Parssse: an Adaptive Parallel State Space Search Engine
نویسندگان
چکیده
State space search problems abound in the artificial intelligence, planning and optimization literature. Solving such problems is generally NP-hard, so that a brute-force approach to state space search must be employed. Given the exponential amount of work that state space search problems entail, it is desirable to solve them on large parallel machines with significant computational power. In this paper, we analyze the parallel performance of several classes of state space search applications. In particular, we focus on the issues of grain size, the prioritized execution of tasks and the balancing of load among processors in the system. We demonstrate the corresponding techniques that are used to scale such applications to large scale. Moreover, we tackle the problem of programmer productivity by incorporating these techniques into a general search engine framework designed to solve a broad class of state space search problems. We demonstrate the efficiency and scalability of our design using three example applications, and present scaling results up to 32,768 processors.
منابع مشابه
An Intelligent Control Strategy in a Parallel Hybrid Vehicle
This paper presents a design procedure for an adaptive power management control strategy based on a driving cycle recognition algorithm. The design goal of the control strategy is to minimize fuel consumption and engine-out NOx, HC and CO emissions on a set of diversified driving schedules. Seven facility-specific drive cycles are considered to represent different driving scenarios. For each fa...
متن کاملInformed and Probabilistically Complete Search for Motion Planning under Differential Constraints
Sampling-based search has been shown effective in motion planning, a hard continuous state-space problem. Motion planning is especially challenging when the robotic system obeys differential constraints, such as an acceleration controlled car that cannot move sideways. Methods that expand trajectory trees in the state space produce feasible solutions for such systems. These planners can be view...
متن کاملA Comparison of Random Search versus
We have integrated the distributed search of genetic programming (GP) based systems with collective memory to form a collective adaptation search method. Such a system signiicantly improves search as problem complexity is increased. Since the pure GP approach does not scale well with problem complexity, a natural question is which of the two components is actually contributing to the search pro...
متن کاملModern Cooperative Parallel SAT Solving
Nowadays, powerful parallel SAT solvers are based on an algorithm portfolio. The alternative approach, (iterative) search space partitioning, cannot keep up, although, according to the literature, iterative partitioning systems should scale better than portfolio solvers. This rises often! In this paper we identify key problems in current parallel cooperative SAT solving approaches, most importa...
متن کاملRandom Search versus Genetic Programming as Engines for Collective Adaptation
We have integrated the distributed search of genetic programming (GP) based systems with collective memory to form a collective adaptation search method. Such a system signiicantly improves search as problem complexity is increased. Since the pure GP approach does not scale well with problem complexity, a natural question is which of the two components is actually contributing to the search pro...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Parallel Processing Letters
دوره 21 شماره
صفحات -
تاریخ انتشار 2011