Re-Configurable Parallel Match Evaluators Applied to Scheduling Schemes for Input-Queued Packet Switches

Abstract

The performance of matching schemes for inputqueued (IQ) packet switches is mainly defined by the selection policy adopted. This policy can be aimed to produce a large weight sum for matched input-output pairs, where each inputoutput pair is assigned a weight, or to produce a large match size in the number of matched pairs, giving place to maximum weight matching or maximum size matching, respectively. However, schedulers can only provide a single match in function of the selection (of candidate ports) policy adopted and of the backlogged traffic at the input queues. A parallel match evaluator was recently proposed to provide not one but several match options at the same time. This approach evaluates several predefined and fixed matches and picks the match with the largest size. However, the fixed permutations of the evaluated matches may produce low performance under traffic with nonuniform distributions because of the limited number of choices. This paper proposes to make the parallel match evaluator configurable and two schemes to provide diverse and changeable matches such that the matches (and therefore, the evaluator) become adaptable to the traffic pattern. The proposed schemes were tested under uniform and nonuniform traffic patterns and the results show that these schemes provide high performance, even when scheduling is performed between periods of multiple time slots, or framed intervals. The proposed approach can be used for configuring slow micro-electro-mechanical (MEM) optical switch fabrics.Index Terms-packet switches, maximal weight matching, parallel matching, input-queued switch, iterative matching.

Mathematical Model for Dynamic Pump-Wavelength Selection Switch

“…Packet loss rates under non-uniform traffic were examined using four well-known traffic models: unbalanced [23] [24], power of two (PO2) [25], diagonal [26], and hotspot [27].…”

“…The diagonal traffic [26] is generated using a diagonal probability, d , to represent the traffic from the ith input to jth output, , …”

Towards low-cost high-performance all-optical interconnection networks

“…In this paper we avoid the request-grant overhead and the buffering requirements of that scheme, using static prescheduling that visits connections in a periodic manner. Such scheduling schemes have their roots to time-divisionmultiplexing (TDM) from old-telephony (circuit-switching) networks, and have reappeared recently, in various flavors, in packet-switched networks [ [13].…”