Please note: We are aware of an issue affecting replies on the Arm Community forums, which may not be loading as expected.

We apologize for any inconvenience and appreciate your patience while we investigate and work to resolve the issue.

Thank you for your understanding.

  • State Not Answered
  • Locked Locked
  • Replies 2 replies
  • Subscribers 16 subscribers
  • Views 4694 views
  • Users 0 members are here
Options
Related
This discussion has been locked.
You can no longer post new replies to this discussion. If you have a question you can start a new discussion

Which CMSIS-DSP parts are used by CMSIS-NN

trembel

Which parts of CMSIS-DSP are used for CMSIS-NN? I'm asking because I want to disable as much options as possible of the CMSIS-DSP.

  • 0 Arm Employee Badge

    CMSIS-NN is a lib accelerating neural network kernels that can help TFLM and TVM accelerate inference while CMSIS-DSP is a lib for more mathematical calculations. ARM_MATH_MVEI and ARM_MATH_DSP flags are defined automatically (in arm_math_types.h) depending on the CPU for which you compile and based upon compiler #defines. But generally, both are defined since your core kernels can have a vector part using MVEI extensions and a scalar part using DSP extension. You can disable either using these flag options. 

  • 0 in reply to Sandeep Singh

    The functions supporting TensorFlow Lite framework is identified by the _s8 suffix and can be invoked from TFL micro. The functions are bit exact to TensorFlow Lite. Refer to the TensorFlow's documentation in [3] on how to run a TensorFlow Lite model using optimized CMSIS-NN kernels.