PGO/LTO optimizations for riscv qemu platforms#29
Merged
Conversation
* additional Docker stage riscv-gnu-glibc-clang-installer * time-based PGO (instead of step-based as in current measurements) * stateless improves from 2147554329 steps without LTO/PGO to 1993332842 steps (7%)
Benchmark Results (933ad25)
|
* Configurable since it affects compile time * Extra -flto argument in OPT_LEVEL * Additional PGO_OPT variable
Benchmark Results (044b762)
|
psilva261
changed the title
Collaborator
Author
|
I think I'll merge this for now. The way it's implemented, PGO/LTO are anyway optional |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
PGO explicitly takes time measurements to decide which improvements to do. So the current optimization might be skewed, also being related to #20
For simplicity the GCC RISC-V project provides a clang version with PGO enabled. And most importantly with the compiler-rt profile library. For baremetal riscv64 soft-float a custom compiled clang would be needed though. This is realized through the GCC RISC-V build.
It's not part of benchmarking though because RAM usage is too high for the Runner even with lld