Back to Results
First PageMeta Content
Computer hardware / Video cards / Numerical software / Graphics hardware / Nvidia / CUDA / Basic Linear Algebra Subprograms / Nvidia Tesla / GPGPU / Numerical analysis / Numerical linear algebra / Computing


An Improved MAGMA GEMM for Fermi GPUs Rajib Nath1 , Stanimire Tomov1 , and Jack Dongarra1,2,3 1 2
Add to Reading List

Document Date: 2010-08-01 22:11:59


Open Document

File Size: 486,71 KB

Share Result on Facebook

City

ISTANBUL / New York / Berlin / /

Company

IBM / GPU / Oak Ridge National Laboratory / IEEE Press / AMD / NVIDIA / Intel / Microsoft / /

Country

United States / United Kingdom / /

Currency

AMD / USD / /

/

Facility

CULA library / University of Tennessee / MAGMA library / University of Manchester / AMD Core Math Library / MAGMA BLAS library / LAPACK library / Scientific Subroutine Library / CUDA CUBLAS Library / Math Kernel Library / /

IndustryTerm

homogeneous x86-based multicore systems / on x86 multicore systems / homogeneous multicore systems / higher level algorithms / multicore x86-based systems / homogeneous multicore-based systems / computing / numerical algorithms / search space / fundamental linear algebra algorithms / web-page / /

OperatingSystem

Fermi / /

Organization

U.S. Department of Energy / U.S. National Science Foundation / Texas Advanced Computing Center / University of Tennessee / University of Manchester / /

Person

Antoine Petitet / R. Clinton Whaley / Everett Phillips / Vasily Volkov / James Demmel / BLAS DGEMM / Jack Dongarra / Massimiliano Fatica / /

/

ProgrammingLanguage

C / /

ProvinceOrState

Tennessee / /

Technology

fundamental linear algebra algorithms / improved GEMM algorithm / shared memory / higher level algorithms / GEMM algorithm / /

URL

http /

SocialTag