Tesla
Product Info
Additional Info
  • Software Development Tools

    Programming CUDA-enabled GPUs

  • NVIDIA CUDA
  • Webinars

    Learn more about GPU computing and CUDA-enabled applications through these webinars

  • Request Resource CD

    If you are new to GPU computing or would like to add to your knowledge of NVIDIA CUDA programming and Tesla hardware then this resource CD is for you.

GPU Acceleration on MATLAB® with Jacket™

 
 
Since 2007, NVIDIA and AccelerEyes have collaborated to deliver the power of GPU computing to MATLAB® users with Jacket™. Jacket programming has become a popular method for accelerating MATLAB® code on the GPU due to its ease-of-use, broad function library, and great GPU performance. Accelereyes

Jacket includes many key features to deliver results on full applications:

> Over 500 functions, including math, signal processing, image processing, and statistics
> Specialized FOR loops to run many iterations simultaneously with GFOR
> An optimized runtime to optimize memory bandwidth and kernel configurations
> Integrate users' own CUDA kernels into MATLAB® via the Jacket SDK
> Compute across multiple NVIDIA GPUs via Jacket MGL and HPC
 


Brief Jacket Tutorial Video in MATLAB
GPU Computing Intro with Jacket
 

With Jacket programming, the MATLAB® community can enjoy GPU-acceleration with an easy, high-level interface. After achieving success with the fast MATLAB® prototypes, Jacket programmers can also use ArrayFire to achieve high-level acceleration directly in C, C++, Fortran, or Python.

Potential Field Extrapolation on Magnetogram
Relative Performance, Potential Field Extrapolation on Magnetogram
 Video Tour
Video tour of GPU Computing with MATLAB® using Jacket
RECOMMENDED PROFESSIONAL PRODUCTS
The powerful GPU computing capabilities in Jacket were developed on Tesla and Quadro GPU computing products and require the use of recent CUDA-capable NVIDIA GPUs, such as NVIDIA Tesla 10-series or 20-series products.

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.

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 and system management tools
   (server products)
> Windows remote desktop support
 
Recommended Tesla & Quadro Configurations
High-End Workstation
> Two Tesla C2075 GPUs
> Quadro 2000
> Two quad-core CPUs
> 24 GB system memory
Mid-Range Workstation
> Tesla C2075 GPU
> Quadro 600
> Quad-core CPU
> 12 GB system memory
Entry Workstation
> Tesla C2075 GPU
> Quadro 600
> Single quad-core CPU
> 6 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.

MATLAB is a registered trademark of The MathWorks, Inc.

Jacket is a trademark of AccelerEyes