Exploring a SOT-MRAM Based In-Memory Computing for Data Processing

In this paper, we propose a Spin-Orbit Torque Magnetic Random-Access Memory (SOT-MRAM) array design that can simultaneously work as non-volatile memory and implement a reconfigurable in-memory logic operation without add-on logic circuits. The computed output can be simply read out like a typical MRAM bit-cell through the modified peripheral circuit. Such intrinsic in-memory computation can be used to process data locally and transfer the “cooked” data to the primary processing unit (i.e., CPU or GPU) for complex computations with high precision requirement. It greatly reduces the power-hungry and long-distance data communication, and further leads to extreme parallel computation within memory. In this work, we further propose an in-memory edge extraction algorithm as a case study to demonstrate the efficiency of the in-memory pre-processing methodology. The simulation results show that our edge extraction method reduces data communication as much as 8x for grayscale image, thus greatly reducing system energy consumption. Meanwhile, the F-measure result shows only $\sim$ 10 percent degradation compared to conventional edge detection operator, such as Prewitt, Sobel, and Roberts. Moreover, the edges extracted from the memory show comparable good quality with Canny edges in the context of edge-based motion detection and cross-modality object recognition.