This repository was archived by the owner on Mar 21, 2024. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 761
Ctk12 sync #1837
Merged
Merged
Ctk12 sync #1837
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
Thrust algorithms inherently synchronize, and device-side syncs aren't supported on sm90+.
The device synchronization was decoupled from `THRUST_CDP_DISPATCH` and was trying to sync regardless of CDP state. This led to device syncs being invoked from device code when CDP is disabled and the thread-serial implementation was used. Some other algorithms that are implemented with `parallel_for` have also been updated. Old behavior: 1. `for_each`: calls `parallel_for` 2. `parallel_for`: calls appropriate impl using `THRUST_CDP_DISPATCH` 3. `parallel_for`: returns 4. `for_each`: calls `cub::detail::device_synchronize` New behavior: 1. `for_each`: calls `parallel_for` 2. `parallel_for`: calls appropriate impl using `THRUST_CDP_DISPATCH` 4. `parallel_for`: calls `cub::detail::device_synchronize` 3. `parallel_for`: returns
…ackport Move sync from for_each to parallel_for to fix CDP usages [2.0.X backport]
Various CMake fixes for new build features
Remove remnants of `throw()` (cherry picked from commit d3e6fa1)
(cherry picked from commit a38978c)
Collaborator
Author
|
run tests |
Merged
gevtushenko
approved these changes
Dec 14, 2022
Collaborator
Author
|
run tests |
jrhemstad
reviewed
Dec 15, 2022
github-actions bot
pushed a commit
that referenced
this pull request
Dec 15, 2022
…k12_sync Ctk12 sync f0ff4b2
github-actions bot
pushed a commit
to clayne/thrust
that referenced
this pull request
Dec 23, 2022
…nti/ctk12_sync Ctk12 sync f0ff4b2
github-actions bot
pushed a commit
to gevtushenko/thrust
that referenced
this pull request
Jan 2, 2023
…nti/ctk12_sync Ctk12 sync f0ff4b2
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Labels
P0: must have
Absolutely necessary. Critical issue, major blocker, etc.
testing: gpuCI in progress
Started gpuCI testing.
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.
Brings in changes that were released as part of CTK 12.