Major chip manufacturers are developing next-generation microprocessor designs that are heterogeneous/hybrid in nature, integrating homogeneous x86-based multicore CPU components and GPU components. The MAGMA (Matrix Algebra on GPU and Multicore Architectures) project’s goal is to develop innovative linear algebra algorithms and to incorporate them into a library that is

• similar to LAPACK in functionality, data storage, and interface

but targeting the

• next-generation of highly parallel, and heterogeneous processors.

Read more...

MAGMA version 0.2 for 32 and 64-bit Linux is now available. This release is intended for a single
CUDA enabled NVIDIA GPU and includes:

• LU, QR, and Cholesky factorizations in both real and complex arithmetic (single and double);
• LQ and QL factorizations in real arithmetic (single and double);
• Linear solvers based on LU, QR, and Cholesky in real arithmetic (single and double);
• Mixed-precision iterative refinement solvers based on LU, QR, and Cholesky in real arithmetic;
• Reduction to upper Hessenberg form in real arithmetic (single and double);
• MAGMA BLAS in real arithmetic (single and double), including gemm, gemv, symv, and trsm.

See the Software section for a download link.

NVIDIA Corp. today recognized the University of Tennessee, Knoxville's (UTK's) Innovative Computing Laboratory (ICL) as a CUDA Center of Excellence, noting its adoption of the CUDA programming model in its curriculum, as well as its pioneering research into the development of linear algebra libraries for the high-performance computing community.

Read more...

Hiding the details of the multi-core and GP-GPU hardware is a really cool goal. Read the full article at Linux Magazine.

The MAGMA team is happy to announce the creation of the MAGMA User Forum. Established to aid with feedback and discussion regarding the newly released MAGMA software, the forum is now up and running.