检索结果-内蒙古大学图书馆

Evaluating synchronization on shared address space multiprocessors: Methodology and performance

Performance Evaluation Review 1999年第1期27卷 23-34页

作者： Kumar, Sanjeev Jiang, Dongming Chandra, Rohit Singh, Jaswinder Pal Department of Computer Science Princeton University Silicon Graphics Inc.

Synchronization is an area that exhibits rich hardware-software interactions in multiprocessors. It was studied extensively using microbenchmarks a decade ago. However, its performance implications are not well understood on modern systems or on real applications. We study the impact of synchronization primitives and algorithms on a modern, 64-processor, hardware-coherent shared address space multiprocessor: the SGI Origin 2000. In addition to the actual results on a modern system, we examine the key methodological issues in studying synchronization, for both microbenchmarks and applications. We find that although the efficient hardware support (Fetch&Op) for synchronization provided on our machine usually helps lock and barrier microbenchmarks, it does not help in improving application performance when compared to good software algorithms that use the processor-provided LL-SC instructions. This is true even in applications that spend a significant amount of time in synchronization operations. More elaborate hardware support is unlikely to have a significant benefit either. From the applications' perspective, it is usually the waiting time due to load imbalance or serialization that dominates synchronization time, not the overhead of the synchronization operations themselves, even in apparently balanced cases where the overhead may be expected to be substantial.

关键词： Multiprocessing systems Algorithms computer software computer systems programming Response time (computer systems) Synchronization Shared address space multiprocessors

来源：评论

学校读者我要写书评

暂无评论

Address trace compression through loop detection and reduction

引用

Performance Evaluation Review 1999年第1期27卷 214-215页

作者： Elnozahy, E.N. IBM Austin Research Lab. 11400 Burnet Rd. Austin TX 78758 United States

This paper introduces a new technique for compressing memory address traces. The technique relies on the simple observation that most programs spend their time executing loops, and therefore the trace will follow the structures of such loops. We adapt classic control flow analysis to detect the loops within an address trace, then analyze them to identify constant and loop-varying memory references. These references are efficiently encoded to reduce the size of the trace, often resulting in an order of magnitude reduction in size compared to the most compact trace format known to date.

关键词： Data storage equipment Data compression Storage allocation (computer) Control flow analysis Memory address trace compression

来源：评论

学校读者我要写书评

暂无评论

Multi-layer tracing of TCP over a reliable wireless link 99

Multi-layer tracing of TCP over a reliable wireless link

引用

international conference on measurement and modeling of computer systems (acm SIGMETRICS 99), Held in Conjunction with acm Federated Computing Research conference 99

作者： Ludwig, R Rathonyi, B Konrad, A Oden, K Joseph, A Ericsson Res Herzogenrath Germany

ISBN: (纸本)158113083X

It is well-known that TCP performance may degrade over paths that include wireless links, where packet losses are often not related to congestion. We examine this problem in the context of the GSM digital cellular network, where the wireless link is protected by a reliable link layer protocol. We propose the use of multi-layer tracing as a powerful methodology to analyze the complex protocol interactions between the layers. Our measurements show that TCP throughput over GSM is mostly ideal and that spurious timeouts are extremely rare. The multi-layer tracing tool we developed allowed us to identify the primary causes of degraded performance: (1) inefficient interactions with TCP/IP header compression, and (2) excessive queuing caused by overbuffered links. We conclude that link layer solutions alone can solve the problem of "TCP over wireless links". We further argue that it is imperative to deploy active queue management and explicit congestion notification mechanisms in wide-area wireless networks;which we expect will be the bottleneck in a future Internet.

关键词： wireless GSM TCP measurement tools

来源：评论

学校读者我要写书评

暂无评论

On the use of trace sampling for architectural studies of desktop applications

引用

Performance Evaluation Review 1999年第1期27卷 208-209页

作者： Crowley, Patrick Baer, Jean-Loup Dept. of Comp. Sci. and Engineering University of Washington Seattle WA United States

Trace sampling for a suit of publicly available desktop application traces for Windows NT on the Intel X86 platform is considered. Commonly used Windows NT applications can run for billions of instructions. Performing architectural studies on traces of billions of references is not feasible from both time and space perspective. Trace sampling is demonstrated as an efficient alternative that greatly reduces simulation time and, in many cases, nominally reduces accuracy. Among the several trace sampling techniques, stitch most accurately predicts cache miss rates for these workloads. Furthermore, sampling can also be used to efficiently drive architectural studies and gather parameters for analytical cache models.

关键词： computer architecture computer simulation Data storage equipment Personal computers Trace sampling

来源：评论

学校读者我要写书评

暂无评论

Optimal stochastic scheduling in multiclass parallel queues

引用

Performance Evaluation Review 1999年第1期27卷 93-102页

作者： Sethuraman, Jay Squillante, Mark S. Operations Research Center Massachusetts Inst. of Technology Cambridge MA 02139 United States IBM Research Division Thomas J. Watson Research Center Yorktown Heights NY 10598 United States

In this paper we consider the problem of scheduling different classes of customers on multiple distributed servers to minimize an objective function based on per-class mean response times. This problem arises in a wide range of distributed systems, networks and applications. Within the context of our model, we observe that the optimal sequencing strategy at each of the servers is a simple static priority policy. Using this observation, we argue that the globally optimal scheduling problem reduces to finding an optimal routing matrix under this sequencing policy. We formulate the latter problem as a nonlinear programming problem and show that any interior local minimum is a global minimum, which significantly simplifies the solution of the optimization problem. In the case of Poisson arrivals, we provide an optimal scheduling strategy that also tends to minimize a function of the per-class response time variances. Applying our analysis to various static instances of the general problem leads us to rederive many results, yielding simple approximation algorithms whose guarantees match the best known results.

关键词： Parallel processing systems Client server computer systems computer systems programming Mathematical models Matrix algebra Nonlinear programming Random processes Response time (computer systems) Multiclass parallel queues Optimal stochastic scheduling

来源：评论

学校读者我要写书评

暂无评论

Bandwidth-efficient continuous media streaming through optimal multiplexing

引用

Performance Evaluation Review 1999年第1期27卷 13-18页

作者： Zhao, Wei Tripathi, Satish K. Mobile Computing and Multimedia Lab. Department of Computer Science University of Maryland College Park MD 20742 United States Bourns College of Engineering University of California Riverside CA 92521-0425 United States

Maximizing bandwidth efficiency in distributed continuous media streaming systems is the key in delivering cost-effective multimedia services to distributed and heterogeneous receivers. We introduce a technique based on stream multiplexing to achieve the highest possible bandwidth efficiency, while preserving stringent and deterministic quality of service guarantees. The technique accomplishes the optimal multiplexing (i.e. resulting in the lowest possible bandwidth allocation) by exploiting both the temporal and the spatial structures among a group of continuous media streams. We present a family of optimal multiplexing schedules. The adverse per-stream effects of optimal multiplexing are studied and a technique based on transmission rearrangement is proposed to mitigates these effects, without sacrificing the achieved multiplexing optimality. The results presented in the paper provide some fundamental criteria and limits in the design and evaluation of resource allocation, admission control and stream scheduling policies for bandwidth efficient continuous media streaming.

关键词： Telecommunication networks Bandwidth Congestion control (communication) Frequency allocation Multimedia systems Multiplexing Telecommunication services Telecommunication traffic Multimedia streaming Quality of service (QoS)

来源：评论

学校读者我要写书评

暂无评论

Availability and utility of idle memory in workstation clusters 99

Availability and utility of idle memory in workstation clust...

引用

international conference on measurement and modeling of computer systems (acm SIGMETRICS 99), Held in Conjunction with acm Federated Computing Research conference 99

作者： Acharya, A Setia, S Univ Calif Santa Barbara Dept Comp Sci Santa Barbara CA 93106 USA

ISBN: (纸本)158113083X

In this paper, we examine the availability and utility of idle memory in workstation clusters. We attempt to answer the following questions. First, how much of the total memory in a workstation cluster can be expected to be idle? This provides an estimate of the opportunity for hosting guest data. Second, how much memory can be expected to be idle on individual workstations? This helps determine the recruitment policy - how much memory should be recruited on individual hosts? Third, what is the distribution of memory idle-times? This indicates how long guest data can be expected to survive;applications that access their data-sets frequently within the expected life-time of guest data are more likely to benefit from exploiting idle memory. Fourth, how much performance improvement can be achieved for off-the-shelf clusters without customizing the operating system and/or the processor firmware? Finally, how long and how frequently might a user have to wait to reclaim her machine if she volunteers to host guest pages on her machine? This helps answer the question of social acceptability. To answer the questions relating to the availability of idle memory, we have analyzed two-week long traces from two workstation pools with different sizes, locations, and patterns of use. To evaluate the expected benefits and costs, we have simulated five data-intensive applications (0.5 GB-5 GB) on these workstation pools.

关键词： computer workstations

来源：评论

学校读者我要写书评

暂无评论

TCP-friendly rate adjustment protocol for continuous media flows over best effort networks

引用

Performance Evaluation Review 1999年第1期27卷 220-221页

作者： Padhye, Jitendra Kurose, Jim Towsley, Don Koodli, Rajeev University of Massachusetts Amherst MA 01002 United States Nokia Research Center Burlington MA 01803 United States Nokia Research Center

Due to the close interaction between transport control protocols (TCP) congestion control and error control, TCP itself can not be used for continuous media (CM) applications. However, by taking a formula-based approach towards CM congestion control, differentiated services can be realized in which CM flows compete only against one another, and not against TCP. To this end, a TCP-friendly rate adjustment protocol, called CMTCP, is developed for continuous media flows over best-effort channel. TCP-friendliness is achieved by changing the sending rate, corresponding to measured loss rate and roundtrip times. Simulation and prototype tests show a throughput close to that of a TCP connection traveling over the same network path.

关键词： Network protocols Algorithms computer simulation Congestion control (communication) Data communication systems Internet Telecommunication networks Telecommunication services Telecommunication traffic Best effort networks Continuous media networks Rate adjustment congestion control protocols

来源：评论

学校读者我要写书评

暂无评论

Availability and utility of idle memory in workstation clusters

引用

Performance Evaluation Review 1999年第1期27卷 35-46页

作者： Acharya, Anurag Setia, Sanjeev Dept. of Computer Science University of California Santa Barbara CA 93106 United States Dept. of Computer Science George Mason University Fairfax VA 22030 United States

In this paper, we examine the availability and utility of idle memory in workstation clusters. We attempt to answer the following questions. First, how much of the total memory in a workstation cluster can be expected to be idle? This provides an estimate of the opportunity for hosting guest data. Second, how much memory can be expected to be idle on individual workstations? This helps determine the recruitment policy - how much memory should be recruited on individual hosts? Third, what is the distribution of memory idle-times? This indicates how long guest data can be expected to survive; applications that access their data-sets frequently within the expected life-time of guest data are more likely to benefit from exploiting idle memory. Fourth, how much performance improvement can be achieved for off-the-shelf clusters without customizing the operating system and/or the processor firmware? Finally, how long and how frequently might a user have to wait to reclaim her machine if she volunteers to host guest pages on her machine? This helps answer the question of social acceptability. To answer the questions relating to the availability of idle memory, we have analyzed two-week long traces from two workstation pools with different sizes, locations, and patterns of use. To evaluate the expected benefits and costs, we have simulated five data-intensive applications (0.5 GB-5 GB) on these workstation pools.

关键词： computer workstations computer systems programming Data acquisition Data storage equipment Data structures Response time (computer systems) Workstation clusters

来源：评论

学校读者我要写书评

暂无评论

Adaptive globally-synchronizing clock algorithm and its implementation on a Myrinet-based PC cluster

引用

Performance Evaluation Review 1999年第1期27卷 200-201页

作者： Liao, Cheng Martonosi, Margaret Clark, Douglas W. Depts. of Comp. Sci. and Elec. Eng. Princeton University

Fast commodity network-connected PC or workstation clusters are becoming more and more popular. This popularity can be attributed to their ability to provide high-performance parallel computing on a relatively inexpensive platform. An accurate global clock is invaluable for these systems, both for measuring network performance and coordinating distributed applications. Typically, however, these systems do not include dedicated clock synchronization support. Previous clock synchronization methods are not fully suitable to them, either due to their non-commodity hardware requirements or due to insufficient synchronized clock accuracy. In this paper we present and evaluate an adaptive clock synchronization algorithm. We have implemented and tested the algorithm on a Myrinet-based PC cluster. The algorithm has several important features. First, it does not require any extra hardware support. Second, we show that this algorithm places very low intrusion on the system and has a microsecond-level accuracy. Finally, our results indicate that adding the ability to adaptively adjust the clock's re-synchronization period causes almost no extra overhead while achieving a much better global clock accuracy.

关键词： computer networks Adaptive algorithms computer workstations Parallel processing systems Personal computers Synchronization Clock synchronization

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：