Functions
arm_cmsis_nn_status	arm_depthwise_nhwc_conv_f32 (const cmsis_nn_context ctx, const cmsis_nn_dw_conv_params_f32 dw_conv_params, const cmsis_nn_dims input_dims, const float32_t input, const cmsis_nn_dims filter_dims, const float32_t kernel, const cmsis_nn_dims bias_dims, const float32_t bias, const cmsis_nn_dims output_dims, float32_t output)
	Depthwise convolution, NHWC layout.

arm_cmsis_nn_status	arm_depthwise_conv_f32 (const cmsis_nn_context ctx, const cmsis_nn_dw_conv_params_f32 dw_conv_params, const cmsis_nn_dims input_dims, const float32_t input, const cmsis_nn_dims filter_dims, const float32_t kernel, const cmsis_nn_dims bias_dims, const float32_t bias, const cmsis_nn_dims output_dims, float32_t output, arm_nn_tensor_layout layout)
	Depthwise convolution, dispatch by layout.

arm_cmsis_nn_status	arm_depthwise_conv_wrapper_f32 (const cmsis_nn_context ctx, const cmsis_nn_dw_conv_params_f32 dw_conv_params, const cmsis_nn_dims input_dims, const float32_t input, const cmsis_nn_dims filter_dims, const float32_t kernel, const cmsis_nn_dims bias_dims, const float32_t bias, const cmsis_nn_dims output_dims, float32_t output)
	Depthwise convolution wrapper using the CMSIS-NN baseline path.

int32_t	arm_depthwise_conv_f32_get_buffer_size (const cmsis_nn_dw_conv_params_f32 dw_conv_params, const cmsis_nn_dims input_dims, const cmsis_nn_dims filter_dims, const cmsis_nn_dims output_dims, arm_nn_tensor_layout layout)
	Get the temporary buffer size required by depthwise convolution.

int32_t	arm_depthwise_conv_wrapper_f32_get_buffer_size (const cmsis_nn_dw_conv_params_f32 dw_conv_params, const cmsis_nn_dims input_dims, const cmsis_nn_dims filter_dims, const cmsis_nn_dims output_dims)
	Get the buffer size required by the depthwise convolution wrapper.

arm_cmsis_nn_status	arm_convolve_nhwc_f32 (const cmsis_nn_context ctx, const cmsis_nn_conv_params_f32 conv_params, const cmsis_nn_dims input_dims, const float32_t input_data, const cmsis_nn_dims filter_dims, const float32_t filter_data, const cmsis_nn_dims bias_dims, const float32_t bias_data, const cmsis_nn_dims output_dims, float32_t output_data)
	Convolution, NHWC layout.

arm_cmsis_nn_status	arm_convolve_f32 (const cmsis_nn_context ctx, const cmsis_nn_conv_params_f32 conv_params, const cmsis_nn_dims input_dims, const float32_t input_data, const cmsis_nn_dims filter_dims, const float32_t filter_data, const cmsis_nn_dims bias_dims, const float32_t bias_data, const cmsis_nn_dims output_dims, float32_t output_data, arm_nn_tensor_layout layout)
	Convolution, dispatch by layout.

arm_cmsis_nn_status	arm_convolve_wrapper_f32 (const cmsis_nn_context ctx, const cmsis_nn_conv_params_f32 conv_params, const cmsis_nn_dims input_dims, const float32_t input_data, const cmsis_nn_dims filter_dims, const float32_t filter_data, const cmsis_nn_dims bias_dims, const float32_t bias_data, const cmsis_nn_dims output_dims, float32_t output_data)
	Convolution wrapper using the CMSIS-NN baseline path.

arm_cmsis_nn_status	arm_convolve_1x1_nhwc_f32 (const cmsis_nn_context ctx, const cmsis_nn_conv_params_f32 conv_params, const cmsis_nn_dims input_dims, const float32_t input_data, const cmsis_nn_dims filter_dims, const float32_t filter_data, const cmsis_nn_dims bias_dims, const float32_t bias_data, const cmsis_nn_dims output_dims, float32_t output_data)
	1x1 convolution, NHWC layout.

arm_cmsis_nn_status	arm_convolve_1x1_f32 (const cmsis_nn_context ctx, const cmsis_nn_conv_params_f32 conv_params, const cmsis_nn_dims input_dims, const float32_t input_data, const cmsis_nn_dims filter_dims, const float32_t filter_data, const cmsis_nn_dims bias_dims, const float32_t bias_data, const cmsis_nn_dims output_dims, float32_t output_data, arm_nn_tensor_layout layout)
	1x1 convolution, dispatch by layout.

arm_cmsis_nn_status	arm_convolve_1_x_n_nhwc_f32 (const cmsis_nn_context ctx, const cmsis_nn_conv_params_f32 conv_params, const cmsis_nn_dims input_dims, const float32_t input_data, const cmsis_nn_dims filter_dims, const float32_t filter_data, const cmsis_nn_dims bias_dims, const float32_t bias_data, const cmsis_nn_dims output_dims, float32_t output_data)
	1xN convolution, NHWC layout.

arm_cmsis_nn_status	arm_convolve_1_x_n_f32 (const cmsis_nn_context ctx, const cmsis_nn_conv_params_f32 conv_params, const cmsis_nn_dims input_dims, const float32_t input_data, const cmsis_nn_dims filter_dims, const float32_t filter_data, const cmsis_nn_dims bias_dims, const float32_t bias_data, const cmsis_nn_dims output_dims, float32_t output_data, arm_nn_tensor_layout layout)
	1xN convolution, dispatch by layout.

int32_t	arm_convolve_f32_get_buffer_size (const cmsis_nn_conv_params_f32 conv_params, const cmsis_nn_dims input_dims, const cmsis_nn_dims filter_dims, const cmsis_nn_dims output_dims, arm_nn_tensor_layout layout)
	Get the temporary buffer size required by convolution.

int32_t	arm_convolve_wrapper_f32_get_buffer_size (const cmsis_nn_conv_params_f32 conv_params, const cmsis_nn_dims input_dims, const cmsis_nn_dims filter_dims, const cmsis_nn_dims output_dims)
	Get the buffer size required by the convolution wrapper.

int32_t	arm_convolve_1x1_f32_get_buffer_size (const cmsis_nn_conv_params_f32 conv_params, const cmsis_nn_dims input_dims, const cmsis_nn_dims filter_dims, const cmsis_nn_dims output_dims, arm_nn_tensor_layout layout)
	Get the buffer size required by 1x1 convolution.

int32_t	arm_convolve_1_x_n_f32_get_buffer_size (const cmsis_nn_conv_params_f32 conv_params, const cmsis_nn_dims input_dims, const cmsis_nn_dims filter_dims, const cmsis_nn_dims output_dims, arm_nn_tensor_layout layout)
	Get the buffer size required by 1xN convolution.

arm_cmsis_nn_status	arm_max_pool_f32 (const cmsis_nn_context ctx, const cmsis_nn_pool_params_f32 pool_params, const cmsis_nn_dims input_dims, const float32_t src, const cmsis_nn_dims filter_dims, const cmsis_nn_dims output_dims, float32_t *dst)
	Max pooling.

arm_cmsis_nn_status	arm_avg_pool_f32 (const cmsis_nn_context ctx, const cmsis_nn_pool_params_f32 pool_params, const cmsis_nn_dims input_dims, const float32_t src, const cmsis_nn_dims filter_dims, const cmsis_nn_dims output_dims, float32_t *dst)
	Average pooling.

arm_cmsis_nn_status	arm_nn_activation_f32 (const float32_t input, float32_t output, int32_t size, arm_nn_activation_type_flt type, float32_t act_param)
	Elementwise activation.

arm_cmsis_nn_status	arm_elementwise_add_f32 (const float32_t input_1_vect, const float32_t input_2_vect, float32_t *output, float32_t out_activation_min, float32_t out_activation_max, int32_t block_size)
	Elementwise add with optional output clamp.

arm_cmsis_nn_status	arm_elementwise_mul_f32 (const float32_t input_1_vect, const float32_t input_2_vect, float32_t *output, float32_t out_activation_min, float32_t out_activation_max, int32_t block_size)
	Elementwise multiply with optional output clamp.

arm_cmsis_nn_status	arm_minimum_f32 (const cmsis_nn_context ctx, const float32_t input_1_data, const cmsis_nn_dims input_1_dims, const float32_t input_2_data, const cmsis_nn_dims input_2_dims, float32_t output_data, const cmsis_nn_dims *output_dims)
	Elementwise minimum.

arm_cmsis_nn_status	arm_maximum_f32 (const cmsis_nn_context ctx, const float32_t input_1_data, const cmsis_nn_dims input_1_dims, const float32_t input_2_data, const cmsis_nn_dims input_2_dims, float32_t output_data, const cmsis_nn_dims *output_dims)
	Elementwise maximum.

arm_cmsis_nn_status	arm_fully_connected_nhwc_f32 (const cmsis_nn_context ctx, const cmsis_nn_fc_params_f32 fc_params, const cmsis_nn_dims input_dims, const float32_t input, const cmsis_nn_dims filter_dims, const float32_t kernel, const cmsis_nn_dims bias_dims, const float32_t bias, const cmsis_nn_dims output_dims, float32_t output)
	Fully connected layer, NHWC layout.

arm_cmsis_nn_status	arm_fully_connected_f32 (const cmsis_nn_context ctx, const cmsis_nn_fc_params_f32 fc_params, const cmsis_nn_dims input_dims, const float32_t input, const cmsis_nn_dims filter_dims, const float32_t kernel, const cmsis_nn_dims bias_dims, const float32_t bias, const cmsis_nn_dims output_dims, float32_t output, arm_nn_tensor_layout layout)
	Fully connected layer, dispatch by layout.

int32_t	arm_fully_connected_f32_get_buffer_size (const cmsis_nn_fc_params_f32 fc_params, const cmsis_nn_dims input_dims, const cmsis_nn_dims filter_dims, const cmsis_nn_dims output_dims, arm_nn_tensor_layout layout)
	Get the temporary buffer size required by the fully connected layer.

arm_cmsis_nn_status	arm_transpose_f32 (const cmsis_nn_context ctx, const cmsis_nn_transpose_params_f32 params, const cmsis_nn_dims input_dims, const float32_t input, const cmsis_nn_dims output_dims, float32_t output)
	Transpose a floating-point tensor.

void	arm_concatenation_f32_x (const float32_t input, int32_t input_x, int32_t input_y, int32_t input_z, int32_t input_w, float32_t output, int32_t output_x, uint32_t offset_x)
	Concatenate tensors along the X axis.

void	arm_concatenation_f32_y (const float32_t input, int32_t input_x, int32_t input_y, int32_t input_z, int32_t input_w, float32_t output, int32_t output_y, uint32_t offset_y)
	Concatenate tensors along the Y axis.

void	arm_concatenation_f32_z (const float32_t input, int32_t input_x, int32_t input_y, int32_t input_z, int32_t input_w, float32_t output, int32_t output_z, uint32_t offset_z)
	Concatenate tensors along the Z axis.

void	arm_concatenation_f32_w (const float32_t input, int32_t input_x, int32_t input_y, int32_t input_z, int32_t input_w, float32_t output, uint32_t offset_w)
	Concatenate tensors along the W axis.

arm_cmsis_nn_status	arm_pad_f32 (const float32_t input, float32_t output, float32_t pad_value, const cmsis_nn_dims input_size, const cmsis_nn_dims pre_pad, const cmsis_nn_dims *post_pad)
	Pad a tensor with a constant value.

arm_cmsis_nn_status	arm_batch_norm_f32 (const float32_t input, float32_t output, const float32_t scale, const float32_t bias, const cmsis_nn_dims *input_dims, arm_nn_tensor_layout layout)
	Apply batch normalization.

void	arm_reshape_f32 (const float32_t input, float32_t output, uint32_t total_size)
	Reshape by copying data without changing element order.

arm_cmsis_nn_status	arm_batch_matmul_f32 (const cmsis_nn_context ctx, const cmsis_nn_bmm_params_f32 bmm_params, const cmsis_nn_dims input_lhs_dims, const float32_t input_lhs, const cmsis_nn_dims input_rhs_dims, const float32_t input_rhs, const cmsis_nn_dims output_dims, float32_t output)
	Batched matrix multiplication.

int32_t	arm_batch_matmul_f32_get_buffer_size (const cmsis_nn_bmm_params_f32 bmm_params, const cmsis_nn_dims input_lhs_dims, const cmsis_nn_dims input_rhs_dims, const cmsis_nn_dims output_dims)
	Get the temporary buffer size required by batched matrix multiplication.

arm_cmsis_nn_status	arm_transpose_conv_wrapper_f32 (const cmsis_nn_context ctx, const cmsis_nn_context output_ctx, const cmsis_nn_transpose_conv_params_f32 transpose_conv_params, const cmsis_nn_dims input_dims, const float32_t input_data, const cmsis_nn_dims filter_dims, const float32_t filter_data, const cmsis_nn_dims bias_dims, const float32_t bias_data, const cmsis_nn_dims output_dims, float32_t *output_data, arm_nn_tensor_layout layout)
	Transpose convolution wrapper using the CMSIS-NN baseline path.

arm_cmsis_nn_status	arm_transpose_conv_nhwc_f32 (const cmsis_nn_context ctx, const cmsis_nn_context output_ctx, const cmsis_nn_transpose_conv_params_f32 transpose_conv_params, const cmsis_nn_dims input_dims, const float32_t input_data, const cmsis_nn_dims filter_dims, const float32_t filter_data, const cmsis_nn_dims bias_dims, const float32_t bias_data, const cmsis_nn_dims output_dims, float32_t *output_data)
	Transpose convolution, NHWC layout.

arm_cmsis_nn_status	arm_transpose_conv_f32 (const cmsis_nn_context ctx, const cmsis_nn_context output_ctx, const cmsis_nn_transpose_conv_params_f32 transpose_conv_params, const cmsis_nn_dims input_dims, const float32_t input_data, const cmsis_nn_dims filter_dims, const float32_t filter_data, const cmsis_nn_dims bias_dims, const float32_t bias_data, const cmsis_nn_dims output_dims, float32_t *output_data, arm_nn_tensor_layout layout)
	Transpose convolution, dispatch by layout.

int32_t	arm_transpose_conv_f32_get_buffer_size (const cmsis_nn_transpose_conv_params_f32 transpose_conv_params, const cmsis_nn_dims input_dims, const cmsis_nn_dims filter_dims, const cmsis_nn_dims out_dims)
	Get the temporary buffer size required by transpose convolution.

int32_t	arm_transpose_conv_f32_get_reverse_conv_buffer_size (const cmsis_nn_transpose_conv_params_f32 transpose_conv_params, const cmsis_nn_dims input_dims, const cmsis_nn_dims *filter_dims)
	Get the reverse-convolution workspace size used by transpose convolution helpers.

arm_cmsis_nn_status	arm_svdf_f32 (const cmsis_nn_context ctx, const cmsis_nn_context input_ctx, const cmsis_nn_context output_ctx, const cmsis_nn_svdf_params_f32 svdf_params, const cmsis_nn_dims input_dims, const float32_t input_data, const cmsis_nn_dims state_dims, float32_t state_data, const cmsis_nn_dims weights_feature_dims, const float32_t weights_feature_data, const cmsis_nn_dims weights_time_dims, const float32_t weights_time_data, const cmsis_nn_dims bias_dims, const float32_t bias_data, const cmsis_nn_dims output_dims, float32_t output_data)
	Stateful singular value decomposition filter.

arm_cmsis_nn_status	arm_lstm_unidirectional_f32 (const float32_t input, float32_t output, const cmsis_nn_lstm_params_f32 params, cmsis_nn_lstm_context_f32 buffers)
	Unidirectional LSTM inference.

arm_cmsis_nn_status	arm_softmax_f32 (const float32_t input, int32_t num_rows, int32_t row_size, float32_t output)
	Softmax using the float-native API signature.

arm_cmsis_nn_status	arm_depthwise_nhwc_conv_f16 (const cmsis_nn_context ctx, const cmsis_nn_dw_conv_params_f16 dw_conv_params, const cmsis_nn_dims input_dims, const float16_t input, const cmsis_nn_dims filter_dims, const float16_t kernel, const cmsis_nn_dims bias_dims, const float16_t bias, const cmsis_nn_dims output_dims, float16_t output)
	Depthwise convolution, NHWC layout.

arm_cmsis_nn_status	arm_depthwise_conv_f16 (const cmsis_nn_context ctx, const cmsis_nn_dw_conv_params_f16 dw_conv_params, const cmsis_nn_dims input_dims, const float16_t input, const cmsis_nn_dims filter_dims, const float16_t kernel, const cmsis_nn_dims bias_dims, const float16_t bias, const cmsis_nn_dims output_dims, float16_t output, arm_nn_tensor_layout layout)
	Depthwise convolution, dispatch by layout.

arm_cmsis_nn_status	arm_depthwise_conv_wrapper_f16 (const cmsis_nn_context ctx, const cmsis_nn_dw_conv_params_f16 dw_conv_params, const cmsis_nn_dims input_dims, const float16_t input, const cmsis_nn_dims filter_dims, const float16_t kernel, const cmsis_nn_dims bias_dims, const float16_t bias, const cmsis_nn_dims output_dims, float16_t output)
	Depthwise convolution wrapper using the CMSIS-NN baseline path.

int32_t	arm_depthwise_conv_f16_get_buffer_size (const cmsis_nn_dw_conv_params_f16 dw_conv_params, const cmsis_nn_dims input_dims, const cmsis_nn_dims filter_dims, const cmsis_nn_dims output_dims, arm_nn_tensor_layout layout)
	Get the temporary buffer size required by depthwise convolution.

int32_t	arm_depthwise_conv_wrapper_f16_get_buffer_size (const cmsis_nn_dw_conv_params_f16 dw_conv_params, const cmsis_nn_dims input_dims, const cmsis_nn_dims filter_dims, const cmsis_nn_dims output_dims)
	Get the buffer size required by the depthwise convolution wrapper.

arm_cmsis_nn_status	arm_convolve_nhwc_f16 (const cmsis_nn_context ctx, const cmsis_nn_conv_params_f16 conv_params, const cmsis_nn_dims input_dims, const float16_t input_data, const cmsis_nn_dims filter_dims, const float16_t filter_data, const cmsis_nn_dims bias_dims, const float16_t bias_data, const cmsis_nn_dims output_dims, float16_t output_data)
	Convolution, NHWC layout.

arm_cmsis_nn_status	arm_convolve_f16 (const cmsis_nn_context ctx, const cmsis_nn_conv_params_f16 conv_params, const cmsis_nn_dims input_dims, const float16_t input_data, const cmsis_nn_dims filter_dims, const float16_t filter_data, const cmsis_nn_dims bias_dims, const float16_t bias_data, const cmsis_nn_dims output_dims, float16_t output_data, arm_nn_tensor_layout layout)
	Convolution, dispatch by layout.

arm_cmsis_nn_status	arm_convolve_wrapper_f16 (const cmsis_nn_context ctx, const cmsis_nn_conv_params_f16 conv_params, const cmsis_nn_dims input_dims, const float16_t input_data, const cmsis_nn_dims filter_dims, const float16_t filter_data, const cmsis_nn_dims bias_dims, const float16_t bias_data, const cmsis_nn_dims output_dims, float16_t output_data)
	Convolution wrapper using the CMSIS-NN baseline path.

arm_cmsis_nn_status	arm_convolve_1x1_nhwc_f16 (const cmsis_nn_context ctx, const cmsis_nn_conv_params_f16 conv_params, const cmsis_nn_dims input_dims, const float16_t input_data, const cmsis_nn_dims filter_dims, const float16_t filter_data, const cmsis_nn_dims bias_dims, const float16_t bias_data, const cmsis_nn_dims output_dims, float16_t output_data)
	1x1 convolution, NHWC layout.

arm_cmsis_nn_status	arm_convolve_1x1_f16 (const cmsis_nn_context ctx, const cmsis_nn_conv_params_f16 conv_params, const cmsis_nn_dims input_dims, const float16_t input_data, const cmsis_nn_dims filter_dims, const float16_t filter_data, const cmsis_nn_dims bias_dims, const float16_t bias_data, const cmsis_nn_dims output_dims, float16_t output_data, arm_nn_tensor_layout layout)
	1x1 convolution, dispatch by layout.

arm_cmsis_nn_status	arm_convolve_1_x_n_nhwc_f16 (const cmsis_nn_context ctx, const cmsis_nn_conv_params_f16 conv_params, const cmsis_nn_dims input_dims, const float16_t input_data, const cmsis_nn_dims filter_dims, const float16_t filter_data, const cmsis_nn_dims bias_dims, const float16_t bias_data, const cmsis_nn_dims output_dims, float16_t output_data)
	1xN convolution, NHWC layout.

arm_cmsis_nn_status	arm_convolve_1_x_n_f16 (const cmsis_nn_context ctx, const cmsis_nn_conv_params_f16 conv_params, const cmsis_nn_dims input_dims, const float16_t input_data, const cmsis_nn_dims filter_dims, const float16_t filter_data, const cmsis_nn_dims bias_dims, const float16_t bias_data, const cmsis_nn_dims output_dims, float16_t output_data, arm_nn_tensor_layout layout)
	1xN convolution, dispatch by layout.

int32_t	arm_convolve_f16_get_buffer_size (const cmsis_nn_conv_params_f16 conv_params, const cmsis_nn_dims input_dims, const cmsis_nn_dims filter_dims, const cmsis_nn_dims output_dims, arm_nn_tensor_layout layout)
	Get the temporary buffer size required by convolution.

int32_t	arm_convolve_wrapper_f16_get_buffer_size (const cmsis_nn_conv_params_f16 conv_params, const cmsis_nn_dims input_dims, const cmsis_nn_dims filter_dims, const cmsis_nn_dims output_dims)
	Get the buffer size required by the convolution wrapper.

int32_t	arm_convolve_1x1_f16_get_buffer_size (const cmsis_nn_conv_params_f16 conv_params, const cmsis_nn_dims input_dims, const cmsis_nn_dims filter_dims, const cmsis_nn_dims output_dims, arm_nn_tensor_layout layout)
	Get the buffer size required by 1x1 convolution.

int32_t	arm_convolve_1_x_n_f16_get_buffer_size (const cmsis_nn_conv_params_f16 conv_params, const cmsis_nn_dims input_dims, const cmsis_nn_dims filter_dims, const cmsis_nn_dims output_dims, arm_nn_tensor_layout layout)
	Get the buffer size required by 1xN convolution.

arm_cmsis_nn_status	arm_max_pool_f16 (const cmsis_nn_context ctx, const cmsis_nn_pool_params_f16 pool_params, const cmsis_nn_dims input_dims, const float16_t src, const cmsis_nn_dims filter_dims, const cmsis_nn_dims output_dims, float16_t *dst)
	Max pooling.

arm_cmsis_nn_status	arm_avg_pool_f16 (const cmsis_nn_context ctx, const cmsis_nn_pool_params_f16 pool_params, const cmsis_nn_dims input_dims, const float16_t src, const cmsis_nn_dims filter_dims, const cmsis_nn_dims output_dims, float16_t *dst)
	Average pooling.

arm_cmsis_nn_status	arm_nn_activation_f16 (const float16_t input, float16_t output, int32_t size, arm_nn_activation_type_flt type, float16_t act_param)
	Elementwise activation.

arm_cmsis_nn_status	arm_elementwise_add_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)
	Elementwise add with optional output clamp.

arm_cmsis_nn_status	arm_elementwise_mul_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)
	Elementwise multiply with optional output clamp.

arm_cmsis_nn_status	arm_minimum_f16 (const cmsis_nn_context ctx, const float16_t input_1_data, const cmsis_nn_dims input_1_dims, const float16_t input_2_data, const cmsis_nn_dims input_2_dims, float16_t output_data, const cmsis_nn_dims *output_dims)
	Elementwise minimum.

arm_cmsis_nn_status	arm_maximum_f16 (const cmsis_nn_context ctx, const float16_t input_1_data, const cmsis_nn_dims input_1_dims, const float16_t input_2_data, const cmsis_nn_dims input_2_dims, float16_t output_data, const cmsis_nn_dims *output_dims)
	Elementwise maximum.

arm_cmsis_nn_status	arm_fully_connected_nhwc_f16 (const cmsis_nn_context ctx, const cmsis_nn_fc_params_f16 fc_params, const cmsis_nn_dims input_dims, const float16_t input, const cmsis_nn_dims filter_dims, const float16_t kernel, const cmsis_nn_dims bias_dims, const float16_t bias, const cmsis_nn_dims output_dims, float16_t output)
	Fully connected layer, NHWC layout.

arm_cmsis_nn_status	arm_fully_connected_f16 (const cmsis_nn_context ctx, const cmsis_nn_fc_params_f16 fc_params, const cmsis_nn_dims input_dims, const float16_t input, const cmsis_nn_dims filter_dims, const float16_t kernel, const cmsis_nn_dims bias_dims, const float16_t bias, const cmsis_nn_dims output_dims, float16_t output, arm_nn_tensor_layout layout)
	Fully connected layer, dispatch by layout.

int32_t	arm_fully_connected_f16_get_buffer_size (const cmsis_nn_fc_params_f16 fc_params, const cmsis_nn_dims input_dims, const cmsis_nn_dims filter_dims, const cmsis_nn_dims output_dims, arm_nn_tensor_layout layout)
	Get the temporary buffer size required by the fully connected layer.

arm_cmsis_nn_status	arm_transpose_f16 (const cmsis_nn_context ctx, const cmsis_nn_transpose_params_f16 params, const cmsis_nn_dims input_dims, const float16_t input, const cmsis_nn_dims output_dims, float16_t output)
	Transpose a floating-point tensor.

void	arm_concatenation_f16_x (const float16_t input, int32_t input_x, int32_t input_y, int32_t input_z, int32_t input_w, float16_t output, int32_t output_x, uint32_t offset_x)
	arm concatenation f16 x

void	arm_concatenation_f16_y (const float16_t input, int32_t input_x, int32_t input_y, int32_t input_z, int32_t input_w, float16_t output, int32_t output_y, uint32_t offset_y)
	arm concatenation f16 y

void	arm_concatenation_f16_z (const float16_t input, int32_t input_x, int32_t input_y, int32_t input_z, int32_t input_w, float16_t output, int32_t output_z, uint32_t offset_z)
	arm concatenation f16 z

void	arm_concatenation_f16_w (const float16_t input, int32_t input_x, int32_t input_y, int32_t input_z, int32_t input_w, float16_t output, uint32_t offset_w)
	arm concatenation f16 w

arm_cmsis_nn_status	arm_pad_f16 (const float16_t input, float16_t output, float16_t pad_value, const cmsis_nn_dims input_size, const cmsis_nn_dims pre_pad, const cmsis_nn_dims *post_pad)
	Pad a tensor with a constant value.

arm_cmsis_nn_status	arm_batch_norm_f16 (const float16_t input, float16_t output, const float16_t scale, const float16_t bias, const cmsis_nn_dims *input_dims, arm_nn_tensor_layout layout)
	Apply batch normalization.

void	arm_reshape_f16 (const float16_t input, float16_t output, uint32_t total_size)
	Reshape by copying data without changing element order.

arm_cmsis_nn_status	arm_batch_matmul_f16 (const cmsis_nn_context ctx, const cmsis_nn_bmm_params_f16 bmm_params, const cmsis_nn_dims input_lhs_dims, const float16_t input_lhs, const cmsis_nn_dims input_rhs_dims, const float16_t input_rhs, const cmsis_nn_dims output_dims, float16_t output)
	Batched matrix multiplication.

int32_t	arm_batch_matmul_f16_get_buffer_size (const cmsis_nn_bmm_params_f16 bmm_params, const cmsis_nn_dims input_lhs_dims, const cmsis_nn_dims input_rhs_dims, const cmsis_nn_dims output_dims)
	Get the temporary buffer size required by batched matrix multiplication.

arm_cmsis_nn_status	arm_transpose_conv_wrapper_f16 (const cmsis_nn_context ctx, const cmsis_nn_context output_ctx, const cmsis_nn_transpose_conv_params_f16 transpose_conv_params, const cmsis_nn_dims input_dims, const float16_t input_data, const cmsis_nn_dims filter_dims, const float16_t filter_data, const cmsis_nn_dims bias_dims, const float16_t bias_data, const cmsis_nn_dims output_dims, float16_t *output_data, arm_nn_tensor_layout layout)
	Transpose convolution wrapper using the CMSIS-NN baseline path.

arm_cmsis_nn_status	arm_transpose_conv_nhwc_f16 (const cmsis_nn_context ctx, const cmsis_nn_context output_ctx, const cmsis_nn_transpose_conv_params_f16 transpose_conv_params, const cmsis_nn_dims input_dims, const float16_t input_data, const cmsis_nn_dims filter_dims, const float16_t filter_data, const cmsis_nn_dims bias_dims, const float16_t bias_data, const cmsis_nn_dims output_dims, float16_t *output_data)
	Transpose convolution, NHWC layout.

arm_cmsis_nn_status	arm_transpose_conv_f16 (const cmsis_nn_context ctx, const cmsis_nn_context output_ctx, const cmsis_nn_transpose_conv_params_f16 transpose_conv_params, const cmsis_nn_dims input_dims, const float16_t input_data, const cmsis_nn_dims filter_dims, const float16_t filter_data, const cmsis_nn_dims bias_dims, const float16_t bias_data, const cmsis_nn_dims output_dims, float16_t *output_data, arm_nn_tensor_layout layout)
	Transpose convolution, dispatch by layout.

int32_t	arm_transpose_conv_f16_get_buffer_size (const cmsis_nn_transpose_conv_params_f16 transpose_conv_params, const cmsis_nn_dims input_dims, const cmsis_nn_dims filter_dims, const cmsis_nn_dims out_dims)
	Get the temporary buffer size required by transpose convolution.

int32_t	arm_transpose_conv_f16_get_reverse_conv_buffer_size (const cmsis_nn_transpose_conv_params_f16 transpose_conv_params, const cmsis_nn_dims input_dims, const cmsis_nn_dims *filter_dims)
	Get the reverse-convolution workspace size used by transpose convolution helpers.

arm_cmsis_nn_status	arm_svdf_f16 (const cmsis_nn_context ctx, const cmsis_nn_context input_ctx, const cmsis_nn_context output_ctx, const cmsis_nn_svdf_params_f16 svdf_params, const cmsis_nn_dims input_dims, const float16_t input_data, const cmsis_nn_dims state_dims, float16_t state_data, const cmsis_nn_dims weights_feature_dims, const float16_t weights_feature_data, const cmsis_nn_dims weights_time_dims, const float16_t weights_time_data, const cmsis_nn_dims bias_dims, const float16_t bias_data, const cmsis_nn_dims output_dims, float16_t output_data)
	Stateful singular value decomposition filter.

arm_cmsis_nn_status	arm_lstm_unidirectional_f16 (const float16_t input, float16_t output, const cmsis_nn_lstm_params_f16 params, cmsis_nn_lstm_context_f16 buffers)
	Unidirectional LSTM inference.

arm_cmsis_nn_status	arm_softmax_f16 (const float16_t input, int32_t num_rows, int32_t row_size, float16_t output)
	Softmax using the float-native API signature.

Functions