Abstract: A magnetic multi-pole propulsion array system is applied to at least one external cathode and includes a plurality of magnetic multi-pole thrusters connected adjacent to each other. Each magnetic multi-pole thruster includes a propellant provider, a discharge chamber, an anode and a plurality of magnetic components. The propellant provider outputs propellant. The discharge chamber is connected with the propellant provider to accommodate the propellant. The anode is disposed inside the discharge chamber to generate an electric field. The plurality of magnetic components is respectively disposed on several sides of the discharge chamber. One of the several sides of the discharge chamber of the magnetic multi-pole thruster is applied for one side of a discharge chamber of another magnetic multi-pole thruster.

Abstract: A computing in memory method for a memory device is provided. The computing in memory method includes: based on a stride parameter, unfolding a kernel into a plurality of sub-kernels and a plurality of complement sub-kernels; based on the sub-kernels and the complement sub-kernels, writing a plurality of weights into a plurality of target memory cells of a memory array of the memory device; inputting an input data into a selected word line of the memory array; performing a stride operation in the memory array; temporarily storing a plurality of partial sums; and summing the stored partial sums into a stride operation result when all operation cycles are completed.

Abstract: A computing in memory method for a memory device is provided. The computing in memory method includes: based on a stride parameter, unfolding a kernel into a plurality of sub-kernels and a plurality of complement sub-kernels; based on the sub-kernels and the complement sub-kernels, writing a plurality of weights into a plurality of target memory cells of a memory array of the memory device; inputting an input data into a selected word line of the memory array; performing a stride operation in the memory array; temporarily storing a plurality of partial sums; and summing the stored partial sums into a stride operation result when all operation cycles are completed.