Hello, I will be working on applying machine learning to optimize the LLVM's pass pipeline for GSoC. Specifically, I am investigating how we can use predictive models to select the best set of passes and their order for a given application/ source program. You can find the proposal here for more details. https://github.com/tarinduj/GSoC2021/raw/master/docs/Proposal.pdf Best, Tarindu -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20210521/083cee8d/attachment.html>