wence/feature/codegen updates #590
Merged
Conversation
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
Member
Author
|
@sv2518 I think this branch (if you merge it in vectorisation) + wence/fix/interpolate-max in Firedrake fixes the test_real_space bug. |
Contributor
|
Yes, it does! Thanks! |
It conflicts with the name of the function, which loopy doesn't like.
Necessary to handle tsfc-generated kernels that have a par_loop access descriptor for their outputs that is not INC.
Will be used for global packs.
Until such time as the vectorisation stuff lands, this just makes the compilation process slower for no gain.
Previously we were not separately prefetching the base and extruded part of the maps. As a consequence it is possible that we were paying higher indirection costs than necessary. Additionally, compress offset arrays of a single value to a single literal offset. This marginally decreases the "hot" memory footprint.
This is necessary so that vectorising over the outer loop correctly privatises the accumulation variables.
Used to handle new Kernel requirement when the Kernel expects output arguments to be zero on entry. Fixes firedrakeproject/firedrake#1768.
wence-
force-pushed
the
wence/feature/codegen-updates
branch
from
11d558f to
d086159
Compare
Closed
sv2518
approved these changes
Jul 22, 2020
Contributor
sv2518
left a comment
sv2518
left a comment
There was a problem hiding this comment.
Can confirm that this works on the vectorisation branches now.
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Outdated suggestions cannot be applied.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.
No description provided.