嵌入式系统线程库同步机制的实现

NPTL（本地POSIX线程库）具有较好的性能和稳定性，已成为Glibc的首选线程库。同步是为了达到多线程协同工作目的而设计的一种机制。线程库中同步函数的底层实现大多用汇编语言编写，因此，在将NPTL移植到不同嵌入式硬件平台时，必须重写相关代码。通过引入一个虚拟的锁设备，实现原子操作，进而实现同步函数，最小化硬件平台的相关性，方便地实现不同嵌入式平台上NPTL的同步机制。     

基于uClinux的NPTL线程库移植

在Linux2．6中,NPTL（native posix thread library）已取代Limux Threads成为glibc的首选线程库,但是在嵌入式操作系统中普遍使用的基于POSIX标准的线程库仍是Linux Threads。分析了NPTL线程库的内存管理机制,基于嵌入式操作系统uClinux无MMU的特性,修改了线程栈及uClibc库,实现了NPTL无uClinux上的移植,并在兼容性与效率两方面相对于Linux Threads线程库进行了测试。     

利用Java的多线程技术实现数据库的访问

针对如何高速访问数据库,提出了Java线程库机制,结合实例讨论实际编程中运用同步机制和并发机制时可能会出现的几个问题,并分析了不同平台上使用Java线程库的区别。     

通用线程库的设计与实现

随着采集、处理、解释一体化地震勘探软件的发展,构建跨硬件、操作系统的云计算平台成为必要;而云计算平台中,通用线程库成为开发有大计算量算法的地震勘探软件的关键.通过对线程模型和同步机制的分析,分类整理出线程的属性、线程的控制、线程执行流的构建和同步的属性及操作;最后在这些通用的组件基础上,通过对各种本地线程库的封装,实现基于任意本地线程库的跨平台通用线程库.     

基于嵌入式Linux系统的内核级线程库的研究与实现

在当前嵌入式系统应用中,性能问题一直是人们关注的重点.大多数嵌入式Linux应用往往运行在用户态,系统运行时需要经常在内核态和用户态之间反复切换,降低了关键业务的执行效率.以往的研究较少从内核态下的线程库出发来考虑性能优化的实现方法,影响了嵌入式系统的整体性能.对此,本文提出一种适用于嵌入式Linux系统的内核级线程库(LKTL),并且分析了实现的关键技术.LKTL提供了线程管理、信号量同步、内存的动态分配和回收、日志管理以及基本的GNU C库的功能,不但大大提高了应用程序的运行效率,还方便了应用程序的开发和移植.实验表明LKTL能够显著优化嵌入式Linux系统的整体性能.     

利用Java的多线程技术的实现数据库的访问

针对如何高速访问数据库，提出了Java线程库机制，结合实例讨论实际编程中运用同步机制和并发机制时可能会出现的几个问题，并分析了不同平台上使用Java线程库的区别。     

实时线程库研究与实现

并发已经日益成为当今软件的一个重要方面。该文力图通过实现一个高级的面向对象的,跨平台的C++线程和同步库,提供本地线程机制的高层抽象,从而获得更多的灵活性和控制性。特别是,针对实时系统中的优先级和调度的基本需求,开发了线程库的实时特性,实现了线程的本地优先级映射和支持优先级继承协议的锁机制。     

多处理机环境下线程模型性能评测与分析

在线程环境设计中存在三种结构不同的线程模型:多对一、一对一和多对多,一直以来,线程模型的特性分析仍然主要位于感性层面,缺乏完整的测试数据验证。FreeBSD5提供了基于三种线程模型的线程环境,为评测不同线程环境的性能提供了条件。论文以FreeBSD5下的测试结果为基础,结合Linux下一对一模型线程库NPTL的测试结果,分析了三种模型的不同特点,指出一对一模型和多对多模型均具有良好的性能,同时,基于SchedulerActivations的多对多模型也有很大的发展空间。     

Open Source

GNU于3月6号发布最新版glibc 2．4。新版的最大特点在于整合Linus Kernal的NPTL本地线程库的系统调用。众所周知,NPTL诞生自Kernel 2.6,它的出现大大提升了Linux系统的多线程执行能力。随后经过Redhat公司努力, NPTL被移植到了kernel 2．4上,Redhat还修改了glibc 2．3,使其也支持NTPL,这样早在RHEL3时代,Redhat就已经能够很好支持NPTL线程库。这也是为何众多企业级用户特别是J2EE的用户选择RHEL的原因。不过对于其它的Linux发行版、对于glibc来说,对NPTL的支持并非正式(在编译时,需要附加额外的库以及参数),这也多少限制NPTL能力的发挥。终于,在glibc 2．4中对NPTL的正式支持,将大大改善Linux系统的多线程能力,也将改善Linux对于企业级用户的支持能力。     

ARM平台上LXI C类仪器底层驱动和应用程序开发

在ARM硬件平台上,建立嵌入式Linux开发环境并对系统进行成功移植;通过对基于PC机的RPC服务器源代码的分析和研究,在ARM平台上构建RPC服务器;实现在ARM平台上的成功运行仪器发现机制,并基于VXI-11协议对该机制进行了测试和验证;参考SCPI命令标准制定简化的指令集,通过嵌入式Linux线程的编程完成命令解析机制的研发;开发网络接口驱动程序和A/D采集驱动程序;分析VISA函数与RPC消息的对应关系,使用Web浏览仪器软件实现客户端对服务器端仪器模块的操作和访问.     

Conservative distributed discrete-event simulation on the Amazon EC2 cloud: An evaluation of time synchronization protocol performance and cost efficiency

Distributed execution of simulation models comes into play when memory limitations of a single computational resource prohibit their execution. In addition, the potential for parallel execution of a model on a distributed platform through the integration of multiple computational cores, can potentially reduce the execution time of a simulation. However, such gains can be voided by the overhead that time synchronization protocols for parallel and distributed simulation induce. This overhead is determined by the protocol used, the characteristics of the simulation model, as well as the architectural and performance characteristics of the hardware platform used. Recently, Infrastructure-as-a-Service offerings in the cloud computing domain have introduced flexibility in acquiring access to virtualized hardware platforms on a pay-as-you-go basis. At present, it is however unclear to what extent these offerings are suited for the distributed execution of discrete-event simulations, and how the characteristics of different resource types impact the performance of distributed simulation under different time synchronization protocols. Likewise, it is unclear which type of resources are most cost-efficient for this type of workload. To our knowledge, this paper is the first to investigate these aspects through an assessment of the performance and cost efficiency of different conservative time synchronization protocols on a range of cloud resource types that are currently available on Amazon EC2. Our analysis shows that performance levels comparable to those realized on commodity hardware based-clusters are attainable, and that the relative performance of different synchronization protocols is retained on high-end IaaS resources. In terms of cost-efficiency, we find that IaaS products tailored to traditional cluster workloads do not necessarily constitute the optimal choice, and we assess the impact of different packing configurations for logical processes in this regard.     

FLOPSYNC-QACS: Quantization-aware clock synchronization for wireless sensor networks

Distributed real-time systems often rely on clock synchronization. However, the achievement of precise synchronization in Wireless Sensor Networks (WSNs) is hampered by competing design challenges, which finally causes many WSN hardware platforms to rely on low frequency clock crystal for local timebase provision. Although this solution is inexpensive and with a remarkably low energy consumption, it limits the resolution at which time can be measured. The FLOPSYNC synchronization scheme was then introduced to compensate for possible quartz crystal imperfections. The main limitation of FLOPSYNC is that it does not account for the effects of quantization. In this paper we propose a switched control variant of the base FLOPSYNC scheme to address quantization explicitly in the compensator design, providing clock synchronization in cost-sensitive WSN node platforms with a minimal additional overhead. Experimental evidence is given that the approach reaches a synchronization error of at most 1 clock tick in a real WSN.     

Efficient Time Synchronization Approach for Wireless Communication Systems on GPP-Based Software-Defined Radio Platform

General purpose processer (GPP) based software-defined radio (SDR) platforms provide wireless communication system engineers with maximal architecture flexibility and versatility to construct a wideband wireless communication system. Nevertheless, the lack of hardware real-time timing control makes it difficult to achieve time synchronization between the base station and the terminals. In this paper, a software-based time synchronization (STS) method is proposed to realize the time synchronization of time division multiple access (TDMA) based wireless communication systems. A high precision software clock source is firstly constructed to measure the elapse of processing time. The Round-Trip Delay (RTD) algorithm is then presented to calculate timing advance values and achieve time synchronization. An example TDMA system is implemented on Microsoft Sora platforms to evaluate the performance. Experiments show that the proposed mechanism is effective to enable time synchronization for wideband wireless communication systems on GPP-based SDR platforms.     

How to program and configure a heterogeneous multiprocessor

This paper describes a software environment that allows the programming and configuration of a heterogeneous multiprocessor architecture consisting of specialized hardware and a general purpose trasputer net. Run-time-behavior estimation is done at a compile time by using directed dataflow graphs to represent the program and a database containing all the relevant information about functions. The system offers the implementations of functions running on different hardware platforms, static configuration and scheduling, and integrated performance measurement. We show how programmers can handle such a system without any deeper knowledge of the underlying specialized hardware.     

国产平台下可靠文件传输软件的设计及实现

在国产自主可控平台加速推广的当下,为实现文件在测控数据传输网不同软硬件平台之间的可靠、快速传输,本文根据相关技术规范,基于文件交换协议(File Exchange Protocol,简称FXP协议),设计并实现功能完备、运行稳定的可靠文件传输软件。软件具备模块化、可移植、基于TCP协议满足用户可靠性需求、基于UDP协议满足用户传输效率需求、兼容不同软硬件平台等的功能特点,并具备满足安全编程需求的软件特性,立足核心代码设计、验证,对软件功能和稳定运行两个方面做了进一步的改良和提升,以满足跨不同软硬件平台稳定运行、恶劣网络环境中可靠传输、畅通网络环境中尽力快速传输的新要求。     

一种按需加载的DSP程序扩容方法

随着软件无线电的发展,软件无线电平台的处理能力越来越强大、平台上实现的功能越来越多,平台的硬件结构也多种多样,各平台之间无法实现软硬件资源的共享,在实现通用数字中频的工作中,DSP程序的扩容需求逐步增大.针对上述问题,本文提供一种按需加载的DSP程序扩容方法,这种方法可以根据需要加载不同的DSP函数,相当于对DSP的内...     

运载火箭测发控软件的中间件技术应用

由于不同型号硬件平台和软件平台的多样性,跨型号大规模融合应用系统通常要求在拥有多种软硬件平台(异构平台)的分布式环境下运行。借助中间件(Middleware)技术改进软件重用形式,提高软件重用程度,以实现支持分布式应用有效开发、部署、运行和管理的目的。本文在对现有火箭测发控系统软件的子系统功能聚类和程序架构分析基础上,开发基于中间件模型的通用火箭测发控系统软件。     

面向嵌入式系统的功耗管理硬件抽象层

由于缺乏面向嵌入式系统的功耗管理硬件标准接口，嵌入式操作系统在不同硬件平台上的功耗管理功能缺乏可移植性。该文针对嵌入式系统提出了一种功耗管理硬件抽象层模型，同时引入了抽象功耗可管理组件模型，为操作系统提供了统一的功耗状态转移函数。基于此抽象层，可屏蔽不同硬件结构的功耗管理细节，有效地提高嵌入式操作系统的可移植性。     

无线传感器网络高精度硬件时钟同步方法

为实现无线传感器网络高精度的时间同步功能,提出一种基于Zigbee技术的硬件时钟同步方法。采用跨层思想提取接收信号强度指示值信号作为同步触发信号,设计复杂可编程逻辑器件的硬件电路时钟模块实现计时,并配合软件算法完成整个网络的时间同步,在保证低能耗和复杂度的基础上,提高时间同步精度。对同步精度进行理论研究和测试分析,结果表明,该方法可使系统节点间达到10μs级的时钟同步精度,满足多数无线传感器网络要求。