Add Buffer type, improve Datatype handling #329
Merged
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
simonbyrne
force-pushed
the
sb/buffer
branch
5 times, most recently
from
1f911c6
to
89609b8
Compare
This contains two related changes: 1. Defines a specific `Buffer` type, which contains the reference to the storage buffer, its count and datatype. This allows us to simplify the type signatures of various functions, as `count` and `datatype` no longer need to be arguments to the functions. This also adds default conversion methods for `Array`s and `Subarray`s (creating the derived datatypes where necessary, and determining the appropriate `count`s), and moves the point-to-point operations to use these conversions. 2. Improves the handling of `Datatype` handles, by making them garbage-collected objects (like other MPI handles), moves lower-level functions to a submodule, defines consistent interfaces. Also fixes #327. I still need to move the collective calls over as well, however that will require more thought on how to handle the "chunked" operations like scatter/gather. I also removed the inverse dictionary mappings from MPI Datatype -> Julia Type, as that is no longer so easy to determine.
This was referenced Jan 6, 2020
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Outdated suggestions cannot be applied.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.
This contains two related changes:
Defines a specific
Buffertype, which contains the reference to the storage buffer, its count and datatype. This allows us to simplify the type signatures of various functions, ascountanddatatypeno longer need to be arguments to the functions. This also adds default conversion methods forArrays andSubarrays (creating the derived datatypes where necessary, and determining the appropriatecounts), and moves the point-to-point operations to use these conversions.Improves the handling of
Datatypehandles, by making them garbage-collected objects (like other MPI handles), moves lower-level functions to a submodule, defines consistent interfaces. Also fixes MPI crashing when buffer contains a reference tonothing#327.I still need to move the collective calls over as well, however that will require more thought on how to handle the "chunked" operations like scatter/gather.
I also removed the inverse dictionary mappings from MPI Datatype -> Julia Type, as that is no longer so easy to determine.