Abstract: A digital compute-in-memory (DCIM) macro includes a memory cell array and an arithmetic logic unit (ALU). The memory cell array stores weight data of a neural network. The ALU receives parallel bits of a same input channel in an activation input, and generates a convolution computation output of the parallel bits and target weight data in the memory cell array.

Abstract: A digital compute-in-memory (DCIM) system includes a first DCIM macro. The first DCIM macro includes a first memory cell array and a first arithmetic logic unit (ALU). The first memory cell array has N rows that are configured to store weight data of a neural network in a single weight data download session, wherein N is a positive integer not smaller than two. The first ALU is configured to receive a first activation input, and perform convolution operations upon the first activation input and a single row of weight data selected from the N rows of the first memory cell array to generate first convolution outputs.

Abstract: A data writing method, a memory control circuit unit, and a memory storage apparatus are provided. The method includes: receiving a write command from a host system; and determining whether to write a data corresponding to the write command into a first area or a second area according to a write amplification factor of the first area, where if it is determined to write the data into the second area, copying the written data to the first area after writing the data.

Abstract: A data writing method, a memory control circuit unit, and a memory storage apparatus are provided. The method includes: receiving a write command from a host system; and determining whether to write a data corresponding to the write command into a first area or a second area according to a write amplification factor of the first area, where if it is determined to write the data into the second area, copying the written data to the first area after writing the data.

Abstract: The invention provides a memory management method, a memory storage device, and a memory control circuit unit. The method includes: recording an error bit number of each upper physical programming unit and an error bit number of each lower physical programming unit of each of the physical erasing units; determining whether a first physical erasing unit is a bad physical erasing unit according to distributions of the error bit numbers of the upper physical programming units and the lower physical programming units of the first physical erasing unit of the physical erasing units; and performing a data transfer operation on data in the first physical erasing unit if the first physical erasing unit is determined as the bad physical erasing unit.