Browse > Article

A Hybrid Value Predictor using Static and Dynamic Classification in Superscalar Processors  

김주익 (수원대학교 컴퓨터학과)
박홍준 (극동정보대학 전산정보처리과)
조영일 (수원대학교 정보공학대학 컴퓨터학과)
Abstract
Data dependencies are one of major hurdles to limit ILP(Instruction Level Parallelism), so several related works have suggested that the limit imposed by data dependencies can be overcome to some extent with use of the data value prediction. Hybrid value predictor can obtain the high prediction accuracy using advantages of various predictors, but it has a defect that same instruction has overlapping entries in all predictor. In this paper, we propose a new hybrid value predictor which achieves high performance by using the information of static and dynamic classification. The proposed predictor can enhance the prediction accuracy and efficiently decrease the prediction table size of predictor, because it allocates each instruction into single best-suited predictor during the fetch stage by using the information of static classification. Also, it can enhance the prediction accuracy because it selects a best- suited prediction method for the “Unknown”pattern instructions by using the dynamic classification mechanism. Simulation results based on the SimpleScalar/PISA tool set and the SPECint95 benchmarks show the average correct prediction rate of 85.1% by using the static classification mechanism. Also, we achieve the average correction prediction rate of 87.6% by using static and dynamic classification mechanism.
Keywords
Superscalar Processor; Data Dependency; Instruction-Level Parallelism; Dynamic Classification; Static Classification; Hybrid Value Prediction;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 J. Gonzalez, and A. Gonzalez, 'The Potential of Data Value Speculation to Boot ILP,' In 12th International Conference on Supercomputing, 1998
2 K. Wang and M. Franklin, 'Highly Accurate Data Value Prediction Using Hybrid Predictors,' MICRO-30, pp. 281-290, December 1997   DOI
3 B. Rychlik, J. W. Faist!, B. P. Krug, A. Y. Kurland, J. J. Sung, M. N. Velev, J. P. Shen, 'Efficient and Accurate Value Prediction Using Dynamic Classification,' Tech. Rep, CMUART, April 1998
4 M. H. Lipasti and J. P. Shen, 'Exceeding the Dataflow Limit via Value Prediction,' MICRO-29, pp. 226-237, December 1996   DOI
5 G. Reinman and B. Calder, 'Predictive Techniques for Aggressive Load Speculation,' MICRO-31, pp. 127-137, December 1998   DOI
6 박홍준, 신영호, 조영일, '슈퍼스칼라 프로세서에서 모험적 갱신을 사용한 하이브리드 결과 값 예측기', 한국정보과학회 논문지(시스템 및 이론), 제28권 제11호, pp. 592-600, December 2001   과학기술학회마을
7 박홍준, 조영일, '슈퍼스칼라 프로세서에서 예상 테이블의 모험적 갱신과 명령어 실행 유형의 정적 분류를 이용한 혼합형 결과 값 예측기', 한국정보과학회 논문지(컴퓨팅의 실제), 제8권 제1호, pp. 107-115, February, 2002   과학기술학회마을
8 Q. Zhao. D. J. Lilja, 'Compiler-Directed Static Classification of Value Locality Behavior,' Laboratory for Advanced Research in Computing Technology and Compilers Technical Report No. ARCTiC 00-07, July, 2000
9 F. Gabbay, and A. Mendelson, 'The Effect of Instruction Fetch Bandwidth on Value Prediction,' ISCA-25, pp. 272-281, 1998   DOI
10 B. Calder, G. Reinman, D. M. Tullsen, 'Selective Value Prediction,' ISCA-26, May 1999   DOI
11 Sang-Jung Lee, Yuan Wang and Pen-Chung Yew, 'Decoupled Value Prediction on Trace Processors,' HPCA-6, pp. 231-240, January 2000   DOI
12 Sang-Jung Lee, Pen-Chung Yew, 'On Some Implementation Issue for Value Prediction on Wide-Issue ILP Processors,' PACT 2000, October 2000
13 D. C. Burger and T. M. Austin, 'The Simple-Scalar Tool Set, Version 2.0,' Technical Report CS-TR-97-1342, University of Wisconsin, Madison, June 1997