Documentation

Ne10 Conditions for DSP Blocks to Support ARM Cortex-A Processors

DSP blocks you can use with the Support Package for ARM® Cortex®-A processors require specific conditions to allow code replacement with the Ne10 library. You use this code replacement when generating C code from a model or from MATLAB® code. The Ne10 library supports these DSP blocks only when you set specific properties, as indicated in the following table:

DSP BlockInput RequirementsParameter RequirementsEquivalent Ne10 Functions
Discrete FIR Filter
  • Real values (output must also be real values).

  • Single channel (one column).

  • single data type.

  • Filter structure: Direct Form or Lattice MA.

  • Input processing: Columns as channels (frame based).

  • Initial states: 0.

  • Coefficient source: Dialog parameters or Input port.

'Direct Form' structure

  • ne10_fir_init_float

  • ne10_fir_float_neon

'Lattice MA' structure

  • ne10_fir_lattice_init_float

  • ne10_fir_lattice_float_neon

FIR Decimation
  • Real values (output must also be real values).

  • Single channel (one column).

  • single data type.

  • Filter structure: Direct Form.

  • Input processing: Columns as channels (frame based).

  • Rate options: Enforce single-rate processing.

  • Coefficient source: Dialog parameters.

  • ne10_fir_decimate_init_float

  • ne10_fir_decimate_float_neon

FIR Interpolation
  • Real values (output must also be real values).

  • Single channel (one column).

  • single data type.

  • Input processing: Columns as channels (frame based).

  • Rate options: Enforce single-rate processing.

  • Coefficient source: Dialog parameters.

  • ne10_fir_interpolate_init_float

  • ne10_fir_interpolate_float_neon

FFT
  • Real or complex values.

  • Single channel.

  • single data type.

  • Input length must equal FFT length.

  • FFT implementation: Radix-2.

  • Scale result by FFT length: Off (check box is cleared).

  • Inherit FFT length from input dimensions: Check box selected (inherit from input) or check box is cleared (specified in FFT length property).

  • FFT length: Power of 2. Minimum length is 4 when input is complex. Minimum length is 8 when input is real.

  • ne10_fft_alloc_c2c_float32

  • ne10_fft_c2c_1d_float32_neon

  • ne10_fft_alloc_r2c_float32

  • ne10_fft_r2c_1d_float32_neon

Wrapper functions, each with an mw_ prefix, are provided to bridge the library interface.

IFFT
  • Complex values. Output can be complex or real values.

  • Single channel.

  • single data type.

  • Input length must equal FFT length.

  • FFT implementation: Radix-2.

  • Divide output by FFT length: On (check box is selected).

  • Inherit FFT length from input dimensions: Check box selected (inherit from input) or check box is cleared (specified in FFT length property).

  • FFT length: Power of 2. Minimum length is 4 when input is complex. Minimum length is 8 when input is conjugate symmetric.

  • ne10_fft_alloc_c2c_float32

  • ne10_fft_c2c_1d_float32_neon

  • ne10_fft_alloc_r2c_float32

  • ne10_fft_c2r_1d_float32_neon

Wrapper functions, each with an mw_ prefix, are provided to bridge the library interface.