Huei-hsiung Chuang · 1973
A program's instruction working set Wi (ti,Ti) at instruction reference time ti is the set of distinct pages among Ti most recently referenced instruction pages. This program's data working set Wd (td,Td) at data reference time td is the set of distinct pages among Td most recently referenced data pages. Using These definitions, a study of properties of this separate working-set model is presented. Results are compared to that of single working-set model1. A model of multiprogramming implementing separate working-set principle is developed. Analysis of this model is also conducted.
Cited by 0
Masatoshi Miyazaki, Shingo Tomita, Shoichi Noguchi et al. · Medical Entomology and Zoology · 1976
Cited by 0
Edsger W. Dijkstra · 1968
A multiprogramming system is described in which all activities are divided over a number of sequential processes. These sequential processes are placed at various hierarchical levels, in each of which one or more independent abstractions have been implemented. The hierarchical structure proved to be vital for the verification of the logical soundness of the design and the correctness of its implementation.
Cited by 9
M. A. Sencer · uO Research (University of Ottawa) · 1974
Abstract not available.
Cited by 0Open access
S. Howry · 1971
This paper describes an operational small computer multiprogramming system developed for the control of the Stanford Two Mile Linear Accelerator (SLAC). The system has many features of larger systems such as dynamic memory allocation and interprocess control, but does not have to handle typical batch type jobs which need large arrays and many other system resources. This difference results in a drastic reduction in the complexity of both design and implementation. The accelerator control problem is discussed in terms of what requirements are imposed on the system by the environment. Then the basic subsystems are described with sufficient examples to show the reader other areas where such a system may be applicable.
Cited by 4Open access
David L. Mills · 1969
Article Free Access Share on Multiprogramming in a small-systems environment Author: David L. Mills University of Michigan, Ann Arbor, Michigan University of Michigan, Ann Arbor, MichiganView Profile Authors Info & Claims SOSP '69: Proceedings of the second symposium on Operating systems principlesOctober 1969 Pages 112–119https://doi.org/10.1145/961053.961096Online:20 October 1969Publication History 4citation188DownloadsMetricsTotal Citations4Total Downloads188Last 12 Months2Last 6 weeks0 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF
Cited by 3Open access
Wijnands, AIJ · TU/e Research Portal (Eindhoven University of Technology) · 1994
Cited by 0
Pierre Courtois · Elsevier eBooks · 1977
Cited by 9
Leonard J. Bass · SIAM Journal on Computing · 1973
Related DatabasesWeb of Science You must be logged in with an active subscription to view this.Article DataHistorySubmitted: 29 September 1972Published online: 13 July 2006Keywordsmultiprogramming, scheduling, processor bound programsPublication DataISSN (print): 0097-5397ISSN (online): 1095-7111Publisher: Society for Industrial and Applied MathematicsCODEN: smjcat
Cited by 5
Timothy Creech, Aparna Kotha, Rajeev Barua · Digital Repository at the University of Maryland (University of Maryland College Park) · 2013
As hardware becomes increasingly parallel and the availability of scalable parallel software improves, the problem of managing multiple multithreaded applications (processes) becomes important. Malleable processes, which can vary the number of threads used as they run, enable sophisticated and flexible resource management. Although many existing applications parallelized for SMPs with parallel runtimes are in fact already malleable, deployed run-time environments provide no interface nor any strategy for intelligently allocating hardware threads or even preventing oversubscription. Work up until SCAF either depends upon profiling applications ahead of time in order to make good decisions about allocations, or does not account for process efficiency at all. This paper presents the Scheduling and Allocation with Feedback (SCAF) system, a drop-in runtime solution which supports existing malleable applications in making intelligent allocation decisions based on observed efficiency without any paradigm change, changes to semantics, program modification, offline profiling, or even recompilation. Our existing implementation can control most unmodified OpenMP applications. Other malleable threading libraries can also easily be supported with small modifications, without requiring application modification.
Cited by 21Open access
Appelbe, Ito · IEEE Transactions on Computers · 1978
Utilization of a uniprocessor system in a multiprogramming environment can be optimized by maximizing the overlap of processor and input-output operations. A computational process can be modeled by a directed graph each node of which represents a task comprising processor and input-output segments. Any optimal schedulng algorithm for the model cannot be polynomially bounded, but the optimal criteria can be used to develop a hierarchy of dispatching heuristics based upon selecting an optimal partial task schedule. These heuristics are analyzed and evaluated by a simulation study and are shown to be more effective than those previously proposed. The dispatching heuristics developed have a wide range of potential applications to systems requiring dynamic task scheduling.
Cited by 3
Ivo Adan, W.H.M. Zijm · SIAM Journal on Applied Mathematics · 1993
The generating function approach for analysing queueing systems has a long-standing tradition. One of the highlights is the seminal paper by Kingman [Ann. Math. Statist., 32(1961), pp. 1314–1323] on the shortest-queue problem, where the author shows that the equilibrium probabilities $p_{m,n} $ of the queue lengths can be written as an infinite sum of products of powers. The same approach is used by Hofri [Internal. J. Computer and Information Sci., 7 (1978), pp. 121–155] to prove that, for a multiprogramming model with two queues, the boundary probability $p_{0, j} $ can be expressed as an infinite sum of powers. This paper shows that the latter representation does not always hold, which implies that the multiprogramming problem is essentially more complicated than the shortest-queue problem. However, it appears that the generating function approach is very well suited to show when such a representation is available and when it is not.
Cited by 8Open access
Per Brinch Hansen · ACM SIGOPS Operating Systems Review · 1972
This paper defines a set of scheduling primitives which have evolved from multiprogramming systems described by Dijkstra, Lampson, Saltzer, and the present author. Compared to earlier papers on the same subject, the present one illustrates a more concise description of operating system principles by means of algorithms. This is achieved by (1) describing the primitives as the instructions of an abstract machine which in turn is defined by its instruction execution algorithm; (2) introducing a notation which distinguishes between the use of synchronizing variables (semaphores) to achieve mutual exclusion of critical sections, and to exchange signals between processes which have explicit input/output relationships; (3) considering the influence of critical sections on preemption and resumption; and (4) using a programming language, Pascal, which includes natural data types (records, classes, and pointers) for the representation of process descriptions and scheduling queues. The algorithms are written at a level of detail which clarifies the fundamental problems of process scheduling and suggests efficient methods of implementation.
Cited by 3Open access
Anant Agarwal · Kluwer international series in engineering and computer science · 1989
Cited by 0
Arthur M. Rosenberg · Communications of the ACM · 1966
At the Spring Joint Computer Conference, Mr. Walter Finke charged our industry with standing aloof and disregarding the
Cited by 0Open access
Hatch Ross R, Rxval Post, Ross R. Hatch et al. · 1964
Cited by 0
Nasef, Mehdi · UCrea (University of Cantabria) · 2023
With every generation, GPUs incorporate an ever-increasing amount of computational resources, which are dedicated to accelerate data-parallel applications. Using those resources efficiently requires applications to expose high levels of parallelism. Even then, they may not be able to maximize the usage of each resource type (bandwidth, compute resources, memory, the different execution units of the same core, etc). \nNot all applications can fully use a complete GPU, but when executing more than one application concurrently, they may compensate for each other’s lacks. this is the idea behind multiprogramming. It is supported by current GPUs, but the techniques they use only tackle the lack of thread level parallelism (TLP) issue. Other methods like Warped- Slicer have been proposed to reduce resource underutilization by making applications share the resources of the same SM (Streaming Multiprocessor, which is a core of the GPU in Nvidia terminology). This is called Intra-SM-sharing. Warped-Slicer, which is the state of the art for thread block scheduling, tries to make an efficient partitioning of the resources between kernels (programs executed by the GPU) to maximize performance. However, its profiling strategy makes it agnostic to the interference between the kernels. \nThis dissertation proposes MIAS (Memory Interference Aware Scheduler), a thread block scheduling algorithm that tackles the issues Warped-Slicer has. It carries out a profiling phase where, unlike Warped-Slicer, it profiles kernels jointly, making them share the SMs during that phase. It profiles all the resource partitioning configurations (or thread block configurations) in parallel, in different SMs. It, then, chooses the best configuration using different metrics to estimate the interference between the profiled alternatives in the memory system, which they share. Evaluation results show that MIAS improves performance by 32% over sequential execution and 20% over Warped-Slicer.
Cited by 0Open access
S. Howry · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · 2014
This paper describes an operational small computer multiprogramming system developed for the control of the Stanford Two Mile Linear Accelerator (SLAC). The system has many features of larger systems such as dynamic memory allocation and interprocess control, but does not:have to handle typical batch type jobs which need large arrays and many other system resources. This difference results in a drastic reduction in the complexity of both design and implementation. The accelerator control problem is discussed in terms of what requirements are imposed on the system by the environment. Then the basic subsystems are described with sufficient examples to show the reader other areas where such a system may be applicable. I.
Cited by 0Open access
Alexandre Brandwajn · 1982
Queueing network models of computer systems with multiprogramming constraints generally do not possess a product-form solution in the sense of Jackson. Therefore, one is usually led to consider approximation techniques when dealing with such models. Equivalence and decomposition is one way of approaching their solution. With multiple job classes, the equivalent network may be viewed as a set of interdependent queues. In general, the state-dependence in this equivalent network precludes a product-form solution, and the size of its state space grows rapidly with the number of classes and of jobs per class. This paper presents two methods for approximate solution of the equivalent state-dependent queueing network. The first approach is a manifold application of equivalence and decomposition. The second approach, less accurate than the first one, is a fast-converging iteration whose computational complexity grows near-linearly with the number of job classes and jobs in a class. Numerical examples illustrate the accuracy of the two methods.
Cited by 24
Donald D. Chamberlin, Samuel H. Fulier, Leonard Y. Liu · 1973
In a multiprogramming, virtual-memory computing system, many processes compete simultaneously for system resources, which include CPU's, main memory page frames, and the transmission capacity of the paging drum. (We define a “process” here as a program with its own virtual memory, requiring an allocation of real memory and a CPU in order to execute). This paper studies ways of allocating resources to processes in order to maximize throughput in systems which are not CPU-bound.
Cited by 5