Scheduling constrained dynamic applications on clusters
SC '99 Proceedings of the 1999 ACM/IEEE conference on Supercomputing
An Open Distributed Shared Memory System
HPCN Europe 2001 Proceedings of the 9th International Conference on High-Performance Computing and Networking
Stampede: A Programming System for Emerging Scalable Interactive Multimedia Applications
LCPC '98 Proceedings of the 11th International Workshop on Languages and Compilers for Parallel Computing
Consistency and event ordering in the shared regions model
CASCON '93 Proceedings of the 1993 conference of the Centre for Advanced Studies on Collaborative research: distributed computing - Volume 2
ParADE: An OpenMP Programming Environment for SMP Cluster Systems
Proceedings of the 2003 ACM/IEEE conference on Supercomputing
Overcoming performance bottlenecks in using OpenMP on SMP clusters
Parallel Computing
Application-specific thread schedulers for distributed applications
Concurrency and Computation: Practice & Experience
Proceedings of the 6th ACM International Conference on Distributed Event-Based Systems
Hi-index | 0.00 |
This paper describes the motivation, design and performance of Midway, a programming system for a distributed shared memory multicomputer (DSM) such as an ATM-based cluster, a CM-5, or a Paragon. Midway supports a new memory consistency model called entry consistency. Entry consistency guarantees that shared data becomes consistent at a processor when the processor acquires a synchronization object known to guard the data. Entry consistency is weaker than other models described in the literature, such as processor consistency and release consistency, but it makes possible higher performance implementations of the underlying consistency protocols. Midway programs are written in C, and the association between synchronization objects and data must be made with explicit annotations. As a result, pure entry consistent programs can require more annotations than programs written to other models. In addition to entry consistency, Midway also supports the stronger release consistent and processor consistent models at the granularity of individual data items. Consequently, the programmer can tradeoff potentially reduced performance for the additional programming complexity required to write an entry consistent parallel program.