Abstract. High speed networks are now providing incredible performances. Software evolution is slow and the old protocol stacks are no longer adequate for these kind of communication speed. When bandwidth increases, the latency should decrease as much in order to keep the system balance. With the current network technology, the main bottleneck is most of the time the software that makes the interface between the hardware and the user. We designed and implemented new protocols of transmission targeted to parallel computing that squeeze the most out of the high speed Myrinet network, without wasting time in system calls or memory copies, giving all the speed to the applications. This design is presented here as well as experimental results that lead to achieve real Gigabit/s throughput and less than 5 s latency on a cluster of PC workstations, with this a ordable network hardware. Moreover, our networking results compare favorably with the expensive parallel computers or ATM LANs. 1

High speed networks are now providing incredible performances. Software evolution is slow and the old protocol stacks are no longer adequate for these kind of communication speed. When throughput increases, the latency should decrease as much in order to keep the system balance. With the current network technology, the main bottleneck is most of the time the software that makes the interface between the hardware and the user. We designed and implemented new protocols of transmission targeted first to parallel computing that squeeze the most out of the high speed Myrinet network, giving all the speed to the applications. A precise modeling of the high speed hardware was necessary to analytically determine the optimal pipelines parameters. This modeling and design is presented here as well as experimental results that lead to achieve real Gigabit/s throughput and less than 5¯s latency with half of the best performance (n 1=2 ) for 4KBytes messages on a cluster of PC workstations with this...

Parallel simulation techniques are promising for reducing the simulation time and for increasing the system size as well. Traditionally executed on state-of-the-art parallel machines, parallel simulation can now benet from the availability of high-performance clusters (HPC) based on commodity hardware. In this paper, we present our experiments with parallel simulations of large-scale communication networks on a Myrinet-based cluster. The model requires high performance communication as a large number of small messages are sent. The speedup results show that HPC can be a serious alternative to parallel machines even for high-demanding communication applications. Keywords: High-speed LANs, Myrinet network, Parallel simulation. 1 Introduction Simulation is nowadays widely used for system prediction and performance analysis tasks. However as the demand for larger and more complex models increases, sequential simulations, i.e. those performed on a single processor, become very time-consum...

Parallel simulation techniques are promising for reducing the simulation time and for increasing the system size as well. Traditionally executed on state-of-the-art parallel machines, parallel simulation can now benet from the availability of high-performance clusters (HPC) based on commodity hardware. In this paper, we present our solutions for ecient parallel simulation of ne-grained communication network models on a Myrinet-based cluster of commodity PC workstations. Since the model requires a large number of small messages to be exchanged, achieving high performance communications is a key point to obtain speedup. Therefore, the paper describes both the high-performance communication layers and the parallel simulation application and takes into account both single-processor and multi-processor components. The results show that HPC with adequate communication software can be a serious alternative to parallel machines even for high-demanding communication applications. 1 ...

High speed networks are now providing incredible performance. Software evolution is slow and the old protocol stacks are no longer adequate for these kind of communication speeds. When bandwidth increases, the latency should decrease as much in order to keep the system balance. With the current network technology, the main bottleneck is most often the software that is the interface between the hardware and the user. We designed and implemented new transmission protocols, targeted to parallel computing, that squeeze the most out of a high speed network (Myrinet in this paper) without wasting time in system calls or memory copies, giving all the speed to the applications. This design is presented here as well as experimental results. We achieve Gigabit/s bandwidth and less than 5s latency on a cluster of PC workstations with inexpensive network hardware. Moreover, our results compare favorably with the expensive parallel computers or ATM LANs. Keywords: High-speed networks, Co...