Skip to content

[OpenMP][FIX] Remove unsound omp_get_thread_limit deduplication #79524

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Feb 22, 2024
Merged

[OpenMP][FIX] Remove unsound omp_get_thread_limit deduplication #79524

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4167b66
[OpenMP][FIX] Remove unsound omp_get_thread_limit deduplication
MattPD Jan 25, 2024
31efd7d
Update llvm/test/Transforms/OpenMP/deduplication_soundness.ll
MattPD Feb 21, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion llvm/lib/Transforms/IPO/OpenMPOpt.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1471,7 +1471,6 @@ struct OpenMPOpt {
OMPRTL_omp_get_num_threads,
OMPRTL_omp_in_parallel,
OMPRTL_omp_get_cancellation,
OMPRTL_omp_get_thread_limit,
OMPRTL_omp_get_supported_active_levels,
OMPRTL_omp_get_level,
OMPRTL_omp_get_ancestor_thread_num,
Expand Down
59 changes: 59 additions & 0 deletions llvm/test/Transforms/OpenMP/deduplication_soundness.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,59 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function main --scrub-attributes --filter "@omp_get_thread_limit|@use" --version 4
; RUN: opt -passes=openmp-opt-cgscc -S < %s | FileCheck %s
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

For a test like this I'd recommend generating the check lines with llvm/utils/update_test_checks.py --function-signature.

Copy link
Member Author

@MattPD MattPD Feb 5, 2024 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks! I'd prefer this too, if possible; will see if there's a way to avoid generating more check lines than I already have (in the past had to use UTC_ARGS for in certain cases, but perhaps won't be needed here).

Edit: UTC_ARGS: --function main --scrub-attributes --filter "@omp_get_thread_limit|@use" does it.

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done!


declare void @use(i32 noundef)
declare i32 @omp_get_thread_limit()
declare void @__kmpc_set_thread_limit(ptr, i32, i32)
declare i32 @__kmpc_global_thread_num(ptr)
declare noalias ptr @__kmpc_omp_task_alloc(ptr, i32, i32, i64, i64, ptr)
declare void @__kmpc_omp_task_complete_if0(ptr, i32, ptr)
declare void @__kmpc_omp_task_begin_if0(ptr, i32, ptr)

%struct.ident_t = type { i32, i32, i32, i32, ptr }

@0 = private unnamed_addr constant [23 x i8] c";unknown;unknown;0;0;;\00", align 1
@1 = private unnamed_addr constant %struct.ident_t { i32 0, i32 2, i32 0, i32 22, ptr @0 }, align 8

define i32 @main() local_unnamed_addr {
; CHECK-LABEL: define i32 @main() local_unnamed_addr {
; CHECK: [[CALL_I_I_I:%.*]] = call i32 @omp_get_thread_limit()
; CHECK: call void @use(i32 noundef [[CALL_I_I_I]])
; CHECK: [[CALL_I_I_I2:%.*]] = call i32 @omp_get_thread_limit()
; CHECK: call void @use(i32 noundef [[CALL_I_I_I2]])
;
entry:
%0 = call i32 @__kmpc_global_thread_num(ptr nonnull @1)
%1 = call ptr @__kmpc_omp_task_alloc(ptr nonnull @1, i32 %0, i32 1, i64 40, i64 0, ptr nonnull @.omp_task_entry.)
call void @__kmpc_omp_task_begin_if0(ptr nonnull @1, i32 %0, ptr %1)
call void @__kmpc_set_thread_limit(ptr nonnull @1, i32 %0, i32 4)
%call.i.i.i = call i32 @omp_get_thread_limit()
call void @use(i32 noundef %call.i.i.i)
call void @__kmpc_omp_task_complete_if0(ptr nonnull @1, i32 %0, ptr %1)
%2 = call ptr @__kmpc_omp_task_alloc(ptr nonnull @1, i32 %0, i32 1, i64 40, i64 0, ptr nonnull @.omp_task_entry..2)
call void @__kmpc_omp_task_begin_if0(ptr nonnull @1, i32 %0, ptr %2)
call void @__kmpc_set_thread_limit(ptr nonnull @1, i32 %0, i32 3)
%call.i.i.i2 = call i32 @omp_get_thread_limit()
call void @use(i32 noundef %call.i.i.i2)
call void @__kmpc_omp_task_complete_if0(ptr nonnull @1, i32 %0, ptr %2)
ret i32 0
}

define internal noundef i32 @.omp_task_entry.(i32 noundef %0, ptr noalias nocapture noundef readonly %1) {
entry:
tail call void @__kmpc_set_thread_limit(ptr nonnull @1, i32 %0, i32 4)
%call.i.i = tail call i32 @omp_get_thread_limit()
tail call void @use(i32 noundef %call.i.i)
ret i32 0
}

define internal noundef i32 @.omp_task_entry..2(i32 noundef %0, ptr noalias nocapture noundef readonly %1) {
entry:
tail call void @__kmpc_set_thread_limit(ptr nonnull @1, i32 %0, i32 3)
%call.i.i = tail call i32 @omp_get_thread_limit()
tail call void @use(i32 noundef %call.i.i)
ret i32 0
}

!llvm.module.flags = !{!0}

!0 = !{i32 7, !"openmp", i32 51}