We describe the facilities that TPIE provides to support scientific computation. TPIE, a transparent parallel I/O environment, is a system designed to assist programmers in implementing I/O-efficient computations. It ...
详细信息
We describe the facilities that TPIE provides to support scientific computation. TPIE, a transparent parallel I/O environment, is a system designed to assist programmers in implementing I/O-efficient computations. It supports I/O-efficient paradigms for problems from a variety of domains, including sorting and permuting, computational geometry, graph algorithms, and scientific computation. Our main focus in on the algorithmic issues faced in designing the portions of TPIE that support scientific computation. We consider four computing paradigms: scanning, sorting, sparse matrix methods, and dense matrix methods. Benchmark results using TPIE are also briefly described. References to more detailed discussions of these benchmarks, as well as the overall goals, philosophy, and structure of TPIE are provided.
The activity of research group of massively parallelprogramming language is introduced. This group is developing two types of languages. The first one is the SIMD type language called NCX which is oriented toward dat...
详细信息
The activity of research group of massively parallelprogramming language is introduced. This group is developing two types of languages. The first one is the SIMD type language called NCX which is oriented toward data parallel execution, and the second is the MIMD type highly asynchronous language called V, which is oriented toward data parallel and concurrent object oriented language. The NCX is designed as a data parallel extension of the language C in order to support practical massively parallel computations especially in the application area of scientific computations. The language V on the other hand is designed as an experimental language for exploring a new massively parallelprogramming paradigm.
Maher proposed the ALPS class of committed-choice languages, which can be seen as a further development of concurrent logic programming languages in the direction of CLP(X). However, due to the lack of OR-nondetermini...
详细信息
Maher proposed the ALPS class of committed-choice languages, which can be seen as a further development of concurrent logic programming languages in the direction of CLP(X). However, due to the lack of OR-nondeterminism, ALPS is a class of declarative algorithmic programming languages. In this paper, we present the FENG class of concurrent constraint logic programming languages and give its soundness and completeness results. With the novel feature of constraint based nondeterminism, FENG enriches the semantics of the ALPS and CLP(X). One of the features of FENG is that it supports constraint based nondeterminism. For some class of programs, this much improves the efficiency of program execution. FENG reveals a direction for data-parallel implementations of constraint logic programs. This has been confirmed by our experience in design and implementation of Firebird, a restriction of FENG, on the massively parallel machine DECmpp.
National Research Center for Intelligent Computing Systems (NCIC for short) is the unique national hi-tech R/D center for advanced computing technology in China. In this overview we first introduce China's Hi-Tech...
详细信息
National Research Center for Intelligent Computing Systems (NCIC for short) is the unique national hi-tech R/D center for advanced computing technology in China. In this overview we first introduce China's Hi-Tech R&D Programme (863 programme) and NCIC, then we reported the state of the art of parallel processing at NCIC. This article discussed the key technologies being exploited by the representative Chinese R&D teams and the wide applications of parallel computers in China. The key technologies in parallel processing we are attacking and reported in this article include wormhole routing and other efficient switching techniques, the Easter series MPP systems, the Dawning series symmetric and multi-thread multiprocessor, parallel operating systems and parallel file systems, parallel compiler and efficient programming tool. The future research directions at NCIC are also mentioned.
A simple greedy algorithm is presented for task clustering with duplication (or recomputation) which, for a task graph with arbitrary granularity, produces a schedule whose makespan is at most twice optimal. Furthermo...
详细信息
A simple greedy algorithm is presented for task clustering with duplication (or recomputation) which, for a task graph with arbitrary granularity, produces a schedule whose makespan is at most twice optimal. Furthermore, the quality of the schedule improves as the granularity of the task graph increases. For example, if the granularity is at least 1/2 , the makespan of the schedule is at most 5/3 times optimal. For a task graph with n tasks and e inter-task communication constraints, the algorithm runs in O(n(n lg n + e)) time, which is n times faster than the currently best known algorithm for this problem. Similar algorithms are developed that produce: (1) optimal schedules for coarse grain graphs;(2) 2-optimal schedules for trees with no task duplication;and (3) optimal schedules for coarse grain trees with no task duplication.
Many combinatorial problems can be efficiently solved for partial k-trees (graphs of treewidth bounded by k). The edge-coloring problem is one of the well-known combinatorial problems for which no NC algorithms have b...
详细信息
Many combinatorial problems can be efficiently solved for partial k-trees (graphs of treewidth bounded by k). The edge-coloring problem is one of the well-known combinatorial problems for which no NC algorithms have been obtained for partial k-trees. This paper gives an optimal and first NC parallel algorithm to find an edge-coloring of any given partial k-tree using a minimum number of colors if k and the maximum degree /spl Delta/ are bounded.< >
M.J. Maher (1987) proposed the ALPS class of committed-choice languages, which can be seen as a further development of concurrent logic programming languages in the direction of CLP(X). However, due to the lack of OR-...
详细信息
ISBN:
(纸本)0818665076
M.J. Maher (1987) proposed the ALPS class of committed-choice languages, which can be seen as a further development of concurrent logic programming languages in the direction of CLP(X). However, due to the lack of OR-nondeterminism, ALPS is a class of declarative algorithmic programming languages. In this paper, we present the FENG class of concurrent constraint logic programming languages and give its soundness and completeness results. With the novel feature of constraint based nondeterminism, FENG enriches the semantics of the ALPS and CLP(X). One of the features of FENG is that it supports constraint bared nondeterminism. For some class of programs, this improves the efficiency of program execution. FENG reveals a direction for data-parallel implementations of constraint logic programs. This has been confirmed by our experience in design and implementation of Firebird, a restriction of FENG, on the massively parallel machine DECmpp.< >
We are pursuing research on programming languages for massively parallel processing. The objective of the research is the following two points according to the top level research objective of our Massively parallel Pr...
详细信息
We are pursuing research on programming languages for massively parallel processing. The objective of the research is the following two points according to the top level research objective of our Massively parallel Processing Principle Research Project: firstly to develop a prototype of a massively parallelprogramming language and compiler system, which is competitive to commercial language systems like data parallel C, Fortran D or HPF; and secondly to explore a massively parallel computation model, and design an experimental language as an implementation of the newly explored massively parallel computation model.< >
National Research Center for Intelligent Computing Systems (NCIC) is the unique national hi-tech R/D center for advanced computing technology in China. We introduce China's Hi- Tech R&D Programme (863 programm...
详细信息
ISBN:
(纸本)0818665076
National Research Center for Intelligent Computing Systems (NCIC) is the unique national hi-tech R/D center for advanced computing technology in China. We introduce China's Hi- Tech R&D Programme (863 programmes) and NCIC, and we report on the state of the art of parallel processing at NCIC. The article discusses the key technologies being exploited by the representative Chinese R & D teams and the wide applications of parallel computers in China. The key technologies in parallel processing we are attacking are reported and include wormhole routing and other efficient switching techniques, the Easter series, MPP systems, the Dawning series symmetric and multi-thread multiprocessor, parallel operating systems and parallel file systems, parallel compilers and efficient programming tools. Future research directions at NCIC are also mentioned.< >
This paper describes the design and implementation of a comprehensive operating system (COS) for highly parallel machine. This is one of the research themes in the Japanese University Highly parallel Research Project ...
详细信息
This paper describes the design and implementation of a comprehensive operating system (COS) for highly parallel machine. This is one of the research themes in the Japanese University Highly parallel Research Project supported by the Special Grant of the Research Funds of Ministry of Education. The target machine is called JUMP-1 originally developed in this project. Several design policies are discussed, and the user service classes are defined. COS architecture is based on the micro kernel, and it includes both Partition OS and Service OS. The development environment is also discussed briefly.< >
暂无评论