home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!gumby!destroyer!cs.ubc.ca!jonathan
- From: jonathan@geop.ubc.ca (Jonathan Thornburg)
- Newsgroups: comp.arch
- Subject: alpha performance for IEEE vs DEC FP (was: Re: More Alpha AXP Performance Numbers)
- Date: 11 Nov 1992 00:50:02 GMT
- Organization: U of BC Astronomy + U of Texas at Austin Physics / Relativity
- Lines: 14
- Sender: Jonathan Thornburg <jonathan@geop.ubc.ca>
- Message-ID: <1dplbqINNg1t@cs.ubc.ca>
- References: <1992Nov10.204139.5148@ryn.mro4.dec.com>
- NNTP-Posting-Host: rubis.astro.ubc.ca
- Summary: how does alpha FP performance depend on IEEE vs DEC FP?
- Keywords: alpha performance benchmark floating point SPEC FP IEEE DEC
-
- In article <1992Nov10.204139.5148@ryn.mro4.dec.com>
- bhandarkar@wrksys.enet.dec.com (Dileep Bhandarkar) writes:
- [ very nice table of Alpha benchmark data ]
-
- I presume these are for VAX format floating point? More generally,
- it would be interesting to see how these numbers vary for VAX vs IEEE
- formats, single vs double precision, and what the penalties are for
- turning on precise exceptions and/or full IEEE denormalized support.
-
- - Jonathan Thornburg
- <jonathan@geop.ubc.ca> through mid-November 92, then
- <jonathan@einstein.ph.utexas.edu> or <jonathan@hermes.chpc.utexas.edu>
- [for a few more months] UBC / {Geophysics & Astronomy, Physics}
- [then through Aug/92] U of Texas at Austin / Physics / Center for Relativity
-