Add a host map option for a UVM tensor alloc#3073
Closed
sryap wants to merge 1 commit into
Closed
Conversation
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D61401239 |
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D61401239 |
sryap
added a commit
to sryap/FBGEMM
that referenced
this pull request
Sep 5, 2024
Summary: X-link: facebookresearch/FBGEMM#167 Pull Request resolved: pytorch#3073 FBGEMM-GPU provides two options to allocate a UVM buffer: (1) `malloc` & `cudaHostRegister` and (2) `cudaMallocManaged`. Each one of them has a different performance implication (this is platform specific). This diff adds an option for a user to choose a UVM buffer allocation method in TBE. Reviewed By: q10, spcyppt Differential Revision: D61401239
sryap
force-pushed
the
export-D61401239
branch
from
737c96b to
bdde624
Compare
Summary: X-link: facebookresearch/FBGEMM#167 Pull Request resolved: pytorch#3073 FBGEMM-GPU provides two options to allocate a UVM buffer: (1) `malloc` & `cudaHostRegister` and (2) `cudaMallocManaged`. Each one of them has a different performance implication (this is platform specific). This diff adds an option for a user to choose a UVM buffer allocation method in TBE. Reviewed By: q10, spcyppt Differential Revision: D61401239
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D61401239 |
sryap
force-pushed
the
export-D61401239
branch
from
bdde624 to
9ec00e2
Compare
Contributor
|
This pull request has been merged in d3aae06. |
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.
Summary:
FBGEMM-GPU provides two options to allocate a UVM buffer: (1)
malloc&
cudaHostRegisterand (2)cudaMallocManaged. Each one of themhas a different performance implication (this is platform specific).
This diff adds an option for a user to choose a UVM buffer allocation
method in TBE.
Differential Revision: D61401239