AIDA Asynchronous Parallel IDA
نویسنده
چکیده
We present AIDA*, a generic adaptable scheme for highly parallel iterative-deepening search on large-scale asynchronous MIMD systems. AIDA* is based on a data partitioning scheme, where the di erent parts of the search space are processed asynchronously in parallel. Existing sequential solution algorithms can be linked to the AIDA* routines to build a fast, highly parallel search program. Taking the 15-puzzle as an application domain, we achieved an average speedup of 807 on a 1024 processor system, corresponding to an efciency of 79% on Korf's [1985] 25 largest problem instances. Speci c problem instances yield more than 90% e ciency. The total time taken by AIDA* to solve Korf's 100 random puzzles on a 1024-node system was 24.2 minutes. This is 5.7 times faster than the most e cient parallel algorithm on a 32K CM2 machine, SIDA* by Powley et al.
منابع مشابه
A statistical approach to virtual cellular experiments: improved causal discovery using accumulation IDA (aIDA)
MOTIVATION We address the following question: Does inhibition of the expression of a gene X in a cellular assay affect the expression of another gene Y? Rather than inhibiting gene X experimentally, we aim at answering this question computationally using as the only input observational gene expression data. Recently, a new statistical algorithm called Intervention calculus when the Directed acy...
متن کاملSystems biology A statistical approach to virtual cellular experiments: improved causal discovery using accumulation IDA (aIDA)
Motivation: We address the following question: Does inhibition of the expression of a gene X in a cellular assay affect the expression of another gene Y? Rather than inhibiting gene X experimentally, we aim at answering this question computationally using as the only input observational gene expression data. Recently, a new statistical algorithm called Intervention calculus when the Directed ac...
متن کاملIntroducing Adaptive Incremental Dynamic Analysis: A New Tool for Linking Ground Motion Selection and Structural Response Assessment
Adaptive Incremental Dynamic Analysis (AIDA) is a novel ground motion selection scheme that adaptively changes the ground motion suites at different ground motion intensity levels to match hazardconsistent properties for structural response assessment. Incremental Dynamic Analysis (IDA), a current dynamic response history analysis practice in Performance-Based Earthquake Engineering (PBEE), use...
متن کاملIn Proceedings of the First IEEE IPPS Workshop on Parallel and Distributed Real - Time Systems , Newport Beach , CA , April 1993 . AIDA
In this paper, we propose a superior technique for distributed time-critical communication using AIDA, a novel elaboration on Michael O. Rabin's IDA A 1 9 ]. We s h o w that using a small dynamically-controlled amount of redundancy, stringent timing constraints imposed on periodic as well as sporadic communication requests in a distributed real-time system can be fulllled up to any degree of co...
متن کاملResearch on programming languages for massively parallel processing
a research group involved in the research project \New Information Processing System on Massively Parallel Processing Principle" in the Grant-in-Aid for Scienti c Research on Priority Areas of the Ministry of Education, Science and Culture, Japan. The objective of the research is the following two points according to the top level research objective of our Massively Parallel Processing Principl...
متن کامل