porting ipp 5.1 to oneAPI for small vector and matrix manipulation

[jbengt]

Hi, I am attempting to port an application that uses matrix methods in ipp 5.1 such as ippmInvert_m_32f to the new oneAPI math methods.  Can anyone suggest the best approach to porting small matrix operations used for 2d rendering to the oneAPI methods?

Thank you

[ShanmukhS_Intel]

Hi,

Thank you for posting on Intel communities.

Please find the below link regarding porting of the small matrix operations. The mentioned function "ippmInvert_m_32f" has been deprecated and equivalent MKL functions were DGETRF/DGETRI for ippmInvert_m_64f and SGETRF/SGETRI for ippmInvert_m_32f.

More information regarding several MKL functions which are equivalent to ippMX functions were available in the below link.

https://www.intel.com/content/www/us/en/developer/articles/technical/the-alternatives-for-intel-ipp-legacy-small-matrices-domain.html

In addition, Please refer to the below link for details regarding the usage and porting of legacy applications to oneAPI methods.

Intel® IPP Legacy Libraries need to be used with Intel IPP 9.0 and the later versions. You could refer to Download and installation section for any installation-related information under the same path.

https://www.intel.com/content/www/us/en/developer/articles/tool/intel-ipp-legacy-libraries.html

Best Regards,

Shanmukh.SS

[ShanmukhS_Intel]

Hi,

A gentle reminder:

As we haven't heard back from you for a while, could you please let us know if there is any update regarding the issue?

Regards,

Shanmukh.SS

[ShanmukhS_Intel]

Hi,

We assume that your issue is resolved. If you need any additional information, please post a new question as this thread will no longer be monitored by Intel.

Best Regards,

Shanmukh.SS