Re: ELEMENTAL functions and performance
- From: Mark Westwood <markc.westwood@xxxxxxxxx>
- Date: Wed, 30 Jul 2008 04:49:18 -0700 (PDT)
Hi
I'd like to know too -- any chance of you writing some variant codes,
comparing them and posting your results ?
Regards
Mark
On Jul 29, 6:57 pm, deltaquattro <deltaquat...@xxxxxxxxx> wrote:
Hi,
I would like to know if the attribute ELEMENTAL for a function/
subroutine can negatively affect performance or not.
I am going to code a lot of small functions, for things like Jacobi
polynomial evalution, Gauss point generation, etc. etc., to be used in
a "huge" code. I would like the functions to work for scalar as well
as for rank-1 array input/output. I'd prefer to write them as
ELEMENTAL, rather than forcing the user to read/write a scalar into a
rank-1 array of size 1 each time he has to use the subroutine for
scalars.
However, sometimes I heard that some "new" features of the language
may have an hit on performance, because they make optimization more
difficult for the compiler. I don't know if this is the case with
ELEMENTAL, however these functions will be called a lot of times, so
it's not a good idea if they are slow. The code will run on parallel
vectorial supercomputers. According to these informations, what would
you suggest me to do?
Thanks,
Best Regards,
deltaquattro
.
- Prev by Date: Re: Issue from IVF 9.0 to IVF 10.1
- Next by Date: Re: Writing $00-$FF via Fortran
- Previous by thread: Re: ELEMENTAL functions and performance
- Next by thread: Re: ELEMENTAL functions and performance
- Index(es):
Relevant Pages
|