This paper proposes a dynamic shared-memory packet buffer management algorithm for a protocol processor in a network terminal. The protocol processor is located in a network interface card (NIC). In general, two types of packet buffer management algorithms, static and dynamic, can be used in a NIC; the dynamic buffer management algorithms work better than the static ones for reducing the packet...

We propose the concept of cognitive networking for large-scale wireless systems, which opportunistically utilises network resources including both spectrum bandwidth and radio availability. Both types of resources cannot be predetermined in large-scale wireless systems, due to various reasons such as interferences and dynamic traffic load. The proposed technology not only establishes dynamic wi...

Interconnection networks consist of a set of switches interconnected by point-to-point links, and hosts linked to those switches through a network interface card. These networks are becoming increasingly popular as a cost-effective alternative to parallel computers. One of the most wellknown example is the Myrinet network. These networks use techniques and incorporate components that have been ...

Computer interfaces provide an environment that allows for multiple objectively optimal solutions but individuals will, over time, use a smaller number of subjectively optimal solutions, developed as habits that have been formed and tuned by repetition. Designing an interface agent to provide assistance in this environment thus requires not only knowledge of the objectively optimal solutions, b...

We believe that designing a new network protocol stack whether for conventional communications or for perceptual time multimedia applications should be based on new concepts that suit the specific goals. Our aim is to build a platform for multimedia applications. It has hence to consider suitable concepts that will hopefully lead to an optimal design. The Multimedia platform (PRISM) design had ...

Parallel programs written using the standard Message Passing Interface (MPI) frequently depend upon the ability to efficiently execute collective operations. MPI_Scan is a collective operation defined in MPI that implements parallel prefix scan which is very useful primitive operation in several parallel applications. This operation can be very time consuming. In this paper, we explore the use ...

We explore parallel fiber-optics and single-chip CMOS interface solutions to support broadband multimedia applications in a small workgroup environment. Initial implementation of a network interface card used in our testbed of Intel Pentium-based PCs is described. Feasibility of a CMOS bridge to parallel optics is demonstrated using an adapter chip implemented in 0.5 μm CMOS technology for a po...

The CoABS Grid integrates heterogeneous agent-based systems, object -based applications, and legacy systems. The CoABS Grid does not mandate the network protocol used to deliver messages to an agent or the agent communication language. A CoABS Grid agent registers a proxy object supporting a well-known message-delivery interface in a lookup service. Default proxy implementations are provided th...

ties and consequences in the context of designing a network AN INTERFACE ARCHITECTURE FOR A LOW-LATENCY NETWORK OF WORKSTATIONS USING 10 GBIT/S SWITCHED LAN TECHNOLOGY A network of workstations, NOW, based on standard busbased multiprocessor nodes, interconnected by standard LAN technology, may be a very cost effective alternative to current large, tightly coupled systems with dedicated interna...

Previous results on traf£c shaping on Switched Ethernet technology demonstrate its practicability and effectiveness for hard real-time communication [8]. The application-toapplication delays on a 5-node network were reported to be less than a millisecond with both Fast Ethernet and Gigabit Ethernet technology with a link utilization of 93% and 49%. In this paper we describe directions of resear...