home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!ogicse!flop.ENGR.ORST.EDU!rutgers!cbmvax!cbmehq!cbmger!peterk
- From: peterk@cbmger.de.so.commodore.com (Dr Peter Kittel Germany)
- Newsgroups: comp.sys.amiga.misc
- Subject: Re: 32bit versions of wb3 ??
- Message-ID: <10605@cbmger.de.so.commodore.com>
- Date: 26 Jan 93 13:36:03 GMT
- Article-I.D.: cbmger.10605
- References: <1jmnp8INNfan@mercury.kingston.ac.uk> <jmarin.727691754@messi.uku.fi> <C1F5n9.708@dcs.ed.ac.uk>
- Reply-To: peterk@cbmger.de.so.commodore.com (Dr Peter Kittel Germany)
- Organization: Commodore Germany
- Lines: 27
-
- In article <C1F5n9.708@dcs.ed.ac.uk> dcc@dcs.ed.ac.uk (David Crooke) writes:
- >In article <jmarin.727691754@messi.uku.fi>, jmarin@messi.uku.fi (Jukka Marin) writes:
- >
- >> 68020 and higher add several new addressing modes and a few new instructions
- >> but they don't really help that much.
- >
- >I found quite a difference with the PC-optimised version of Dhrystone, compiling it
- >with -m68000 and -m68020 under older versions of GCC:
- >
- > Compiler Target Speed
- >
- > Lattice 68000 ~5500
- > GCC " ~7000
- > GCC 68020 ~7800
- >
- >This probably doen't apply in general cases though, and I find the
- >compatibility a more important issue.
-
- Well, you see a ca. 11 % speed increase here. But the whole topic of
- "32-bit optimization" stems from PCs where one is accustomed to
- ca. 100 % speed increase by 32-bit optimization. Taking this in the
- comparison shows that also the 68000 is already "very" 32-bit'ish.
-
- --
- Best regards, Dr. Peter Kittel // E-Mail to \\ Only my personal opinions...
- Commodore Frankfurt, Germany \X/ {uunet|pyramid|rutgers}!cbmvax!cbmger!peterk
- Wer's nicht kann, soll's bleiben klopfen oder Steine lassen!
-