Optimizing CMOS technology for maximum performance

被引:33
作者
Frank, D. J.
Haensch, W.
Shahidi, G.
Dokumaci, O. H.
机构
[1] IBM Corp, Thomas J Watson Res Ctr, Yorktown Hts, NY 10598 USA
[2] IBM Corp, Syst & Technol Grp, Fishkill, NY 12533 USA
关键词
D O I
10.1147/rd.504.0419
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Since power dissipation is becoming a dominant limitation on the continued improvement of CMOS technology, technologists must understand the best way to design transistors in the presence of power constraints. The primary objective is to obtain as much performance as possible for a fixed amount of power, and it is chip performance, not device performance, that matters. In order to investigate this regime, we have captured in simplified models the basic elements for determining chip performance, including intrinsic transistor characteristics, circuit delay, tolerance issues, basic microprocessor composition, and power dissipation and heat removal considerations. These models have been assembled in a processor-level technology-optimization program to study the characteristics of optimal technology across many generations of CMOS. The results that are presented elucidate the limits of future CMOS technology improvements, the optimal energy consumption conditions, and the relative benefits of various proposed technology enhancements, including high-k gate insulators, metal gates, highmobility semiconductors, improved heat removal, and the use of multiple layers of circuitry.
引用
收藏
页码:419 / 431
页数:13
相关论文
共 25 条
[1]  
Bakoglu H., 1990, CIRCUITS INTERCONNEC
[2]  
BAKOGLU HB, 1987, P INT SOL STAT CIRC, P308
[3]   A minimum total power methodology for projecting limits on CMOS GSI [J].
Bhavnagarwala, AJ ;
Austin, BL ;
Bowman, KA ;
Meindl, JD .
IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2000, 8 (03) :235-251
[4]   Moore's law governs the silicon revolution [J].
Bondyopadhyay, PK .
PROCEEDINGS OF THE IEEE, 1998, 86 (01) :78-81
[5]  
Buturla E., 1989, P NASECODE 6, P291
[6]   Improved a priori interconnect predictions and technology extrapolation in the GTX system [J].
Cao, Y ;
Hu, CM ;
Huang, XJ ;
Kahng, AB ;
Markov, IL ;
Oliver, M ;
Stroobandt, D ;
Sylvester, D .
IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2003, 11 (01) :3-14
[7]  
Chen ZJ, 1995, INTERNATIONAL ELECTRON DEVICES MEETING, 1995 - IEDM TECHNICAL DIGEST, P63, DOI 10.1109/IEDM.1995.497183
[8]  
Colgan EG, 2005, P IEEE SEMICOND THER, P1
[9]   CMOS SCALING FOR HIGH-PERFORMANCE AND LOW-POWER - THE NEXT 10 YEARS [J].
DAVARI, B ;
DENNARD, RH ;
SHAHIDI, GG .
PROCEEDINGS OF THE IEEE, 1995, 83 (04) :595-606
[10]   A stochastic wire-length distribution for gigascale integration (GSI) - Part I: Derivation and validation [J].
Davis, JA ;
De, VK ;
Meindl, JD .
IEEE TRANSACTIONS ON ELECTRON DEVICES, 1998, 45 (03) :580-589