Re: [linux-audio-dev] Re: -O3 etc

From: Paul Coccoli <pcoccoli@email-addr-hidden>
Date: Thu Jan 12 2006 - 16:45:09 EET

On 1/12/06, Bill Schottstaedt <bil@email-addr-hidden> wrote:
> I ran some timing tests, partly to check out -fast-math -- my informal impression
> is that it speeds up exp by a factor of about 2, but can slow down other things
> (FIR filters). I didn't see any obvious improvement in -O3 over -O2. The
> actual numbers are in the snd tarball, snd-edits.c -- look for "fast-math".
> (The table is aimed more at comparing int/float/double operations). These
> timing numbers change by a factor of, say, 20% on each run, so don't put
> much weight on them.
>
>

I read somewhere that -Os (optimize for "smaller" code, intended for
embedded systems maybe?) sometimes produces faster code than -O2 or
-O3. Has anybody tried that on their plugins or anything else?

Might not help at all if, as Steve Harris said, most plugin inner
loops fit in cache already.
Received on Thu Jan 12 20:15:05 2006

This archive was generated by hypermail 2.1.8 : Thu Jan 12 2006 - 20:15:05 EET