We consider crossbar switching networks with base b (that is, constructed from b × b crossbar switches), scale k (that is, with b inputs, b outputs and b links between each consecutive pair of stages) and depth l (that is, with l stages). We assume that the crossbars are interconnected according to the spider-web pattern, whereby two diverging paths reconverge only after at least k stages. We a...

Most of today’s high-speed switches and routers adopt an input-queued crossbar switch architecture. Such a switch needs to compute a matching (crossbar schedule) between the input ports and output ports during each switching cycle (time slot). A key research challenge in designing large (in number of input/output ports N) input-queued crossbar switches is to develop crossbar scheduling algorith...

High-speed operation of free-space optical interconnect for a three-dimensional optoelectronic crossbar switching has been analyzed. System architecture, transmitter and receiver design are presented. The effect of ghost talk caused by the superposition of the delayed reflections of the original signal due to the multiple propagation of the wave between the vertical-cavity surface-emitting lase...

Switches Cheng-Shang Chang Wen-Jyh Chen Hsiang-Yi Huang Dept. of Electrical Engineering National Tsing Hua University Hsinchu 30043 Taiwan, R.O.C. Email: [email protected] fwjchen, [email protected] Abstract| In our previous paper [5], we proposed a scheduling algorithm that is capable of providing rate guarantees for input-bu ered crossbar switches. The algorithm is based on a...

It is well known that crossbar switch has the best performance among the multiprocessor interconnection networks. However expanding this switch so that the performance grows linearly with the number of processing elements (N) is costly and complicated. The size of the switch grows as a function of N. This paper presents an expansion scheme, which keeps the linearity between the performance, the...

* This material is based upon work supported by the National Science Foundation under Grant No. 9875177. Abstract Input buffered switches with Virtual Output Queues (VOQ) are scalable to very high speeds, but require switch matrix scheduling algorithms to achieve high throughput. Existing scheduling algorithms based on parallel requestgrant-accept cycles cannot natively support variable length ...

Crossbar-based switches are commonly used to implement routers with throughputs up to about 1 Tb/s. The advent of work-conserving crossbar scheduling algorithms now makes it possible to engineer systems that perform well, even under extreme traffic conditions. Unfortunately, all the published work-conservation results for crossbar scheduling apply only to systems that switch fixed-length cells,...