News
Displaying 16-20 of 36 Entries
clMAGMA 0.2 Released
2012-05-24
clMAGMA 0.2 is now available. This release provides the following new functionalities:
  • Solvers for general and symmmetric dense matrices;
  • Least squares solver;
  • Multiple precision support for the LU factorization;
  • Support for s/d/c/z precision arithmetic for all routines provided.

Further detail can be found in the ReleaseNotes.

See the MAGMA software homepage for a download link.

NVIDIA recognizes MAGMA breakthrough at GTC12
2012-05-20

CUDA Centers of Excellence (CCOEs) include some of the world's top universities engaged in cutting-edge work with CUDA and GPU computing.  To highlight and reward the excellent research, each of the world's 18 CCOEs was asked to submit an abstract describing their top achievement in GPU computing over the past year and a half.  A panel of experts, led by NVIDIA Chief Scientist Bill Dally, selected four CCOEs to present their achievements at a special event during GTC 2012. UTK's CCOE was selected as one out of four CCOE finalists to showcase at GTC12 their work (see slides) on MAGMA: A Breakthrough in Solvers for Eigenvalue Problems (see abstract). 

Each of the four finalists received an HP ProLiant SL250 Gen8 system configured with dual NVIDIA Tesla K10 GPU accelerators

For further information see the NVIDIA press release.


MAGMA 1.2 Released
2012-05-10
MAGMA 1.2 is now available. This release provides the following new functionalities:
  • Two-stage reduction to tridiagonal form;
  • Updated eigensolvers for standard and generalized eigenproblems for symmetric/Hermitian matrices;
  • Tracing functions;
  • Improved error checking, interfaces, and documentation;
  • Extended LAPACK testing.

Further detail can be found in the ReleaseNotes.


See the MAGMA software homepage for a download link.

clMAGMA 0.1 Beta Released
2012-04-04
clMAGMA 0.1 Beta is now available. This release provides OpenCL implementations for MAGMA's one-sided dense matrix factorizations (LU, QR, and Cholesky), and thus extending MAGMA's support to include AMD GPUs. The clMAGMA library dependancies, in particular optimized GPU OpenCL BLAS and CPU optimized BLAS and LAPACK for AMD hardware, can be found in the AMD Accelerated Parallel Processing Math Libraries (APPML). Sample performance results on AMD Tahiti GPU are illustrated on the figures below. 

Cholesky factorization

LU factorization

QR factorization

See the Software section for a download link.


2012-02-22

Displaying 16-20 of 36 Entries
Apr 16 2014 Admin Login