Function arm_batch_matmul_f16_get_buffer_size¶

Defined in File arm_nnfunctions_flt.h

Function Documentation¶

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.

Parameters:

bmm_params – [in] Batch matmul parameters.
input_lhs_dims – [in] Left-hand-side input tensor dimensions.
input_rhs_dims – [in] Right-hand-side input tensor dimensions.
output_dims – [in] Output tensor dimensions.

Returns:

Required buffer size in bytes, or 0 when no scratch buffer is needed.