An experimental multiprocessor system for distributed parallel computations.

De Maeyer, L.; Di Nicola, A.; Maetche, R.; Von der Malsburg, C.; Wiskott, L.

doi:10.1016/0165-6074(90)90330-C

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Journal Article

An experimental multiprocessor system for distributed parallel computations.

MPS-Authors

/persons/resource/persons14972

De Maeyer, L.
Abteilung Experimentelle Methoden, MPI for biophysical chemistry, Max Planck Society;

/persons/resource/persons14990

Di Nicola, A.
Abteilung Experimentelle Methoden, MPI for biophysical chemistry, Max Planck Society;

Maetche, R.
Max Planck Society;

External Resource

No external resources are shared

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

603051.pdf
(Publisher version), 932KB

Supplementary Material (public)

There is no public supplementary material available

Citation

De Maeyer, L., Di Nicola, A., Maetche, R., Von der Malsburg, C., & Wiskott, L. (1990). An experimental multiprocessor system for distributed parallel computations. Microprocessing and Microprogramming, 26(5), 305-317. doi:10.1016/0165-6074(90)90330-C.

Cite as: https://hdl.handle.net/11858/00-001M-0000-0013-0E4C-6

Abstract

The availability of low-cost microprocessor chips with efficient instruction sets for specific numerical tasks (signal processors) has been exploited for building a versatile multiprocessor system, consisting of a host minicomputer augmented by a number of joint processors. The host provides a multiuser-multitasking environment and manages system resources and task scheduling. User applications can call upon one or more joint processors for parallel execution of adequately partitioned, computationally intensive numeric operations. Each joint processor has sufficient local memory for storing procedures and data and has access to regions in host memory for shared data. Kernel processes in the host and in the joint processors provide the necessary mechanism for initialization and synchronization of the distributed parallel execution of procedures.