Intel® oneAPI Math Kernel Library
Ask questions and share information with other developers who use Intel® Math Kernel Library.
Announcements
The Intel sign-in experience has changed to support enhanced security controls. If you sign in, click here for more information.

VSL for Convolution

Paul_S_Intel2
Employee
227 Views

I'm getting started with using MKL VSL for convolutions. For learning, I first I want to conduct a 1D convolution. I'm confused with the usage example given here: https://software.intel.com/en-us/node/521925 because it seems the naming and terminology is different than on the other description links.

In the other reference material there is mention of xstride, ystride etc. Where are those in this example? Where do you set the parameter dim? What would be an example of the set up and call for convolution of, say x and y:

x[0]=1

x[1]=2

x[2]=3

x[3]=4

x[4]=5

y[0]=1

y[1]=2

y[2]=3

y[3]=4

y[4]=5

 

Thanks!

Paul Safier

paul.a.safier@intel.com

0 Kudos
2 Replies
Zhen_Z_Intel
Employee
227 Views

Hi Paul,

There's no entry point (main function) of this sample, you could not build it directly. If you would like to learn how to use this function and test, please find MKL samples' source code in your MKL installation path. And the main function which is used to initialize data and call scond sub routine and is saved in:
%MKLROOT%\examples_core_c\vslc\essl\sample_scond.c

And the code for MKL scond function is saved in:
%MKLROOT%\examples_core_c\vslc\essl\vsl_wrappers\sample_scond.c

Please following this example to test, Thank you.

Best regards,
Fiona

 

Paul_S_Intel2
Employee
227 Views

Thanks Fiona!

Reply