Parallel programming for computer vision

Two Unix environments developed for programming parallel computers to handle image-processing and vision applications are described. Visx is a portable environment for the development of vision applications that has been used for many years on serial computers in research. Visx was adapted to run on a multiprocessor with modest parallelism by using functional decomposition and standard operating-system capabilities to exploit the parallel hardware. Paragon is a high-level environment for multiprocessor systems that has facilities for both functional decomposition and data partitioning. It provides primitives that will work efficiently on several parallel-processing systems. Paragon's primitives can be used to build special image-processing operations, allowing one's own programming environment to be grown naturally     

A construction set for multimedia applications

The authors describe an interface system called Athena Muse. Muse is an experiment kit for the construction of multimedia learning environments. Learning environments developed with Muse offer a diverse set of complementary interaction techniques, styles, and devices. An interface developer can choose from four representation approaches: directed graphs, multidimensional spatial frameworks, declarative constraints, and procedural languages     

Symbolic quality control for multimedia applications

We present a fine grain quality control method for multimedia applications. The method takes as input an application software composed of actions. The execution times of actions are unknown increasing functions of quality level parameters. The method allows the construction of a Controller which computes adequate action schedules and corresponding quality levels, so as to meet QoS requirements for a given platform. These include requirements for safety (action deadlines are met) as well optimality (maximization and smoothness of quality levels). The Controller consists of a Quality Manager and a Scheduler. For each action, the Controller uses a quality management policy for choosing a schedule and quality levels meeting the QoS requirements. The schedule is selected amongst a set of optimal schedules computed by the Scheduler. We extend and improve results of previous papers providing a solid theoretical basis for designing and implementing the Controller. We propose a symbolic quality management method using speed diagrams, a representation of the controlled system’s dynamics. Instead of numerically computing a quality level for each action, the Quality Manager changes action quality levels based on the knowledge of constraints characterizing control relaxation regions. These are sets of states in which quality management for a given number of computation steps can be relaxed without degrading quality. We study techniques for efficient computation of optimal schedules. We present experimental results including the implementation of the method and benchmarks for an MPEG4 video encoder. The benchmarks show drastic performance improvement for controlled quality with respect to constant quality. They also show that symbolic quality management allows significant reduction of the overhead with respect to numeric quality management. Finally, using optimal schedules can lead to considerable performance gains.     

Parallel dynamic programming

Recurrence formulations for various problems, such as finding an optimal order of matrix multiplication, finding an optimal binary search tree, and optimal triangulation of polygons, assume a similar form. A. Gibbons and W. Rytter (1988) gave a CREW PRAM algorithm to solve such dynamic programming problems. The algorithm uses O(n⁶/log n) processors and runs in O(log² n) time. In this article, a modified algorithm is presented that reduces the processor requirement to O(n⁶/log ⁵n) while maintaining the same time complexity of O(log² n)     

Parallel programming inPanda

Distributed systems are an alternative to shared-memory multiprocessors for the execution of parallel applications.Panda is a run-time system that provides architectural support for efficient parallel and distributed programming. It supplies fast user-level threads and a means for transparent and coordinated sharing of objects across a homogeneous network. The paper motivates the major architectural choices that guided our design. The problem of sharing data in a distributed environment is discussed, and the performance of the mechanisms provided by thePanda prototype implementation is assessed.     

Parallel programming interface for distributed data

The Parallel Programming Interface for Distributed Data (PPIDD) library provides an interface, suitable for use in parallel scientific applications, that delivers communications and global data management. The library can be built either using the Global Arrays (GA) toolkit, or a standard MPI-2 library. This abstraction allows the programmer to write portable parallel codes that can utilise the best, or only, communications library that is available on a particular computing platform.Program summaryProgram title: PPIDDCatalogue identifier: AEEF_v1_0Program summary URL: http://cpc.cs.qub.ac.uk/summaries/AEEF_1_0.htmlProgram obtainable from: CPC Program Library, Queen's University, Belfast, N. IrelandLicensing provisions: Standard CPC licence, http://cpc.cs.qub.ac.uk/licence/licence.htmlNo. of lines in distributed program, including test data, etc.: 17 698No. of bytes in distributed program, including test data, etc.: 166 173Distribution format: tar.gzProgramming language: Fortran, CComputer: Many parallel systemsOperating system: VariousHas the code been vectorised or parallelized?: Yes. 2–256 processors usedRAM: 50 MbytesClassification: 6.5External routines: Global Arrays or MPI-2Nature of problem: Many scientific applications require management and communication of data that is global, and the standard MPI-2 protocol provides only low-level methods for the required one-sided remote memory access.Solution method: The Parallel Programming Interface for Distributed Data (PPIDD) library provides an interface, suitable for use in parallel scientific applications, that delivers communications and global data management. The library can be built either using the Global Arrays (GA) toolkit, or a standard MPI-2 library. This abstraction allows the programmer to write portable parallel codes that can utilise the best, or only, communications library that is available on a particular computing platform.Running time: Problem dependent. The test provided with the distribution takes only a few seconds to run.     

Declarative programming for agent applications

This paper introduces the execution model of a declarative programming language intended for agent applications. Features supported by the language include functional and logic programming idioms, higher-order functions, modal computation, probabilistic computation, and some theorem-proving capabilities. The need for these features is motivated and examples are given to illustrate the central ideas.     

Object-oriented programming for engineering applications

The object-oriented programing (OOP) methodology is introduced as a means for improving the management of a complex engineering software. The drawbacks of existing engineering software development techniques are pinpointed. The basic concepts of the OOP methodology are interpreted in the context of engineering applications. The familiar concept of a matrix is used as an example to interpret the ideas presented. It is concluded that the OOP methodology facilitates the management of complex engineering software systems.     

一种面向多对象多媒体应用的同步控制方法

多对象多媒体应用允许多路媒体同时呈现,其同步控制比较复杂,可分为传输过程中与呈现过程中的同步。然而现有的同步方法忽略了媒体在最后呈现过程中的同步,也没有考虑各媒体对象之间的同步要求差异。针对以上问题,为视频点播提出了一种在应用层上控制多对象多媒体同步呈现质量的方法。在采用多级缓冲门限实现媒体内同步反馈控制的基础上,依据主要媒体对象的呈现时间戳,在每一个呈现场景内调整次要媒体对象的呈现速率,从而实现媒体间的同步呈现。实验结果表明该方案能够有效地提高同步质量,且媒体间的同步性能平均提高28.45%。     

Supporting interactive presentation for distributed multimedia applications

In this paper we present IMP, a platform to support the authoring and run-time management of interactive multimedia applications in distributed environments. The multi-level platform model encourages slot-in extensibility to cater for the evolving environment. We illustrate with our prototype platform built above the Cambridge multimedia environment. The authoring model emphasises reusability, tailorability and use of environment features in a uniform way. We have shown the validity of our approach by constructing a variety of application types.     

Energy efficiency for edge multimedia elastic applications

With the rise of edge computing paradigms, multimedia applications will have to tackle unprecedented management issues, pursuing an optimal balance between performance, Quality of Service (QoS), and power consumption. In this paper, we investigate a novel paradigm to deploy multimedia elastic applications at the edge in a very energy-efficient manner. Our approach is based on pre-provisioning virtual resources that remain “frozen” until the application scales out. Frozen resources are treated in a special way by the infrastructure, leveraging aggressive power-saving mechanisms that keep negligible their impact on energy consumption and performance. We report extensive measurements on QoS and power consumption that we carried out in a real testbed, which is the first working implementation of the proposed paradigm. Our work shows how resource utilization and performance can be increased by leveraging SDN technologies and conscious setting of cloud parameters. We investigate the trade-off between performance and power consumption (i.e., energy efficiency), in relation to different consolidation strategies. Finally, we measure power consumption and estimate energy saving for an elastic video transcoding application deployed at the network edge.

     

Counting-based secret sharing technique for multimedia applications

Multimedia Tools and Applications - Secret Sharing is required in situations where access to important resources has to be protected by more than one person. We propose new secret-sharing scheme...     

Advances in fractal compression for multimedia applications

Fractal image compression is a promising new technology but is not without problems. Most critically, fast encoding is required for it to find wide use in multimedia applications. This is now within reach: recent methods are five orders of magnitude faster than early attempts. Beginning with the basic ideas and problems, this paper explains how to accelerate fractal image compression.     

A support platform for distributed multimedia applications

Abstract

Considerable progress has been made in the development of technologies to support distributed multimedia computing, such that there is now a wide range of pilot applications under development. The design of support systems which help in the development of multimedia applications is therefore an emerging area of research. This paper discusses the requirements of distributed multimedia applications with respect to their support environments. A number of experimental systems are then described which intend to provide the necessary facilities for multimedia applications. Particular focus is placed on the Lancaster system which provides multimedia support for open distributed systems.     

Parallel linear genetic programming for multi-class classification

Motivated by biological inspiration and the issue of instruction disruption, we develop a new form of Linear Genetic Programming (LGP) called Parallel LGP (PLGP) for classification problems. PLGP programs consist of multiple lists of instructions. These lists are executed in parallel after which the resulting vectors are combined to produce the classification result. PLGP limits the disruptive effects of crossover and mutation, which allows PLGP to significantly outperform regular LGP. Furthermore, PLGP programs are naturally suited to caching due to their parallel architecture. Although caching techniques have been used in tree based GP, to our knowledge, there are no caching techniques specifically developed for LGP. Thus, a novel caching technique is also developed with the intrinsic properties of PLGP in mind, which can decrease fitness evaluation time by almost an order of magnitude for the classification problems.     

Parallel programming for a chess endgame database

This paper presents a parallel implementation in APL of an algorithm to set up a database for the KRK -endgame in chess. It shows clearly the techniques necessary to achieve the parallelism and thereby proves that APL can be a valuable productivity increasing aid in this kind of Artificial Intelligence (AI)-research. The complete APL-functions are given in the Appendix. Both reversed pigeon hole and bit map techniques are used. Move generation is table driven with a new technique to cater for the blockage of sliding pieces like a rook. In order to maintain parallelism ‘if’ statements are avoided and extensive use is made of compression and identity elements.     

Parallel programming with Polaris

Parallel programming tools are limited, making effective parallel programming difficult and cumbersome. Compilers that translate conventional sequential programs into parallel form would liberate programmers from the complexities of explicit, machine oriented parallel programming. The paper discusses parallel programming with Polaris, an experimental translator of conventional Fortran programs that target machines such as the Cray T3D