Toward Enhancing OpenMP's Work-Sharing Directives
OpenMP provides a portable programming interface for shared memory parallel computers (SMPs). Although this interface has proven successful for small SMPs, it requires greater flexibility in light of the steadily growing size of individual SMPs and the recent advent of multithreaded chips. In this paper, we describe two application development experiences that exposed these expressivity problems in the current OpenMP specification. We then propose mechanisms to overcome these limitations, including thread subteams and thread topologies. Thus, we identify language features that improve OpenMP application performance on emerging and large-scale platforms while preserving ease of programming.
- Research Organization:
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- W-7405-ENG-48
- OSTI ID:
- 894767
- Report Number(s):
- UCRL-CONF-221478; TRN: US200702%%349
- Resource Relation:
- Journal Volume: 4128; Conference: Presented at: Euro-Par 2006, Dresden, Germany, Aug 29 - Sep 01, 2006
- Country of Publication:
- United States
- Language:
- English
Similar Records
Parallel, Distributed Scripting with Python
An Integrated Performance Visualizer for MPI/OpenMP Programs
A White Paper Prepared for the OpenMP Architectural Review Board on DMPL: An OpenMP DLL Debugging Interface
Conference
·
Fri May 24 00:00:00 EDT 2002
·
OSTI ID:894767
An Integrated Performance Visualizer for MPI/OpenMP Programs
Conference
·
Sun Feb 25 00:00:00 EST 2001
·
OSTI ID:894767
+5 more
A White Paper Prepared for the OpenMP Architectural Review Board on DMPL: An OpenMP DLL Debugging Interface
Technical Report
·
Wed Mar 17 00:00:00 EST 2004
·
OSTI ID:894767
+1 more