Transputer-based Parallel Systems for Performance Evaluation of Bidirectional Associative Memory
نویسنده
چکیده
In this paper, we discuss parallel implementation of an artificial neural network for pattern d a t i o n , the Bidirectional Associative Memory(BAM). Transputer-based parallel architecture8 like hypercube, mesh and linear array are used to exploit the parallelism in BAM. A comparitive study of utilization and speedup for various architectures is made. Hypercube performs better in terms of utilization and speedup when compared to the other architectures.
منابع مشابه
Fast recognition of real objects by an optimized hetero-associative neural network
2014 We have developed and realized a concept which is very well suited for a quick recognition of highly correlated patterns. For a hetero-associative memory we used a minimal optimized output code (index memory). We constructed a tree structure in which the assignment of indices has been optimized by simulated annealing. Thus the algorithm for optimal stability of the learned patterns works m...
متن کاملA Scalable Tuple Space Model for Structured Parallel Programming
The paper proposes and analyses a scalable model of an associative distributed shared memory for massively parallel architectures. The proposed model is hierarchical and fits the modern style of structured parallel programming. If parallel applications are composed of a set of modules with a well-defined scope of interaction, the proposed model can induce a memory access latency time that only ...
متن کاملImplementing a Transputer SCSI Interface
The work described in this report is part of a project to investigate high performance communication network interface structures which are compatible with existing operating systems The aim of the project is to increase the e ective speed of Remote Procedure Calls RPC for an application by adding parallel processing power to the communication subsystem without making major changes to the appli...
متن کاملAndes: a Performance Analyzer for Parallel Programs
ANDES is a performance monitor designed for MIMD distributed memory machines that inserts additional code in the program to be analyzed. ANDES determines the following metrics: speedup, eeciency, experimentally determined serial fraction, percentage of idle time per processor, load and communication balancing, synchronization time and percentage of cpu-communication overlapping. Within ANDES, a...
متن کاملParallel transport subsystem implementation for high-performance communication
Requirements of emerging applications together with rapid changes in networking technology towards gigabit speeds require new adequate transport systems. Integrated designs of transport services, protocol architecture, and implementation platforms are required by forthcoming applications in high-speed network environments. The transport subsystem PATROCLOS (parallel transport subsystem for cell...
متن کامل