[DRAFT][NATIVECPU] using tbb::parallel_for when oneTBB is enabled #20064
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…queue_async_ops_eventswait_onetbb_merge
…queue_async_ops_eventswait
…_ops_eventswait' into uwe/fasternativecpuenqueue_async_ops_eventswait_onetbb_merge
…queue_async_ops_eventswait
…_ops_eventswait' into uwe/fasternativecpuenqueue_async_ops_eventswait_onetbb_merge
…queue_async_ops_eventswait_onetbb_merge
…queue_async_ops_eventswait_onetbb_merge_parallelfor_exp
uwedolinsky
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
uwedolinsky
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
uwedolinsky
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
hvdijk
reviewed
Sep 24, 2025
Comment on lines
+284
to
285
| auto thread_id = getTBBThreadID(); | ||
| task(thread_id); |
There was a problem hiding this comment.
Suggested change
| auto thread_id = getTBBThreadID(); | |
| task(thread_id); | |
| task(getTBBThreadID()); |
The variable doesn't seem like it's still needed. Likewise in the other file.
| using tbb_nd_executor = nativecpu_tbb_executor; | ||
|
|
||
| template <template <class> class RangeTpl, class... T> | ||
| static inline void invoke_tbb_parallel_for(const tbb_nd_executor &tbb_ex, |
There was a problem hiding this comment.
I think it would be clearer to remove this function and call tbb::parallel_for directly in the other invoke_tbb_parallel_for overload.
| IndexT groupsPerThread; | ||
| size_t dim = 0; | ||
| for (size_t t = 0; t < 3; t++) | ||
| groupsPerThread[t] = numWG[t] / numParallelThreads; |
There was a problem hiding this comment.
This is confusing, groupsPerThread is an array but after initialization, only a single element of that array is used.
More to the point, in #19550, for non-oneTBB, I simplified the splitting across threads to be done over the linear range, rather than over any specific dimension, and that would probably be better with oneTBB as well.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Using the
tbb::parallel_forapi to enqueue NativeCPU kernel invocations when oneTBB is enabled