On Mon, 25 Aug 2025 15:27:54 GMT, Magnus Ihse Bursie <i...@openjdk.org> wrote:
> The new PCH file is surprisingly short. But we should trust the performance > measurements, and this seems to be much better than the existing file. It > might be an indication that gcc/clang have improved in performance for > non-PCH headers. If you are up to it, it would be interesting to have a > comparison run on your test platforms for running without PCH. You don't have > to retest everything you ran, but just some representative selection perhaps? > It's not relevant to this PR, but more to the general discussion of how > relevant it is to keep PCH at all. @magicus it seems that PCH still makes quite a difference, I re-ran `server` builds: | Branch | Compiler | Build flavor | Avg | Stddev | |---------|----------|-------|---------|--------| | master | gcc | server no-pch| 3375.60 | 2.04 | | master | clang | server no-pch| 2554.08 | 6.25 | | master | gcc | server | 2962.90 | 3.04 | | master | clang | server | 2247.31 | 4.27 | | 892ecb5a | gcc | server | 2570.87 | 0.96 | | 892ecb5a | clang | server | 1824.21 | 2.31 | The platform is the first in my [comment](https://github.com/openjdk/jdk/pull/26681#issuecomment-3219345092) above. ------------- PR Comment: https://git.openjdk.org/jdk/pull/26681#issuecomment-3220911147
