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
73 lines
3.3 KiB
LLVM
73 lines
3.3 KiB
LLVM
; RUN: opt < %s -passes=loop-interchange -cache-line-size=64 -pass-remarks-missed='loop-interchange' -pass-remarks-output=%t -S \
|
|
; RUN: -verify-dom-info -verify-loop-info -verify-loop-lcssa -stats 2>&1
|
|
; RUN: FileCheck --input-file=%t --check-prefix=REMARKS %s
|
|
|
|
; Triply nested loop, should be able to do interchange three times
|
|
; to get the ideal access pattern.
|
|
; void f(int e[restrict 10][10][10], int f[restrict 10][10][10]) {
|
|
; for (int a = 0; a < 10; a++) {
|
|
; for (int b = 0; b < 10; b++) {
|
|
; for (int c = 0; c < 10; c++) {
|
|
; f[c][b][a] = e[c][b][a];
|
|
; }
|
|
; }
|
|
; }
|
|
; }
|
|
|
|
; REMARKS: --- !Analysis
|
|
; REMARKS-NEXT: Pass: loop-interchange
|
|
; REMARKS-NEXT: Name: Dependence
|
|
; REMARKS-NEXT: Function: pr43326-triply-nested
|
|
; REMARKS-NEXT: Args:
|
|
; REMARKS-NEXT: - String: Computed dependence info, invoking the transform.
|
|
; REMARKS-NEXT: ...
|
|
|
|
; REMARKS: --- !Passed
|
|
; REMARKS-NEXT: Pass: loop-interchange
|
|
; REMARKS-NEXT: Name: Interchanged
|
|
; REMARKS-NEXT: Function: pr43326-triply-nested
|
|
; REMARKS: --- !Passed
|
|
; REMARKS-NEXT: Pass: loop-interchange
|
|
; REMARKS-NEXT: Name: Interchanged
|
|
; REMARKS-NEXT: Function: pr43326-triply-nested
|
|
; REMARKS: --- !Passed
|
|
; REMARKS-NEXT: Pass: loop-interchange
|
|
; REMARKS-NEXT: Name: Interchanged
|
|
; REMARKS-NEXT: Function: pr43326-triply-nested
|
|
|
|
define void @pr43326-triply-nested(ptr noalias %e, ptr noalias %f) {
|
|
entry:
|
|
br label %for.outermost.header
|
|
|
|
for.outermost.header: ; preds = %entry, %for.outermost.latch
|
|
%indvars.outermost = phi i64 [ 0, %entry ], [ %indvars.outermost.next, %for.outermost.latch ]
|
|
br label %for.middle.header
|
|
|
|
for.cond.cleanup: ; preds = %for.outermost.latch
|
|
ret void
|
|
|
|
for.middle.header: ; preds = %for.outermost.header, %for.middle.latch
|
|
%indvars.middle = phi i64 [ 0, %for.outermost.header ], [ %indvars.middle.next, %for.middle.latch ]
|
|
br label %for.innermost
|
|
|
|
for.outermost.latch: ; preds = %for.middle.latch
|
|
%indvars.outermost.next = add nuw nsw i64 %indvars.outermost, 1
|
|
%exitcond.outermost = icmp ne i64 %indvars.outermost.next, 10
|
|
br i1 %exitcond.outermost, label %for.outermost.header, label %for.cond.cleanup
|
|
|
|
for.middle.latch: ; preds = %for.innermost
|
|
%indvars.middle.next = add nuw nsw i64 %indvars.middle, 1
|
|
%exitcond.middle = icmp ne i64 %indvars.middle.next, 10
|
|
br i1 %exitcond.middle, label %for.middle.header, label %for.outermost.latch
|
|
|
|
for.innermost: ; preds = %for.middle.header, %for.innermost
|
|
%indvars.innermost = phi i64 [ 0, %for.middle.header ], [ %indvars.innermost.next, %for.innermost ]
|
|
%arrayidx12 = getelementptr inbounds [10 x [10 x i32]], ptr %e, i64 %indvars.innermost, i64 %indvars.middle, i64 %indvars.outermost
|
|
%0 = load i32, ptr %arrayidx12
|
|
%arrayidx18 = getelementptr inbounds [10 x [10 x i32]], ptr %f, i64 %indvars.innermost, i64 %indvars.middle, i64 %indvars.outermost
|
|
store i32 %0, ptr %arrayidx18
|
|
%indvars.innermost.next = add nuw nsw i64 %indvars.innermost, 1
|
|
%exitcond.innermost = icmp ne i64 %indvars.innermost.next, 10
|
|
br i1 %exitcond.innermost, label %for.innermost, label %for.middle.latch
|
|
}
|