One potentially attractive way to build large-scale shared-memory machines is to use small-scale to medium-scale shared-memory machines as clusters that are interconnected with an off-the-shelf network. To create a shared-memory programming environment across the clusters, it is possible to use a virtual shared-memory software layer. Because of the low latency and high bandwidth of the interconnect available within each cluster, there are clear advantages in making the clusters as large as possible. The critical question then becomes whether the latency and bandwidth of the top-level network and the software system are sufficient to support the communication demands generated by the clusters.To explore these questions, we have built an aggressive kernel implementation of a virtual shared-memory system using SGI multiprocessors and 100Mbyte/sec HIPPI interconnects. The system obtains speedups on 32 processors (four nodes, eight processors per node plus additional reserved protocol processors) that range from 6.9 on the communication-intensive FFT program to 21.6 on Ocean (both from the SPLASH 2 suite). In general, clustering is effective in reducing internode miss rates, but as the cluster size increases, increases in the remote latency, mostly due to increased TLB synchronization cost, offset the advantages. For communication-intensive applications, such as FFT, the overhead of sending out network requests, the limited network bandwidth, and the long network latency prevent the achievement of good performance. Overall, this approach still appears promising, but our results indicate that large low latency networks may be needed to make cluster-based virtual shared-memory machines broadly useful as large-scale shared-memory multiprocessors.

The Xpress Transfer Protocol (XTP) is a lightweight transport protocol with unified internetwork services conforming to OSI (Open Systems Interconnection) layers 3 and 4. The Protocol Engine (PE) is a chip set designed to execute XTP and other protocols in real time. The author provides an overview of both developments. The VLSI strategy is shown, and the main technical issues in configuring an XTP/PE system at 1 Gbit/sec are described.>

A transmitter sends packets over a local area network to a receiver. The receiver has a finite amount of storage capacity for buffering messages. A sliding window protocol is employed to insure all packets are delivered without error in order of arrival. Mean throughput rate and packet delay statistics are studied as a function of model parameters. Simulation data are presented.

A transmitter breaks a message up into packets and transmits the packets to a receiver over a single virtual circuit within a local area network. The receiver has a finite amount of storage capacity for buffering messages. A sliding window protocol turns the transmitter on and off to ensure there is always storage room in the receiver for packets. Mean throughput rate and delay statistics are studied as a function of model parameters.

A Network Interface Program (NIP) is that part of an operating system which interfaces with similar entities in a network. Normally, the NIP is a collection of software routines which implement interprocess communication, interhost protocols, data flow controls, and other necessary executive functions. This paper discusses the organization of the NIP currently being used with the Unix operating system on the ARPA network. The Network Unix system is noteworthy because of the natural way that network and local functions are merged. As a result the network appears as a logical extension to the local system - from the point of view of both the interactive terminal and user program.