this paper examines the scalability of "shared-nothing" architectures as the future platforms of choice for large, scalable, transaction processing systems. Capacity planners need some means of assessing thr...
详细信息
the proceedings contain 43 papers. the topics discussed include: graph contraction for physical optimization methods: a quality-cost tradeoff for mapping data on parallel computers;managing pages in shared virtual mem...
ISBN:
(纸本)089791600X
the proceedings contain 43 papers. the topics discussed include: graph contraction for physical optimization methods: a quality-cost tradeoff for mapping data on parallel computers;managing pages in shared virtual memory systems: getting the compiler into the game;the EM-4 under implicit parallelism;data stream control optimization in dataflow architectures;the effectiveness of decoupling;speculative prefetching;increasing the instruction fetch rate via multiple branch prediction and a branch address cache;speculative execution and branch prediction on parallel machines;and PARADIGM: a compiler for automatic distribution on multicomputers.
the trend in modal extraction algorithms is to use all the available FRF data to obtain a global estimate of the natural frequencies, damping ratios and mode shapes. Improvements in transducer and signal processing te...
详细信息
ISBN:
(纸本)0912053410
the trend in modal extraction algorithms is to use all the available FRF data to obtain a global estimate of the natural frequencies, damping ratios and mode shapes. Improvements in transducer and signal processing technology allow the simultaneous measurement of many hundreds of channels of response data. the quality of data available and the complexity of the extraction algorithms make considerable demands on the available computer power and require a fast PC or work station to perform satisfactorily. An alternative to ever faster sequential processors is to implement the algorithm in parallel, for example on a network of transputers. parallelarchitectures are a cost effective means of increasing computational power, and a large number of response channels simply require more processors. this paper considers how one typical modal extraction algorithm, the Rational Fraction Polynomial Method, may be implemented on a network of transputers. the Rational Fraction Polynomial Method is a frequency domain curve fitting algorithm and is one of the easiest algorithms to convert to parallel computation. this paper reviews the algorithm and considers the problems involved in a parallel implementation.
In this paper we present a new methodology for the performance prediction of parallel programs on parallel platforms ranging from shared-memory to distributed-memory (vector) machines. the methodology comprises a proc...
详细信息
this paper discusses the architecture of the new Hitachi supercomputer series, which is capable of achieving 8 GFLOPS in each of up to four processors. this architecture provides high-performance processing for fine-g...
详细信息
the proceedings contain 60 papers. the special focus in this conference is on Methodologies for Intelligent Systems. the topics include: On extended disjunctive logic programs;model finding strategies in semantically ...
ISBN:
(纸本)9783540568049
the proceedings contain 60 papers. the special focus in this conference is on Methodologies for Intelligent Systems. the topics include: On extended disjunctive logic programs;model finding strategies in semantically guided instance-based theorem proving;an expressive three-valued logic with two negations;compiling proof search in semantic tableaux;short CNF in finitely-valued logics;a modal approach;an admissible heuristic search algorithm;building an expert system language interpreter withthe rule network technique;input-driven control of rule-based expert systems;case-based planning for medical diagnosis;a methodology for expert systems development;towards intelligent databases;combining classification and nonmonotonic inheritance reasoning;mechanical proof systems for logic ii, consensus programs and their processing;the logic of only knowing as a unified framework for non-monotonic reasoning;terminological logic involving time and evolution;knowledge management by example;system reorganization and load balancing of parallel database rule processing;using semantic information for processing negation and disjunction in logic programs;methodologies for knowledge-based software engineering;updating logic programs;expressing program requirements using refinement lattices;finding logical consequences using unskolemization;controlled explanation systems;a liftable meta-logic for multiple-valued logics;text-based and fuzzy-centered architectures;boolean reasoning for decision rules generation;upper and lower entropies of belief functions using compatible probability functions;reasoning about higher order uncertainty in possibilistic logic and approximation methods for knowledge representation systems.
Cost-effective multiprocessor designs may be obtained by combining processors of different speeds (heterogeneous architecture) in the same architecture. this way, the serial and critical portions of the application ma...
详细信息
A high-performance parallel system for processing databases is presented, which adopts a distributed memory architecture and has been successfully implemented on a transputer platform. In addition to developing and im...
详细信息
the proceedings contain 26 papers. the special focus in this conference is on Computer Performance Modeling, Measurement and Evaluation. the topics include: parallel simulation;properties and analysis of queueing netw...
ISBN:
(纸本)9783540572978
the proceedings contain 26 papers. the special focus in this conference is on Computer Performance Modeling, Measurement and Evaluation. the topics include: parallel simulation;properties and analysis of queueing network models with finite capacities;performance analysis and optimization withthe power-series algorithm;multiprocessor and distributed system design;response time distributions in queueing network models;fast simulation of rare events in queueing and reliability models;an inlxoduction to modeling dynamic behavior with time series analysis;issues in trace-driven simulation;maximum entropy analysis of queueing network models;performance modeling using DSPN express;relaxation for massively parallel discrete event simulation;an overview of tes processes and modeling methodology;performance engineering of client-server systems;queueing networks with finite capacities;performance instrumentation techniques for parallel systems;a survey of bottleneck analysis in closed networks of queues;software performance engineering;performance measurement using system monitors;providing quality of service packet switched networks;dependability and performability analysis;architectures and algorithms for digital multimedia on-demand servers;analysis and control of polling systems;modeling and analysis of transaction processing systems.
EMC-Y is a new processing element for highly parallel computers designed to achieve high performance parallel computation by fusing a dataflow mechanism and a von Neumann execution pipeline. We have already developed ...
详细信息
暂无评论