nrf_axon_dma_2d()

nrf_axon_result_e nrf_axon_dma_2d	(	const int8_t *	input_ptr,
		int8_t *	out_ptr,
		uint16_t	height,
		uint16_t	width,
		nrf_axon_syncmode_blocking_e	block_mode,
		bool	keep_reservation )

#include <include/drivers/axon/nrf_axon_dsp_intrinsics.h>

"DMA" => "Direct Memory Access" Transfers data from one address to another. The regions must not overlap. For the best performance, use "2d" mode by setting height > 1. height height should also be <= width, but this is not required. When in 2d mode (ie, height > 1), width must be a multiple of 4.

Parameters

input_ptr	pointer to the input to move data from.
out_ptr	pointer to the output, where data will be moved to. Must be 32bit aligned.
height	height of the input shape (in elements). maximum 512, input_height * decimation_width <= 512 input_height >= filter_height.
width	width of the input shape. If not a multiple of 4 padding bytes will be placeced at the end of each output row.
block_mode	recommended to be set to NRF_AXON_SYNC_MODE_BLOCKING_POLLING.
keep_reservation	set to true if there are subsequent axon operations to execute immediately on completion. true prevents axon from be taken by another user and/or being powered off. Set to false if axon will not be used immediately after to free axon for other users and/or power down if idle.

Returns

kAxonResultSuccess on success or a negative error code (see nrf_axon_result_e)