Function arm_svdf_state_s16_s8_input_ctx_get_buffer_size

Function Documentation

int32_t arm_svdf_state_s16_s8_input_ctx_get_buffer_size(const cmsis_nn_dims *input_dims, const cmsis_nn_dims *weights_feature_dims)

Get size of the input_ctx staging buffer required by arm_svdf_state_s16_s8(). Refer to arm_svdf_s8_input_ctx_get_buffer_size() for argument details, the -1-on-invalid contract and the degenerate-0 caveat.

Returns input_dims->n * weights_feature_dims->n * sizeof(int32_t) - the same figure as arm_svdf_s8_input_ctx_get_buffer_size() for the same shape. The accumulators are int32_t even though arm_svdf_state_s16_s8() carries an int16_t state tensor, so this buffer does not shrink with the state width.