You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Optimize Leo tools (like the compiler) with Profile-Guided Optimization (PGO) and LLVM BOLT.
Motivation
Deliver better performance for the Leo ecosystem. It would be useful for CI/CD pipelines (faster pipelines == cheaper pipelines) and better developer experience (faster write-compile-test feedback loop).
Implementation
Recently I checked Profile-Guided Optimization (PGO) improvements on multiple projects. The results are here. E.g. PGO results for LLVM-related tooling are here. According to the tests, PGO usually helps with the compiler and compiler-like workloads (like static analysis) - e.g. Clang gets +20% compilation speed with PGO, CPython achieves +10% in pybench. So I think optimizing Leo tooling with PGO would be a good idea at least to try.
I can suggest the following action points:
Perform PGO benchmarks on the Leo tooling. If it shows improvements - add a note to the documentation about possible improvements in Leo's performance with PGO.
Providing an easier way (e.g. a build option) to build scripts with PGO can be helpful for the end-users and maintainers since they will be able to optimize the Leo tools according to their own workloads.
Optimize pre-built binaries with PGO
Testing Post-Link Optimization techniques (like LLVM BOLT) would be interesting too (CPython, Clang, and Rustc already use BOLT as an addition to PGO) but I recommend starting from the usual PGO.
For the Rust projects, I recommend starting with cargo-pgo.
Here are some examples of how PGO optimization is integrated in other projects:
Are you willing to open a pull request? (See CONTRIBUTING)
Not yet.
How the Leo compiler performance is critical for the project - I don't know right now. If it's the problem right now - we could leave the issue open for the future improvements.
The text was updated successfully, but these errors were encountered:
🚀 Feature
Optimize Leo tools (like the compiler) with Profile-Guided Optimization (PGO) and LLVM BOLT.
Motivation
Deliver better performance for the Leo ecosystem. It would be useful for CI/CD pipelines (faster pipelines == cheaper pipelines) and better developer experience (faster write-compile-test feedback loop).
Implementation
Recently I checked Profile-Guided Optimization (PGO) improvements on multiple projects. The results are here. E.g. PGO results for LLVM-related tooling are here. According to the tests, PGO usually helps with the compiler and compiler-like workloads (like static analysis) - e.g. Clang gets +20% compilation speed with PGO, CPython achieves +10% in
pybench
. So I think optimizing Leo tooling with PGO would be a good idea at least to try.I can suggest the following action points:
Testing Post-Link Optimization techniques (like LLVM BOLT) would be interesting too (CPython, Clang, and Rustc already use BOLT as an addition to PGO) but I recommend starting from the usual PGO.
For the Rust projects, I recommend starting with cargo-pgo.
Here are some examples of how PGO optimization is integrated in other projects:
configure
scriptAre you willing to open a pull request? (See CONTRIBUTING)
Not yet.
How the Leo compiler performance is critical for the project - I don't know right now. If it's the problem right now - we could leave the issue open for the future improvements.
The text was updated successfully, but these errors were encountered: