use keyed jagged index select for lengths permute #1719
Closed
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
Summary:
we've seen better performance and gpu util from switching to keyed_jagged_index_select_dim1 for permuting values.
the traces also show that there is further performance gains to be had by switching lengths permute to use keyed_jagged_index_select_dim1 as well.
for example:
the permute 1d lengths takes the most time, while in the past the permute 1d for values took even longer but with keyed_jagged_index_select_dim1 can barely be seen
{F1456534243}
https://www.internalfb.com/intern/perfdoctor/trace_view?filepath=tree/traces/dynocli/aps-combo2_uhm_igfm_200x_baseline-ac3cbf3708/0/rank-1.Feb_08_22_34_41.5280.pt.trace.json.gz&bucket=aps_traces
Differential Revision: D53776313
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D53776313 |
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Outdated suggestions cannot be applied.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.
Summary:
we've seen better performance and gpu util from switching to keyed_jagged_index_select_dim1 for permuting values.
the traces also show that there is further performance gains to be had by switching lengths permute to use keyed_jagged_index_select_dim1 as well.
for example:
the permute 1d lengths takes the most time, while in the past the permute 1d for values took even longer but with keyed_jagged_index_select_dim1 can barely be seen
{F1456534243}
https://www.internalfb.com/intern/perfdoctor/trace_view?filepath=tree/traces/dynocli/aps-combo2_uhm_igfm_200x_baseline-ac3cbf3708/0/rank-1.Feb_08_22_34_41.5280.pt.trace.json.gz&bucket=aps_traces
Differential Revision: D53776313