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

Advances in computing, and their impact on scientific computing.

Mike Giles1

  • 1Oxford University Computing Laboratory, Wolfson Building, Parks Road, Oxford OX1 3QD, UK.

Novartis Foundation Symposium
|January 24, 2003
PubMed
Summary

This paper reviews computer hardware and software trends in scientific computing, noting the shift to PC clusters and the challenges of large-scale academic software development.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Using GPUs to accelerate computational diffusion MRI: From microstructure estimation to tractography and connectomes.

NeuroImage·2018
Same author

STOCHSIMGPU: parallel stochastic simulation for the Systems Biology Toolbox 2 for MATLAB.

Bioinformatics (Oxford, England)·2011
See all related articles

Area of Science:

  • Computer Science
  • Scientific Computing

Background:

  • Evolution of computer hardware components like microprocessors and memory.
  • Analysis of complete systems, including the decline of vector supercomputing and the rise of PC clusters.

Purpose of the Study:

  • To discuss current developments and trends in scientific computing hardware and software.
  • To highlight the challenges in software engineering for large academic projects.

Main Methods:

  • Review of hardware trends, from basic components to complete systems.
  • Examination of software environments, including shared-memory (OpenMP) and distributed-memory (MPI) programming.
  • Discussion of grid computing and software packages.

Main Results:

  • Observed decline in vector supercomputing and large shared-memory systems.
  • Significant growth in large clusters of PCs for scientific computation.
  • Maturity of OpenMP and MPI programming environments, with emerging grid computing.

Conclusions:

  • Scientific computing is increasingly reliant on large PC clusters and sophisticated software packages.
  • Implementing effective software engineering practices in large academic projects is crucial and challenging.

Related Experiment Videos