Packet Routing in Dynamically Changing Networks on Chip
IPDPS '05 Proceedings of the 19th IEEE International Parallel and Distributed Processing Symposium (IPDPS'05) - Workshop 3 - Volume 04
Full-system simulation of distributed memory multicomputers
Cluster Computing
Journal of Parallel and Distributed Computing
CIS'04 Proceedings of the First international conference on Computational and Information Science
Entropy throttling: a physical approach for maximizing packet mobility in interconnection networks
ACSAC'06 Proceedings of the 11th Asia-Pacific conference on Advances in Computer Systems Architecture
A parallel routing algorithm on circulant networks employing the hamiltonian circuit latin square
NPC'05 Proceedings of the 2005 IFIP international conference on Network and Parallel Computing
A parallel routing algorithm on 2-circulant networks employing the hamiltonian circuit latin square
PDCAT'04 Proceedings of the 5th international conference on Parallel and Distributed Computing: applications and Technologies
A parallel routing algorithm on circulant networks employing the Hamiltonian circuit latin square
Information Sciences: an International Journal
A high performance adaptive miss handling architecture for chip multiprocessors
Transactions on High-Performance Embedded Architectures and Compilers IV
Efficient implementation of globally-aware network flow control
Journal of Parallel and Distributed Computing
| Hi-index | 0.00 |
Network performance in tightly-coupled multiprocessors typically degrades rapidly beyond network saturation. Consequently, designers must keep a network below its saturation point by reducing the load on the network. Congestion control via source throttling-a common technique to reduce the network load-prevents new packets from entering the network in the presence of congestion. Unfortunately, prior schemes to implement source throttling either lack vital global information about the network to make the correct decision (whether to throttle or not) or depend on specific network parameters, or communication patterns. This paper presents a global-knowledge-based, self-tuned, congestion control technique that prevents saturation at high loads across different communication patterns for k-ary n-cube networks. Our design is composed of two key components. First, we use global information about a network to obtain a timely estimate of network congestion. We compare this estimate to a threshold value to determine when to throttle packet injection. The second component is a self-tuning mechanism that automatically determines appropriate threshold values based on throughput feedback. A combination of these two techniques provides high performance under heavy load, does not penalize performance under light load, and gracefully adapts to changes in communication patterns.