feat(example): add CUDA notification-strategies example#342
Merged
sgerbino merged 1 commit intoJun 29, 2026
Merged
Conversation
Demonstrate that the IoAwaitable protocol is independent of the GPU-completion notification mechanism. One GPU pipeline is awaited three structurally different ways, each satisfying capy::IoAwaitable, all producing identical results at runtime: - callback_awaitable: a cudaLaunchHostFunc host callback - poll_awaitable: a service thread looping cudaEventQuery - deferred_sync_awaitable: a service thread running blocking cudaStreamSynchronize Each awaitable owns its continuation as a member and hands the notification source a pointer, honoring the executor's stable-address contract. Mirrors example/cuda/datamovement conventions but is run, not just compiled: identical checksums across the three mechanisms plus a zero exit code is the pass condition. The README documents the multi-threaded scaling tradeoff with an attributed citation.
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## develop-2 #342 +/- ##
============================================
Coverage ? 98.39%
============================================
Files ? 83
Lines ? 4237
Branches ? 0
============================================
Hits ? 4169
Misses ? 68
Partials ? 0
Flags with carried forward coverage won't be shown. Click here to find out more. Continue to review full report in Codecov by Harness.
🚀 New features to boost your workflow:
|
|
An automated preview of the documentation is available at https://342.capy.prtest3.cppalliance.org/index.html If more commits are pushed to the pull request, the docs will rebuild at the same URL. 2026-06-29 21:23:20 UTC |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
Demonstrate that the IoAwaitable protocol is independent of the GPU-completion notification mechanism. One GPU pipeline is awaited three structurally different ways, each satisfying capy::IoAwaitable, all producing identical results at runtime:
Each awaitable owns its continuation as a member and hands the notification source a pointer, honoring the executor's stable-address contract. Mirrors example/cuda/datamovement conventions but is run, not just compiled: identical checksums across the three mechanisms plus a zero exit code is the pass condition. The README documents the multi-threaded scaling tradeoff with an attributed citation.