OneAPI Support for Intel ARC GPU

[craigpod]

I'm using OneAPI mkl blas functions and the TBB parallel_for and concurrent_vector features to accelerate my Windows 11 c++ application.  They work great. I'm using the latest versions of Visual Studio and OneAPI. I'm running an I9-13900KS CPU.  

It would be great if I could implement these or similar features on one of your ARC GPUs. 

Can you tell me how I can accomplish this.

It would be great if I could prototype the function calls I would be on the GPU that is part of my CPU.

Regards

Craig

[Shiquan_Su · Accepted solution]

Hi, Craig:

The mkl has different implementations on CPU and GPU. You may refer to our link line advisor tool to see if the option exists for your desired scenario.

Shiquan

[Shiquan_Su]

Hi, Craig:

You may also check out the following pages:

https://www.intel.com/content/www/us/en/docs/oneapi/optimization-guide-gpu/2025-0/using-performance-libraries.html

https://www.intel.com/content/www/us/en/docs/onemkl/developer-reference-dpcpp/2025-0/overview.html

and let us know if any blas functions on Arc GPU need our developer's attention. Thanks.

Shiquan