检索结果-内蒙古大学图书馆

12th IEEE/IFIP International Conference on Embedded and ubiquitous computing (EUC)

作者： Burgio, Paolo Marongiu, Andrea Coussy, Philippe Benini, Luca Univ Bretagne Sud LabSTICC Lorient France Univ Bologna DEI I-40126 Bologna Italy Swiss Fed Inst Technol Integrated Syst Lab Zurich Switzerland

ISBN: (纸本)9780769552491

This work describes how we use High-Level Synthesis to support design space exploration (DSE) of heterogeneous many-core systems. Modern embedded systems increasingly couple hardware accelerators and processing cores on the same chip, to trade specialization of the platform to an application domain for increased performance and energy efficiency. However, the process of designing such a platform is complex and error-prone, and requires skills on algorithmic aspects, ardware synthesis, and software engineering. DSE can partially be automated, and thus simplified, by coupling the use of HLS tools and virtual prototyping platforms. In this paper we enable the design space exploration of heterogeneous many-cores adopting a shared-memory architecture template, where communication and synchronization between the hardware accelerators and the cores happens through L1 shared memory. This communication infrastructure leverages a "zero-copy" scheme, which simplifies both the design process of the platform and the development of applications on top of it. Moreover, the shared-memory template perfectly fits the semantics of several high-level programming models, such as OpenMP. We provide programmers with simple yet powerful abstractions to exploit accelerators from within an OpenMP application, and propose a low-cost implementation of the necessary runtime support. An HLS-based automatic design flow is set up, to quickly explore the design space using a cycle-accurate virtual platform.

关键词： embedded systems parallel programming shared memory systems DSE HLS-based toolflow L1 shared memory OpenMP application cycle-accurate virtual platform design space exploration high-level programming models high-level synthesis modern embedded systems next-generation heterogeneous many-core platforms shared-memory architecture template Acceleration Computer architecture Hardware Program processors programming Registers Synchronization OpenMP clustered architectures heterogeneous architectures hls many-core systems shared-memory systems Embedded systems shared memory systems high level synthesis Space Exploration DSE gene Program processors Computer Architecture Registers Parallel programming shared memory Computer hardware programming hardware accelerator Platform acceleration

来源：评论

学校读者我要写书评

暂无评论

Scalable Collectives for Distributed Asynchronous Many-Task Runtimes 32

Scalable Collectives for Distributed Asynchronous Many-Task ...

引用

27th International Heterogeneity in computing workshop in conjunction with 32nd IEEE International Parallel and Distributed Processing Symposium (IPDPS)

作者： Whitlock, Matthew Kolla, Hemanth Treichler, Sean Pebay, Philippe Bennett, Janine C. Oklahoma State Univ Stillwater OK 74078 USA Sandia Natl Labs Livermore CA 94550 USA Stanford Univ Stanford CA 94305 USA NexGen Analyt Sheridan WY USA

ISBN: (纸本)9781538655559

Global collectives (reductions/aggregations) are ubiquitous and feature in nearly every application of distributed high-performance computing (HPC). While it is advisable to devise algorithms by placing collectives off the critical path of execution, they are sometimes unavoidable for correctness, numerical convergence and analyses purposes. Scalable algorithms for distributed collectives are well studied and have become an integral part of MPI, but new and emerging distributed computing frameworks and paradigms such as Asynchronous Many-Task (AMT) models lack the same sophistication for distributed collectives. Since the central promise of AMT runtimes is that they automatically discover, and expose, task dependencies in the underlying program and can schedule work optimally to minimize idle time and hide data movement, a naively designed collectives protocol can completely offset any gains made from asynchronous execution. In this study we demonstrate that scalable distributed collectives are indispensable for performance in AMT models. We design, implement and test the performance of a scalable collective algorithm in Legion, an exemplar data-centric AMT programming model. Our results show that AMT systems contain the necessary primitives that allow for fully scalable collectives without breaking the transparent data movement abstractions. Scalabiity tests of an integrated Legion 1D stencil mini-application show the clear benefit of implementing scalable collectives and the performance degradation when a naive collectives alternative is used instead.

关键词： programming models Asynchronous Many-Task Parallel computing Distributed Collectives Computational Statistics

来源：评论

学校读者我要写书评

暂无评论

Process mining for ubiquitous mobile systems: An overview and a concrete algorithm

引用

2nd CAiSE workshop on ubiquitous Mobile Information and Collaboration Systems

作者： de Medeiros, AKA van Dongen, BF van der Aalst, WMP Weijters, AJMM Eindhoven Univ Technol Dept Technol Management NL-5600 MB Eindhoven Netherlands

ISBN: (纸本)3540241000

ubiquitous Mobile Systems (UMSs) allow for automated capturing of events. Both mobility and ubiquity are supported by electronic means such as mobile phones and PDAs and technologies such as RFID, Bluetooth, WLAN, etc. These can be used to automatically record human behavior and business processes in detail. UMSs-typically also allow for more flexibility. The combination of flexibility (i.e., the ability to deviate from standard procedures) and the automated capturing of events, provides an interesting application domain for process mining. The goal of process mining is to discover process models from event logs. The a-algorithm is a process mining algorithm whose application is not limited to ubiquitous and/or mobile systems. Unfortunately, the alpha-algorithm is unable to tackle so-called "short loops", i.e., the repeated occurrence of the same event. Therefore, a new algorithm is proposed to deal with short loops: the alpha(+)-algorithm. This algorithm has been implemented in the EMiT tool.

关键词： process mining workflow mining Petri nets mobile computing ubiquitous computing

来源：评论

学校读者我要写书评

暂无评论

Next-generation Grids: requirements and knowledge-based services

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2006年第8期18卷 887-898页

作者： Cannataro, Mario Magna Graecia Univ Catanzaro I-88100 Catanzaro Italy

To be effectively adopted in different application domains, next-generation Grids need to address different issues such as: an increasing complexity and distribution of applications;different goals, skills and habits of Grid users;availability of different programming and deployment models;heterogeneous capabilities and performances of access networks and devices. Moreover, scientific and commercial applications, as well as Grid middleware, will increasingly produce an overwhelming quantity of application and usage data. Although the ongoing convergence between Grids, Web Services, and the Semantic Web constitutes a milestone towards a service-oriented Grid architecture, which has the potential to face important issues such as application programming and business modelling, many other issues need research and development efforts. The great availability of data and information at the different layers of Grids, the maturity of data exploration techniques able to extract and synthesize knowledge, such as data mining, text summarization, semantic modelling, and knowledge management, and the demand for intelligent services in different phases of application life cycle are the driving forces towards novel knowledge-based Grid services. Guided by those considerations, the paper first introduces main requirements of next-generation Grids and then describes some representative knowledge-based Grid services for both applications support and system management. Simple cases study showing how such services could be employed are discussed. Copyright (c) 2005 John Wiley & Sons, Ltd.

关键词： next-generation Grids knowledge Grids Semantic Grids knowledge-based Grid services ontologies data mining adaptive systems ubiquitous computing context-awareness

来源：评论

学校读者我要写书评

暂无评论

On the Migration of OpenACC-Based applications into OpenMP 5+ 18th

On the Migration of OpenACC-Based Applications into OpenMP 5...

引用

18th International workshop on OpenMP (IWOMP)

作者： Servat, Harald Rossi, Giacomo Duran, Alejandro Narayanaswamy, Ravi Intel Corp Santa Clara CA 95054 USA

ISBN: (纸本)9783031159220;9783031159213

OpenACC* and OpenMP* have been supporting offloading to accelerators for almost a decade now, with OpenACC leading the adoption rate for the usage in the context of accelerated computing. However, as OpenACC only supports limited device vendors, there has been a growing interest in adopting OpenMP for offloading to accelerators, especially now with an increasing number of accelerator vendors supporting OpenMP offload. Motivated by the recent additions into the OpenMP 5+ specifications and the wider compiler adoption of these versions, we have developed and open-sourced the Intel (R) application Migration Tool for OpenACC to OpenMP API. We present the tool in this paper and discuss the singularities and commonalities of both programming models, and then we present the migration tool, discuss its implementation and its limitations, and present successful stories when migrating applications from OpenACC to OpenMP 5+.

关键词： Accelerated computing application portability tools

来源：评论

学校读者我要写书评

暂无评论

A model based architecture for the semi-automatic generation of multiplatform applications: Brake system diagnostic application

A model based architecture for the semi-automatic generation...

引用

1st Iberoamerican Congress on ubiquitous computing, CICU 2005

作者： Jurado, Francisco Santofimia, María José Redondo, Miguel A. Grupo de Investigación CHICO Escuela Superior de Informática Universidad de Castilla - La Mancha Paseo de la Universidad 4 13071 Ciudad Real Spain

The diagnostics of electro-pneumatic brake system for industrial vehicles is a process dependent on the system manufacturer. With regard to this, the tools developed by manufactures are usually aimed to steady platforms devoid of standards. In order to lighten this drawback, we propose the design of model based tools for the semi-automatic generation of multiplatform applications, from domain, task, and platform (PC, Tablet PC, PDA, "proprietary devices", etc.) models. This paper describes the architectural approach for the diagnostic application generator tool. This paper also points out some of the problems that need to be solved, and lines of work are proposed on this regard.

关键词： Personal computers

来源：评论

学校读者我要写书评

暂无评论

Next-generation Grids: requirements and knowledge-based services

Next-generation Grids: requirements and knowledge-based serv...

引用

1st International workshop on Emerging Technologies for Next-Generation GRID (ETNGRID 2004)

作者： Cannataro, Mario Magna Graecia Univ Catanzaro I-88100 Catanzaro Italy

关键词： next-generation Grids knowledge Grids Semantic Grids knowledge-based Grid services ontologies data mining adaptive systems ubiquitous computing context-awareness

来源：评论

学校读者我要写书评

暂无评论

Towards Next-Generation Graph Processing and Management Platform

Towards Next-Generation Graph Processing and Management Plat...

引用

ACM workshop on High Performance Graph Processing (HPGP)

作者： Suzumura, Toyotaro IBM Corp Thomas J Watson Res Ctr Yorktown Hts NY 10598 USA Univ Tokyo Barcelona Supercomp Ctr Tokyo 1138654 Japan

ISBN: (纸本)9781450343503

application which need to process and manage large graph data sets have imposed significant challenges for data science community inrecent times. This talk discusses the key challenges which need to be handled when implementing a next-generation graph processing and management platform. There are severalkey problems which needs to bead dressed in building such large graph processing system. First, optimized techniques needs to be followed for managing extremely large graph data. Second, new programming models and software tools need to be created for efficiently processing large graphs. This talk will discuss the approaches which need to be followed in addressing these two major issues and will highlight our vision in achieving the challenges of next-generation graph processing and management.

关键词： Large Graph Processing High Performance computing Graph Data Management Graph Algorithm

来源：评论

学校读者我要写书评

暂无评论

NATO Advanced Research workshop on Advanced Environments, tools and applications for Cluster computing, IWCC 2001

NATO Advanced Research Workshop on Advanced Environments, To...

引用

NATO Advanced Research workshop on Advanced Environments, tools and applications for Cluster computing, IWCC 2001

ISBN: (纸本)9783540436720

The proceedings contain 32 papers. The special focus in this conference is on Advanced Environments, tools, and applications for Cluster computing. The topics include: A new technology for the advanced web;programming models for cluster computing;about design and efficiency of distributed programming;a collaborative environment for high performance computing;reliability techniques for cluster system in internet services;computational issues in E-commerce trading exchanges;embedded cluster computing through dynamic reconfigurability of inter-processor connections;parallelisation of wave propagation algorithms for odour propagation in multi-agent systems;parallel and distributed solutions for the optimal binary search tree problem;a framework for efficient sparse LU factorization in a cluster based platform;task allocation using processor load prediction on multiprocessors cluster;multi-application scheduling in networks of workstations and clusters of processors;the parallel algorithm of conjugate gradient method;a parallel similarity search in high dimensional metric space using M-tree;a user level interface for clustering mathematical software kernels;communication balancing for wireless nodes in a LAN-WAN cluster;an architecture and task scheduling algorithm for systems based on dynamically reconfigurable shared memory clusters;a distributed application for Monte Carlo simulations;a model for accessing resources of the distributed file systems;coarse-grain parallelization of test vectors generation on multiprocessor systems and advanced collaboration techniques between java objects distributed on clusters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ubiquitous 3D for the network-centric battlefield - Smaller is better

Ubiquitous 3D for the network-centric battlefield - Smaller ...

引用

2005 Spring Simulation Interoperability workshop, SIW 2005

作者： Snyder, Mark Quantum3D Inc 7055 W. Bell Rd Ste 6 GlendaleAZ85308 United States

This paper discusses advancements in computer graphics technology for mobile systems and its potential impact on the battlefield of tomorrow. The advent of graphics technology targeted for mobile gaming systems combined with emerging standards like OpenGL-ES will result in the availability of very low power and low cost systems capable of delivering advanced 2D and 3D graphics anywhere. 2D and 3D moving maps, self-contained training and mission planning, and sensor fusion capabilities are just some of the areas where advanced graphics capabilities will aid the soldier of tomorrow. Graphical computing systems integrated into a soldier's gear, from his helmet to his weapon to his clothing, are now becoming possible. This paper addresses several topic areas relative to ubiquitous 3D. How can the network-centric battlefield benefit from this forthcoming revolution in graphics? What kind of capabilities can we envision equipping the soldier of tomorrow with? What hardware and software tools can be used to develop graphics for these systems. © 2005 The MITRE Corporation. All rights reserved.

关键词： application programming interfaces (API)

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：