The System for Transforming the Code of Dataflow Programs into Imperative

Functional dataflow programming languages are designed to create parallel portable programs. The source code of such programs is translated into a set of graphs that reflect information and control dependencies. The main way of their execution is interpretation, which does not allow to perform calculations efficiently on real parallel computing systems and leads to poor performance. To run programs directly on existing computing systems, you need to use specific optimization and transformation methods that take into account the features of both the programming language and the architecture of the system. Currently, the most common is the Von Neumann architecture, however, parallel programming for it in most cases is carried out using imperative languages with a static type system. For different architectures of parallel computing systems, there are various approaches to writing parallel programs. The transformation of dataflow parallel programs into imperative programs allows to form a framework of imperative code fragments that directly display sequential calculations. In the future, this framework can be adapted to a specific parallel architecture. The paper considers an approach to performing this type of transformation, which consists in allocating fragments of dataflow parallel programs as templates, which are subsequently replaced by equivalent fragments of imperative languages. The proposed transformation methods allow generating program code, to which various optimizing transformations can be applied in the future, including parallelization taking into account the target architecture.

Download Full-text

Evolution of Visualization Methods for Research Publication Collections

Russian Digital Libraries Journal ◽

10.26907/1562-5419-2020-23-4-788-807 ◽

2020 ◽

Vol 23 (4) ◽

pp. 788-807

Author(s):

Alexander Ivanovich Legalov ◽

Igor Alexandrovich Legalov ◽

Ivan Vasilievich Matkovsky

Keyword(s):

Parallel Computing ◽

Parallel Programming ◽

Programming Language ◽

Functional Model ◽

Parallel Programs ◽

Instrumental Support ◽

Static System ◽

Research Publication ◽

Computing Systems ◽

Static Typing

It is proposed to add a static system of types to the dataflow functional model of parallel computing and the dataflow functional parallel programming language developed on its basis. The use of static typing increases the possibility of transforming dataflow functional parallel programs into programs running on modern parallel computing systems. Language constructions are proposed. Their syntax and semantics are described. It is noted that the need to use the single assignment principle in the formation of data storages of a particular type. The features of instrumental support of the proposed approach are considered.

Download Full-text

Software complex for modeling and optimization of program implementation on parallel calculation systems

Open Computer Science ◽

10.1515/comp-2018-0019 ◽

2018 ◽

Vol 8 (1) ◽

pp. 228-234

Author(s):

Valery Bakanov

Keyword(s):

Parallel Computing ◽

Programming Language ◽

Program Implementation ◽

Parallel Programs ◽

Software Environment ◽

Computing Systems ◽

Plan Execution ◽

Modeling And Optimization ◽

Software Complex

Abstract The paper considers the problem of developing rational methods for the creation of a framework (a plan, execution timetable) of parallel programs for real parallel computing systems. To solve this problem, a software environment (software stand) has been developed that allows implementing different strategies for building a framework for parallel programs and assessing the quality of these strategies. The built-in script Lua programming language is used to increase the flexibility of modeling and optimization capabilities. Results of applying some of the proposed strategies for constructing rational plans for parallel programming are outlined.

Download Full-text

Shaping the foundations of programming languages

Communications of the ACM ◽

10.1145/3460442 ◽

2021 ◽

Vol 64 (6) ◽

pp. 120

Author(s):

Leah Hoffmann

Keyword(s):

Science Education ◽

Computer Science ◽

Programming Languages ◽

Computer Science Education ◽

The Future ◽

Turing Award

ACM A.M. Turing Award recipients Alfred Aho and Jeffrey Ullman discuss their early work, the 'Dragon Book,' and the future of 'live' computer science education.

Download Full-text

A Neural Network Decomposition Algorithm for Mapping on Crossbar-Based Computing Systems

Electronics ◽

10.3390/electronics9091526 ◽

2020 ◽

Vol 9 (9) ◽

pp. 1526 ◽

Cited By ~ 1

Author(s):

Choongmin Kim ◽

Jacob A. Abraham ◽

Woochul Kang ◽

Jaeyong Chung

Keyword(s):

Neural Network ◽

Neural Networks ◽

Predictive Performance ◽

Fixed Number ◽

Decomposition Algorithm ◽

Computing Systems ◽

Network Decomposition ◽

Von Neumann ◽

Analog Computing ◽

The Neural Network

Crossbar-based neuromorphic computing to accelerate neural networks is a popular alternative to conventional von Neumann computing systems. It is also referred as processing-in-memory and in-situ analog computing. The crossbars have a fixed number of synapses per neuron and it is necessary to decompose neurons to map networks onto the crossbars. This paper proposes the k-spare decomposition algorithm that can trade off the predictive performance against the neuron usage during the mapping. The proposed algorithm performs a two-level hierarchical decomposition. In the first global decomposition, it decomposes the neural network such that each crossbar has k spare neurons. These neurons are used to improve the accuracy of the partially mapped network in the subsequent local decomposition. Our experimental results using modern convolutional neural networks show that the proposed method can improve the accuracy substantially within about 10% extra neurons.

Download Full-text

PARALLEL COMPUTING OF NUMERICAL SCHEMES AND BIG DATA ANALYTIC FOR SOLVING REAL LIFE APPLICATIONS

Jurnal Teknologi ◽

10.11113/jt.v78.9552 ◽

2016 ◽

Vol 78 (8-2) ◽

Cited By ~ 2

Author(s):

Norma Alias ◽

Nadia Nofri Yeni Suhari ◽

Hafizah Farhah Saipan Saipol ◽

Abdullah Aysh Dahawi ◽

Masyitah Mohd Saidi ◽

...

Keyword(s):

Big Data ◽

Parallel Computing ◽

Parallel Algorithm ◽

Sparse Matrices ◽

Real Life ◽

Poor Performance ◽

Equation System ◽

Numerical Schemes ◽

Linear Equation System ◽

Data Analytic

This paper proposed the several real life applications for big data analytic using parallel computing software. Some parallel computing software under consideration are Parallel Virtual Machine, MATLAB Distributed Computing Server and Compute Unified Device Architecture to simulate the big data problems. The parallel computing is able to overcome the poor performance at the runtime, speedup and efficiency of programming in sequential computing. The mathematical models for the big data analytic are based on partial differential equations and obtained the large sparse matrices from discretization and development of the linear equation system. Iterative numerical schemes are used to solve the problems. Thus, the process of computational problems are summarized in parallel algorithm. Therefore, the parallel algorithm development is based on domain decomposition of problems and the architecture of difference parallel computing software. The parallel performance evaluations for distributed and shared memory architecture are investigated in terms of speedup, efficiency, effectiveness and temporal performance.

Download Full-text