DocumentCode
122389
Title
Characterizing Traffic Locality in 3D NoC-Based CMPs Using a Path-Based Partitioning Method
Author
Bahrebar, Poona ; Stroobandt, Dirk
Author_Institution
Dept. of Electron. & Inf. Syst. (ELIS), Ghent Univ., Ghent, Belgium
fYear
2014
fDate
26-28 Aug. 2014
Firstpage
63
Lastpage
70
Abstract
The incorporation of the third dimension in the design of Networks-on-Chip (NoCs) provides a major performance improvement for Chip Multi-Processors (CMPs). Since multicast communication is necessary for parallelization, it is of significant importance to design routing methods that support multicast. The partitioning strategy has a major impact on the efficiency of the multicast routing method. The existing 3D partitioning methods are designed oblivious to the coherent traffic distribution in CMP networks. In this paper, we propose a novel partitioning method which is compatible with the locality of the traffic distribution across the network. By increasing the parallelism through eliminating the unnecessary long paths, a high performance structure is provided which is a valuable asset for CMPs. The experimental results indicate an average gain of 18% in performance and 4% in power consumption near the saturation points by exploiting the proposed partitioning strategy.
Keywords
integrated circuit design; multiprocessing systems; network-on-chip; three-dimensional integrated circuits; 3D NoC-based CMPs; 3D partitioning methods; CMP networks; chip multiprocessors; coherent traffic distribution; multicast communication; multicast routing method; network-on-chip design; path-based partitioning method; power consumption; saturation points; traffic locality characterization; DH-HEMTs; Integrated circuit interconnections; Multicast communication; Parallel processing; Routing; Three-dimensional displays; Very large scale integration; 3D NoCs; Rentian traffic; multicast communication; path-based partitioning methods; traffic locality;
fLanguage
English
Publisher
ieee
Conference_Titel
High-Performance Interconnects (HOTI), 2014 IEEE 22nd Annual Symposium on
Conference_Location
Mountain View, CA
Type
conf
DOI
10.1109/HOTI.2014.22
Filename
6925720
Link To Document