Myrinet: a gigabit-per-second local area network

Boden, N.J.; Cohen, Danny; Felderman, Robert E.; Kulawik, Alan E.; Seitz, Charles L.; Seizovic, Jakov N.; Su, Wen-King

doi:10.1109/40.342015

Cited by 1,364 publications

(657 citation statements)

References 5 publications

Supporting

Mentioning

642

Contrasting

Unclassified

Order By: Relevance

“…In the recent years, the bandwidth of these networks has been increased by two orders of magnitude [6,18,29], which has greatly narrowed the performance gap between them and the dedicated networks used in commercial storage systems, such as the fiber channels. The significant improvement in network bandwidth offers an appealing opportunity to provide cost-effective highperformance storage services by aggregating the capacity and bandwidth of all commodity disks that already exist as an integral part of each node in a typical cluster.…”

Section: Introductionmentioning

confidence: 99%

CEFT: A cost-effective, fault-tolerant parallel virtual file system

Zhu

Jiang

2006

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

The vulnerability of computer nodes due to component failures is a critical issue for cluster-based file systems. This paper studies the development and deployment of mirroring in cluster-based parallel virtual file systems to provide fault tolerance and analyzes the tradeoffs between the performance and the reliability in the mirroring scheme. It presents the design and implementation of CEFT, a scalable RAID-10 style file system based on PVFS, and proposes four novel mirroring protocols depending on whether the mirroring operations are server-driven or client-driven, whether they are asynchronous or synchronous. The comparisons of their write performances, measured in a real cluster, and their reliability and availability, obtained through analytical modeling, show that these protocols strike different tradeoffs between the reliability and performance. Protocols with higher peak write performance are less reliable than those with lower peak write performance, and vice versa. A hybrid protocol is proposed to optimize this tradeoff.

show abstract

Section: Introductionmentioning

confidence: 99%

CEFT: A cost-effective, fault-tolerant parallel virtual file system

Zhu

Jiang

2006

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

show abstract

“…This section considers overall performance of these processor architectures in the context of a programmable network interface that is similar to the high-speed Myrinet [4] managed by an operating system, called SPINE, designed to enable application specific software to process messages as they stream through the system [6].…”

Section: Operating System Overheadmentioning

confidence: 99%

Characterizing processor architectures for programmable network interfaces

Crowley

Fluczynski

Baer

et al. 2014

25th Anniversary International Conference on Supercomputing Anniversary Volume -

View full text Add to dashboard Cite

The rapid advancements of networking technology have boosted potential bandwidth to the point that the cabling is no longer the bottleneck. Rather, the bottlenecks lie at the crossing points, the nodes of the network, where data traffic is intercepted or forwarded. As a result, there has been tremendous interest in speeding those nodes, making the equipment run faster by means of specialized chips to handle data trafficking. The Network Processor is the blanket name thrown over such chips in their varied forms. To date, no performance data exist to aid in the decision of what processor architecture to use in next generation network processor. Our goal is to remedy this situation. In this study, we characterize both the application workloads that network processors need to support as well as emerging applications that we anticipate may be supported in the future. Then, we consider the performance of three sample benchmarks drawn from these workloads on several state-of-the-art processor architectures, including: an aggressive, out-of-order, speculative super-scalar processor, a fine-grained multithreaded processor, a single chip multiprocessor, and a simultaneous multithreaded processor (SMT). The network interface environment is simulated in detail, and our results indicate that SMT is the architecture best suited to this environment.

show abstract

“…In this work, we have used a¯ow control protocol based on control¯its. In particular, we have used the Stop and Go protocol, very much like in Myrinet networks [6]. The bu er size has been accurately calculated in order to avoid the loss of¯its or the appearance of bubbles in the message pipeline.…”

Section: Implementation Detailsmentioning

confidence: 99%

Dynamic reconfiguration of node location in wormhole networks

Sánchez

García

2000

Journal of Systems Architecture

View full text Add to dashboard Cite

Several techniques have been developed to increase the performance of parallel computers. Recon®gurable networks can be used as an alternative to increase the performance. Network recon®guration can be carried out in di erent ways. Our research has focused on distributed memory systems with dynamic recon®guration of node location. Brie¯y, this technique consists of positioning the processors in the network depending on the existing communication pattern among them, to suit the requirements of each computation.In this article, we present a dynamic recon®guration technique for wormhole networks. We have used both a crossbar and a multistage interconnection network to implement a recon®gurable logical two-dimensional (2-D) torus topology. The recon®guration mechanism is based on a distributed recon®guration algorithm. The algorithm is based on a cost function that requires only local information. We discuss recon®guration features and adjust the di erent parameters of the recon®guration algorithm. We have also studied the deadlock problem in recon®gurable wormhole networks, and give details of our solution. Finally, we have evaluated the performance of this technique under several workloads. Ó

show abstract

Myrinet: a gigabit-per-second local area network

Cited by 1,364 publications

References 5 publications

CEFT: A cost-effective, fault-tolerant parallel virtual file system

CEFT: A cost-effective, fault-tolerant parallel virtual file system

Characterizing processor architectures for programmable network interfaces

Dynamic reconfiguration of node location in wormhole networks

Contact Info

Product

Resources

About