emscripten-core / emscripten-core/emscripten
Huge performance regression in 2.0.17
Open
- Dominant language
- C++
- Stars
- 27.6k
- Forks
- 3.6k
- Avg merge
- 1d 1h
- Merged PRs (30d)
- 105
Description
We've experienced a drastic performance regression (between 3x - 8x) in our app by updating from 2.0.16 to 2.017.
On the other hand, size has decreased 14%.
I suspect it's due to LLVM's new pass manager. Is there any flag we can use to select the legacy LLVM pass manager? This new behavior is preventing us from updating as performance is mission critical for our use case and we don't really care about size.
Thanks.
Contributor guide
Assessment
This issue has not been assessed yet.