home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.benchmarks
- Path: sparky!uunet!think.com!enterpoop.mit.edu!bloom-picayune.mit.edu!athena.mit.edu!jfc
- From: jfc@athena.mit.edu (John F Carr)
- Subject: Re: Alpha benchmarks vs other
- Message-ID: <1993Jan1.204419.21094@athena.mit.edu>
- Sender: news@athena.mit.edu (News system)
- Nntp-Posting-Host: achates.mit.edu
- Organization: Massachusetts Institute of Technology
- References: <1993Jan1.170625.20690@zooid.guild.org>
- Date: Fri, 1 Jan 1993 20:44:19 GMT
- Lines: 15
-
- In article <1993Jan1.170625.20690@zooid.guild.org>
- kovarski@zooid.guild.org (Mark Kovarski) writes:
-
- >According to the July issue of "IEEE Spectrum," Digital's Alpha running at
- >200 MHz produces 400 MIPS peak or 200 Mflops. IBM's RIOS (32-Bit) at 50 MHz
- >produces 200 MIPS or 100 Mflops. I don't know why they include MIPS since
- >there are a number of manufacturers who do not use this cathegory any more
-
- Note that these are peak native MIPS, not the VAX MIPS which the dhrystone
- benchmark reports. The latter does have some use (it is reasonably well
- correlated with performance on real integer applications, though not as well
- as SPEC), the former has almost none.
-
- --
- John Carr (jfc@athena.mit.edu)
-