Skip to Main Content
Home
  • About
  • People
  • Publications
  • Sponsors
  • Media Center
  • Research
  • Login

About Par Lab

  • Get Involved
  • Come Visit
  • 2009 Short Course on Parallel Programming
  • Seminars
  • Contact
  • Research Projects

James Demmel

  • Professor
  • demmel@cs.berkeley.edu
  • Website: EECS Homepage

  • Address:
    564 Soda Hall

    Additional:
    UC Berkeley

    City:
    Berkeley
    ,
    State:
    Zip Code:
    94720-1776

Advisees

  • Kaushik Datta
  • Mark Hoemmen
  • Andrew Gearhart
  • Rajesh Nishtala
  • Vasily Volkov
  • Erin Carson
  • Nicholas Knight

Projects

  • Sketching
  • Automatic Performance Tuning (Autotuning)
  • Personalized Medicine for Coronary Heart Disease (CHD)

Publications

  • 2009, Minimizing Communication in Linear Algebra
  • 2009, Minimizing Communication in Sparse Matrix Solvers
  • 2009, A View of the Parallel Computing Landscape
  • 2009, SEJITS: Getting Productivity and PerformanceWith Selective Embedded JIT Specialization
  • 2008, Avoiding Communication in Sparse Matrix Computations
  • 2008, The Parallel Computing Laboratory at U.C. Berkeley: A Research Agenda Based on the Berkeley View
  • 2008, Communication-optimal parallel and sequential QR and LU factorizations
  • 2008, Benchmarking GPUs to tune dense linear algebra
  • 2008, Communication-Avoiding Gaussian Elimination
  • 2008, LU, QR and Cholesky factorizations using vector capabilities of GPUs
  • 2007, Optimization of Sparse-Matrix-Vector Multiplication on Emerging Multicore Platform
  • Site Map
  • Accessibility
  • Site Credit
  • Internal
© 2009 The Regents of the University of California. All Rights Reserved.