Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

36% faster encode_mcu_AC_first(), by eliminating an unpredictable branch in the inner loop #38

Merged
merged 1 commit into from
Apr 14, 2014

Conversation

pengvado
Copy link
Contributor

Which corresponds to 15% faster overall encoding in "progressive scan optimization" mode.
(And a negligible speedup in -fastcrush mode.)

…nch in the inner loop

Which corresponds to 15% faster overall encoding in "progressive scan optimization" mode.
(And a negligible speedup in -fastcrush mode.)
@bdaehlie
Copy link
Contributor

Frank - can you review this?

@fbossen
Copy link
Contributor

fbossen commented Apr 14, 2014

Can do. May have to wait until tomorrow.

Sent from my iPhone

On Apr 14, 2014, at 4:32 PM, Josh Aas notifications@github.com wrote:

Frank - can you review this?


Reply to this email directly or view it on GitHub.

fbossen added a commit that referenced this pull request Apr 14, 2014
36% faster encode_mcu_AC_first(), by eliminating an unpredictable branch in the inner loop
@fbossen fbossen merged commit 5d4e113 into mozilla:master Apr 14, 2014
@ace-dent
Copy link

@pengvado - Out of interest, is this based on the cache missing analysis published here? ...
http://fenrir.cse.unt.edu/publications/papers/gleipnir_journal.pdf

  • This flags: encode_mcu_AC_refine, encode_mcu_AC_first and rgb_ycc_convert (analysis from Dec 2012).

@pengvado
Copy link
Contributor Author

@ace-dent This patch is about branch misses, not cache misses. I found it with perf.

@ace-dent
Copy link

@pengvado - Neat. Thanks for the info :)

@jiangdongguo jiangdongguo mentioned this pull request Dec 2, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants