On Dec 18, 2006, at 4:29 AM, Tim Blechmann wrote:
These flags are used in the standard build:
-Os -funroll-loops -fomit-frame-pointer -mcpu=powerpc -mtune=7450 - mpowerpc-gfxopt
the standard build is optimized for size ???
On Apple:
-Os Optimize for size, but not at the expense of speed. -Os enables all -O2 optimizations that do not typically increase code size. However, instructions are chosen for best performance, regardless of size. To optimize solely for size on Darwin, use -Oz (APPLE ONLY).
(fdn~ NOT vectorized; d_soundfile.c, d_ctl.c, m_sched.cvectorized)
have the _whole_ files been vectorized or only certain loops? which loops have been vectorized, which haven't?
That I don't know, you'll have to compile with higher vectorizing log level than I did. But not all the loops were vectorized, only some. s_audio.c had a lot of loops vectorized, so you can choose your soundcard really fast with this build ;)
.hc
tim
-- tim@klingt.org ICQ: 96771783 http://www.mokabar.tk
Linux is like a wigwam: no windows, no gates, apache inside, stable.
------------------------------------------------------------------------
Looking at things from a more basic level, you can come up with a more direct solution... It may sound small in theory, but it in practice, it can change entire economies. - Amy Smith