dc.contributor.author |
Dimitrakopoulos, G |
en |
dc.contributor.author |
Galanopoulos, K |
en |
dc.date.accessioned |
2014-03-01T02:47:29Z |
|
dc.date.available |
2014-03-01T02:47:29Z |
|
dc.date.issued |
2011 |
en |
dc.identifier.uri |
https://dspace.lib.ntua.gr/xmlui/handle/123456789/33171 |
|
dc.subject |
Bufferless router |
en |
dc.subject |
Deflection routing |
en |
dc.subject |
Logic design |
en |
dc.subject |
Switch allocation |
en |
dc.subject.other |
Allocators |
en |
dc.subject.other |
Bufferless router |
en |
dc.subject.other |
Bufferless switches |
en |
dc.subject.other |
Clock frequency |
en |
dc.subject.other |
Control logic |
en |
dc.subject.other |
Deflection routing |
en |
dc.subject.other |
Design option |
en |
dc.subject.other |
Energy-efficient design |
en |
dc.subject.other |
Faster implementation |
en |
dc.subject.other |
Large delays |
en |
dc.subject.other |
Low-latency |
en |
dc.subject.other |
Net work utilization |
en |
dc.subject.other |
Network on chip |
en |
dc.subject.other |
On-chip networks |
en |
dc.subject.other |
Switch allocation |
en |
dc.subject.other |
Computer architecture |
en |
dc.subject.other |
Energy efficiency |
en |
dc.subject.other |
Interconnection networks |
en |
dc.subject.other |
Logic design |
en |
dc.subject.other |
Routers |
en |
dc.subject.other |
Switching circuits |
en |
dc.subject.other |
VLSI circuits |
en |
dc.subject.other |
Network architecture |
en |
dc.title |
Switch allocator for bufferless network-on-chip routers |
en |
heal.type |
conferenceItem |
en |
heal.identifier.primary |
10.1145/1930037.1930043 |
en |
heal.identifier.secondary |
http://dx.doi.org/10.1145/1930037.1930043 |
en |
heal.publicationDate |
2011 |
en |
heal.abstract |
Bufferless switches can be an attractive and energy-efficient design option for on-chip networks when network utilization is low and low-latency operation matters the most. However, this promising design option is limited by the complexity of the control logic required to operate a bufferless switch that imposes large delays and limits the clock frequency. Pipelining is not an option in this low-latency environment. In this paper, we propose a new switch allocator for bufferless switches that parallelizes the steps required for achieving a match between requesting inputs and available outputs and offers significantly faster implementations. Copyright © 2011 ACM. |
en |
heal.journalName |
ACM International Conference Proceeding Series |
en |
dc.identifier.doi |
10.1145/1930037.1930043 |
en |
dc.identifier.spage |
19 |
en |
dc.identifier.epage |
22 |
en |