Ensure highest precision on device are the same as the host's #1848
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
yhmtsai
added
1:ST:WIP
ginkgo-bot
added
reg:build
yhmtsai
force-pushed
the
highest_precision
branch
from
d2d92ff to
240e13a
Compare
yhmtsai
changed the title
yhmtsai
changed the title
yhmtsai
force-pushed
the
highest_precision
branch
from
563fb7d to
323f6bd
Compare
yhmtsai
added
1:ST:ready-for-review
MarcelKoch
approved these changes
May 28, 2025
yhmtsai
added
1:ST:ready-to-merge
yhmtsai
force-pushed
the
highest_precision
branch
from
323f6bd to
0e0656e
Compare
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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 PR adds the highest precision test to ensure we get the same thing among backends.
In general, we tend to avoid type promotion implicitly. We handle it either from accessor or static_cast to the
highest_precision<Type...>.However, decltype(T1{}, T2{}) on device type may not give the same result or is not compiled successfully.
Additionally, it fixes the
unintialized_array<bfloat>pointer shift's ambiguous operation before oneapi 2024.2 and assignment issue before cuda 12.2 on CC > 80.