An Efficient Value Predictor Dynamically Using Loop and Locality Properties

doi:10.1023/B:SUPE.0000032779.88101.24

淡江大學機構典藏 > 工學院 > 電機工程學系暨研究所 > 期刊論文 > Item 987654321/46078

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/46078

题名:	An Efficient Value Predictor Dynamically Using Loop and Locality Properties
作者:	Chuang, PO-JEN;Hsiao, YOUNG-TZONG;Chiu, YU-SHIAN
贡献者:	淡江大學電機工程學系
关键词:	Benchmarking;Computer simulation;Cost effectiveness;Costs;Data processing;Hardware;Parallel processing systems;Program processors;Signal filtering and prediction;Benchmarks;Experimental performance evaluation;Hardware costs;Loop and locality properties;Value prediction;Value engineering
日期:	2004-10
上传时间:	2013-06-13 11:30:15 (UTC+8)
出版者:	Secaucus: Springer New York LLC
摘要:	Value prediction, a technique to break data dependency, is important in enhancing instruction-level parallelism and processor performance. A new value predictor utilizing both the loop and locality properties of data values has been proposed in this paper to pursue desirable prediction accuracy at reasonable cost. The proposed value predictor, called the Dynamic Loop and Locality-based (DLL) predictor, makes predictions by dynamically practicing the loop or locality-based prediction policy according to the state. With certain simple designs, the DLL predictor gains prediction accuracy in an efficient way. To secure more comprehensive experimental evaluation of value predictors, a new performance measure, accuracy improvement per cost, briefed as the A/C ratio, is introduced in the paper. Simulation results show that, compared with other existing value predictors, the proposed DLL predictor produces better A/C ratios in almost all situations due to flexible application of different prediction policies and reduced cost.
關聯:	Journal of Supercomputing 30(1), pp.19-36+65
DOI:	10.1023/B:SUPE.0000032779.88101.24
显示于类别:	[電機工程學系暨研究所] 期刊論文

文件中的档案:

档案	大小	格式	浏览次数
0920-8542_30(1)p19-36+65.pdf	257Kb	Adobe PDF	165	检视/开启

在機構典藏中所有的数据项都受到原著作权保护.

TAIR相关文章

数据加载中.....