패턴/패스 통합 분기 예측 전략의 성능 분석

• 영문명: Performance Analysis of Pattern/Path Hybrid Branch Prediction Strategy
• 발행기관: 한국시뮬레이션학회
• 저자명: 조경산(Kyungsan Cho) 주영상(Youngsang Joo)
• 간행물 정보: 『한국시뮬레이션학회 논문지』제8권 제3호, 17~28쪽, 전체 12쪽
• 주제분류: 공학 > 기타공학
• 파일형태: PDF
• 발행일자: 1999.09.30

영문 초록

Recently studies have shown that conditional branches can be accurately predicted by recording the path leading up to the branch. But path predictors are more complex and uncompatible with existing pattern branch predictors. In order to solve these problems, we propose a simple path branch predictor(SPBP) that hashes together two most recent branch instruction addresses. In addition, we propose a pattern/path hybrid branch predictor composed of the SPBP and existing pattern branch predictors. Through the trace-driven simulation of six benchmark programs, the perfoπnance improvement by the proposed pattern/path hybrid branch predicti is analysed and validated. The proposed predictor can improve the prediction accuracy from 94.21% to 95.03%.

목차

1. 서론

2. 관련 연구

3. 작업부하 및 trace-driven 시뮬레이션

4. 패턴/패스 통합 분기 예측 구조와 시뮬레이션 결과 분석

5. 결론

참고문헌