Remove memory allocation on GPU from MPI worker nodes #3911
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
cudaStreamCreate() allocates around 130 MB of data on the GPU, yet the GPU is only used on the head node. This allocation is unnecessary on worker nodes and locks resources that could be used by the head node, e.g. to run a GPU LB simulation with a finer grid.
mkuron
approved these changes
Sep 23, 2020
|
ping @RudolfWeeber |
|
Is this urgent? Otherwise I’m currently reviewing tutorials.
|
RudolfWeeber
approved these changes
Sep 30, 2020
jngrad
pushed a commit
to jngrad/espresso
that referenced
this pull request
Oct 13, 2020
Fixes espressomd#3910 Description of changes: - create an asynchronous stream on the GPU only for the head node
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Outdated suggestions cannot be applied.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.
Fixes #3910
Description of changes: