In-Memory Computing with Associative Memories — A Cross-Layer Perspective

Data transfer between processors and memory is a major bottleneck in improving application-level performance. This is particularly true for data intensive tasks such as many machine learning and security applications. In-memory computing, where certain data processing is performed directly in the memory array, can be an effective solution to address this bottleneck. Associative memory (AM), a type of memory that can efficiently “associate” an input query with appropriate data words/locations in the memory, is a powerful in-memory computing core. Nonetheless harnessing the benefits of AM requires cross-layer efforts spanning from devices and circuits to architectures and systems. In this talk, I will showcase several representatives cross-layer AM based design efforts. In particular, I will highlight how different non-volatile memory technologies (such as RRAM, FeFET memory and Flash) can be exploited to implement various types of AM (e.g., exact and approximate match, ternary and multi-bit data representation, and different distance functions). I will use several popular machine learning and security applications to demonstrate how they can profit from these different AM designs. End-to-end (from device to application) evaluations will be analyzed to reveal the benefits contributed by each design layer, which can serve as guides for future research efforts.