Accurate Machine-Learning-Based On-Chip Router Modeling

被引:32
作者
Jeong, Kwangok [1 ]
Kahng, Andrew B. [2 ]
Lin, Bill [1 ]
Samadi, Kambiz [1 ]
机构
[1] Univ Calif San Diego, Dept Elect & Comp Engn, La Jolla, CA 92093 USA
[2] Univ Calif San Diego, Dept Elect & Comp Engn, La Jolla, CA 92093 USA
关键词
Machine learning; nonparemetric regression; on-chip networks;
D O I
10.1109/LES.2010.2051413
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
As industry moves towards multicore chips, networks-on-chip (NoCs) are emerging as the scalable fabric for interconnecting the cores. With power now the first-order design constraint, early-stage estimation of NoC power, performance, and area has become crucially important. In this work, we develop accurate architecture-level on-chip router cost models using machine-learning-based regression techniques. Compared against existing models (e.g., ORION 2.0 and parametric models), our models reduce estimation error by up to 89% on average.
引用
收藏
页码:62 / 66
页数:5
相关论文
共 17 条
[1]   A power and performance model for network-on-chip architectures [J].
Banerjee, N ;
Vellanki, P ;
Chatha, KS .
DESIGN, AUTOMATION AND TEST IN EUROPE CONFERENCE AND EXHIBITION, VOLS 1 AND 2, PROCEEDINGS, 2004, :1250-1255
[2]   System level power modeling and simulation of high-end industrial network-on-chip [J].
Bona, A ;
Zaccaria, V ;
Zafalon, R .
DESIGNERS' FORUM: DESIGN, AUTOMATION AND TEST IN EUROPE CONFERENCE AND EXHIBITION, 2004, :318-323
[3]   Using multiple adaptive regression splines to support decision making in code inspections [J].
Briand, LC ;
Freimut, B ;
Vollei, F .
JOURNAL OF SYSTEMS AND SOFTWARE, 2004, 73 (02) :205-217
[4]   NoCEE : Energy macro-model extraction methodology for network on chip routers [J].
Chan, J ;
Parameswaran, S .
ICCAD-2005: INTERNATIONAL CONFERENCE ON COMPUTER AIDED DESIGN, DIGEST OF TECHNICAL PAPERS, 2005, :254-259
[5]  
Dally WJ, 2001, DES AUT CON, P684, DOI 10.1109/DAC.2001.935594
[6]  
De Micheli G., 2002, P DATE, P2
[7]   MULTIVARIATE ADAPTIVE REGRESSION SPLINES [J].
FRIEDMAN, JH .
ANNALS OF STATISTICS, 1991, 19 (01) :1-67
[8]   Architectural-Level Prediction of Interconnect Wirelength and Fanout [J].
Jeong, Kwangok ;
Kahng, Andrew B. ;
Samadi, Kambiz .
2009 INTERNATIONAL SOC DESIGN CONFERENCE (ISOCC 2009), 2009, :53-56
[9]  
Kahng Andrew B., 2010, 2010 15th Asia and South Pacific Design Automation Conference (ASP-DAC 2010), P241, DOI 10.1109/ASPDAC.2010.5419887
[10]  
Kahng AB, 2009, DES AUT TEST EUROPE, P423