[PR] LIBJACKET v1.0 – The Matrix Companion to CUDA

Atlanta, GA, June 1, 2011 – AccelerEyes today released version 1.0 of libJacket enabling GPU programmers to achieve better GPU performance with less programming hassle. It builds upon the big success of Jacket for MATLAB®, bringing that popular runtime system and vast GPU function library to new programming languages.

The library is available for C, C++, Fortran, and Python. It is designed for use with any CUDA application, in the same way that the native CUBLAS and CUFFT libraries are leveraged. It can also be leveraged to avoid writing any tedious kernel code, for productivity and performance gains.

LIBJACKET scales across all CUDA-capable GPUs, from laptops to workstations to high-end supercomputers.

It enables high-level, matrix style code to achieve low-level, down-to-metal speeds so that developers can quickly build high-performance applications. This high-level interface makes it easy to experiment and change various parts of algorithms without having to recode and tune from scratch. LIBJACKET is the largest and fastest set of GPU algorithms available in one package.

This new v1.0 release also incorporates the popular GFOR loop for running FOR loop iterations simultaneously on the GPU. Download a free 15-day trial from the AccelerEyes website.

In conjunction with this launch, AccelerEyes is offering two important promotions:

Enterprise customers have already started adopting libJacket. Northrop Grumman engineer, Xiang Ma, says of libJacket: “I spent a lot of time searching for efficient ways to utilize GPU power without spending too much time on low-level detail. LIBJACKET is the best solution currently available in the market for our goal of significantly improving performance with the least amount of time and effort. I also really like AccelerEyes’ super customer support for helping us with great response time.”

Tags:

• CUDA
• LIBJACKET
• MATLAB