一种多核动态可重配置处理器设计

动态可重配置技术因其所具有的高性能，低功耗和高度灵活性等特点，已经成为研究的热点。本文从动态可重配置处理器技术的基本概念，产生背景，实现方案分类等方面进行了介绍。提出了一种多核动态可重配置处理器设计方案。并简述了该技术目前存在的问题，展望了未来的研究方向。     

基于FPGA的多模块动态可重配置系统

提出了一种基于现场可编程门阵列FPGA的多模块动态可重配置系统平台,并在该平台上实现了一个多模块动态自重配置发射机系统.与传统的动态可重配置系统相比,多模块动态可重配置系统的各动态模块能够单独地进行重配置,重配置控制比较灵活,部分重配置比特流较小,所需的部分重配置比特流数量较少.     

基于FPGA的高速网络入侵检测系统

处理速度成为制约基于软件的网络入侵检测系统性能的瓶颈。文中提出了用可重配置硬件(FPGA)和商用千兆以太网MAC实现的网络入侵检测系统体系结构。在该体系结构中，网络数据包的特征匹配以及复杂协议分析等高强度的计算均由可重配置硬件电路完成，而使主机CPU更专注于对复杂入侵方式的检测和对入侵行为的实时响应。分析表明，该体系结构能够快速适应入侵特征变化对硬件电路的重配置需求，使网络入侵检测系统可以以线速处理网络数据包。     

动态部分重配置及其FPGA实现

动态部分重配置充分利用了FPGA芯片提供的可重配置功能，提高了FPGA芯片的利用率，减小了FPGA芯片的配置时间，有效地提高了系统的整体性能。该文介绍了动态部分重配置的两种实现方法，并在Spartan-II FPGA上进行了验证。     

分布式可重配置航空测控系统设计与实现

通用化、小型化、高可靠性、使用便捷是对大型军用复杂武器装备外场保障设备的通用要求;近年来,随着网络技术、嵌入式计算机技术特别是"可重构计算"技术的发展,可重配置的嵌入式测控系统开发技术成为当前研究的一个热点;文章对该项技术进行了深入研究,并结合飞机子系统外场测试的实际情况,提出并设计实现了一种分布式可重配置航空测控系统;与传统的集中控制测试系统相比较,该系统的体积小、重量轻,使用方便,通过可重配置技术使得测控系统可适应不同的测试需求;该系统的设计实现对军用复杂武器装备外场检测设备设计具有很好的借鉴意义。     

基于多核ARM的可重构LXI测试设备设计

借鉴合成仪器的设计理念,提出一种LXI总线标准的可重构便携测试设备设计.该设备以多核ARM处理器与大容量FPGA组成的软硬件在线可重配置结构,通过LVDS高速总线与紧凑通用测试功能模块通信,实现测试现场软硬件灵活编程配置,很好地解决了通用性、灵活性与小型化等相互制约矛盾的测试需求;采用Android操作系统,支持手机、平板电脑等智能终端通过无线网络进行操作,为现场配置和操作提供了更大的灵活性.     

可管理型交换机及其配置软件的设计

针对现有可管理型交换机命令行配置方式需要记忆并需严格按顺序输入配置命令,使用繁琐不易掌握的问题,采用VB实现了可管理型交换机窗口化配置界面,采用C语言编写了管理CPU的配置命令帧收发和解析程序及模拟SMI时序软件,并通过该模拟SMI时序软件完成了管理CPU对交换机片内寄存器的读取/写入,从而实现了对交换机的可管理型配置。测试结果表明,配置软件使用简单可靠,配置后的可管理型交换机运行稳定。     

二维离散小波变换的可重配置VLSI架构

设计一种二维离散小波变换的可重配置VLSI架构。根据二维图像处理中数据量大、芯片面积主要由片上的SRAM存储器决定的特点,提出使用单13SRAM的内存优化技术,在偶数周期,源数据由片上RAM读出,计算结果存在寄存器组中,在奇数周期,源数据由寄存器组读出,计算结果存放在RAM中。该方法较传统的双口SRAM实现节省了约56％的芯片面积。以此为基础,提出一种改进的基于图像块的扫描方式,使模块之间的数据传输性能相比于通常的基于行的实现方式提高了20％。     

可重配置系统研究与分析

随着通信和多媒体技术的发展,出现了大量新的应用模型,传统的嵌入式设备一般采用专用硬件芯片或者基于纯粹的软件方案,很难兼顾性能和灵活性两个方面的要求。为此,能够兼顾两者优点的可重配置系统越来越受到工业界和学术界的重视,成为研究的热点。文章对可重配置系统进行了综述,从可重配置系统的硬件和软件结构两个角度出发,介绍了相关的研究工作,并展望了其未来的发展方向。     

可重配置DNC系统的设计与实现

为了使DNC系统适应不同配置的制造单元,同时有效地控制和管理制造单元中数控机床的加工过程,该文从DNC系统的控制软件可重配置以及硬件通讯平台可重配置的角度出发,提出了一种可重配置制造单元中数控机床的DNC控制设计方法,同时采用面向对象技术进行DNC系统软件的设计和开发,所开发的系统集NC程序编辑、NC程序管理、DNC控制为一体,能够满足动态单元和可重构制造单元等DNC的控制要求。     

可重构制造系统的可重构控制器

可重构控制器是可重构制造系统的重要组成部分之一。该文提出了可重构控制器的体系结构。分析了实现可重构制造系统的可重构控制的方法。仿真研究表明可重构控制是实现可重构制造系统控制系统可重构的有效方法。     

基于免疫重构的阴性选择算法

针对阴性选择算法在解决实际问题中,易误判及自修复能力差的弱点,该文基于生物免疫系统内部学习优化机制以及工业领域中的可重构系统,提出了一种基于免疫重构的阴性选择算法.新算法将可重构系统的思想融入到阴性选择算法中,提出了重构串、重构模型与重构操作的概念与实现方法,以保证系统发生意外的时候能够及时恢复、重组.将算法应用于一个Web系统进行仿真实验,结果表明该算法是有效的.     

Modular machine tools: Design and barriers to industrial implementation

The Reconfigurable Manufacturing System (RMS) paradigm has been developed to address challenges in the design of manufacturing systems and equipment that will meet the demands of modern manufacturing. This research involved the development of Modular Reconfigurable Machines (MRMs); as an emerging technology in reconfigurable manufacturing. MRMs are mechanically modular machines. The modularity permits the kinematic architecture and processing functions of the machine to be reconfigured to meet changing production requirements. This paper will focus on aspects of the mechanical design and the development of a control system that supported the modularity and reconfigurability of the mechanical platform. A modular electronic system is presented that is characterized by a plug and play approach to control scalability. This is complemented by a software architecture that has been developed with a focus on hardware abstraction for the management of an augmented mechanical and electronic architecture. The implications of MRMs for RMSs are discussed and key inhibitors to industrial implementation are identified.     

A process-driven computing model for reconfigurable semiconductor manufacturing

Reconfigurability is essential for semiconductor manufacturing systems to remain competitive. Reconfigurable systems avoid costly modifications required to change and adapt to changes in product, production and services. A fully automated, collaborative, and integrated while reconfigurable manufacturing system proves cost-effective in the long term and is a promising strategy for the semiconductor manufacturing industry. However, there is a lack of computing models to facilitate the design and development of control and management systems in a truly reconfigurable manner. This paper presents an innovative computing model for reconfigurable systems and controlled manufacturing processes while allowing for the integration of modern technologies to facilitate reconfiguration, such as radio frequency identification (RFID) and reconfigurable field programmable gate array (FPGA). Shop floor manufacturing activities are modeled as processes from a business perspective. A process-driven formal method that builds on prior research on virtual production lines is proposed for the formation of a reconfigurable cross-facility manufacturing system. The trajectory of the controlled manufacturing systems is optimized for on-demand production services. Reconfigurable process controllers are introduced in support of the essential system reconfigurability of future semiconductor manufacturing systems. Implementation of this approach is also presented.     

Scaling multiple addition and prefix sums on the reconfigurable mesh

Multiple addition is the problem of adding Nb-bit integers. Prefix sums and multiple addition play fundamental roles in many algorithms, particularly on the reconfigurable mesh (R-Mesh). Scaling algorithms on the R-Mesh to run with the same or increased efficiency on fewer processors is a challenging and important proposition. In this paper, we present algorithms that scale with increasing efficiency for multiple addition, prefix sums, and matrix-vector multiplication. Along the way, we obtain an improved multiple addition algorithm.     

Towards a generic design method for reconfigurable manufacturing systems: Analysis and synthesis of current design methods and evaluation of supportive tools

In today’s global manufacturing environment, changes are inevitable and something that every manufacturer must respond to and take advantage of, whether it is in regards to technology changes, product changes, or changes in the manufacturing processes. The reconfigurable manufacturing system (RMS) meets this challenge through the ability to rapidly and efficiently change capacity and functionality, which is the reason why it has been widely labelled the manufacturing paradigm of the future. However, design of the RMS represents a significant challenge compared to the design of traditional manufacturing systems, as it should be designed for efficient production of multiple variants, as well as multiple product generations over its lifetime. Thus, critical decisions regarding the degree of scalability and convertibility of the system must be considered in the design phase, which affects the abilities to reconfigure the system in accordance with changes during its operating lifetime. However, in current research it is indicated that conventional manufacturing system design methods do not support the design of an RMS and that a systematic RMS design method is lacking, despite the fact that numerous contributions exist. Moreover, there is currently only limited evidence for the breakthrough of reconfigurability in industry. Therefore, the research presented in this paper aims at synthesizing current contributions into a generic method for RMS design. Initially, currently available design methods for RMS are reviewed, in terms of classifying and comparing their content, structure, and scope, which leads to a synthesis of the reviewed methods into a generic design method. In continuation of this, the paper includes a discussion of practical implications related to carrying out the design, including an identification of potential challenges and an assessment of which tools that can be applied to support the design. Conclusively, further areas for research are indicated, which provides valuable knowledge of how to develop and realize the benefits of reconfigurability in industry.     

Multi-level decision making in reconfigurable machining systems using fuzzy logic

Reconfigurable machine tools (RMTs) are synthesised using the principles of modular design in order to achieve the required structural design for a particular part to be manufactured. In this paper, an effective method that uses multi-level fuzzy decisions to create dynamic optimal configurations of machine structures with respect to a given part geometry is presented. A system of modular machine configuration is utilised to arrive at machine configurations considering the fuzzy constraints that are pertinent in this process. With the utilisation of fuzzy decisions for the configuration system model, selection of optimal modular tool configurations is done. Decisions are made at a particular threshold level so as to verify the appropriateness of such decisions.     

A transparent and adaptive reconfigurable system

In the current scenario, where computer systems are characterized by a high diversity of applications coexisting in a single device, and with the stagnation in frequency scaling because of the excessive power dissipation, reconfigurable systems have already proven to be very effective. However, they all present two major drawbacks, which are addressed by this work: lack of transparency (the need for special tools or compilers that changes the original code) and no ability to adapt to applications with different behaviors and characteristics, so significant gains are achieved only in very specific data stream oriented applications. Therefore, this work proposes the Dynamic Instruction Merging (DIM), a Binary Translation mechanism responsible for transforming sequences of instructions into a coarse-grained array configuration at run-time, in a totally transparent process, with support to speculative execution. The proposed system does not impose any kind of modification to the source or binary codes, so full binary compatibility is maintained. Moreover, it can optimize any application, even those that do not present specific kernels for optimization. DIM presents, on average, 2.7 times of performance gains and 2.35 times of energy savings over a MIPS processor, and a higher IPC than an out-of-order superscalar processor, running the MIBench benchmark set.     

A systematic approach for product families formation in Reconfigurable Manufacturing Systems

The aim of this work is to establish a methodology for an effective working of Reconfigurable Manufacturing Systems (RMSs). These systems are the next step in manufacturing, allowing the production of any quantity of highly customised and complex products together with the benefits of mass production. In RMSs, products are grouped into families, each of which requires a system configuration. The system is configured to produce the first family of products. Once it is finished, the system is reconfigured in order to produce the second family, and so forth. Therefore, the effectiveness of a RMS depends on the formation of the best set of product families. Therefore, a methodology for grouping products into families, which takes into account the requirements of products in RMSs, is an issue of core importance. These requirements are modularity, commonality, compatibility, reusability, and product demand. The methodology starts by calculating, for each product requirement, a matrix that summarises the similarity between pairs of products. Then, through the use of the AHP methodology, a unique matrix that comprises the similarity values between products is obtained. The Average Linkage Clustering algorithm is applied to this matrix in order to obtain a dendogram that shows the diverse sets of product families that may be formed.     

可重构计算机技术在航天系统中的应用

随着小卫星技术的不断发展,卫星的功能、种类也越来越多,这就对星载计算机的性能提出了更高的要求,而传统的CPU难以胜任现代小卫星繁重的任务。由于ARM微处理器具有体积小、性能高、功率低、操作系统便于移植等优点。本文给出了基于AR91R40008处理器的可重构星载计算机的设计方案,并详细论证了方案的技术细节和可行性,以及所采用的一些关键设计技术。