CMSIS-NN
Version 3.0.0
CMSIS NN Software Library
|
Functions | |
q7_t * | arm_nn_mat_mult_kernel_s8_s16_reordered (const q7_t *input_a, const q15_t *input_b, const uint16_t output_ch, const int32_t *out_shift, const int32_t *out_mult, const int32_t out_offset, const int16_t activation_min, const int16_t activation_max, const uint16_t num_col_a, const int32_t *const output_bias, q7_t *out_0) |
Matrix-multiplication of re-ordered input B with A. More... | |
q7_t* arm_nn_mat_mult_kernel_s8_s16_reordered | ( | const q7_t * | input_a, |
const q15_t * | input_b, | ||
const uint16_t | output_ch, | ||
const int32_t * | out_shift, | ||
const int32_t * | out_mult, | ||
const int32_t | out_offset, | ||
const int16_t | activation_min, | ||
const int16_t | activation_max, | ||
const uint16_t | num_col_a, | ||
const int32_t *const | output_bias, | ||
q7_t * | out_0 | ||
) |
For arguments, refer arm_nn_mat_mult_kernel_s8_s16. The re-ordering is a consequence of sign extension done by the SXTB16 command on input_b. The outputs are clamped in the range provided by activation min and max.
References arm_nn_read_q15x2_ia(), arm_nn_requantize(), MAX, and MIN.