By Topic

Computers, IEEE Transactions on

Issue 12 • Date Dec 1989

Filter Results

Displaying Results 1 - 10 of 10
  • Evaluating associativity in CPU caches

    Page(s): 1612 - 1630
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1564 KB)  

    The authors present new and efficient algorithms for simulating alternative direct-mapped and set-associative caches and use them to quantify the effect of limited associativity on the cache miss ratio. They introduce an algorithm, forest simulation, for simulating alternative direct-mapped caches and generalize one, which they call all-associativity simulation, for simulating alternative direct-mapped, set-associative, and fully-associative caches. The authors find that although all-associativity simulation is theoretically less efficient than forest simulation or stack simulation (a commonly used simulation algorithm), in practice it is not much slower and allows the simulation of many more caches with a single pass through an address trace. The authors also provide data and insight into how varying associatively affects the miss ratio View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An evaluation of multiple-disk I/O systems

    Page(s): 1680 - 1690
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1020 KB)  

    Alternative ways of configuring an I/O subsystem with multiple disks to improve the I/O performance are considered. Specifically, the author consider disk synchronization, data declustering/disk striping, and a combination of both these approaches. They evaluate many different organizations that have not been considered before. The effects of block size and other parameters of the system are examined. Two different workloads are considered for the evaluation: a file/transaction system workload and a scientific applications workload. Through simulations it is shown that synchronized organizations perform better than other organizations at very low request rates; that there is a tradeoff in the amount of declustering/synchronization to be used in a system; and that systems with higher parallelism in reading a file perform better in a scientific workload View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Estimating the reliability of regeneration-based replica control protocols

    Page(s): 1691 - 1702
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (980 KB)  

    The accessibility of vital information can be enhanced by replicating the data on several sites and employing a consistency control protocol to manage the replicas. The reliability of a replicated data object depends on maintaining a viable set of current replicas. When storage is limited, it may not be feasible to simply replicate a data object at enough sites to achieve the desired level of reliability. Regeneration approximates the reliability provided by additional replicas for a modest increase in storage costs, and is applicable whenever a new replica of a data object can be created faster than a system failure can be repaired. Regeneration enhances reliability by creating new replicas on other sites in response to site failures. Several strategies for replica maintenance are considered, and the benefits of each are analyzed using simulation and both algebraic and numeric solutions to systems of differential equations View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Machine characterization based on an abstract high-level language machine

    Page(s): 1659 - 1679
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1824 KB)  

    Measurements are presented for a large number of machines ranging from small workstations to supercomputers. The authors combine these measurements into groups of parameters which relate to specific aspects of the machine implementation, and use these groups to provide overall machine characterizations. The authors also define the concept of pershapes, which represent the level of performance of a machine for different types of computation. A metric based on pershapes is introduced that provides a quantitative way of measuring how similar two machines are in terms of their performance distributions. The metric is related to the extent to which pairs of machines have varying relative performance levels depending on which benchmark is used View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bounding availability of repairable systems

    Page(s): 1714 - 1723
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (872 KB)  

    Markov models are widely used for the analysis of availability of computer/communication systems. Realistic models often involve state-space cardinalities that are so large that it is impractical to generate the transition-rate matrix let alone solve for availability measures. An approximation technique is presented for determining steady-state availability. Of particular interest is that the method also provides bounds on the error. Examples are given to illustrate the method View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The optimal control of heterogeneous queueing systems: a paradigm for load-sharing and routing

    Page(s): 1724 - 1735
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1036 KB)  

    The essence of the basic control decisions implicit in load-sharing and routing algorithms is captured in a simple model of heterogeneous queue control. The authors solve for the optimal control policy and investigate the performance of previously proposed policies in a tractable limit of this model. Using their understanding of this solvable limit, the authors propose heuristic policies for the general model. Simulation data for these policies suggest that they perform well over a wide range of system parameters View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A performance analysis of minimum laxity and earliest deadline scheduling in a real-time system

    Page(s): 1736 - 1744
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (740 KB)  

    A study is made of the performance of a real-time system in which jobs all have deadlines for either the beginning or the end of service. In the first case the authors analyze the minimum laxity (ML) scheduling policy when there are c processors, and in the latter case they analyze the preemptive-resume earliest deadline (ED) scheduling policy when there is one server. In both cases, the analysis assumes a Poisson arrival process, exponential service times that are not known to the scheduler, and exponential laxities or deadlines, and families of upper and lower bounds on the fraction of jobs that miss their deadlines are developed. The pessimistic bounds are of special interest because they correspond to a family of implementable policies, ML(n) and ED( n), n a positive integer 1, for which the performance approaches that of ML and ED as n increases, but at the cost of increasing overhead View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Failure dependent performance analysis of a fault-tolerant multistage interconnection network

    Page(s): 1703 - 1713
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (920 KB)  

    To provide fault tolerance and improve system reliability and performance, a class of fault-tolerant multistage interconnection networks, called augmented shuffle-exchange networks (ASENs) has been proposed. ASENs are gracefully degradable; although an individual component failure reduces ASEN performance, it does not cause a total network failure. The purpose of this work is to analyze how these component failures affect ASEN performance. A key step in performance and reliability modeling is the choice of an appropriate metric for analysis. Because network bandwidth can be an inadequate performance measure when fault are present. The authors consider other network performance measures, including the interreference time distribution for individual outputs (memories) View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The performance implications of thread management alternatives for shared-memory multiprocessors

    Page(s): 1631 - 1644
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1312 KB)  

    An examination is made of the performance implications of several data structure and algorithm alternatives for thread management in shared-memory multiprocessors. Both experimental measurements and analytical model projections are presented. For applications with fine-grained parallelism, small differences in thread management are shown to have significant performance impact, often posing a tradeoff between throughput and latency. Per-processor data structures can be used to to improve throughput, and in some circumstances to avoid locking, improving latency as well. The method used by processors to queue for locks is also shown to affect performance significantly. Normal methods of critical resource waiting can substantially degrade performance with moderate numbers of waiting processors. The authors present an Ethernet-style backoff algorithm that largely eliminates this effect View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The nonuniform distribution of instruction-level and machine parallelism and its effect on performance

    Page(s): 1645 - 1658
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1268 KB)  

    A methodology for quickly estimating machine performance is developed. A first-order estimate is based on the average degree of machine parallelism. A second-order model corrects for the effects of nonuniformities in instruction-level and machine parallelism and is shown to be accurate to within 15% for three widely different machine pipelines: the CRAY-1, the MultiTitan, and a dual-issue superscalar machine View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.

Aims & Scope

The IEEE Transactions on Computers is a monthly publication with a wide distribution to researchers, developers, technical managers, and educators in the computer field.

Full Aims & Scope

Meet Our Editors

Editor-in-Chief
Albert Y. Zomaya
School of Information Technologies
Building J12
The University of Sydney
Sydney, NSW 2006, Australia
http://www.cs.usyd.edu.au/~zomaya
albert.zomaya@sydney.edu.au