Overcoming performance bottlenecks in using OpenMP on SMP clusters

Authors:
Woo-Chul Jeun;Yang-Suk Kee;Soonhoi Ha;Changdon Kee
Affiliations:
Electrical Engineering and Computer Science, Seoul National University, Seoul 151-742, South Korea;Information Sciences Institute, University of Southern California, Marina del Rey, CA 90292, USA;Electrical Engineering and Computer Science, Seoul National University, Seoul 151-742, South Korea;Mechanical and Aerospace Engineering, Seoul National University, Seoul 151-742, South Korea
Venue:
Parallel Computing
Year:
2008

Citing 19
Cited 0

Memory coherence in shared virtual memory systems

ACM Transactions on Computer Systems (TOCS)
Using predictive prefetching to improve World Wide Web latency

ACM SIGCOMM Computer Communication Review
Scope consistency: a bridge between release consistency and entry consistency

Proceedings of the eighth annual ACM symposium on Parallel algorithms and architectures
Parallel programming in OpenMP

Parallel programming in OpenMP
OpenMP for networks of SMPs

Journal of Parallel and Distributed Computing
MPI versus MPI+OpenMP on IBM SP for the NAS benchmarks

Proceedings of the 2000 ACM/IEEE conference on Supercomputing
Compiling Global Name-Space Parallel Loops for Distributed Execution

IEEE Transactions on Parallel and Distributed Systems
Towards OpenMP Execution on Software Distributed Shared Memory Systems

ISHPC '02 Proceedings of the 4th International Symposium on High Performance Computing
Message passing and shared address space parallelism on an SMP cluster

Parallel Computing
Comparative Evaluation of Latency Tolerance Techniques for Software Distributed Shared Memory

HPCA '98 Proceedings of the 4th International Symposium on High-Performance Computer Architecture
Strings: A High-Performance Distributed Shared Memory for Symmetrical Multiprocessor Clusters

HPDC '98 Proceedings of the 7th IEEE International Symposium on High Performance Distributed Computing
The Midway Distributed Shared Memory System

The Midway Distributed Shared Memory System
Home-based shared virtual memory

Home-based shared virtual memory
Optimizing OpenMP programs on software distributed shared memory systems

International Journal of Parallel Programming - Special issue: OpenMP: Experiences and implementations
ParADE: An OpenMP Programming Environment for SMP Cluster Systems

Proceedings of the 2003 ACM/IEEE conference on Supercomputing
Parallel Programming in C with MPI and OpenMP

Parallel Programming in C with MPI and OpenMP
Brazos: a third generation DSM system

NT'97 Proceedings of the USENIX Windows NT Workshop on The USENIX Windows NT Workshop 1997
Implementing an OpenMP execution environment on InfiniBand clusters

IWOMP'05/IWOMP'06 Proceedings of the 2005 and 2006 international conference on OpenMP shared memory parallel programming
Improving performance of OpenMP for SMP clusters through overlapped page migrations

IWOMP'05/IWOMP'06 Proceedings of the 2005 and 2006 international conference on OpenMP shared memory parallel programming

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a new parallel programming environment called ParADE to enable easy, portable, and high-performance computing for SMP clusters. Different from the prior studies, ParADE separates the programming model from the execution model: it enables shared-address-space programming while it realizes hybrid execution of message-passing and shared-address-space. To overcome the poor performance of conventional OpenMP on SDSM (Software Distributed Shared Memory), ParADE implements an intelligent OpenMP translator supporting efficient mutual exclusion and efficient page transmission. The experimental results on a Linux cluster demonstrate that ParADE reduces mutual exclusion overhead and overall execution time.