Abstract
In this paper we present ToCL a thread oriented communication library specially designed to fully exploit multithreading in a multi-networked cluster environment. ToCL provides a basic set of primitives to handle zero-copy message passing between application threads spread among cluster nodes. Large messages are fragmented and sent to remote threads as single messages using multiple low-level communication subsystems. The current implementation supports both Myrinet through GM and Gigabit Ethernet through VIA but we plan to extend it to other communication subsystems.
Chapter PDF
Similar content being viewed by others
References
A. Alves, A. Pina, J. Exposto, and J. Rufino. Scalable Multithreading in a Low Latency Myrinet Cluster. In VECPAR’02, 2002.
R. Bhoedjang, T. Ruhl, and H. E. Bal. LFC: A Communication Substrate for Myrinet. In 4th Conf. of the Advanced School for Computing and Imaging, 1998.
R. Bhoedjang, T. Ruhl, R. Hofman, K. Langendoen, and H. Bal. Panda: A Portable Platform to Support Parallel Programming Languages. In SEDMS IV, 1993.
L. Bougé, J. Méhaut, and R. Namyst. Madeleine: Efficient and Portable Communication Interface for RPC-based Multithread Environments. In PACT’98, 1998.
Y. Chen, X. Wang, Z. Jiao, J. Xie, Z. Du, and S. Li. MyVIA: A Design and Implementation of the High Performance Virtual Interface Architecture. In IEEE Int. Conference on Cluster Computing, 2002.
Compaq Computer Corp., Intel Corporationnand & Microsoft Corporation. Virtual Interface Architecture Specification, 1997.
S. Fitzgerald, I. Foster, C. Kesselman, G. von Laszewski, W. Smith, and S. Tuecke. A Directory Service for Configuring High-Performance Distributed Computations. In 6th Int. Symposium on High Performance Distributed Computing, 1997.
A. Geist, A. Beguelin, J. Dongarra, W. Jiang, R. Manchek, and V. Sunderam. PVM: Parallel Virtual Machine. A User’s Guide and Tutorial for Networked Parallel Computing. Scientific and Engineering Computation. MIT Pres, 1994.
P. Geoffray, L. Prylli, and B. Tourancheau. BIP-SMP: High Performance Message Passing over a Cluster of Commodity SMPs. In SC’99, 1999.
Hansen, J. & Jul, E. Latency Reduction using a Polling Scheduler. In Second Workshop on Cluster-Based Computing, pages 27–31. ACM, 2000.
Langendoen, K., Romein, J., Bhoedjang, R. & Bal, H. Integrating Polling, Interrupts, and Thread Management. In 6th Symp. on the Frontiers of Massively Parallel Computing, 1996.
Myricom. The GM Message Passing System, 2000.
R. Namyst and J. Méhaut. PM2: Parallel Multithreaded Machine. A computing environment for distributed architectures. In ParCo’95, 1995.
National Energy Research Scientific Comp. Center. M-VIA: A High Performance Modular VIA for Linux. http://www.nersc.gov/research/FTG/via/index, 2002.
S. Pakin, M. Lauria, and A. Chien. High Performance Messaging on Workstations: Illinois Fast Messages (FM) for Myrinet. In Supercomputing 95, 1995.
M. Snir, S. Otto, S. Huss-Lederman, D. Walker, and J. Dongarra. MPI-The Complete Reference. Scientific and Engineering Computation. MIT Pres, 1998.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Alves, A., Pina, A., Exposto, J., Rufino, J. (2003). ToCL: A Thread Oriented Communication Library to Interface VIA and GM Protocols. In: Sloot, P.M.A., Abramson, D., Bogdanov, A.V., Gorbachev, Y.E., Dongarra, J.J., Zomaya, A.Y. (eds) Computational Science — ICCS 2003. ICCS 2003. Lecture Notes in Computer Science, vol 2658. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44862-4_110
Download citation
DOI: https://doi.org/10.1007/3-540-44862-4_110
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40195-7
Online ISBN: 978-3-540-44862-4
eBook Packages: Springer Book Archive