>From: [EMAIL PROTECTED] (Bill Davidsen)
>Lastly, I wish I could find a compressor which uses all the CPUs in the
>system. I hate to watch one CPU cook at 100 usage, while the other three
>sit with their thumbs up their idle loop. I actually wrote a test
>program to read 1MB of data and put it in a shared memory buffer. Four
>processes compressed it using gzip with settings of 1, 3, 7, and 9. When
>each finished it left the result in a different shared buffer and marked
>its compression as done. When the next process downstream indicated that
>it needed more data NOW, the best finished compression buffer was
>selected and sent, and the rest of the processes were told to give it
>up.
IIRC, then even gzip started with less than -9 as default.
>Actually, thinking back on when I did that, it wasn't gzip but old
>compress running with 10, 12, 14 and 16 bit compression on a super
>powerful SunOS server with four 68040's (or so). State of the art in
>1990. :-(
Mmmm in 1989 I already had a Sparcstation-1 at home and ths was really fast
compared to a MC680x0. In 1989 we got a SS-2 in the company and Intel needed
development until ~ 1995 to catch the speed of the SS-2.
BTW: in 1992 the compression hype was a program called freeze from Russia/Moscow.
It if better than gzip but a bit worse than bzip2.
J�rg
EMail:[EMAIL PROTECTED] (home) J�rg Schilling D-13353 Berlin
[EMAIL PROTECTED] (uni) If you don't have iso-8859-1
[EMAIL PROTECTED] (work) chars I am J"org Schilling
URL: http://www.fokus.gmd.de/usr/schilling ftp://ftp.fokus.gmd.de/pub/unix
--
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED]
