Run all of WAMINTGR on GPU
#29
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
awnawab
force-pushed
the
naan-promote-data-movement
branch
from
cae0d8b to
dd0b386
Compare
mlange05
approved these changes
Sep 30, 2024
wdeconinck
force-pushed
the
naan-promote-data-movement
branch
from
dd0b386 to
98551c8
Compare
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Outdated suggestions cannot be applied.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 is the first of two PRs targeted at reducing the frequency of data transfers between host and device. As a first step, everything under
WAMINTGRis ported to run on device. This will actually increase the amount of data transfers by moving them out of conditional clauses. The next PR will complete the work by hoisting the data transfers out of the advection loop inWAMODEL, leading to significant reductions in overall walltime.In order to cut down on the FIELD_API related boilerplate in the model code, the derived-types are offloaded to device and they now own the field pointers that were previously local in
WAMINTGR_LOKI_GPU.The PR also includes a minor cleanup of the data offload directives in the wave propagation kernel.