| Document Date: 2011-06-21 08:58:21
Open Document File Size: 160,41 KBShare Result on Facebook
Company Hanson / Lawson / NVIDIA / GPU / Intel / / Facility MKL library / Intel Math Kernel Library / COLLEGE PARK Abstract / CORE ARCHITECTURES YUANCHENG LUO AND RAMANI DURAISWAMI UNIVERSITY OF MARYLAND / / IndustryTerm equivalent matrix-vector product / performance computing / sequential processors / parallel applications / parallel algorithms / active-set iterative algorithm / efficient algorithm / active-set algorithm / feasible solution / multi-core processors / large and sparse matrix systems / signal processing applications / inner products / on-line applications / multi-processor / scalar-processors / computing / computable analytical solution / real-time and on-line processing / pre-computing / vector processor / linear systems / constrained solution / successive applications / square systems / efficient algorithms / / OperatingSystem Fermi / / Organization UNIVERSITY OF MARYLAND / COLLEGE PARK / / Person Ai / / Product OpenMP / / ProvinceOrState Maryland / / Technology NNLS Algorithms / efficient algorithm / active-set algorithm / efficient algorithms / API / vector processor / In algorithm / caching / active-set iterative algorithm / shared memory / NNLS algorithm / /
SocialTag |
EFFICIENT PARALLEL NON-NEGATIVE LEAST SQUARES ON MULTI-CORE ARCHITECTURES YUANCHENG LUO AND RAMANI DURAISWAMI UNIVERSITY OF MARYLAND, COLLEGE PARK Abstract. We parallelize a version of the active-set iterative algorithm