Jacket version 1.3

AccelerEyes has introduced version 1.3 of its Jacket GPU computing software that integrates double precision linear algebra, is easier to setup, performs faster, and is less expensive. Version 1.3 has been designed and developed with participation of AccelerEyes' customers and prospective customers who shaped the product feature set to meet their needs and requirements.

Jacket is a software platform that delivers GPU computing power to desktop users of Matlab and other high-level languages. It enables faster prototyping and problem solving across a range of government, manufacturing, energy, media, biomedical, financial, and scientific research applications. Jacket 1.3 integrates the ability for Jacket users to perform double precision linear algebra functionality with Nvidia hardware based on the Fermi architecture. To obtain this Lapack functionality for GPUs, Jacket 1.3 users will need to license the Jacket DLA add‐on.

AccelerEyes has partnered with EM Photonics to extend the Jacket product family to support double precision linear algebra by integrating Cula tools to the platform. Jacket 1.3, together with Jacket DLA, offers double precision linear algebra functionality for inv, svd, eig, lu, chol, mpower, norm, and mldivide.

The software also provides expanded functional capabilities for conv2, sort, sortrows, eps, nnz, sind, cosd, tand, nextpow2, nthroot, and interp2. Support for Jacket's 'gfor' function has also been expanded or added in 1.3 for kron, cross, permute, repmat, circshift, cat, and filter.

In addition, Jacket 1.3 makes it easier for users to install, setup, and configure Jacket on both Windows and Linux platforms. The Cuda toolkit is now pre-packaged with Jacket. This release supports Matlab 2010A as well as previous versions of Matlab back to R2006B.

Analysis and opinion

Robert Roe looks at research from the University of Alaska that is using HPC to change the way we look at the movement of ice sheets


Robert Roe talks to cooling experts to find out what innovation lies ahead for HPC users

Analysis and opinion