Neural Network Simulation on the MasPar MP-1 Massively Parallel Processor

Grajski, Kamil A.; Chinn, G.C.; Chen, C.; Kuszmaul, Christopher L.; Tomboulian, S.

doi:10.1007/978-94-009-0643-3_38

Cited by 17 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have investigated the trade-offs of different approaches to parallelization of neural networks, as given in [16], [6], [2] and [24] and decided on implementations which combine unit parallelism with training vector parallelism (the first two implementations) resp. link weight parallelism with training vector parallelism.…”

Section: The Architecture Of the Mp-1216mentioning

confidence: 99%

<title>Performance aspects of mapping neural networks onto a massively parallel SIMD computer</title>

Zell

Vogt²,

Mache

et al. 1993

SPIE Proceedings

View full text Add to dashboard Cite

In this paper we present and compare three different massively parallel implementations of multilayer feedforward neural networks on a MasPar MP.-1216, a parallel SIMD computer with 16,384 processors. For multilayer feedforward networks we have obtained sustainedrates ofup to 348 MCPS and 129 MCUPS with backpropagation, a high mark for general purpose SIMI) computers. After a brief introduction to SNNS, the paper first focuses on the problems of mapping neural networks to parallel hardware. Different aspects of parallelism are presented. Two combinations of unit and training pattern parallelism were implemented as well as link and training panern parallelism. We describe the implementation problems in obtaining high propagation rates on a SIMD machine and problems with the resulting learning algorithms in general.

show abstract

Section: The Architecture Of the Mp-1216mentioning

confidence: 99%

<title>Performance aspects of mapping neural networks onto a massively parallel SIMD computer</title>

Zell

Vogt²,

Mache

et al. 1993

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…It is unfair to quote times for the latter because time has not permitted completion of the work, however, using only the front-end processor the conditioning time was 5.5 seconds. Properly to utilize the power of the machine for parallel computation of a large number of channels requires a complex program but previous work [3] suggests that this may result in speed improvements of the order of 20.…”

Section: Future Workmentioning

confidence: 99%

Using neural nets to identify marine mammals

Booth

Proceedings of OCEANS '93

View full text Add to dashboard Cite

show abstract

“…From this data it can be seen that it is advisable to use the local grid as much as possible since the communication bandwidth is much larger than with the router. Also on our machine we experi- Having investigated the trade-offs of different approaches to parallelization of neural networks, as given in [131, [14], [151 and [16] we decided on an implementation which combines unit parallelism with training vector parallelism. All implementations of our parallel simulator kernel were done in MPL, a parallel extension of C. Two of them have recently been converted to AMPL, the ANSI C extension of MPL.…”

Section: A Architecture Of the Mp-1mentioning

confidence: 99%

Problems of massive parallelism in neural network simulation

Zell

Mache

Vogt

et al.

IEEE International Conference on Neural Networks

View full text Add to dashboard Cite

We here present and compare different massively paraIIe1 Implementatlous of multilayer feedfomard neural networks on a MasPar MP-1216, a parallel SIMD computer with 16,384 p r 0 c e . e " For mukllayer feedforward networks we have obtained sustphed rates of up to 348 M CPS and 129 M CUPS with backpropagation, a hlgh mark for general purpose SIMD computers. This paper focuses on the problems of mapping neural networks to parallel hardware, on implementation problems in obtainlng high propagatlon rates on a SIMD machine and on problems with the resulting learning algorithms.Keywords: artlllclal neural networks, neural network simulators, massive parallelism I. INTRODUCTlON AND MOTIVATION Our research group wants to understand the advantages and the trade-offs of the various artificial neural network paradigms and learning algorithms, their training efficiency and generalization capabilities and their suitability for massively parallel implementation. We have developed a neural network simulator, SNNS, which has proven well suited for research on learning algorithms, on issues of visualization, training and performance and on parallel implementation of neural networks. SNNS is also used in a number of other university research groups and with growing acceptance in industry as a neural network evaluation and prototyping tool. In this paper we are describing the experiences we gained in developing a massively parallel simulator kernel for SNNS running on our 16 K processor MasPar MP-1216. STUTTGART NEURAL NETWORK S W A T O R SNNS (Stuttgart Neural NetworkSimulator) [ll, 121, [31, is an efficient and portable neural network simulation environment for Unix workstations developed at the University of Stuttgart. It is a software tool to generate, train, test and visualize artificial neural networks. The whole network simulator has been developed in C on Unix workstations. The graphical user interface was implemented under X-Windows XllR5 (Athena widget set), for maximal portability.SNNS now consists of a sequential and a parallel simulator kemel and a graphical user interface (Fig. 1). The simulator kemel operates on the internal representation of the neural networks and performs all operations of the learning and recall phase. It is coupled with the graphical user interface via an interface of function calls. The simulator kernel has already been ported to a number of architectures (Sun, HP, DEC, IBM, etc.). A. Graphical User Inregace of SNNSThe graphical user interface is used to create, visualize and modify the network topology interactively. All display elements are kept in separate windows and thus can be arbitrarily arranged. The user has a powerful set of operations (insertion, deletion, copying, moving) which may be applied to individual units or to selections of units and may affect links as well, like 'copy all selected units with their input links' or 'delete all links into the selected units'. Networks can be modified through the user interface during simulation. Units can be introduced, removed, or have their...

show abstract

Neural Network Simulation on the MasPar MP-1 Massively Parallel Processor

Cited by 17 publications

References 0 publications

<title>Performance aspects of mapping neural networks onto a massively parallel SIMD computer</title>

<title>Performance aspects of mapping neural networks onto a massively parallel SIMD computer</title>

Using neural nets to identify marine mammals

Problems of massive parallelism in neural network simulation

Contact Info

Product

Resources

About