Performance evaluation of a new routing strategy for irregular networks with source routing
Proceedings of the 14th international conference on Supercomputing
The Impact of Pipelined Channels on k-ary n-Cube Networks
IEEE Transactions on Parallel and Distributed Systems
A First Implementation of In-Transit Buffers on Myrinet GM Software
IPDPS '01 Proceedings of the 15th International Parallel & Distributed Processing Symposium
IPDPS '01 Proceedings of the 15th International Parallel & Distributed Processing Symposium
ISHPC '00 Proceedings of the Third International Symposium on High Performance Computing
A New Methodology to Computer Deadlock-Free Routing Tables for Irregular Networks
CANPC '00 Proceedings of the 4th International Workshop on Network-Based Parallel Computing: Communication, Architecture, and Applications
Fibre Channel Fabrics: Evaluation and Design
HICSS '96 Proceedings of the 29th Hawaii International Conference on System Sciences Volume 1: Software Technology and Architecture
Hi-index | 0.00 |
Clusters of workstations (COWs) are becoming increasingly popular as a cost-effective alternative to parallel computers. In previous papers we presented the in-transit buffer mechanism (ITB) to improve network performance, applying it to COWs with irregular topology and source routing. This mechanism considerably improves the performance of this kind of networks when compared to current source routing algorithms, however it introduces a latency penalty. Moreover, an implementation of this mechanism was performed, showing that the latency overhead of the mechanism may be noticeable, especially for short messages and at low network loads. In this paper, we analyze in detail the latency overhead of ITBs proposing several mechanisms in order to reduce, hide, and remove it. Firstly, we show by simulation the effect of an ITB implementation much slower than the one implemented. Then, we propose three mechanisms that will try to overcome the latency penalty. All the mechanisms are simple and can be easily implemented. Also they are out of the critical path of the ITB packet processing procedure. Results show a very good behavior of the proposed mechanisms, reducing considerably, and even removing the latency overhead.