Function arm_elementwise_sub_f16

• Defined in File arm_nnfunctions_flt.h

Function Documentation

arm_cmsis_nn_status arm_elementwise_sub_f16(const float16_t *input_1_vect, const float16_t *input_2_vect, float16_t *output, float16_t out_activation_min, float16_t out_activation_max, int32_t block_size)

float16 elementwise subtract of two vectors with fused clamp.

Parameters:

• input_1_vect – [in] pointer to input vector 1

• input_2_vect – [in] pointer to input vector 2

• output – [out] pointer to output vector

• out_activation_min – [in] minimum value to clamp the output to

• out_activation_max – [in] maximum value to clamp the output to

• block_size – [in] number of samples

Returns:

ARM_CMSIS_NN_SUCCESS on success, or ARM_CMSIS_NN_ARG_ERROR on invalid arguments.