Parallel performance of the XL Fortran random{_}number intrinsic function on Seaborg
The Fortran intrinsic function random{_}number is shown to perform very poorly when simultaneously called from 16 tasks per node on NERSC's IBM SP Seaborg in its default runtime configuration. Setting the runtime option intrinthds=16 improves runtime performance significantly and gives good results for all possible numbers of tasks per node. It is speculated that the cause of the problem is the creation of an excessive number of threads in the default configuration. It is noted that these threads appear to be created by default, without specifying a ''thread-safe'' compiler or other user interaction.
- Research Organization:
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
- Sponsoring Organization:
- USDOE Director. Office of Science. Computational and Technology Research (US)
- DOE Contract Number:
- AC03-76SF00098
- OSTI ID:
- 817243
- Report Number(s):
- LBNL-53531; R&D Project: KX0510; TRN: US200321%%337
- Resource Relation:
- Other Information: PBD: 30 Jul 2003
- Country of Publication:
- United States
- Language:
- English
Similar Records
CLOMP v1.5
The Nexus task-parallel runtime system
Data Locality Enhancement of Dynamic Simulations for Exascale Computing (Final Report)
Technical Report
·
Thu Feb 01 00:00:00 EST 2018
·
OSTI ID:817243
The Nexus task-parallel runtime system
Conference
·
Sat Dec 31 00:00:00 EST 1994
·
OSTI ID:817243
Data Locality Enhancement of Dynamic Simulations for Exascale Computing (Final Report)
Technical Report
·
Fri Nov 29 00:00:00 EST 2019
·
OSTI ID:817243