Architecture - 1. Introduction

Chapter navigation menu:
[Architecture - 1. Introduction]
[Architecture - 2. Initial situation and objective]
[Architecture - 3. Architecture & Technologies]
[Architecture - 4. Use cases]
[Architecture - 5. Security relevant requirements]

[Installation - 1. Introduction]
[Installation - 2. Installation]
[Installation - 3. Getting the use cases]

Document navigation:

• 1. Introduction
  • 1.1 Parallel computing
  • 1.2 Messaging Passing Interface
  • 1.3 OpenMPI
  • 1.4 High Performance Computing

1. Introduction

For this Software Project the area of Parallel Computing was the main subject, what the Software is going to be developed and used for.

1.1 Parallel computing

Parallel computing is a method of computation in which many calculations are solved simultaneously with the main focus on dividing large problems into smaller ones. The conclusion out of this is that those smaller problems can be then solved concurrently (“in parallel”). Obviously the difference between parallel programs and sequential programs is the communication and synchronization between the different subtasks, which are some of the biggest obstacles. To help the development of parallel programs there are different libraries on the market. One of those is called OpenMPI (Open Messaging Passing Interface) and is one of the most widely used parallel computing libraries out there.

1.2 Messaging Passing Interface

In general a Messaging Passing Interface is a standardized and portable message passing system designed to function on a wide variety of parallel computers. “The standard defines the syntax and semantics of a core of library routines useful to a wide range of users writing portable message-passing programs in Fortran 77 or the C programming language.” (Wikipedia 1) Having a clearly defined base set of routines allows hardware vendors to build upon this distributed-memory communication environment supplied with their parallel machines. In short, MPI is a language-independent communications protocol used to program parallel computers. Its goals are high performance, scalability and portability which make it the dominant model used in high-performance computing.

1.3 OpenMPI

OpenMPI is an open source MPI-2 implementation that is developed and maintained by a consortium of academic, research and industry partners. Open MPI is therefore able to combine the expertise, technologies and resources from all across the High Performance Computing community in order to build the best MPI library available.

Features of OpenMPI:

• Full MPI-2 standards conformance
• Thread safety and concurrency
• Dynamic process spawning
• Network and process fault tolerance
• Support network heterogeneity
• Single library supports all networks
• Run-time instrumentation
• Many job schedulers supported
• Many OS's supported (32 and 64 bit)
• Production quality software
• High performance on all platforms
• Portable and maintainable
• Tunable by installers and end-users
• Component-based design, documented APIs
• Active, responsive mailing list
• Open source license.

1.4 High Performance Computing

It uses supercomputers and computer clusters to solve advanced computation problems. This includes computers, networks, algorithms and environments to make cluster of computers or supercomputer systems usable in profoundly efficient and effective manner.