CUDA Programming with Mathematica

Mathematica is a sophisticated development environment that combines a flexible programming language with a wide range of symbolic and numeric computational capabilities, production of high-quality visualizations, built-in application packages, and a range of immediate deployment options. With access to thousands of datasets and the ability to load external dynamic libraries and automatically generate C code, Mathematica is the most intuitive build-to-deploy environment in the market.

Mathematica’s CUDALink: Integrated GPU Programming Mathematica provides GPU programming support via the built-in CUDALink package, which gives you GPU accelerated linear algebra, discrete Fourier transform, and image processing algorithms. You can also write your own CUDALinkmodules with minimal effort. The CUDALink package included within Mathematica at no additional cost offers: Access to Mathematica’s automatic interface builders, import/export capabilities, and visualization features Access to Mathematica’s curated datasets Support for single and double arithmetic precision Ability to load user-defined CUDA programs into Mathematica Scalability to multiple devices Integration with existing Mathematica technologies, such as remote sessions

Additional Resources

• Mathematica GPU Computing Guide [here]
• Mathematica CUDALink Tutorial [here]
• Mathematica OpenCLLink Tutorial [here]
• CUDA Programming within Mathematica – Wolfram whitepaper [here]

Example: Performing Canny edge detection

 

Example: Simulating a random walk

RECOMMENDED PROFESSIONAL PRODUCTS

The powerful GPU computing capabilities in Mathematica were developed on Tesla and Quadro GPU computing products and require the use of recent CUDA-capable NVIDIA GPUs. Tesla and Quadro GPU computing products are designed to deliver the highest computational performance with the most reliable numerical accuracy, and are available and supported by the world’s leading professional system manufacturers. To utilize Mathematica's CUDALink, the following is required: Operating System: Windows, Linux, or Mac OS X, both 32- and 64-bit architecture NVIDIA CUDA enabled products Mathematica 8.0 or later

TESLA BENEFITS Highest Computational Performance > High-speed double precision operations > Large dedicated memory > High-speed bi-directional PCIe communication > NVIDIA GPUDirect™ with InfiniBand Most Reliable > ECC memory > Rigorous stress testing Best Supported > Professional support network > OEM system integration > Long-term product lifecycle > 3 year warranty > Cluster & system management tools    (server products) > Windows remote desktop support

RECOMMENDED TESLA & QUADRO CONFIGURATIONS High-End Workstation > Two Tesla C2050 or C2070 GPUs > Quadro NVS 295 > Two quad-core CPUs > 12 GB system memory Mid-Range Workstation > Tesla C2050 or C2070 GPU > Quadro NVS 295 > Quad-core CPU > 8 GB system memory Entry Workstation > Quadro 4000 GPU > Single quad-core CPU > 4 GB system memory

NVIDIA Tesla and Quadro products are available from all major professional workstation OEMs. Only Tesla GPU computing products are designed and qualified for compute cluster deployment.

BUY OPTIMIZED TESLA SYSTEMS
We partner with our system vendors to provide optimal solutions that accelerate your workload. Buy now and enjoy all the benefits of GPU-acceleration on Mathematica.