Amortized efficiency of list update and paging rules
Communications of the ACM
High-speed switch scheduling for local-area networks
ACM Transactions on Computer Systems (TOCS)
Wide area traffic: the failure of Poisson modeling
IEEE/ACM Transactions on Networking (TON)
Scheduling algorithms for input-queued cell switches
Scheduling algorithms for input-queued cell switches
Online computation and competitive analysis
Online computation and competitive analysis
Bounded latency scheduling scheme for ATM cells
Computer Networks: The International Journal of Computer and Telecommunications Networking
Optimal smoothing schedules for real-time streams (extended abstract)
Proceedings of the nineteenth annual ACM symposium on Principles of distributed computing
Loss-bounded analysis for differentiated services
SODA '01 Proceedings of the twelfth annual ACM-SIAM symposium on Discrete algorithms
Competitve buffer management for shared-memory switches
Proceedings of the thirteenth annual ACM symposium on Parallel algorithms and architectures
Buffer overflow management in QoS switches
STOC '01 Proceedings of the thirty-third annual ACM symposium on Theory of computing
Competitive queueing policies for QoS switches
SODA '03 Proceedings of the fourteenth annual ACM-SIAM symposium on Discrete algorithms
Dynamic routing on networks with fixed-size buffers
SODA '03 Proceedings of the fourteenth annual ACM-SIAM symposium on Discrete algorithms
Management of multi-queue switches in QoS networks
Proceedings of the thirty-fifth annual ACM symposium on Theory of computing
Providing qos guarantees in input-buffered crossbar switches with speedup
Providing qos guarantees in input-buffered crossbar switches with speedup
Buffer management for shared-memory ATM switches
IEEE Communications Surveys & Tutorials
On the speedup required for combined input- and output-queued switching
Automatica (Journal of IFAC)
Matching output queueing with a combined input/output-queued switch
IEEE Journal on Selected Areas in Communications
On the performance of greedy algorithms in packet buffering
STOC '04 Proceedings of the thirty-sixth annual ACM symposium on Theory of computing
The zero-one principle for switching networks
STOC '04 Proceedings of the thirty-sixth annual ACM symposium on Theory of computing
SIGACT news online algorithms column 4
ACM SIGACT News
Competitive weighted throughput analysis of greedy protocols on DAGs
Proceedings of the twenty-fourth annual ACM symposium on Principles of distributed computing
An improved algorithm for CIOQ switches
ACM Transactions on Algorithms (TALG)
A survey of buffer management policies for packet switches
ACM SIGACT News
Packet buffering: randomization beats deterministic algorithms
STACS'05 Proceedings of the 22nd annual conference on Theoretical Aspects of Computer Science
WAOA'04 Proceedings of the Second international conference on Approximation and Online Algorithms
| Hi-index | 0.00 |
Combined input and output queued (CIOQ) architectures with a moderate fabric speedup S1 have come to play a major role in the design of high performance switches. The switch policy that controls such switches must consist of two components. A buffer management policy that controls admission to buffers, and a scheduling policy that schedules the transfer of packets from input buffers to output buffers. The goal of the switch policy is to maximize the throughput of the switch. When all packets have a uniform value (or importance), this corresponds to the number of packets sent from the switch. When packets have variable values, this corresponds to the total value of the packets sent.We mainly consider switches with virtual output queuing (VOQ) at the inputs. For the case of packets with uniform values we present a switch policy that is 3-competitive for any speedup. For the case of packets with variable values we propose two preemptive switch policies. One achieves a competitive ratio of 4S, and the other achieves a competitive ratio of 8min(k, 2log α), where k is the number of distinct packet values and α is the ratio between the largest and smallest values.