Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!utgpu!water!watnot!watmath!clyde!cbatt!ihnp4!ptsfa!lll-lcc!styx!ames!sri-spam!rutgers!mit-eddie!bacchus!husc6!endor!reiter
From: reiter@endor.UUCP
Newsgroups: comp.arch
Subject: Re: 01/31/87 Dhrystone Results and Source
Message-ID: <1224@husc6.UUCP>
Date: Fri, 13-Feb-87 12:38:53 EST
Article-I.D.: husc6.1224
Posted: Fri Feb 13 12:38:53 1987
Date-Received: Sat, 14-Feb-87 19:39:26 EST
References: <2348@homxb.UUCP> <15203@onfcanim.UUCP>
Sender: news@husc6.UUCP
Reply-To: reiter@harvard.UUCP (Ehud Reiter)
Organization: Aiken Computation Lab Harvard, Cambridge, MA
Lines: 16
Keywords: Benchmark, performance measurement

Has anyone actually tried to evaluate the Dhrystone (and other benchmarks)
by seeing how well it predicts performance on real applications?  It would
seem straightforward to take ten random applications running on specific test
data, measure their performance on some target machine/compiler combinations,
and statistically analyze how much of the peformance differences had been
predicted by the Dhrystone figures.

The debate on flaws of the Dhrystone is quite interesting, but it would be nice
to have some real data on how good or bad the Dhrystone was.  I'm not even sure
that a good benchmark is possible in principle - that is, I wonder whether
it is possible to come up with a single number which can predict
(with any reasonable accuracy) performance on a range of different
applications.

					Ehud Reiter
					reiter@harvard	(ARPA,UUCP,BITNET)