Development of Theoretical Basis and Practical Implementation of a new Skeletal Parallel Programming System

新的骨架并行编程系统的理论基础和实际实现的发展

• 批准号: 15500020
• 负责人: IWASAKI Hideya
• 金额: $ 2.11万
• 依托单位: The University of Electro-Communications
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (C)
• 财政年份: 2003
• 资助国家: 日本
• 起止时间: 2003 至 2004
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-15500020/
• 关键词: Parallel Programming; Parallel Skeleton Library; Constructive Algorithmics; Fusion Transformation; C++; MPI; スケルトン並列プログラミング; プログラム変換; 並列スケルトン; スケルトンプログラミング

Parallel programming has proved to be difficult, requiring expert knowledge of both parallel algorithms and hardware architectures to achieve good results. Skeletal parallel programming enables programmers to build a parallel program from ready-made components (parallel skeletons) for which efficient implementations are known to exist, making both the parallel program development and the parallelization process easier.This research aims to develop both theoretical basis and practical programming environment system for skeletal parallel programming. Through this research, we have achieved the following results.1)We have developed a new skeleton that abstracts a good combination of primitive parallel skeletons for recursive data structures such as lists and binary trees.2)We have developed an optimization rules that fuses two successive calls of skeletons, based on the idea of constructive algorthmics.3)We have developed a practical skeletal library in C++ and MPI that can be used in general parallel environments.Our library has the following characteristic features that have not implemented in existing libraries. a)The library provides accumulate skeleton that abstracts typical form of recursive functions. b)The library implements fusion transformation that avoids unnecessary intermediate data structures. c) The library has no syntactic extensions that sacrifice generality of C++.

事实证明，并行编程很困难，需要对并行算法和硬件体系结构的专业知识才能取得良好的结果。骨骼并行编程使程序员能够从已知有效实现的现成组件（并行骨架）中构建一个并行程序，从而使并行程序的开发和并行化过程都更加容易。这项研究旨在开发理论基础和实用的骨骼并行编程编程环境系统。通过这项研究，我们达到了以下结果。1）我们开发了一个新的骨骼，该骨骼在递归数据结构（例如列表和二进制树）等原始平行骨骼的良好组合中，融合了一个优化规则，该规则融合了两个连续的骨骼呼吁，基于构造性Algorthmics的概念，我们可以在C+ selletal tibral of consepers selkele corme confe confe and。环境库具有以下特征功能，这些功能尚未在现有库中实现。 a）库提供了累积的骨骼，以抽象递归功能的典型形式。 b）图书馆实现了避免不必要的中间数据结构的融合转换。 c）库没有句法扩展，可以牺牲C ++的通用性。

项目成果

Kakehi, K., Hu, Z., Takeichi, M.: "List Homomorphism with Accumulation"Proc.4th International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing. 250-259 (2003)

Kakehi, K.、Hu, Z.、Takeichi, M.：“List Homomorphism with Accumulation”Proc.第四届软件工程、人工智能、网络和并行/分布式计算国际会议。

Systematic Derivation of Tree Contraction Algorithms

树收缩算法的系统推导

• 发表时间: 2004
• 期刊: Proc. 4th International workshop on Constructive Methods for Parallel Programming (CMPP2004)
• 作者: Matsuzaki;K.;Hu;Z.;Kakehi;K.;Takeichi;M.
• 通讯作者: M.

A Parallel Skeleton Library in C++ with Optimization Mechanism

具有优化机制的C并行骨架库

• 期刊: Computer Software (to appear)
• 作者: Akashi;Y.;Matsuzaki;K.;Iwasaki;H.;Kakehi;K.;Hu;Z
• 通讯作者: Z

PType System : A Featherweight Parallelizability Detector

PType 系统：轻量级并行性检测器

• 发表时间: 2004
• 期刊: Proc.2nd ASIAN Symposium on Programming Languages and Systems(APLAS2004)
• 作者: Xu;D.N.;Khoo;S.C.;Hu;Z.
• 通讯作者: Z.

森本武資, 岩崎英哉, 竹内郁雄: "枝刈り機構とメモ化機構をもつ言語"日本ソフトウェア科学会第20回大会論文集. CD-ROM. (2003)

Takeshi Morimoto、Hideya Iwasaki、Ikuo Takeuchi：“具有修剪和记忆机制的语言”第 20 届日本软件科学学会年会论文集（2003 年）。