[rescue] Sparc Classic

[Greg A. Woods]

[ On Tuesday, January 15, 2002 at 15:26:36 (-0500), Kurt Mosiejczuk wrote: ]
> Subject: Re: [rescue] Sparc Classic
>
> On Tue, 15 Jan 2002, Greg A. Woods wrote:
> 
> > > What OS and how did you compile mpg123?
> 
> > NetBSD of course [:-)], with the in-tree gcc, which is apparently
> > egcs-1.1.2 in the release I'm using.

Well I must apologise if I've lead anyone astray w.r.t. the processing
power of a 75MHz SS-20 under gcc.

I'm currently listening to a 128kbit mp3 stereo audio stream comming in
off the internet and being decoded into a NAS stream for my NCD via my
SS-20 clone using mpg123-0.59r.  Top shows mpg123 using only an average
of maybe 38% CPU, and never more than 40%.  There's no skipping
whatsoever.  Aurally it's identical-sounding to doing the same decoding
on my P-II 300MHz server (as one would expect).

$ mpg123 -v http://205.188.245.131:8002/
High Performance MPEG 1.0/2.0/2.5 Audio Player for Layer 1, 2 and 3.
Version 0.59r (1999/Jun/15). Written and copyrights by Michael Hipp.
Uses code from various people. See 'README' for more!
THIS SOFTWARE COMES WITH ABSOLUTELY NO WARRANTY! USE AT YOUR OWN RISK!

Directory: http://205.188.245.131:8002/
Playing MPEG stream from  ...
MPEG 1.0, Layer: III, Freq: 44100, mode: Joint-Stereo, modext: 2, BPF : 418
Channels: 2, copyright: No, original: Yes, CRC: No, emphasis: 0.
Bitrate: 128 Kbits/s, Extension value: 0
Audio: 1:1 conversion, rate: 44100, encoding: signed 16 bit, channels: 2
Frame# 33240 [    0], Time: 14:28.31 [00:00.00], 


I've no idea what I was thinking of w.r.t. any problems before.

> The one other suggestion I'd make then is recompile using
> -mcpu=supersparc or =mcpu=v8
> 
> By default gcc puts out v7 code and that's what OpenBSD and NetBSD
> compile things with to not break all the sun4c machines... however,
> that means a lot of the oomph in the calculation department
> (particularly multiplication and division) is left unused...

Hmm.... this is interesting.  If I had no sun4c machines I'd be tempted
to try a full build with the appropriate '-mcpu', but as-is I'm having a
hard enough time maintining my NetBSD builds with one per architecture!  ;-)

I am tempted though to try decoding the same stream with the binary I
have on an SS-1.  Unfortunately I need to replace the disk in my test
SS-1 first.  My SS-2 is still running too ancient a NetBSD to even
bother trying to build mpg123, though hopefully I'll get around to
upgrading it in not too much time....

-- 
								Greg A. Woods

+1 416 218-0098;  <gwoods at acm.org>;  <g.a.woods at ieee.org>;  <woods at robohack.ca>
Planix, Inc. <woods at planix.com>; VE3TCP; Secrets of the Weird <woods at weird.com>