[M:%.*]] = getelementptr double, ptr [[OUT]], i32 16
|
|
; CHECK-NEXT: call void @llvm.memmove.p0.p0.i64(ptr align 8 [[OUT]], ptr align 8 [[M]], i64 256, i1 false)
|
|
; CHECK-NEXT: br label %[[FOR_BODY4:.*]]
|
|
; CHECK: [[FOR_BODY4]]:
|
|
; CHECK-NEXT: [[J_020:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[INC:%.*]], %[[FOR_BODY4]] ]
|
|
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds double, ptr [[M]], i64 [[J_020]]
|
|
; CHECK-NEXT: [[A0:%.*]] = load double, ptr [[ARRAYIDX]], align 8, !tbaa [[DOUBLE_TBAA0]]
|
|
; CHECK-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds double, ptr [[OUT]], i64 [[J_020]]
|
|
; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[J_020]], 1
|
|
; CHECK-NEXT: [[CMP2:%.*]] = icmp ult i64 [[J_020]], 31
|
|
; CHECK-NEXT: br i1 [[CMP2]], label %[[FOR_BODY4]], label %[[FOR_COND_CLEANUP:.*]]
|
|
; CHECK: [[FOR_COND_CLEANUP]]:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%M = getelementptr double, ptr %out, i32 16
|
|
br label %for.body4
|
|
|
|
for.body4: ; preds = %for.cond1.preheader, %for.body4
|
|
%j.020 = phi i64 [ 0, %entry ], [ %inc, %for.body4 ]
|
|
%arrayidx = getelementptr inbounds double, ptr %M, i64 %j.020
|
|
%a0 = load double, ptr %arrayidx, align 8, !tbaa !5
|
|
%arrayidx8 = getelementptr inbounds double, ptr %out, i64 %j.020
|
|
store double %a0, ptr %arrayidx8, align 8
|
|
%inc = add nuw nsw i64 %j.020, 1
|
|
%cmp2 = icmp ult i64 %j.020, 31
|
|
br i1 %cmp2, label %for.body4, label %for.cond.cleanup
|
|
|
|
for.cond.cleanup: ; preds = %for.cond.cleanup3
|
|
ret void
|
|
}
|
|
|
|
|
|
!3 = !{!4, !4, i64 0}
|
|
!4 = !{!"float", !7, i64 0}
|
|
!5 = !{!6, !6, i64 0}
|
|
!6 = !{!"double", !7, i64 0}
|
|
!7 = !{!"omnipotent char", !8, i64 0}
|
|
!8 = !{!"Simple C++ TBAA"}
|
|
;.
|
|
; CHECK: [[DOUBLE_TBAA0]] = !{[[META1:![0-9]+]], [[META1]], i64 0}
|
|
; CHECK: [[META1]] = !{!"double", [[META2:![0-9]+]], i64 0}
|
|
; CHECK: [[META2]] = !{!"omnipotent char", [[META3:![0-9]+]], i64 0}
|
|
; CHECK: [[META3]] = !{!"Simple C++ TBAA"}
|
|
; CHECK: [[CHAR_TBAA4]] = !{[[META2]], [[META2]], i64 0}
|
|
;.
|