Replace direct cudaMemcpyAsync calls with utility functions (within /src)
#17550
Conversation
This file contains 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
…avoid-cudamemcpy-rest
…avoid-cudamemcpy-rest
…avoid-cudamemcpy-rest
…avoid-cudamemcpy-rest
vuule
added
improvement
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
vuule
commented
Dec 9, 2024
| @@ -78,7 +78,7 @@ class device_scalar : public rmm::device_scalar<T> { | |||
| [[nodiscard]] T value(rmm::cuda_stream_view stream) const | |||
| { | |||
| cuda_memcpy<T>(bounce_buffer, device_span<T const>{this->data(), 1}, stream); | |||
| return bounce_buffer[0]; | |||
| return std::move(bounce_buffer[0]); | |||
There was a problem hiding this comment.
Just in case we want to make a device_scalar of a non-copyable type.
…avoid-cudamemcpy-rest
…into avoid-cudamemcpy-rest
vuule
changed the title
cudaMemcpyAsync calls with utility functions (limited to /src)cudaMemcpyAsync calls with utility functions (within /src)
davidwendt
requested changes
Dec 10, 2024
…avoid-cudamemcpy-rest
Co-authored-by: David Wendt <[email protected]>
Co-authored-by: David Wendt <[email protected]>
…into avoid-cudamemcpy-rest
ttnghia
reviewed
Dec 13, 2024
ttnghia
reviewed
Dec 13, 2024
ttnghia
reviewed
Dec 13, 2024
ttnghia
reviewed
Dec 13, 2024
…avoid-cudamemcpy-rest
ttnghia
approved these changes
Dec 14, 2024
ttnghia
approved these changes
Dec 14, 2024
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Outdated suggestions cannot be applied.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.
Description
Replaced the calls to
cudaMemcpyAsyncwith the newcuda_memcpy/cuda_memcpy_asyncutility, which optionally avoids using the copy engine.Also took the opportunity to use cudf::detail::host_vector and its factories to enable wider pinned memory use.
Remaining instances are either not viable (e.g. copying
h_needs_fallback, interop) or D2D copies.Checklist