-openmp flag slowing down my code...

Intel® Fortran Compiler

Build applications that can scale for the future with optimized code designed for Intel® Xeon® and compatible processors.

-openmp flag slowing down my code...

353 Views

Id like to know why the serial version of my program, compiled without -openmp flag, runs faster than the parallel version compiled with -openmp and ran in serial mode with OMP_NUM_THREADS=1?

Details:

CPU Itanium 2 1.3Ghz 3mb L3 cache
Red Hat Linux kernel 2.4.21-9.EL
Fortran Compiler for Itanium-based applications
Version 8.1 Build 20040802 Package ID: l_fc_p_8.1.018

------------------------------------
WITH OPENMP
FFLAGS= -c -tpp2 -O3 -fpp -openmp
LFLAGS= -openmp
export OMP_NUM_THREADS=1
The program ran in 167 seconds

-------------------------------------
WITHOUT OPENMP
FFLAGS= -c -tpp2 -O3 -fpp
LFLAGS=
The program ran in 73 seconds

...

PS.: In attach follow my main parallel routine.

Thanks in advance

Renato N. Elias
COPPE/UFRJ
Rio de Janeiro/Brasil
http://www.nacad.ufrj.br/~rnelias

Link Copied

0 Replies

Community support is provided Monday to Friday. Other contact methods are available here.

Intel does not verify all solutions, including but not limited to any file transfers that may appear in this community. Accordingly, Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

For more complete information about compiler optimizations, see our Optimization Notice.