Jakov N. Seizovic

Learn More
Myrinet is a new type of local-area network (LAN) based on the technology used for packet communication and switching within "massivelyparallel processors" (MPPs). Think of Myrinet as an MPP message-passing network that can span campus dimensions, rather than as a wide-area telecommunications network that is operating in close quarters. The technical steps(More)
20 provide the lowest latency and do not require host adapter buuer allocation. However, they require various degrees of complexity in crossbar switch implementation, in order to process source multicast addresses and prevent new types of deadlocks caused by the simultaneous use of multiple paths. None of the proposed schemes can be directly implemented in(More)
Current ber optic networks e ectively provide local connectivity among end user computing devices, and can serve as backbone fabric between LAN subnets across campus and metropolitan areas. However, combining both stream service (in which ATM excels) and low latency datagram service (in which cluster networks like Myrinet and POLO excel) has been di cult to(More)
During the period following the completion of the Cosmic Cube experiment [1], and while commercial descendants of this first-generation multicomputer (message-passing concurrent computer) were spreading through a community that includes many of the attendees of this conference, members of our research group were developing a set of ideas about the physical(More)
1. Overview and Summary 1.1 Scope of this Report This document is a summary of the research activities and results for the seven-month period, 1 April 1987 to 31 October 1987, under the Defense Advanced Research Project Agency (DARPA) Submicron Systems Architecture Project. Technical reports covering parts of the project in detail are listed following these(More)
\EEcient implementation of distributed barrier synchronization in hypercube multicomputers. \EEcient implementation of barrier synchronization in wormhole-routed hypercube multicomputers. 17 Current research projects address the implementation of higher-level SPMD operations and parallel eigensolvers based on the algorithms presented in this paper.(More)
Pipeline synchronization is a simple, low-cost, highbandwidth, high-reliability solution to interfaces between synchronous and asynchronous systems, or between synchronous systems operating from different clocks. The technique can sustain maximum communication bandwidth while achieving an arbitrarily low, nonzero probability of synchronization failure, Pf,(More)
  • 1