Profile-Guided Optimization (PGO) benchmark results #1163
zamazan4ik
started this conversation in
Ideas
Replies: 1 comment 1 reply
-
That's really awesome @zamazan4ik. Thank you for sharing the results of your experiment. Looking at the results, it looks like you can expect about 15-20% improvement. If you're looking for other projects to test PGO on, let me suggest to have a look at |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hi!
I evaluate Profile-Guided Optimization (PGO) performance improvements for applications (and libraries) in different software domains - all current results can be found here. According to the tests, PGO helps to improve performance in various software domains. I decided to perform PGO benchmarks on the
sqlparser-rs
library too since some library users can be interested in improving the library performance. Here are the results.Test environment
main
branch on commit5da66adda99d8cf7a36c1512d41815d94ce542b5
Benchmark
For benchmark purposes, I use sqlparser-bench benchmark. Release measurements are done with
cargo bench
, PGO optimized withcargo pgo optimize bench
, PGO training phase - withcargo pgo bench
. All PGO optimizations are done with cargo-pgo.Results
I got the following results:
At least in the provided by project benchmarks, there are measurable improvements.
Maybe mentioning these results somewhere in the README (or any other user-facing documentation) can be a good idea. Also, I think it will be worth performing benchmarks in more scenarios.
Please do not treat the issue as a bug or something like that - it's just a benchmark report.
Beta Was this translation helpful? Give feedback.
All reactions