共查询到20条相似文献,搜索用时 31 毫秒
1.
单芯片多处理器一直是处理器微体系结构发展的一个热点。对于通用串行应用程序,高效的线程控制方法是实现线程级前瞻、挖据线程级并行性的一个重要组成部分。本文结合一个具体的SCMP模型即Griffon,提出并实现了一种简单、高效的分布式线程控制方法。该方法易于实现,可扩展性强。实验结果表明,线程的控制可以在数个周期内实现
,能够满足片内并行处理的要求 相似文献
,能够满足片内并行处理的要求 相似文献
2.
Satoshi Amamiya Makoto Amamiya Ryuzo Hasegawa Hiroshi Fujita 《The Journal of supercomputing》2009,47(2):228-252
Current trend of research on multithreading processors is toward the chip multithreading (CMT), which exploits thread level
parallelism (TLP) and improves performance of softwares built on traditional threading components, e.g., Pthread. There exist
commercially available processors that support simultaneous multithreading (SMT) on multicore processors. But they are basically
based on the conventional sequential execution model, and execute multiple threads in parallel under the control of OS that
handles interruptions. Moreover, there exist few languages or programming techniques to utilize the multicore processors effectively.
We are taking another approach to develop a multithreading processor, which is dedicated to TLP. Our processor, named Fuce, is based on the continuation-based multithreading. A thread is defined as a block of sequentially ordered instructions which
are executed without interruption. Every thread execution is triggered only by the event called continuation.
This paper first introduces the continuation-based multithread execution model and its processor architecture then gives multithreaded
programming techniques and the continuation-based multithreading language system CML. Last, the performance of the Fuce processor is evaluated by means of the clock-level software simulation. 相似文献
3.
作为BGP扩展机制之一的BGP路由反射,在某些特定的配置情况下,能够导致永久性的BGP路由振荡。本文将通过实例分析路由反射引起振荡的条件,并给出一些网络设计准则以避免振荡的发生。 相似文献
4.
基于IPv6的BGP4+路由策略的研究与实现 总被引:2,自引:0,他引:2
边界网关协议(border gateway protocol,BGP)用于在自治系统之间交换路由信息,其目的是在自治系统之间选择最好的路由,BGP为了控制路由的传播为路由附带了大量的属性信息,这些属性信息和路由策略结合起来,在自治系统之间选取更好的路由.介绍了边界网关协议的基础上,重点分析了IPv6下BGP4 路由策略的实现. 相似文献
5.
面向线程级前瞻的线程划分方法浅析 总被引:1,自引:0,他引:1
正确合理的线程划分方法是提取线程级并行性的必要前提,线程级前瞻技术是简化线程划分复杂度提高系统性能的重要手段。本文讨论了几种支持线程级前瞻的典型线程划分方法,在此基础上提出了线程级划分需要解决的关键问题,并蛄合一典型自动线程划分算法进行了具体分析,提出了线程划分需要进一步研究的问题。 相似文献
6.
Qi LiAuthor Vitae Jianping WuAuthor Vitae 《Journal of Parallel and Distributed Computing》2011,71(8):1098-1110
The instability issues of the Border Gateway Protocol (BGP), such as route oscillations and path explorations, can decrease the performance of packet forwarding and place heavy workload on routers. While BGP instability has been extensively studied, existing solutions mainly solve individual instances of BGP instability. Thus, with the existing solutions, the route selection processes of ASes or routers may not realize the actual root cause of BGP instability and hence cannot effectively solve the BGP instability problem. In this paper, we propose a simple, integrated solution called stable BGP (stableBGP) that practically solve a general class of BGP instability issues, including route oscillations and path explorations. stableBGP seeks to adapt the route selection process to best address the root cause of route changes so that the route selection process can quickly stabilize. We formally prove that stableBGP can achieve BGP stability. Extensive simulation results show that in the link failure scenario, stableBGP significantly reduces the number of route changes, the convergence time, and the number of route update messages when compared to prior solutions. We also analyze the performance of stableBGP when it is partially deployed. Our work provides insights into developing a practical solution that addresses the BGP instability problem. 相似文献
7.
8.
9.
本文对边界网关协议(BGP)的基本操作、路由原理、消息类型、分组格式等基本理论作了科学的阐述。在此基础上指出了边界网关协议存在的缺陷,并对可能存在的漏洞攻击及其防范措施进行了分析。 相似文献
10.
BGP(border gateway protocol)作为一种基于策略的协议,允许每个自治系统独立地选择本地路由策略.自治系统之间可能存在的路由策略冲突会引起BGP路由持续不稳定.当前提出的解决办法要么需要增加额外的通信开销,要么限制自治系统自由的选择路由策略.提出了一种解决策略冲突引起BGP路由不收敛的自适应方法,既不损害自治系统选择路由策略的灵活性,也不需要在BGP消息中增加额外信息.路由的稳定性被加入到BGP的判决过程中,不稳定路由的优先级被降低,使更加稳定的路由得以被选为最优路由,终止路由策略冲突引起的争执.在网络拓扑发生改变的情况下,这种新方法能够自适应地调整路由选择,重新收敛到新的稳定状态. 相似文献
11.
低功耗多线程编译优化技术 总被引:12,自引:1,他引:12
提出了在多线程体系结构中通过降低执行频率有效减小功耗的理论模型和方法.首先研究识别可降频运行的线程的计算模型和降频因子的计算,然后给出在编译过程中基于对应用程序行为的分析,结合线程划分的低功耗编译优化算法和实现策略.该模型和方法可用于具有执行频率可动态调整的多处理器类多线程体系结构,既可开发TLP(thread level parallelism),又可有效减小功率消耗. 相似文献
12.
改善BGP路由收敛的时间窗口机制 总被引:2,自引:0,他引:2
提出了一种时间窗口机制,能够基于路由抖动抑制中路由惩罚值的变化改善BGP(border gateway protocol)路由收敛.这种新机制把来自不同邻居的路由变化情况结合起来,利用BGP路由传播过程形成的路由相关性判断路由在网络中的稳定情况.时间窗口机制使BGP路由器能够更早地发现不稳定路由,优先将稳定路由选择为最优路由,终止路径搜索过程.模拟实验的结果表明,通过选择适当的参数,时间窗口机制能够大大缩短BGP路由收敛延时,减小收敛过程中的通信开销.而且,这种方法不需要在BGP的路由消息中增加额外的信息,因此容易在实际网络中逐步部署. 相似文献
13.
With the trend of growing number of integrated processing cores on Chip Multiprocessors, researchers are working hard to increase the available parallelism of software programs so as to efficiently harness the growing computing power. One noticeable direction among these efforts is speculative multi-threading (SpMT), a.k.a thread level speculation, which aims to extract thread level parallelism by splitting a sequential execution thread into several finer ones and execute them on parallel. A SpMT thread is in speculative status before it “knows” all its input data are correct. A speculative thread needs to write to the L1 cache, but its output might be discarded if the speculation eventually fails. However, another speculative thread may have already read in such speculative output. Therefore, some mechanism is needed to support speculative read and write. And because the SpMT threads are extracted from a single thread, they usually share lots of data, thus there might be intense data coherence among the L1 caches. It would be very complicated to support data coherence and speculation together. This Paper proposes a shared write buffer among the SpMT cores. We are able to confine the speculative read and write in the SWB, thus the speculation will not interference with coherence, and the L1 cache design could be drastically simplified. Experiments show that the SWB can capture a big portion of inter-core data sharing, reduce cache coherence, and drastically improve data access performance of SpMT threads. 相似文献
14.
15.
《Internet Computing, IEEE》2003,7(3):7-9
The predominant worry about BGP (Border Gateway Protocol) is that attackers could figure out a way to take advantage of the implicit trust relationship between peer routers by mounting a man-in-the-middle attack and injecting false information into routing updates. As of yet, that has not happened; however, an accidentally misconfigured BGP router incident in 1997 illustrated that a falsely advertised route could pull immense amounts of traffic from other routes into paths for which it was never intended and cause severe slowdowns or shutdowns. The networking community has stepped up its effort to address BGP security. In the longer term, the most mature method to address BGP security is Secure BGP (S-BGP), developed by researchers at BBN Technologies under a DARPA. However, adopting a BGP security standard is still in its infancy. 相似文献
16.
边界网关协议(BGP)是Internet域间路由的事实标准,它允许各自治系统独立配置路由选择和播发策略,但这种局部配置可能导致全局策略配置冲突和低效,从而引起路由振荡的问题。文章分析了域间路由振荡问题,并综述了其相应的各种解决方案。 相似文献
17.
提出了一种系统实现协议健壮性测试的新方法。该方法通过深入分析BGP的路由信息处理过程,建立场景模型来描述决策过程和更新过程的应用环境和控制参数,并基于该模型提出了健壮性测试案例生成方法。该方法是通信协议测试和软件测试相结合,具有良好的应用发展前景。路由协议BGP的实际测试应用表明,该方法避免了组合爆炸问题,生成的反向测试集的检错能力是正向测试集的2.3倍。 相似文献
18.
在BGP/MPLS VPNs中,用MPLS实现的流量工程主要被限止在单个管理域内。然而,随着企业规模的不断扩大,VPN跨越越来越多的管理域,急需管理域间流量的有效方法。以BGP属性、BGP策略和AS关系为基础的,一方面通过配置LOCAL-PREF属性值,运用输入策略,控制AS的出界流量;另一方面,保证客户AS不在提供者间或对等体间过渡流量,或允许客户AS向它的部分提供者通告路由,或人为增长AS-PATH,控制AS的入界流量。仿真表明此方法能有效地在BGP/MPLS VPNs中用BGP实现域间流量工程。 相似文献
19.
基于IPV6的BGP协议实现技术 总被引:3,自引:0,他引:3
BGP是一个在自治系统间运行的动态路由协议,其功能是在自治系统间交换网络层可达信息。它是骨干路由器必须支持的协议。现在随着IPv6的进一步发展壮大,如何在IPv6下实现BGP协议就成为了急需解决的问题。文中着重于IPv6下BGP的具体实现,主要介绍了其体系结构、模块划分及在实现中的若干关键问题。在系统设计完成以后.利用Sprient的协议测试系统对核心路由器上运行的BGP协议软件进行了一致性和性能测试,其测试结果表明已经很好地完成了设计目标。 相似文献
20.
Bin Liu Yinliang Zhao Yuxiang Li Yanjun Sun Boqin Feng 《The Journal of supercomputing》2014,67(3):778-805
Speculative multithreading (SpMT) is a thread-level automatic parallelization technique, which partitions sequential programs into multithreads to be executed in parallel. This paper presents different thread partitioning strategies for nonloops and loops. For nonloops, we propose a cost estimation based on combined run-time effects of various speculation factors to predict the resulting performance of candidate threads to guide the thread partitioning. For loops, we parallelize all the profitable loops that can potentially offer additional performance benefits by multilevel spawning in loop bodies, loop iterations, and inner loops. Then we select a proper thread boundary located in the front of loop branch instruction to reduce invalid spawning threads that waste core resources. Experimental results show that the proposed approach can obtain a significant increase in speedup and Olden benchmarks reach a performance improvement of 6.62 % on average. 相似文献