Related articles |
---|
90/10 rule... source? jens.troeger@light-speed.de (Jens Troeger) (2004-01-09) |
Re: 90/10 rule... source? nmm1@cus.cam.ac.uk (2004-01-12) |
Re: 90/10 rule... source? derek@knosof.co.uk (Derek M Jones) (2004-01-12) |
Re: 90/10 rule... source? nmm1@cus.cam.ac.uk (2004-01-16) |
Re: 90/10 rule... source? mkent@acm.org (Mike Kent) (2004-01-16) |
Re: 90/10 rule... source? derek@knosof.co.uk (Derek M Jones) (2004-01-17) |
Re: 90/10 rule... source? jcownie@etnus.com (James Cownie) (2004-01-22) |
Re: 90/10 rule... source? vidar@hokstad.name (2004-01-22) |
Re: 90/10 rule... source? derek@knosof.co.uk (Derek M Jones) (2004-01-31) |
From: | Derek M Jones <derek@knosof.co.uk> |
Newsgroups: | comp.compilers |
Date: | 12 Jan 2004 13:27:20 -0500 |
Organization: | Knowledge Software |
References: | 04-01-038 |
Keywords: | optimize, practice, comment |
Posted-Date: | 12 Jan 2004 13:27:20 EST |
Jens,
> I am looking for a (the) original paper on the 90/10 rule of program
> execution. So far I found this reference
I think the 90/10 rule might qualify as an urban legend.
Example 8 of Knuth's paper quotes a 90% figure, but many of the
other examples are around the 50% mark (a few 70%'s).
> @ARTICLE{Knuth71,
> AUTHOR = "Donald E. Knuth",
> TITLE = "An Empirical Study of {FORTRAN} Programs",
> JOURNAL = "Software---Practice and Experience",
> VOLUME = 1,
> PAGES = {105--133},
> YEAR = 1971
> }
>
> but I couldn't get my hands on a copy of that paper. Is it the one I
> am looking for?
The following paper found 88% of the time being spent in 20% of
the code.
@InProceedings{Suresh_03,
author = "Dinesh C. Suresh and Satya R. Mohanty and Walid A.
Najjar and Laxmi N. Bhuyan and Frank Vahid",
title = "Loop Level Analysis of Security and Network
Applications",
booktitle = "Workshop on Computer Architecture Evaluation using
Commercial Workloads ({CAECW}-03)",
pages = "???",
month = feb,
year = "2003",
}
While I have been able to find plenty of papers anlysing loops, I have
not been able to find any that analyse a range of substantial programs
(there are a few dealing with small embedded application) and come to
the conclusion that 90% of the time is spent in 10% of the code.
The following analyses found that most of the time was not even
spent in loops!
@InProceedings{Ramirez_99,
author = "Alex Ram\'{\i}rez and Josep-L. Larriba-Pey and Carlos
Navarro and Xavi Serrano and Josep Torrellas and Mateo
Valero",
booktitle = "{IEEE} International Conference on Parallel Processing
(ICPP99)",
title = "Code Reordering of Decision Support Systems for
Optimized Instruction Fetch",
year = "1999",
}
@Article{Torrellas_98,
author = "Josep Torrellas and Chun Xia and Russell L. Daigle",
title = "Optimizing the Instruction Cache Performance of the
Operating System",
journal = "IEEE Transactions on Computers",
volume = "47",
number = "12",
pages = "1363--1381",
year = "1998",
}
[I think the 90/10 rule comes from databases, where long before there
were computerized files it was well known that in most record systems,
a small set of records got most of the lookups. -John]
Return to the
comp.compilers page.
Search the
comp.compilers archives again.