SCIENCE

AccelerEyes has released version 1.5 of the Jacket GPU programming platform for MATLAB. Version 1.5 delivers an expanded Image Processing Library, additional core functionality widely requested by Jacket programmers, enhancements to Jacket's GFOR capability, performance enhancements across the platform, new capabilities for profiling applications, and the ability to compile full M-code functions to individual GPU kernels.

AccelerEyes develops Jacket, a software platform that delivers GPU computing power to desktop users of MATLAB and other very high-level languages. It enables faster prototyping and problem solving across a range of government, manufacturing, energy, media, biomedical, financial, and scientific research applications. The Jacket software platform enables accelerated performance for common arithmetic and linear algebra functionality across the complete line of CUDA-capable GPUs from NVIDIA.

"With this release of Jacket, AccelerEyes continues to demonstrate our leadership and focus on providing productivity and performance to MATLAB users interested in leveraging GPU technology," said John Melonakos, CEO of AccelerEyes. "Since the initial introduction of Jacket in 2008, AccelerEyes has developed close working relationships with GPU programmers enabling us to continue to deliver the broadest and fastest function library, advanced just-in-time compilation, and advanced memory management functionality. The MathWorks entering the GPU computing space validates the AccelerEyes decision to deliver solutions for MATLAB users. As this community evaluates the various solutions on the market, we are confident that all organizations will see the vast technical advantages of the Jacket platform over other alternatives."

New and advanced capabilities in Jacket 1.5 include two powerful functions for profiling M-code and for compiling individual M-functions directly to the GPU:

• GPROFILE facilitates GPU and CPU profiling from the MATLAB console. GPROFILE records and reports on the time spent in MATLAB functions on the GPU and compares those results against comparable CPU timings. The results indicate sections of code that should or should not be run on the GPU as well as those that could benefit from vectorization or refactoring.
   
• GCOMPILE (and ARRAYFUN) enable Jacket programmers to define GPU kernels using M-code. Through this mechanism, Jacket is able to perform various additional optimizations, which it is otherwise unable to do in standard dynamic MATLAB mode.

Jacket automatically connects M-code to GPUs through its dynamic compiler technology allowing users to accelerate their applications across any CUDA-capable GPUs. Jacket-based MATLAB applications scale effortlessly across GeForce, Tesla C1060, or the new Tesla C2050 without modification. Jacket eliminates the need to manually port MATLAB code to C, C++, or CUDA to run on GPU-based workstations and clusters -- a productivity step that can take months to years to complete for computationally intensive problems. Jacket 1.5 is compatible across 32-bit and 64-bit versions of Linux, Windows, and Mac operating systems.

Pricing and availability

Jacket 1.5 is now available for download on the AccelerEyes website. Pricing for a Jacket base license with support for a single GPU is $999US, $800US, and $350US for commercial, government & research, and academic customers, respectively. AccelerEyes provides 12 months of software maintenance and updates with each software license. Volume packages and development bundles are also now available at special price points for a limited time only.