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.

Sign up for GitHub

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

Jump to bottom

Optimize key encoding #141

Merged

xqrzd merged 3 commits into master from sse-encoding-improvements

Feb 4, 2021

Owner

xqrzd commented Feb 4, 2021 •

edited

Loading

Optimize SSE key encoding, and remove the AVX key encoder. Per the comment in this article https://stackoverflow.com/questions/35663635/why-do-processors-with-only-avx-out-perform-avx2-processors-for-many-simd-algori
it seems using AVX does not make sense for this use case. After some benchmarking, AVX generally did not outperform SSE. Given the extra cost of using AVX registers and no additional performance, it seems like SSE is the clear winner.

Also, fall back to the standard binary encoding (instead of the slow path) if SSE isn't available.

xqrzd added 3 commits

February 3, 2021 20:26


          Optimize key encoding

b13bb32


          Micro optimization

be042d0


          Fall back to standard binary encode if SSE isn't available

efdc0bb

xqrzd merged commit 4fc23d7 into master

xqrzd deleted the sse-encoding-improvements branch

February 4, 2021 02:26

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet