Abstract: A convolution acceleration and computing processing method includes: reading data to be processed of a preset size in a task to be processed from an off-chip memory of an accelerator sequentially through a FIFO port, and storing the data to be processed into at least one input buffer of a first buffer in an on-chip memory of the accelerator; responsive to data to be processed being stored into an input buffer, reading input window data to be processed from the at least one input buffer sequentially, performing convolution on the input window data to be processed by using the convolution kernel data to obtain output window data and storing the output window data in the third buffer; and storing the output window data in the third buffer into the off-chip memory sequentially through the FIFO port.

Abstract: A method for producing a porous metallic structure comprising a metal element from a metal salt comprising a cation part and an anion part, comprising the steps of: providing a volume of metal salt; exposing the volume of metal salt in an atmosphere comprising a reduction gas at a temperature below a melting temperature of the metal element, leading to converting the volume of metal salt into the porous metallic structure by removing the anion part using the reduction gas; wherein the porous metallic structure has a pore size between 1 nanometer and 50 micrometer, and a ligament size between 1 nanometer and 50 micrometer; wherein the ligament size is controlled by the temperature during the exposing.

Abstract: A convolution acceleration and computing processing method includes: reading data to be processed of a preset size in a task to be processed from an off-chip memory of an accelerator sequentially through a FIFO port, and storing the data to be processed into at least one input buffer of a first buffer in an on-chip memory of the accelerator; responsive to data to be processed being stored into an input buffer, reading input window data to be processed from the at least one input buffer sequentially, performing convolution on the input window data to be processed by using the convolution kernel data to obtain output window data and storing the output window data in the third buffer; and storing the output window data in the third buffer into the off-chip memory sequentially through the FIFO port.