지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 저널정보
- Korean Institute of Information Scientists and Engineers Journal of Electrical Engineering and Information Science Journal of Electrical Engineering and Information Science Vol.4 No.1
- 발행연도
- 1999.2
- 수록면
- 105 - 114 (10page)
이용수
초록· 키워드
오류제보하기
Multicomputer systems based on message passing draw attractions in the field of high performance computing, where loop or data parallelism is a main source of parallel processing. When exploiting parallelism on multicomputers, however, we confront several challenging problems. First, the nodes of multicomputer are likely to be heterogeneous with respect to computing power and workload. To minimize the elapsed time of program, loads should be balanced according to the performance of nodes. In addition, various dynamic failures should be managed appropriately. Lastly, selecting a proper number of nodes in a node pool is also desirable to achieve good performance.
We propose a new dynamic load balancing scheme called RAS to simultaneously deal with the three issues. RAS solves the load-balancing problem and dynamic failures by a work stealing mechanism, and the processor selection problem by data distribution based on a reservation scheme. According to our experiments on an IBM SP2 with matrix multiplication and ray tracing, RAS has shown better performance than other algorithms such as static chunk and weighted factoring under a shared running environment and even under the dedicated running environment.
We propose a new dynamic load balancing scheme called RAS to simultaneously deal with the three issues. RAS solves the load-balancing problem and dynamic failures by a work stealing mechanism, and the processor selection problem by data distribution based on a reservation scheme. According to our experiments on an IBM SP2 with matrix multiplication and ray tracing, RAS has shown better performance than other algorithms such as static chunk and weighted factoring under a shared running environment and even under the dedicated running environment.
목차
Abstract
Ⅰ. Introduction
Ⅱ. Previous Work
Ⅲ. RAS Algorithm
Ⅳ. Experimental Results
Ⅴ. Conclusions
References
저자소개
참고문헌 (0)
참고문헌 신청함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
A Robust Dynamic Load Balancing Scheme for Data Parallel Application on Multicomputer Systems
Journal of Electrical Engineering and information Science
1999 .02
-
Message-Based Multicomputer의 성능을 위한 모델에 관한 연구 ( A Study on the Performance Models of Message-Based Multicomputers )
대한전자공학회 학술대회
1988 .11
-
A Dynamic Processor Allocation Strategy for Mesh-Connected Multicomputers
Journal of Electrical Engineering and information Science
1996 .03
-
An Efficient Parallel BP for Large Scale Training-sets and its Implementation on the Multicomputer System
대한전자공학회 기타 간행물
1994 .01
-
An Efficient Submesh Allocation Scheme for Mesh-Connected Multicomputer Systems
ITC-CSCC :International Technical Conference on Circuits Systems, Computers and Communications
2003 .07
-
A Load Distribution Method for Multicomputer System Based on Intercomputer Negotiation
JTC-CSCC : Joint Technical Conference on Circuits Systems, Computers and Communications
1993 .01
-
A Repeated Mapping Scheme of Task Modules with Minimum Communication Cost in Hypercube Multicomputers
[ETRI] ETRI Journal
1998 .08
-
High Performance Multicomputer Type DSP System ` NOVI `
JTC-CSCC : Joint Technical Conference on Circuits Systems, Computers and Communications
1987 .01
-
병렬 다중 컴퓨터의 노드간 효과적인 타스크 매핑 기법
한국통신학회 학술대회 및 강연회
1998 .12
-
MULTICOMPUTER-BASED PARALLEL IMPLEMENTATION OF THE BACKPROPAGATION ALGORITHM FOR LINEAR SPEEDUP EXPANDABILITY
JTC-CSCC : Joint Technical Conference on Circuits Systems, Computers and Communications
1992 .01
-
다중컴퓨터망에서 신경회로망 설계를 위한 고속병렬처리시스템의 구현 ( An Implementation of High-Speed Parallel Processing System for Neural Network Design by Using the Multicomputer Network )
전자공학회논문지-B
1993 .05
-
다중프로세서상에서의 실제적 통신부담을 고려한 스케쥴링 알고리즘 ( A Scheduling Algorithm with Actual Communication Overheads On Multicomputers )
대한전자공학회 학술대회
1992 .11
-
다중컴퓨터 시스템을 이용한 최적화 신경회로망의 최적 병렬구현 ( Optimal Parallel Implementation of an Optimization Neural Network by Using a Multicomputer System )
전자공학회논문지-B
1991 .12
-
메쉬 구조 다중컴퓨터 시스템을 위한 효율적인 서브메쉬 할당방법
대한전자공학회 학술대회
2003 .07
-
An Adaptive Location Policy for Distributed Dynamic Load Balancing Schemes
ITC-CSCC :International Technical Conference on Circuits Systems, Computers and Communications
1996 .01
-
A Robust Load Sharing Control Scheme for Parallel-Connected Multi Systems
제어로봇시스템학회 합동학술대회 논문집
2000 .03
-
다중컴퓨터를 이용한 신경회로망기반 실시간 자동 표적인식시스템의 병렬구현 ( Parallel Implementation of a Neural Network-based Realtime ATR System Using a Multicomputer )
전자공학회논문지-B
1996 .02
이 논문의 저자 정보
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2009-569-017769472