Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Highly parallel computation.

P J Denning, W F Tichy

    Science (New York, N.Y.)
    |November 30, 1990
    PubMed
    Summary
    This summary is machine-generated.

    Advanced scientific problems require highly parallel computing. Current research compares Multiple Instruction, Multiple Data (MIMD) and Single Instruction, Multiple Data (SIMD) architectures, with neither showing a clear advantage for homogeneous problems.

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same journal

    Erratum for the Research Article "Detecting supramolecular organic nanoparticles during heat wave".

    Science (New York, N.Y.)·2026
    Same journal

    Local signals, systemic decline.

    Science (New York, N.Y.)·2026
    Same journal

    The mechanics of liver regeneration.

    Science (New York, N.Y.)·2026
    Same journal

    Computing in a memory with physics.

    Science (New York, N.Y.)·2026
    Same journal

    Retraction.

    Science (New York, N.Y.)·2026
    Same journal

    Making time.

    Science (New York, N.Y.)·2026
    See all related articles

    Area of Science:

    • Computational science and high-performance computing.

    Background:

    • Advanced scientific problems necessitate high computational rates, achievable only through highly parallel computing architectures.
    • A decade of research has confirmed the feasibility of these parallel machines.

    Purpose of the Study:

    • To evaluate the suitability of different parallel computing architectures for specific classes of scientific problems.
    • To identify the most effective architectures for near-homogeneous and complex scientific computations.

    Main Methods:

    • Comparative analysis of Multiple Instruction, Multiple Data (MIMD) and Single Instruction, Multiple Data (SIMD) architectures.
    • Assessment of speculative architectures like neural networks and data flow for heterogeneous problems.

    Main Results:

    Related Experiment Videos

  • MIMD and SIMD architectures have yielded the best results to date for scientific problems.
  • Neither MIMD nor SIMD demonstrates a decisive advantage for most near-homogeneous scientific problems.

    • Conclusions:

    • The choice of parallel architecture depends on the nature of the scientific problem.
    • For problems with many dissimilar parts, novel architectures such as neural networks or data flow may be required.