Architecture Level Design Space Exploration Of Superscalar Processor For Multimedia Applications

被引:0
作者
Maud, Abdur Rahman M. [1 ]
Masud, Shahid [1 ]
Ahmed, Rehan [2 ]
机构
[1] Lahore Univ Management Sci, Dept Comp Sci & Engn, Sect U, DHA, Lahore 54792, Pakistan
[2] Univ Wisconsin Madison, Dept Elect & Comp Engn, Madison, WI USA
来源
PROCEEDINGS OF THE INTERNATIONAL SYMPOSIUM ON PERFORMANCE EVALUATION OF COMPUTER AND TELECOMMUNICATION SYSTEMS | 2009年 / 41卷 / 04期
关键词
Superscalar processor; Power optimization; Multimedia applications; Architecture-level design; Design-space exploration;
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
In this paper, a variant of simulated annealing optimization has been used to derive a power efficient general purpose superscalar processor based on ARM Instruction Set Architecture. SimpleScalar architecture toolset in tandem with power estimation extension Wattch has been used for design space exploration. The use of common open source tools and models makes it easy to adapt the technique for other applications and architectures. MPEG2 decoder of the MPEG Software Simulation Group along with MP3 and JPEG decoders of MiBench Benchmark suite have been used to guide the architecture exploration. The optimization achieves an improvement in power of up to 50% for MPEG and JPEG decoders. The low transistor count and the ability of the optimum configuration to support complex real time multimedia standards makes it suitable for emerging handbeld devices.
引用
收藏
页码:21 / +
页数:2
相关论文
共 20 条
[1]  
AHMED R, 2008, P IEEE CAN C EL COMP
[2]  
[Anonymous], IEEE COMPUT
[3]  
[Anonymous], IEEE 4 ANN WORKSH WO
[4]  
ARM, ARCH DIG WORLD
[5]  
Azencott R., 1992, Simulated Annealing, VVolume 27
[6]  
Brooks D, 2000, PROCEEDING OF THE 27TH INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE, P83, DOI 10.1109/ISCA.2000.854380
[7]   Design and analysis of low-power cache using two-level filter scheme [J].
Chang, YJ ;
Ruan, SJ ;
Lai, FP .
IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2003, 11 (04) :568-580
[8]   System-level power consumption modeling and tradeoff analysis techniques for superscalar processor design [J].
Conte, TM ;
Menezes, KN ;
Sathaye, SW ;
Toburen, MC .
IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2000, 8 (02) :129-137
[9]   Circuit and microarchitectural techniques for reducing cache leakage power [J].
Kim, NS ;
Flautner, K ;
Blaauw, D ;
Mudge, T .
IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2004, 12 (02) :167-184
[10]   OPTIMIZATION BY SIMULATED ANNEALING [J].
KIRKPATRICK, S ;
GELATT, CD ;
VECCHI, MP .
SCIENCE, 1983, 220 (4598) :671-680