Rockbox mail archive
Subject: Re: Proposal to update GCC for ARM
Re: Proposal to update GCC for ARM
Am 08.03.2010 22:00, schrieb Daniel Stenberg:
>
> Noticable binsize gain on targets that don't really need it sprinkled
> with some performance loss. Yeah, I think that qualifies as "no strong
> reason".
>
IMO the performance loss is negible, since it a) only hits FLAC which is
fast enough (it runs unboosted on all targets), and b) I expect the
binsize win to have a bigger impact w.r.t. to battery runtime. The
performance loss won't make a big difference (if at all), but having
over 60k more buffer available could - especially on lossless codecs
where usually not even single file fits into the buffer.. FLAC is simply
a codec where the filesize limits better battery runtime, not codec
performance. I think all HDD-based players need binsize gains where they
can get them. I can't see any other performance loss, the major codecs
are the same, or even faster.
The flac performance loss could also be caused by something other than
"just a bad compiler". For example it could be a gcc decision to not
inline some functions. If we spotted those we could fix it.
Best regards.
Received on 2010-03-08
Page was last modified "Jan 10 2012" The Rockbox Crew
|