A description is given of a recently completed experiment of team performance under stress, in which two organizational structures were considered: a parallel structure and a hierarchical one. Team performance was mea...
详细信息
A description is given of a recently completed experiment of team performance under stress, in which two organizational structures were considered: a parallel structure and a hierarchical one. Team performance was measured in terms of organizational response time and accuracy, while cognitive workload was computed for each individual decision maker (DM). One of the experimental results is that interactions among DMs compensate for differences in individual performance characteristics. The effect is more pronounced when the activities of the organization members are closely coordinated and less pronounced when the DM can operate autonomously.< >
A new model of memory consistency, called release consistency, that allows for more buffering and pipelining than previously proposed models is introduced. A framework for classifying shared accesses and reasoning abo...
详细信息
A new model of memory consistency, called release consistency, that allows for more buffering and pipelining than previously proposed models is introduced. A framework for classifying shared accesses and reasoning about event ordering is developed. The release consistency model is shown to be equivalent to the sequential consistency model for parallel programs with sufficient synchronization. Possible performance gains from the less strict constraints of the release consistency model are explored. Finally, practical implementation issues are discussed, with the discussion concentrating on issues relevant to scalable architectures.< >
K2 is a distributed-memory parallel processor designed to support a multi-user, multi-tasking, time-sharing operating system and an automatically parallelizing FORTRAN compiler. This paper presents the architecture an...
ISBN:
(纸本)9780897913669
K2 is a distributed-memory parallel processor designed to support a multi-user, multi-tasking, time-sharing operating system and an automatically parallelizing FORTRAN compiler. This paper presents the architecture and the hardware implementation of K2, and focuses on the architectural features required by the operating system and the compiler. A prototype machine with 24 processors is currently being developed.
Intelligent networks, which offer enhanced telecommunication services and operations through distributed network resources, are discussed in parallel with ISDN implementation. A user-friendly human-machine interface i...
详细信息
Intelligent networks, which offer enhanced telecommunication services and operations through distributed network resources, are discussed in parallel with ISDN implementation. A user-friendly human-machine interface is one of the most important elements of an intelligent networks. This paper proposes a voice conversation facility with the following configuration and functions to be used in an intelligent network. The human-machine interface is to be implemented as an intelligent peripheral function which is an intelligent network node commonly used for many services. This function is to be conceptualized as an automated network operator, which can operate many services. An instantaneous service activation, automated service operations and easy input/output by interactive voice interface are essential for this concept. In addition, a system design example of an intelligent voice mail system is discussed. The system is based on a conversational model which is determined from 600 operator conversations and applying the voice recognition techniques available in the near future. Using speaker-independent word-spotting techniques which recognize up to 100 words from a continuously spoken sentence, the system will be able to converse naturally with users for selecting voice mail services and functions.
parallel algorithms are presented for solving large-scale systems of algebraic polynomial equations. The algorithms are based on the so-called probability-one homotopy method and they guarantee finding all the roots. ...
详细信息
parallel algorithms are presented for solving large-scale systems of algebraic polynomial equations. The algorithms are based on the so-called probability-one homotopy method and they guarantee finding all the roots. The algorithms are used to obtain all steady-state solutions of the load flow for a three-bus power system. A special probability-one homotopy method is tailored for the load flow to reduce the computational complexity while guaranteeing that all solutions are found. Numerical implementation of the procedures will exploit inherent parallelism in the techniques, providing efficient execution on massively paralleldistributed-memory multiprocessors.
The proceedings contains 84 papers. The following topics are dealt with: object-oriented databases;federated databases;query processing;nontraditional database systems;data security;database machines;database applicat...
详细信息
ISBN:
(纸本)0818619155
The proceedings contains 84 papers. The following topics are dealt with: object-oriented databases;federated databases;query processing;nontraditional database systems;data security;database machines;database applications;communication issues for databases;data modeling;artificial intelligence;distributed database systems;file organizations and data structures;recursive queries;database design;complex objects;DBMS (database management system) performance and implementation;parallel data architectures;neural nets;partitioning in distributeddatabases;query processing techniques;spatial and geographic databases;deductive databases;and data engineering.
An unsupervised paralleldistributed adaptive controller for nonlinear systems is proposed. It is shown to provide bounded tracking and asymptotic regulation following an arbitrary 'teacher.' A two-degrees-of-...
详细信息
ISBN:
(纸本)0818689870
An unsupervised paralleldistributed adaptive controller for nonlinear systems is proposed. It is shown to provide bounded tracking and asymptotic regulation following an arbitrary 'teacher.' A two-degrees-of-freedom robotic simulation example is provided, which demonstrates the feasibility of the proposed method.
The authors have simulated several numerical and nonnumerical algorithms on five distributed-memory parallel processors (DMPPs). All five DMPPs have the same topology (a torus) and the same number of nodes. The archit...
详细信息
ISBN:
(纸本)9780897913195
The authors have simulated several numerical and nonnumerical algorithms on five distributed-memory parallel processors (DMPPs). All five DMPPs have the same topology (a torus) and the same number of nodes. The architectures differ only in the speed of communication between neighboring nodes, with the computation unit unchanged. The authors quantify the effect that interprocessor communication speed and synchronization overhead have on the performance of the DMPPs. After introducing their rationale and reviewing related work, the authors present and discuss the results of the simulations.
COALA (Actor-Oriented Computer for Logic and its Applications) is a multiprocessor architecture project. The aim of the project is to exploit parallelism inherent in logic programs automatically, i.e. without any prog...
详细信息
COALA (Actor-Oriented Computer for Logic and its Applications) is a multiprocessor architecture project. The aim of the project is to exploit parallelism inherent in logic programs automatically, i.e. without any programmer intervention. First, the paper summarizes the work presented earlier: the definition of a parallel interpreting model. Extensions are then presented which allow the model to take into account the execution of independent subgoals. The last part of the paper comments on dynamic measurements obtained from the different versions of the model.
The paper presents the mathematical models, the architecture, the microprogram design and the symbolic programming system of a distributed digital integrating machine, based on fast 16-bit bipolar microprogrammed micr...
详细信息
The paper presents the mathematical models, the architecture, the microprogram design and the symbolic programming system of a distributed digital integrating machine, based on fast 16-bit bipolar microprogrammed microprocessors, which emulate homogeneous parallel integrating structures. After a short introduction in the mathematical theory the working power of the basic computing elements (DDA, servo-adder, comparator), the internal structure of the basic integrating modules, their microprogram design and the internal and external programmable commutation mechanism are explained. An expert system for programming of the machine, implemented in Prolog on the IBM-PC, which determines by symbolic equation transformation the connections in the structure and the initial integrating values, is discussed.
暂无评论