Integrating model-based optimization and program transformation to generate efficient parallel programs

The paper gives an overview on the DSPL programming environment, an integrated approach to automate system design and implementation of applications run on dedicated parallel systems. The programming environment consists of a data-flow language and an integrated set of tools. The tools automatically derive a software model from the given application program. Based on the model, the design decisions as the network topology, the task mapping and schedule as well as the optimal use of buffers are computed. Finally, the design decisions are automatically implemented by transforming the application program in executable code for the chosen processor network. The DSPL programming environment integrates model-based optimization techniques and program transformation techniques. The integration allows to include new aspects in the optimization process. Especially optimizations crucial to the semantics of the program can be included. The most important examples of such optimizations are the enforcement of the schedule in case of data-dependent execution of tasks and the transformation of buffered communication to unbuffered communication. Both aspects are crucial to the generation of efficient parallel implementations. The integration of the two aspects is supported by a formal framework. This allows to formally prove the correctness of the program optimizations performed by the programming environment.     

面向混合并行计算系统编程环境的研究与实现

分析了基于CMP节点的混合并行计算系统并行处理模式,基于分层次的自顶向下、逐步细化的思想,设计并实现了面向此类混合并行计算系统的编程环境,从而大大降低程了序设计人员在此类环境下编写并行应用程序的复杂度,减少了程序编码错误,提高了编程人员的效率。     

Visual programming support for graph‐oriented parallel/distributed processing

GOP is a graph‐oriented programming model which aims at providing high‐level abstractions for configuring and programming cooperative parallel processes. With GOP, the programmer can configure the logical structure of a parallel/distributed program by constructing a logical graph to represent the communication and synchronization between the local programs in a distributed processing environment. This paper describes a visual programming environment, called VisualGOP, for the design, coding, and execution of GOP programs. VisualGOP applies visual techniques to provide the programmer with automated and intelligent assistance throughout the program design and construction process. It provides a graphical interface with support for interactive graph drawing and editing, visual programming functions and automation facilities for program mapping and execution. VisualGOP is a generic programming environment independent of programming languages and platforms. GOP programs constructed under VisualGOP can run in heterogeneous parallel/distributed systems. Copyright © 2005 John Wiley & Sons, Ltd.     

基于并行结构骨架的程序设计环境研究与实现

并行结构骨架理论提供了一种描述并行程序设计模式的通用模型,对设计模式进行更高层次的抽象,能有效解决基于设计模式的并行程序设计方法的局限性问题,降低并行程序设计开发难度.基于并行结构骨架的并行程序设计环境--PASBPE在并行结构骨架理论的基础上,使用参数化设置快速生成用户所需并行程序框架,同时通过可视化的程序设计交互环境,简化并行程序的开发过程,提高开发效率.     

Estimating and optimizing performance for parallel programs

The article describes P³T, a parameter-based performance prediction tool that estimates performance for parallel programs running on distributed-memory parallel architectures. P³ T has been carefully designed to address all of the above performance estimation issues. To achieve high estimation accuracy, P ³T aggressively exploits compiler analysis and optimization information. Our method is based on modeling loop iteration spaces, array access patterns, and data distributions by intersection and volume operations on n-dimensional polytopes. The most critical architecture-specific factors, such as cache line sizes, number of cache lines available, routing policy, start-up times, message transfer time per byte, and so forth, are modeled to reflect the performance impact of the target machine. P³T has been developed in the context of the Vienna Fortran Compilation Systems (VFCS), a state-of-the-art parallelization tool for distributed-memory systems. VFCS translates Fortran programs into explicitly parallel message-passing programs. P ³T successfully guides the interactive and automatic restructuring of programs under this system. The article describes the underlying compilation and programming model and discusses the most critical design decisions made for P³T; in addition, it outlines the implementation of the parallel program parameters. Also described are the VFCS context under which P³T is applied and the P³T graphical user interface     

Parallel software development in the DISC programming environment

This paper describes the architecture of DISC, a system for parallel software development. The system is designed for programming computer systems having several autonomous units, not memory-sharing, and linked by means of a communication network.

The system consists of three parts. The concurrent programming language DISC (DIStributed C), which is an extension of the C language based on the concurrent mechanisms envisaged by the CSP computational model. The programming environment, designed to promote software engineering techniques in the development of distributed-programs. The language run-time support, which provides for the distributed execution of programs.     

地震并行处理模式与应用框架

文中研究石油地震数据处理的并行计算设计模式（流水、扇出／扇入、主从和混合）和应用框架,框架和模式的目的都是复用成功的软件设计自力更生,框架可以看作一类设计模式的具体实现。针对地震数据处理模式设计和实现了GRISYS地震数据处理应用框架。利用这个框架,以往大量的串行地震处理模块,不需要任何改动,可以在工作站集群计算机或大规模并行计算机上实现并行计算,在曙光2000－Ⅱ并行计算机上试验,获得了非常高的并行处理加速比。     

Application of a parallel pattern processor to remote sensing

This paper describes application techniques of satellite remote sensing using a newly developed interactive digital image processing system, where a parallel pattern processor performs characteristic roles. The pattern processor can execute several image processing functions at high speed, which are frequently used in remote sensing studies; affine transformation for geometric correction of LANDSAT MSS data to implement a satellite image database, maximum likelihood estimation for land cover classification, and pixelwise operations for change detection, etc.

These application results indicate that the developed interactive image processing system is sufficiently effective to process remote-sensed data.     

Surface tension calculation of the Ni3S2---FeS---Cu2S mattes

The surface tension of the Ni₃S₂-FeS-Cu₂S ternary mattes have been calculated from those of the Ni₃S₂-FeS·FeS-Cu₂S and Cu₂S-Ni₃S₂ pseudo-binary boundary systems by using geometric models (Kohler and Toop model) and a general solution model (Chou model). Taking account of the experimental accuracy of ±2.5%, the respective calculated results are in agreement with the experimental data. At the same time, surface tensions of molten Ni₃S₂-FeS-Cu₂S mattes and their pseudo-binary boundary systems are predicted based on Butler's original treatment with great attention to the model parameter β. The predicted results also agree with the experimental data. Therefore, the resulting iso-surface tension curves in molten Ni₃S₂-FeS-Cu₂S mattes at 1473K, especially calculated by using Kohler, Toop and Chou models, are generally acceptable.     

The BLAZE language: A parallel language for scientific programming

Programming multiprocessor parallel architectures is a complex task. This paper describes a block-structured scientific programming language, BLAZE, designed to simplify this task. BLAZE contains array arithmetic, ‘forall’ loops, and APL-style accumulation operators, which allow natural expression of fine grained parallelism. It also employs an applicative or functional procedure invocation mechanism, which makes it easy for compilers to extract coarse grained parallelism using machine specific program restructuring. Thus BLAZE should allow one to achieve highly parallel execution on multiprocessor architectures, while still providing the user with conceptually sequential control flow.

A central goal in the design of BLAZE is portability across a broad range of parallel architectures. The multiple levels of parallelism present in BLAZE code, in principle, allow a compiler to extract the types of parallelism appropriate for the given architecture, while neglecting the remainder. This paper describes the features of BLAZE, and show how this language would be used in typical scientific programming.     

Detection of gases by correlation spectroscopy

This paper describes the detection of various common gases by means of correlation spectroscopy, employing a complementary-source-modulation (CoSM) approach based on compact light-emitting diode (LED) sources. Theoretical results for the quantitative detection of O₂, CO, and CO₂ by this CoSM method are presented, using, as their basis, spectral absorption data from the Hitran database. In demonstrating the proposed detection principle, new experimental results for the detection of O₂ in air are presented, with the use of practical low-cost LED sources.     

A variational approach to a problem in boiler control

The paper describes work done in examining a particular problem of boiler control. The overall approach is the consideration of the boiler as a unit in the frequency control of an electrical power system.

The possibilities of including frequency control within the economic scheduling program are limited by the ability of the individual set to follow large amplitude load demands fast. This limitation is real and has arisen due to the previous empirical methods of control system design for this system. The scope of the problem outlined demands a broad approach.

One section describes the derivation of a large analytic non-linear computer model of a natural circulation, non-reheat, boiler. Conclusions are drawn as to the relative importance of various factors, design parameters and existing controls, to the dynamic characteristics of this system.

From these results, an even simpler model structure can be derived. A deterministic criterion, reflecting, for a single set, the regulating requirement of the system is desired and the resulting variational problem in two controls and two state variables is solved.

Similarly a one control problem is solved and by programming the open loop “optimal” control strategy, as input to the large analytic computer model, the effects of model simplification are demonstrated.     

An abstract programming language and correctness proofs

The realization of an abstract programming language is a good approach for automating the software production process and facilitating the correctness proof of a software system.

This paper introduces a formal language for programming at the abstract level by combining Pascal with VDM (Vienna Development Method). The notation provided by the language obliges programmers to consider the correctness of programs throughout the whole process of programming, and the proof axiom and rules presented in this paper may be used to prove the correctness of programs. A complete example is given to illustrate how to program using APL and how to prove the correctness of programs using the given axiom and rules.     

FP──VLSI自动综合系统

ＦＰ—ＶＬＳＩ自动综合系统是一个集成化的ＶＬＳＩ自动设计工具，它能完成从并行算法到脉动算法到脉动结构再到逻辑结构最后到ＣＭＯＳ版图的自动综合过程．ＦＰ—ＶＬＳＩ系统以脉动阵列为ＶＬＳＩ的体系结构，采用具有良好代数性质的ＦＰ／Ｂ语言作为各层次的描述语言，通过程序变换进行综合和优化．该系统支持形式化的ＶＬＳＩ设计方法，能保证设计结果的正确性．     

CCL: a portable and tunable collective communication library forscalable parallel computers

A collective communication library for parallel computers includes frequently used operations such as broadcast, reduce, scatter, gather, concatenate, synchronize, and shift. Such a library provides users with a convenient programming interface, efficient communication operations, and the advantage of portability. A library of this nature, the Collective Communication Library (CCL), intended for the line of scalable parallel computer products by IBM, has been designed. CCL is part of the parallel application programming interface of the recently announced IBM 9076 Scalable POWERparallel System 1 (SP1). In this paper, we examine several issues related to the functionality, correctness, and performance of a portable collective communication library while focusing on three novel aspects in the design and implementation of CCL: 1) the introduction of process groups, 2) the definition of semantics that ensures correctness, and 3) the design of new and tunable algorithms based on a realistic point-to-point communication model     

Towards an Efficient Path-Oriented Tool for Bounded Reachability Analysis of Linear Hybrid Systems using Linear Programming

The existing techniques for reachability analysis of linear hybrid automata do not scale well to problem sizes of practical interest. Instead of developing a tool to perform reachability check on all the paths of a linear hybrid automaton, a complementary approach is to develop an efficient path-oriented tool to check one path at a time where the length of the path being checked can be made very large and the size of the automaton can be made large enough to handle problems of practical interest. This approach of symbolic execution of paths can be used by design engineers to check important paths and thereby, increase the faith in the correctness of the system. Unlike simple testing, each path in our framework represents a dense set of possible trajectories of the system being analyzed. In this paper, we develop the linear programming based techniques towards an efficient path-oriented tool for the bounded reachability analysis of linear hybrid systems.     

A configuration approach to parallel programming

This paper advocates a configuration approach to parallel programming for distributed memory multicomputers, in particular, arrays of transputers. The configuration approach prescribes the rigorous separation of the logical structure of a program from its component parts. In the context of parallel programs, components are processes which communicate by exchanging messages. The configuration defines the instances of these processes which exist in the program and the paths by which they are interconnected.

The approach is demonstrated by a toolset (Tonic) which embodies the configuration paradigm. A separate configuration language is used to describe both the logical structure of the parallel program and the physical structure of the target multicomputer. Different logical to physical mappings can be obtained by applying different physical configurations to the same logical configuration. The toolset has been developed from the Conic system for distributed programming. The use of the toolset is illustrated through its application to the development of a parallel program to compute Mandelbrot sets.     

Development of an optical hydrogen sulphide sensor

A hydrogen sulphide (H₂S)-sensitive optode film has been fabricated by immobilising tetraoctylammonium fluorescein mercury(II) acetate (TOFMA) and tri-n-butyl phosphate in a poly(vinyl chloride) (PVC) matrix. The optode film, coated on an overhead transparency film, was employed as a sensing device for fluorimetric detection of H₂S. The fluorescence intensity monitored at 553 nm (excitation at 503 nm) increased with increasing H₂S concentrations. The optode film showed a good, linear and reversible response to H₂S from 0 to 15 ppm (v/v). It was optically stable and the reproducible response of the film on exposure to 10 ppm (v/v) H₂S was extremely good. There was no sign of degradation after 8 h of continuous use. The response to H₂S levelled off at about 27.5 ppm The response and recovery times of the optical H₂S sensor were fast and less than 2 and 5 s, respectively. An optically-based sensor for H₂S determination was successfully developed. It was anticipated that the system could be used to monitor H₂S with a concentration range of 0–25 ppm (v/v) with satisfactory results. A proposed mechanism for the detection of H₂S by the optode films is described.