# CULA R12 (CUDA 4.0 support) now available GPU Accelerated Linear Algebra Package

**URL:** <https://forums.developer.nvidia.com/t/cula-r12-cuda-4-0-support-now-available-gpu-accelerated-linear-algebra-package/22647>\
**Category:** CUDA Programming and Performance\
**Created:** [May 26, 2011, 5:59pm UTC](https://forums.developer.nvidia.com/t/cula-r12-cuda-4-0-support-now-available-gpu-accelerated-linear-algebra-package/22647 "2011-05-26T17:59:54Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Kyle\_Spagnoli](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@Kyle\_Spagnoli](https://forums.developer.nvidia.com/u/Kyle_Spagnoli)\
**Post date:** [May 26, 2011, 5:59pm UTC](https://forums.developer.nvidia.com/t/cula-r12-cuda-4-0-support-now-available-gpu-accelerated-linear-algebra-package/22647/1 "2011-05-26T17:59:54Z")

</div>

EM Photonics and the CULA team are very pleased to announce that CULA R12, based on CUDA 4.0, is available immediately at our downloads page.

Besides CUDA 4.0 support, this release also introduces the new link-compatible interface, which allows for zero-effort porting of existing codes which use LAPACK routines. For more information, please see the documentation included or read our blog post about the feature.

> [@](#):
>
> CULA is a GPU-accelerated linear algebra library that utilizes the NVIDIA CUDA parallel computing architecture to dramatically improve the computation speed of sophisticated mathematics.
> 
> **Feature Rich and Easy to Use**
> 
> » Familiar LAPACK interface
> 
> » No CUDA experience required
> 
> » MATLAB and Python Integration
> 
> » Read more about CULA’s features
> 
> **Many Functions Available**
> 
> » System Solvers
> 
> » Eigenvalues Routines
> 
> » Singular Value Decomposition
> 
> » See the full function list
> 
> **GPU Acceleration for a Variety of Platforms**
> 
> » Supercomputing performance
> 
> » Parallel GPU implementation
> 
> » Accurate results
> 
> » See how CULA performs (CULA R13 numbers coming soon!)
> 
> **Multiple Interfaces and Platforms Supported**
> 
> » Device & host interfaces
> 
> » C, C++, and Fortran libraries
> 
> » Cross platform (Win, Linux, Mac)
> 
> » Learn more about CULA’s interfaces

---

<div class="post-metadata">

**Author:** ![Kyle\_Spagnoli](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@Kyle\_Spagnoli](https://forums.developer.nvidia.com/u/Kyle_Spagnoli)\
**Post date:** [June 2, 2011, 4:35pm UTC](https://forums.developer.nvidia.com/t/cula-r12-cuda-4-0-support-now-available-gpu-accelerated-linear-algebra-package/22647/2 "2011-06-02T16:35:56Z")

</div>

We just added a blog post with information on using the new link interface in MATLAB.

[http://www.culatools.com/blog/2011/05/31/accelerate-matlab-with-the-cula-link-interface/](http://www.culatools.com/blog/2011/05/31/accelerate-matlab-with-the-cula-link-interface/)

To utilize this new interface in MATLAB you simply have to change a few environment variables – there are no MEX files to compile, no clunky gpuArray objects, and no changes MATLAB function names!

For example, the MATLAB commands:

```auto
>> tic; A = A*A'; toc;

Elapsed time is 3.414187 seconds.

>> tic; [q,r] = qr(B); toc;

Elapsed time is 11.318329 seconds.

```

Will be accelerated with zero effort from the user!