This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

IWR6843AOP: Matrix Library for DSP C674x

Part Number: IWR6843AOP
Other Parts Discussed in Thread: IWR6843, MATHLIB

Hello, I am working on a custom application for the DSP on the IWR6843 AOP that requires doing a lot of matrix operations. I am looking through "dsplib_c674x_3_4_0_0" and am finding it incomplete in terms of the full suite of matrix operations. I specifically need:

matrix multiply (available)

matrix inverse (not available)

matrix add (not available)

matrix transpose (available)

Am I looking in the wrong location, are these operations available and are named something else? I would not like to port the cmsis matrix library since a DSP should have these operations available to the user.

  • Hello, 

    I'm looking into this and will get back to you shortly. 

    Best Regards,

    Josh

  • Do you have any update on this? A week is a long time to "get back to you shortly".

  • Hello, 

    My apologies for the delay here. The C674x DSPLIB library does not have these operations. I am checking if this is something we have internally which is not provided in this library. Please give me another 24 hrs to get back to you with more information. Thank you for your patience.

    Best Regards,

    Josh 

  • Hello, 

    Thank you for your patience on this matter. This library is no longer being actively developed but I have reached out to the team who was previously responsible for developing and supporting this library to check if matrix add and matrix inverse operations are available in their older repositories. Please give until the end of the week for a response here. 

    Thank you, 

    Josh

  • Hi, 

    I'm sorry again for the delay here. We do not have anything officially that TI has developed for this DSP core. It appears that matrix addition is a just a single loop and the compiler will do a good job of optimizing it even the code is written in standard C or intrinsic.

     However, In addition to DSPLIB, we have some functions in IMGLIB and MATHLIB that can be used. But I'm not sure if these libraries have the specific matrix operations you are looking for.

    Best Regards,

    Josh