Browse Research and Tech Reports - Computer Science by Author "Kale, Laxmikant V."

  • Bhatele, Abhinav; Chung, I-Hsin; Kale, Laxmikant V. (2010-04)
    Network contention has an increasingly adverse effect on the performance of parallel applications with increasing size of parallel machines. Machines of the petascale era are forcing application developers to map tasks ...

    application/pdf

    application/pdfPDF (629kB)
  • Jindal, Prateek; Hockenmaier, Julia; Kale, Laxmikant V. (2013-12-04)
    Topic modeling algorithms (like Latent Dirichlet Allocation) tend to be very slow when run over large document collections. In this presentation, we discuss distributed strategies for topic modeling. We use Charm++ as our ...

    application/pdf

    application/pdfPDF (310kB)
  • Jindal, Prateek; Roth, Dan; Kale, Laxmikant V. (2013-12-04)
    Parallel programming is becoming increasingly popular. Computers have increasingly many cores (processors). Also, large computer-clusters are becoming available. But there is still no good programming framework for these ...

    application/pdf

    application/pdfPDF (626kB)
  • Bhatele, Abhinav; Kumar, Sameer; Mei, Chao; Phillips, James C.; Zheng, Gengbin; Kale, Laxmikant V. (2009-02)
    NAMD is a portable parallel application for biomolecular simulations. NAMD pioneered the use of hybrid spatial and force decomposition, a technique used by most scalable programs for biomolecular simulations, including ...

    application/pdf

    application/pdfPDF (350kB)
  • Bhatele, Abhinav; Kumar, Sameer; Mei, Chao; Phillips, James C.; Zheng, Gengbin; Kale, Laxmikant V. (2009-02)
    NAMD is a portable parallel application for biomolecular simulations. NAMD pioneered the use of hybrid spatial and force decomposition, a technique used by most scalable programs for biomolecular simulations, including ...

    application/pdf

    application/pdfPDF (350kB)
  • Jindal, Prateek; Roth, Dan; Kale, Laxmikant V. (2013-12-04)
    SVMs have been used for long for data classification. While solving very large problems, one may encounter hundreds of thousands of features and a large number of training vectors. A natural solution to solving problems ...

    application/pdf

    application/pdfPDF (4MB)