A 10-Gb/s (1.25 Gb/s×8)4×2 0.25-μm CMOS/SIMOX ATM switch based on scalable distributed arbitration

2003

IEEE Commun. Lett.

Self Cite

Abstract-Combined input-crosspoint buffered switches are an alternative to relax arbitration timing and to provide highperformance switching for packet switches with high-speed ports. It has been shown that these switches, with one-cell crosspoint buffer and round-robin arbitration at input and output ports, provide 100% throughput under uniform traffic. However, under admissible traffic patterns with non-uniform distributions, only weight-based selection schemes are reported to provide high throughput. In this paper, we propose a round-robin based arbitration scheme for a combined input-crosspoint buffered packet switch that provides nearly 100% throughput for several admissible traffic patterns, including uniform and unbalanced traffic, using one-cell crosspoint buffers. The presented scheme uses adaptable-size frames, so that the frame size adapts to the traffic pattern.Index Terms-crosspoint-buffered switch, packet scheduling arbitration, virtual output queue, credit-based flow control, adaptable-size frame.

Section: Introductionmentioning

confidence: 99%

Round-robin selection with adaptable-size frame in a combined input-crosspoint buffered switch

2003

IEEE Commun. Lett.

Self Cite

“…An example of the single-stage switch architectures is a crossbar switch. There are many studies on developing crossbar-based high-speed switches [1], [3], [4], [5], [6]. Although this crossbar-based approach is effective up to a certain switch size, the number of the switching elements is proportional to the square of the number of switch ports.…”

Section: Introductionmentioning

confidence: 99%

PCRRD: a pipeline-based concurrent round-robin dispatching scheme for Clos-network switches

2002 IEEE International Conference on Communications. Conference Proceedings. ICC 2002 (Cat. No.02CH37333)

Chao

Self Cite

Abstract-This paper proposes a pipeline-based concurrent round-robin dispatching scheme, called PCRRD, for Clos-network switches. Our previously proposed concurrent round-robin dispatching (CRRD) scheme provides 100% throughput under uniform traffic by using simple round-robin arbiters, but it has the strict timing constraint that the dispatching scheduling has to be completed within one cell time slot. This is a bottleneck in building high-performance switching systems. To relax the strict timing constraint of CRRD, we propose to use more than one scheduler engine, up to È , so called subschedulers. Each subscheduler is allowed to take more than one time slot for dispatching. Every time slot, one out of È subschedulers provides the dispatching result. The subschedulers adopt our original CRRD algorithm. We show that PCRRD preserves 100% throughput under uniform traffic of our original CRRD algorithm, while ensuring the cell-sequence order. Since the constraint of the scheduling timing is dramatically relaxed, it is suitable for high-performance switching systems even when the switch size increases and a port speed is high (e.g., 40 Gbit/s).

“…There are various types of buffering strategies in switch architectures: input buffering, output buffering, or crosspoint buffering [8], [9], [13]. Input buffering is a cost-effective approach for high-speed switches.…”

Section: Introductionmentioning

confidence: 99%

PMM: a pipelined maximal-sized matching scheduling approach for input-buffered switches

GLOBECOM'01. IEEE Global Telecommunications Conference (Cat. No.01CH37270)

Chao

Self Cite

This paper proposes an innovative Pipeline-based Maximal-sized Matching scheduling approach, called PMM, for input-buffered switches. It dramatically relaxes the timing constraint for arbitration with a maximal matching scheme. In the PMM approach, arbitration operates in a pipelined manner. Each subscheduler is allowed to take more than one time slot for its matching. Every time slot, one of them provides the matching result. The subscheduler can adopt a pre-existing efficient maximal matching algorithm such as iSLIP and DRRM. PMM maximizes the efficiency of the adopted arbitration scheme by allowing sufficient time for a number of iterations. We show that PMM preserves 100% throughput under uniform traffic and fairness for best-effort traffic as the pre-existing algorithm does.