Victor E. Malyshkin

Assembly technology for parallel realization of numerical models on MIMD-multicomputers

The main ideas of the assembly technology (AT) in its application to parallel realization of big size numerical models on a rectangular mesh are considered and demonstrated by the parallelization of the particle-in-cell (PIC) method. The realization of the numerical models with the assembly technology is based on the construction of a fragmented parallel program. This provides different useful properties of the target program including dynamic load balance on the basis of the fragments flying from overloaded to underloaded processor elements of a multicomputer.

Fragmentation of numerical algorithms for parallel subroutines library

Fragmentation is a well-known method of the parallelization of numerical algorithms and programs. Algorithm fragmentation allows creating fragmented parallel programs that can be executed on parallel computers of different types (multiprocessors and/or multicomputers) and can be dynamically tuned to all the available resources. Fragmentation of the often used numerical algorithms, their representation for inclusion into the library of parallel numerical subroutines and properties of the runtime system are considered.

Optimization methods of parallel execution of numerical programs in the LuNA fragmented programming system

The organization of high-performance execution of a fragmented program has encountered with the problem of choosing of an acceptable way of its execution. The potentialities of optimizing the execution at the stages of fragmented program development, compilation and execution are considered. The methods and algorithms of such an optimization are proposed to be included into the LuNA fragmented programming language, compiler, generator and run-time system.

LuNA fragmented programming system, main functions and peculiarities of run-time subsystem

The peculiarities of the LuNA run-time subsystem implementation are considered. LuNA is the language and system of fragmented programming. The peculiarities are conditioned by the properties of numerical algorithms, to implementation and execution of which the LuNA is mainly oriented.

Implementation of PIC Method on MIMD Multicomputers with Assembly Technology

Linearization of the PIC method and its implementation for multicomputers is discussed. This program is dynamically tuneable to the available resources of multicomputer and particles distribution.

Runtime system for parallel execution of fragmented subroutines

The architecture of a runtime system supporting parallel execution of fragmented library subroutines on multicomputers is proposed. The approach makes possible to develop the library of parallel subroutines and to provide automatically their dynamic properties such as dynamic load balancing. Usage of the MPI for communications programming provides good portability of an application.

The LuNA library of parallel numerical fragmented subroutines

The LuNA library of parallel numerical fragmented subroutines is now under development. It is aimed at automated treatment of a range of important and stubborn properties of numerical subroutines. The method of algorithm and program fragmentation is used. The library is being developed with the LuNA fragmented programming system. It provides all the necessary properties of subroutines and their high portability.

Filmification of Methods: Representation of Particle-In-Cell Algorithms

Filmification of methods is an approach to find new formats for program and data/knowledge representation. It is also to create a basis for specifying and developing a new generation of programming environments. Within this approach various algorithms are analyzed and represented as cyberFilms where special visual super-symbols (icons) are introduced for defining meaning of the cyberFilm frames. In this paper, the filmification of methods is applied for particle-in-cells algorithms. Results demonstrate a promising compactness of the program representation, covering technical details of parallel implementation and an effectiveness of an open set of icons.

NumGrid Middleware: MPI Support for Computational Grids

The paper presents the design and the first stage of implementation of the NumGRID middleware that is devoted to the development of the multicomputer grid software for the large scale numerical simulation. Global addressing of the NumGRID computational resources and MPI programs execution is provided. This stage is the basis for the development of supporting system that automatically provides the dynamic properties of MPI applications.

Distributed Algorithm of Data Allocation in the Fragmented Programming System LuNA

The paper presents distributed algorithm with local communications Rope-of-Beads for static and dynamic data allocation in the LuNA fragmented programming system. LuNA is intended for implementation of large-scale numerical models on multicomputers with large number of processors and various network topologies. The algorithm takes into account the structure of a numerical model, provides static and dynamic load balancing and can be used in various network topologies.