openMP + optimisation on ifort9 
Author Message
 openMP + optimisation on ifort9

Hi,

I am trying to familiarise myself with openMP by parallelizing a small explicit
finite-element code. I am using ifort 9 and I am running into a problem if I
use the processor-specific optimisations:

If I use the options

-O3 -ipo -fpp -openmp

my code runs and produces the expected results

However, if I insert either -xN or -axN (on my desktop Intel Xeon), the
executable segfaults.

Strangely enough, when I try something similar on my laptop, with -xB in place
of -xN, it seems to work fine. (Need to double check that when I get home)

Any ideas on why this might be happening? I am posting here instead of in the
Intel Support Forums because I am not sure whether this is a problem with the
compiler or with my code.

Thanks,

Ushnish

--

+1 510 644-1906       www.ce.berkeley.edu/~ubasu



Sat, 09 Aug 2008 07:15:31 GMT  
 
 [ 1 post ] 

 Relevant Pages 

1. compilation with ifort9 aborts with strange message

2. Lisp type list, recursion and tail call optimisation

3. Code Optimisation.

4. smalltalk link optimisation

5. Topspeed driver optimisation

6. Suggestions for optimisation

7. Hand v Compiler optimisation

8. Global optimisation in Forth: example and code.

9. optimisation of combinators

10. Optimisation (Re: Common subexpression...)

11. Help on optimisation - shapes with round corners

12. Optimisation of a model

 

 
Powered by phpBB® Forum Software