home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.parallel
- Path: sparky!uunet!gatech!hubcap!fpst
- From: janowsky@boltzmann.rutgers.edu (Steven Janowsky)
- Subject: Re: CM-2 Performance?
- Message-ID: <1992Nov23.125741.9028@hubcap.clemson.edu>
- Summary: CM-2 Integer Performance
- Sender: fpst@hubcap.clemson.edu (Steve Stevenson)
- Organization: Rutgers Univ., New Brunswick, N.J.
- References: <1992Nov19.151504.9426@murdoch.acc.Virginia.EDU> <1992Nov20.125934.25800@hubcap.clemson.edu>
- Date: 22 Nov 92 17:56:54 GMT
- Approved: parallel@hubcap.clemson.edu
- Lines: 19
-
-
-
-
- Here is what TMC claimed (a couple of years ago). All is for the Paris
- model.
-
- Numbers are for a 64K CM2. Divide by the appropriate factor if fewer
- are available
-
- Bits Mips for Add Mips for Move
-
- 64 1500 2000
- 32 2500 3000
- 16 3300 3800
- 8 4000 4500
-
-
- SJ
-
-