Showing papers on "Degree of parallelism published in 1976"
29 Mar 1976
TL;DR: The power of this modeling technique with respect to comprehensibility, accuracy of representation and ease of validation and modification is demonstrated by application to modeling of the UT-2 operating system for the CDC 6000 series computer system.
Abstract: This paper defines and determines a graph model of a computer system in a form applicable to system performance analysis. The power of this modeling technique with respect to comprehensibility, accuracy of representation and ease of validation and modification is demonstrated by application to modeling of the UT-2 operating system for the CDC 6000 series computer system. This multiprocessor-multi-programmed operating system with its high degree of parallelism provides an excellent test for the utility and range of application of graph models in performance evaluation. A programmed representation of the kernel monitor is used. All other system processes are represented in graph form and are input data to the simulator. A generally applicable technique for extracting graph representations of processes are represented in graph form and are input data to the simulator. A generally applicable technique for extracting graph representations of processes from event trace data is described and applied to the event trace generated by the UT-2 operating system. The technique is both complete and general and may be profitably applied for either partial or complete models of any type of complex computer system process where data or techniques for automated graph construction are available or can he applied.
4 citations
22 Apr 1976
TL;DR: Based on experience described herein, multiprocessing provides an effective way to increase the range of system performance with a single CPU product line, thereby serving a wider class of applications and market areas and providing explicit growth channels for applications whose computing requirements grow in time.
Abstract: This paper presents the results of an effort to determine the performance, operational characteristics, hardware and software requirements, and the potential applications base for a symmetric system of closely coupled multiprocessors. Based on experience described herein, multiprocessing provides an effective way to increase the range of system performance with a single CPU product line, thereby serving a wider class of applications and market areas and providing explicit growth channels for applications whose computing requirements grow in time.A prototype system has been built using PDP-11/40 processors, multiported memories, and UNIBUS windows, for the purpose of determining its performance and operational characteristics. The RSX-11M real time operating system has been modified to support multiprocessing on this configuration. Theoretical analysis has provided a mathematical expression for system throughput as a function of the number of processors, memory banks, and memory utilization factors. Performance measurements have been related to theoretical analysis so that analytic means can predict the performance of configurations beyond the scope of the prototype hardware.For certain applications, the system cost-performance ratio is improved. The cost effectiveness of multiprocessing is contingent upon low processor/bus utilization of memory, or a high degree of parallelism in the memory system, such as interleaving or banking. Furthermore, realization of the potential afforded by multiprocessing hardware can only be attained in properly structured multiprogrammed operating systems.
1 citations