2011 IEEE Computer Society Annual Symposium on VLSI 2011
DOI: 10.1109/isvlsi.2011.60
|View full text |Cite
|
Sign up to set email alerts
|

A DRAM Centric NoC Architecture and Topology Design Approach

Abstract: Most communication traffic in today's System on Chips

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2014
2014
2023
2023

Publication Types

Select...
3
2

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(3 citation statements)
references
References 17 publications
0
3
0
Order By: Relevance
“…Several customized irregular topologies can also be found in the literature [7][8][9]. Reconfigurability and reusability is the advantage of our work over them.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…Several customized irregular topologies can also be found in the literature [7][8][9]. Reconfigurability and reusability is the advantage of our work over them.…”
Section: Related Workmentioning
confidence: 99%
“…Regular topologies (like meshes) are reusable; they can be designed and optimized once and then be used in many systems. Fully customized irregular topologies [7][8][9], on the other hand, can achieve superior performance, but at the expense of altering the regularity of standard topologies and losing NoC Contents lists available at ScienceDirect journal homepage: www.elsevier.com/locate/vlsi reusability. The proposed NoC architecture benefits from the advantages of regular mesh topology, as well as the superior performance of customized topologies.…”
Section: Introductionmentioning
confidence: 99%
“…Other related work that focus on improving the averagecase performance of the clients include a memory-centric NoC design that explores the benefits of a dedicated NoC for shared DRAM access by funneling the traffic from different clients to the memory with the right width converters [24]. A connectionless NoC for shared memory access with a binary arbitration tree that multiplexes multiple clients to one bus master are proven to reduce average latency and hardware cost as opposed to a connection-oriented NoC [25].…”
Section: Related Workmentioning
confidence: 99%