Results 1 - 10 of 44,052

Table 1: Summary of notation.

in Collisionless Multiple Access Protocols for Wavelength Division Multiplexed Star-Coupled Photonic Networks
by Kalyani Bogineni, Michael Carrato, Patrick W. Dowd 1993
"... In PAGE 4: ... This architecture has the advantage of superior fanout capability over optical bus based systems, and high fault tolerance characteristic due to the large connectivity and passive nature [3, 4, 21]. Table1 summarizes the notation definitions. 2.... In PAGE 9: ... 4 Performance Model The performance analysis studies protocol behavior with variations in system parameters such as M, C, L, and . Table1 summarizes the architecture parameters and the notation used to denote the performance metrics. The performance metrics of primary concern are throughput and packet delay.... ..."
Cited by 59

Table 2: Number of Virtual Channels provided per Packet Type

in unknown title
by unknown authors 2005
"... In PAGE 4: ... While a more complex router ar- chitecture that manages its buffer entries as cells in a linked list could better utilize the available resources, the additional complexity and increased routing delay render such an architecture unsiutable for our network. Table2 summarizes the number of virtual channels provided for each type of packet and the amount of buffering provided for each virtual channel. The number of virtual channels and the amount of buffering per virutal channel were selected after simulating network configurations in which the parameters were sweept through a reasonable range of values.... ..."

Table 4: Measured Maximum Forwarding Rate and Excess Per-Packet Processor Cycles.

in Building a Robust Software-Based Router Using Network Processors
by Tammo Spalink, Scott Karlin, Larry Peterson, Yitzchak Gottlieb
"... In PAGE 8: ... We also inserted a delay loop on both sides to determine the number of spare cycles available, that is, cycles not involved in the data transfer. The results are given in Table4 , which shows that the router is able to forward up to 534Kpps through the Pen- tium. This rate saturates the StrongARM, but leaves 500 cycles per... ..."

Table 4: Measured Maximum Forwarding Rate and Excess Per-Packet Processor Cycles.

in ABSTRACT Building a Robust Software-Based Router Using Network Processors
by Tammo Spalink, Scott Karlin, Larry Peterson, Yitzchak Gottlieb
"... In PAGE 8: ... We also inserted a delay loop on both sides to determine the number of spare cycles available, that is, cycles not involved in the data transfer. The results are given in Table4 , which shows that the router is able to forward up to 534Kpps through the Pen- tium. This rate saturates the StrongARM, but leaves 500 cycles per... ..."

Table 3: Average Per Packet Cost for HEX network for V1 = 50 + x ; V2 = 10x ; V3 = 10 + x .

in unknown title
by unknown authors 1999
"... In PAGE 20: ...1 (redrawn in Figure 4 to include the dummy nodes). In Table3 we give full results for the load-to-delay functions discussed in that section. We then use load-to-cost functions which are qualitatively... ..."
Cited by 4

Table 1. Mean Delay Per Packet (in Transmission Rounds)

in Time-Varying Fair Queuing Scheduling For Multicode Cdma Based On Dynamic Programming
by A. Stamoulis, N. Sidiropoulos, G.B. Giannakis

Table 1. Average Total Delay per Packet Using Priority Policies

in COMMUNICATION OPTIMIZATION ON BROADCAST-BASED CLUSTERS
by Ming Zhu, Constantine Katsinis, Harsha Narravula, Wentong Cai, Bu-sung Lee

Table 10: Per Packet Cost of Sending a Data Packet

in A Cluster-based Approach for Routing in Dynamic Networks
by P. Krishna, N.H. Vaidya, M. Chatterjee, D. K. Pradhan 1997
"... In PAGE 11: ... Table 9 lists the protocols with the complexities. The per packet cost of sending a packet is listed in Table10 . The complexity parameters are as follows: n0f N: Number of nodes in the network.... ..."
Cited by 104

Table 3: Average Per Packet Cost for BUTTERFLY network for V1 = 50 + log(1 + x) ; V2 = 10x ; V3 = log(1 + x).

in unknown title
by unknown authors 2000
"... In PAGE 5: ...88 two sources from the two halves of the network share a common router on their potential shortest path. u S1T T T u V1 uV2 T T T u D1 u S2T T T uD2 uV3 T T T uV1uS3 @ @ u S1T T T u V3 u V1 uV2 T T T u D1 u S2T T T uD2 uV3 T T T uV1uS3 @ @ Net A Net B Figure 2: Butter y Network Table3 presents results for uniform tra c through all three sources, and then results for asymmetric tra c. For the rst case, the Braess apos; paradox is apparent in the ISPA: adding the new link is bene cial for the network at low load levels where the average per packet cost is reduced by nearly 20%, but deleterious at higher levels.... ..."
Cited by 34

Table 5: Average Per Packet Cost for BUTTERFLY network for V1 = 50 + log(1 + x) ; V2 = 10x ; V3 = log(1 + x).

in unknown title
by unknown authors 1999
"... In PAGE 22: ... Initially the two halves of the network have minimal contact, but with the addition of the extra link two sources from the two two halves of the network share a common router on their potential shortest path. y S1 T T T T T y V1 yV2 T T T T T y D1 y S2 T T T T T yD2 yV3 T T T T T yV1 yS3 @ @ @ y V0 y V0 y S1 T T T T T y V3 y V1 yV2 T T T T T y D1 y S2 T T T T T yD2 yV3 T T T T T yV1 yS3 @ @ @ y V0 y V0 Net A Net B Figure 5: Butter y Network Table5 presents two sets of results: rst we present results for uniform tra c through all three sources, and then results for asymmetric tra c. For the rst case, the Braess apos; paradox is apparent in the ISPA: adding the new link is bene cial for the network at low load levels where the average per packet cost is reduced by nearly 20%, but deleterious at higher levels.... ..."
Cited by 4
Results 1 - 10 of 44,052