Frame-based matching algorithms for input-queued switches

Bianco, A.; Franceschinis, Mirko; Ghisolfi, S.; Hill, A.M.; Leonardi, E.; Neri, F.; Webb, R.

doi:10.1109/hpsr.2002.1024211

Cited by 42 publications

(33 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we make use of the fairness index defined in [29] to evaluate the fairness performance, let erage value of FI as average fairness index (AFI), which is calculated as the fairness index averaged over all the considered loads of input traffic. The fairness index results under log-diagonal traffic and asymmetric traffic [31] for load ρ (90%-100%) are presented in Table 1 and 2. It is shown that MCQF RR and IMCQF RR achieve much better fairness than LQF RR for these two non-uniform traffic patterns, and AFI of IM-CQF RR is significantly higher than LQF RR by almost 20% for log-diagonal traffic.…”

Section: Fairness Performancementioning

confidence: 99%

Novel High Performance Scheduling Algorithms for Crosspoint Buffered Crossbar Switches

Wang

et al. 2015

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThe crossbar-based switch fabric is widely used in today's high performance switches, due to its internally nonblocking and simply implementation properties. Usually there are two main switching architectures for crossbar-based switch fabric: internally bufferless crossbar switch and crosspoint buffered crossbar switch. As internally bufferless crossbar switch requires a complex centralized scheduler which limits its scalability to high speeds, crosspoint buffered crossbar switch has gained more attention because of its simpler distributed scheduling algorithm and better switching performance. However, almost all the scheduling algorithms proposed previously for crosspoint buffered crossbar switch either have unsatisfactory scheduling performance under non-uniform traffic patterns or show poor service fairness between input traffic flows. In order to overcome the disadvantages of existing algorithms, in this paper we propose two novel high performance scheduling algorithms named MCQF RR and IMCQF RR for crosspoint buffered crossbar switches. Both algorithms have a time complexity of O(log N), where N is the number of input/output ports of the switch. MCQF RR takes advantage of the combined weight information about queue length and service waiting time of input queues to perform scheduling. In order to further reduce the scheduling complexity and make it feasible for high speed switches, IMCQF RR uses the compressed queue length information instead of original queue length information to schedule cells in input VOQs. Simulation results show that our novel scheduling algorithms MCQF RR and IMCQF RR can demonstrate excellent delay performance comparable to existing high performance scheduling algorithms under both uniform and non-uniform traffic patterns, while maintain good service fairness performance under severe non-uniform traffic patterns.

show abstract

Section: Fairness Performancementioning

confidence: 99%

Novel High Performance Scheduling Algorithms for Crosspoint Buffered Crossbar Switches

Wang

et al. 2015

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…We simulated these four schemes under several nonuniform traffic models: unbalanced [13], Chang's [10], asymmetric [14], and power-of-two (PO2) [11].…”

Section: B Nonuniform Trafficmentioning

confidence: 99%

“…With a single-stage switch, the exhaustive dual round-robin matching (EDRRM) has been shown to achieve a throughput higher than iSLIP and DRRM under nonuniform traffic patterns. Furthermore, frame 1 based matching have been shown to improve switching performance under different traffic scenarios [11], [12].…”

Section: Introductionmentioning

confidence: 99%

Captured-Frame Eligibility and Round-Robin Matching for Input-Queued Packet Switches

Rojas‐Cessa

Lin

2004

IEEE Commun. Lett.

View full text Add to dashboard Cite

Abstract-A variety of matching schemes that deliver high throughput under traffic with uniform distributions has been proposed. However, there is a need of matching schemes that provide high throughput under several admissible traffic patterns, including those with nonuniform distributions, while keeping implementation complexity low. In this letter, first, we introduce the captured frame concept for matching schemes in IQ switches. Second, we propose a round-robin based matching scheme, uFORM, which uses the proposed concept for cell matching eligibility. We show via simulation that our matching scheme delivers 99% throughput under several nonuniform traffic patterns, and retains the high performance under uniform traffic that roundrobin matching schemes are known to offer.Index Terms-input-queued switch, virtual output queue, captured frame, frame eligibility, unbalanced traffic

show abstract

“…In addition, CICB-SA and CICB-FA were simulated under power-of-two traffic [14] for 30 × 30 switches. The power of two (PO2) traffic model can be represented by matrixρ as: This traffic model presents a large nonuniformity in the traffic distribution among N possible destinations.…”

Section: Nonuniform Traffic: Power Of Twomentioning

confidence: 99%

Combined Input-Crosspoint Buffered Packet Switch with Flexible Access to Crosspoints Buffers

Rojas‐Cessa

Dong

2006

2006 International Caribbean Conference on Devices, Circuits and Systems

View full text Add to dashboard Cite

Abstract-The performance of Internet routers is greatly defined by the adopted switch architecture. Combined inputcrosspoint buffered (CICB) packet switches are being considered of research interest because of their high switching performance. One of the main requirements in these switches is that the amount of memory needed to achieve 100% throughput under flows with high data rates must be proportional to the number of ports and crosspoint buffer size, which is set by the distance between the line cards and the buffered crossbar. Therefore, long distances between the line cards and the buffered crossbar can make a CICB switch costly to implement or infeasible. In this paper, we propose and discuss two CICB packet switches with flexible access to crosspoint buffers. The proposed switches allow an input to use any available crosspoint buffer at a given output, instead of having rigid access where an input can only access a dedicated crosspoint buffer at a given output, as is the case on previous existing architectures. The proposed switches provide high switching performance and support long distances between the buffered crossbar and the line cards, while using crosspoint buffers of small size. Our switches reduce the required crosspoint buffer size by a factor of N , where N is the number of ports, keep service of cells in sequence, and use no speedup.

show abstract

Frame-based matching algorithms for input-queued switches

Cited by 42 publications

References 15 publications

Novel High Performance Scheduling Algorithms for Crosspoint Buffered Crossbar Switches

Novel High Performance Scheduling Algorithms for Crosspoint Buffered Crossbar Switches

Captured-Frame Eligibility and Round-Robin Matching for Input-Queued Packet Switches

Combined Input-Crosspoint Buffered Packet Switch with Flexible Access to Crosspoints Buffers

Contact Info

Product

Resources

About