[PATCH x86] Increase PARAM_MAX_COMPLETELY_PEELED_INSNS when branch is costly
Eric Botcazou
ebotcazou@adacore.com
Tue Nov 11 16:39:00 GMT 2014
> 150 and 200 make Silvermont performance better on 173.applu (+8%) and
> 183.equake (+3%); Haswell spec2006 performance stays almost unchanged.
> Higher value of 300 leave the performance of mentioned tests
> unchanged, but add some regressions on other benchmarks.
>
> So I like 200 as well as 120 and 150, but can confirm performance
> gains only for x86.
IMO it's either 150 or 200. We chose 200 for our 4.9-based compiler because
this gave the performance boost without affecting the code size (on x86-64)
and because this was previously 400, but it's your call.
--
Eric Botcazou
More information about the Gcc-patches
mailing list