Fix intercommunicator overflow with big payload collectives #9942
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
bosilca
reviewed
Jan 28, 2022
* The 'inter' collective component was multiplying the `int` count by
the `int` size of the communicator which can overflow the integer.
- Solution is to preserve the full `size_t` value in the compuation
which the PML supports.
* `allgather`, `gather`, `scatter` all overflowed in a multiply
- Preserve the full `size_t` value in the multiply
- allgather needed extra code to handle the bcast of the result
* `allgatherv`, `gatherv`, `scatterv` all overflowed a `total` variable
that accumulated over the count array.
- Preserve the full `size_t` value in `total` type
Signed-off-by: Joshua Hursey <jhursey@us.ibm.com>
jjhursey
force-pushed
the
big-payload-inter-coll
branch
from
ba01b42 to
fe07940
Compare
|
@bosilca when you have a chance can you re-review? |
bosilca
approved these changes
Feb 4, 2022
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Outdated suggestions cannot be applied.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.
intcount bythe
intsize of the communicator which can overflow the integer.size_tvalue in the compuationwhich the PML supports.
allgather,gather,scatterall overflowed in a multiplysize_tvalue in the multiplyallgatherv,gatherv,scattervall overflowed atotalvariablethat accumulated over the count array.
size_tvalue intotaltype