Haoran Qiu, Weichao Mao, et al.
ASPLOS 2024
For this demonstration, we will showcase the operation of a software stack capable of automatically deploying Matrix-Vector Matrix (MVM) operations of diverse Deep Neural Network (DNN) workloads in a pipelined-manner on a Phase-Change Memory (PCM)-based Analog-Based In-Memory Computing (AIMC) chip with high-accuracy. Using a real chip, each deployment step will be highlighted for a Resnet-based DNN, which was been trained to perform image classification. Additionally, using an emulated mode of operation, these steps will also be highlighted for a transformer-based network trained to perform an organic chemical reaction prediction task.