On Sat, Apr 13, 2024 at 5:55 PM Richard W.M. Jones <rjones@xxxxxxxxxx> wrote:
On Fri, Apr 12, 2024 at 07:08:36PM -0500, Neal Gompa wrote:
> I would like for us to consider evaluating a global change to -O3. I
> am not convinced that there's a good reason anymore to remain at -O2.
FYI here are the optimizations added by gcc -O3 (over -O2), from
https://gcc.gnu.org/onlinedocs/gcc/Optimize-Options.html
-fgcse-after-reload
-fipa-cp-clone
-floop-interchange
-floop-unroll-and-jam
-fpeel-loops
-fpredictive-commoning
-fsplit-loops
-fsplit-paths
-ftree-loop-distribution
-ftree-partial-pre
-funswitch-loops
-fvect-cost-model=dynamic
-fversion-loops-for-strides
Mainly lots of loop optimizations :-)
For clang, -O3 is simply described as this, I can't immediately find
any more detail:
-O3 Like -O2, except that it enables optimizations that take longer
to perform or that may generate larger code (in an attempt to make
the program run faster).
Clang enables a small number of additional optimizations at O3 (the most important of which are probably argument promotion and non-trivial loop unswitching), but probably the largest difference is that O3 uses higher cost thresholds for things like inlining and unrolling.
Regards,
Nikita
-- _______________________________________________ devel mailing list -- devel@xxxxxxxxxxxxxxxxxxxxxxx To unsubscribe send an email to devel-leave@xxxxxxxxxxxxxxxxxxxxxxx Fedora Code of Conduct: https://docs.fedoraproject.org/en-US/project/code-of-conduct/ List Guidelines: https://fedoraproject.org/wiki/Mailing_list_guidelines List Archives: https://lists.fedoraproject.org/archives/list/devel@xxxxxxxxxxxxxxxxxxxxxxx Do not reply to spam, report it: https://pagure.io/fedora-infrastructure/new_issue
