Well said !.
Ravi
On Sun, 28 Mar 1999, Jaehoon Seol wrote:
>
> When I did some testing on the performance of some of the blas routines on
> IBM RISC 6K, the code written in F77 was always faster than the same
> version of the routine written in C. If I remember correctly, the
> performance of the C code was about 70% to 85% of the F77 routines
> depending on which compiler options we use and which compiler we use.
>
> But what I am wondering is how seriously does the performance issue affect
> your project? If you are core library developer, I think it may be a
> serious issue. But if your project is not of such a kind, is the
> performance of a single computer language such a serious problem? In most
> of the cases I find myself combining two or three different kinds of
> languages. In such a case, I spend a lot more time thinking some other
> issues than the performance. So, I think it is a reasonable question to
> ask how seriously sensitive is your project to the performance before we
> discuss which language is faster.
>
>
> -----------------------------------------------------------
> Jaehoon,Seol e-mail : [log in to unmask]
> www : http://www.math.uiowa.edu/~seol
> One good thought may be worth thousands of times on
> the computer
> -----------------------------------------------------------
>
>
> On Mon, 29 Mar 1999, David Annetts wrote:
>
> > Hi Harry,
> >
> > >One of my colleagues has bid a project proposing to convert some Fortran 77
> > >code to C++ claiming it will run faster. I dispute this but do not have hard
> > >facts at hand. Can someone point to a web site with comparison benchmarks?
> > >Or, tell me about personal experience? A Fortran to C comparison would
> > also be
> > > useful.
> >
> > >From memory, Haney published such a comparison between F90, C++ and F77 a
> > couple of years ago in Computers In Physics. F77 compilers produced the
> > fastest-executing code. However, several of his tests showed C++ quicker
> > than F90. A search of their back issues should uncover this article.
> >
> > For web sites, you might try and sarch for Veldhuizen's (sp?) at the
> > University of Waterloo. He claims quite rapid execution for his Blitz
> > library/templates.
> >
> > Regards,
> >
> > Dave.
> > ==================================================================
> > David Annetts _____________
> > http://www.ocs.mq.edu.au/~dannetts/ |C R C A M E T|
> > |-------------|
> > |_____ |
> > CRC for Australian Mineral |````` \ |
> > Exploration Technologies |`````/$\ |
> > Earth & Planetary Sciences |````/$$$\____|
> > Macquarie University, NSW 2109 |```/$$$/.....|
> > AUSTRALIA |``/$$$/......|
> > phone: +(1-61-2) 9850 9280, fax (1-61-2) 9850 8366 -------------
> > ==================================================================
> >
>
>
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|