cient External Memory Algorithms by Simulating Coarse - GrainedParallel
نویسنده
چکیده
External memory (EM) algorithms are designed for computational problems in which the size of the internal memory of the computer is only a small fraction of the problem size. For certain large scale applications this is necessarily true. Typically, the cost models proposed for external memory algorithms have measured only the number of I/O operations, and the algorithms have been specially crafted for the EM situation. In the past, several attempts have been made to relate the large body of work based on parallel algorithms to EM, but with limited success. In this paper we provide simulation techniques which produce eecient EM algorithms from eecient algorithms developed under BSP-like parallel computing models. Our techniques can accommodate one or multiple processors on the EM target machine, each with one or more disks, and they also adapt to the disk blocking factor of the target machine. In addition to the main simulation result we obtain a more comprehensive cost model for EM algorithms, which considers the total costs incurred by the algorithm including computation, I/O and communication costs.
منابع مشابه
E cient External Memory Algorithms by Simulating Coarse
External memory (EM) algorithms are designed for computational problems in which the size of the internal memory of the computer is only a small fraction of the problem size. For certain large scale applications this is necessarily true. Typically, the cost models proposed for external memory algorithms have measured only the number of I/O operations, and the algorithms have been specially craf...
متن کاملReducing I/O Complexity by Simulating Coarse Grained Parallel Algorithms
Block-wise access to data is a central theme in the design of efficient external memory (EM) algorithms. A second important issue, when more than one disk is present, is fully parallel disk I/O. In this paper we present a deterministic simulation technique which transforms parallel algorithms into (parallel) external memory algorithms. Specifically, we present a deterministic simulation techniq...
متن کاملReducing I/o Complexity by Simulating Coarse Grained Parallel Algorithms (1)
Block-wise access to data is a central theme in the design of eecient external memory (EM) algorithms. A second important issue, when more than one disk is present, is fully parallel disk I/O. In this paper, we present a deterministic simulation technique which transforms Coarse Grained Multi-computer (CGM) algorithms into parallel external memory algorithms. It optimizes block-wise data access...
متن کاملTowards Realistic Implementations of External Memory Algorithms Using a Coarse Grained Paradigm
We present an extension to SSCRAP, our C++ environment for the development of coarse grained algorithms, that allows for easy execution of programs in an external memory setting. Our environment is well suited for regular as well as irregular problems and scales from low end PCs to high end clusters and mainframe technology. It allows running algorithms designed on a high level of abstraction i...
متن کاملSome Scaleable Parallel Algorithms for Geometric Problems
This paper considers a variety of geometric problems on input sets of size n using a coarse grained multicomputer model consisting of p processors with (np ) local memory each (i.e., ( n p ) memory cells of (logn) bits apiece), where the processors are connected to an arbitrary interconnection network. It introduces e cient scaleable parallel algorithms for a number of geometric problems includ...
متن کامل