Re: 90/10 rule... source?

Jens Troeger <jens.troeger@light-speed.de> wrote:
>
>I am looking for a (the) original paper on the 90/10 rule of program
>execution. So far I found this reference
>
>@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?
>
>[That's probably the one you want. It was the first to use the term
>program profiling, and it was big news at the time how much of a
>speedup you could get by rewriting tiny bits of a program if it was
>the right tiny bits. It's reprinted in Knuth's new "Selected Papers
>on Computer Languages", ISBN 1575863820. -John]


Knuth may well have been the first to publish, but it was a well-known
principle decades before that. Probably millennia. I was certainly
using it in the 1960s, and I am a mere newcomer. It may have been big
news to SOME people, but it definitely wasn't this side of the pond.


Similarly, I am pretty sure that the term "program profiling" was in
common use before then. It was certainly a standard technique, and
had been for a long time, though I can't swear to what it was normally
called. I can remember seeing it done in the 1960s, and it was not
regard as worth remarking on.


Knuth invented a hell of a lot, no doubt about it, but his lasting
legacy is that he wrote coherent descriptions of things that had often
only been passed around by word of mouth beforehand. At least one of
the great names of that era isn't widely known because he published
only under duress, and often as second or third name on a paper,
leaving the credit to the people who did the leg-work.




Regards,
Nick Maclaren.

Return to the comp.compilers page.
Search the comp.compilers archives again.