home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!ogicse!unmvax!cs.sandia.gov!wllarso
- From: wllarso@sandia.gov (William L Larson)
- Newsgroups: comp.benchmarks
- Subject: Amdahl's Law? (was Re: Regression analysis)
- Message-ID: <1992Sep2.141548.10346@cs.sandia.gov>
- Date: 2 Sep 92 14:15:48 GMT
- Article-I.D.: cs.1992Sep2.141548.10346
- References: <1992Aug31.002356.24988@nosc.mil> <Btwo88.4v0@nntp-sc.Intel.COM> <42239@ogicse.ogi.edu>
- Sender: usenet@cs.sandia.gov (Another name for news)
- Distribution: comp.benchmarks
- Organization: Sandia National Laboratories
- Lines: 11
-
- In article <42239@ogicse.ogi.edu> borasky@ogicse.ogi.edu (M. Edward Borasky) writes:
- >It would be nice if SPEC could
- >estimate the appropriate-dimensional Amdahl's Law surfaces for
- >their benchmarks; if they ask me (REAL NICELY) I'll show them how
- >to do it.
- >
- >3. I use non-linear regression to predict supercomputer performance
- >by fitting Amdahl's Law curves to benchmark data.
-
- I may be dense, but what is Amdahl's Law? (Brief descriptions only, there
- is no need for large volumes).
-