Hybrid Compute-in-Memory: abstract simplified (17695824)

A compute-in-memory array is a technology that combines computing and memory functions in a single system. In this case, the array is used to implement a filter for a specific layer in a neural network.

The purpose of the filter is to process data in the form of activation bits. These activation bits are multiplied by filter weight bits for each channel in a set of channels. The multiplication process is carried out using a charge accumulation method, which involves storing and combining charges in a group of capacitors.

Once the charges have been accumulated, they are digitized, meaning they are converted into a digital representation. This digitized output represents the result of the filter operation.

Overall, this technology enables efficient and parallel processing of data within a neural network layer by performing the filtering operation directly within the memory array.