ROCM reduction code updates #6383
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
jessebenson
force-pushed
the
jesseb/rocm-reduction
branch
from
45c066e to
32d02ab
Compare
…supported, so disable those typed kernels.
jessebenson
force-pushed
the
jesseb/rocm-reduction
branch
from
32d02ab to
c96489f
Compare
weixingzhang
reviewed
Feb 4, 2021
weixingzhang
previously approved these changes
Feb 4, 2021
weixingzhang
approved these changes
Feb 4, 2021
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Outdated suggestions cannot be applied.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.
Description:
CUDA reduction code went through substantial changes after the initial ROCM code was developed, and while MIOpen was still in early development.
This change updates the ROCM-specific reduction code to more closely match the current CUDA code. MIOpen is missing some functionality (no
doublesupport, no support for reduce Avg, no support for reduce L1/L2 norm), so there are still code differences.