In-Memory Computing is Very Promising

 Keywords: integration of storage and computing, integration of computing and storage, PIM (processing-in-memory), in-memory computing, Computational RAM, Resistive random-access memory

According to a market analysis report on "in-memory computing" from 2018 to 2026, in-memory computing is quite promising.

In today's AI technology, as the amount of data increases and the amount of calculation increases, the original von Neumann structure is being challenged more and more. The hardware architecture cannot be expected to expand the CPU if the amount of calculation is large, and to use memory stacking if the amount of storage is large; this is a heavy reliance on the past architecture, and this method is very unsuitable for AI. When the capacity is large to a certain extent, it can only indicate that some technologies need to be innovated.

From a biological point of view, the brain stores a large amount of knowledge, which can be quickly retrieved and accessed. However, the memory and computing of the brain are not separated, and there is more of a certain compatibility. The future computer is not based on computing memory, but memory-based computing, and it should be more integrated.

Of course, it is hard to say whether in-memory computing is the right direction. Because people are still paying more attention to AI algorithms at present, and there are still few attempts to improve the structure of AI, so the development in this direction is relatively slow, and there are relatively few methods. However, in the foreseeable future, more attempts to combine memory and computing will definitely become more and more popular.

In addition, at the research level, students at Princeton University have released a memory-based computing chip for adapting AI: "In-memory neural network chip", what they do is to integrate memory and computation.