High Throughput, Area-Efficient, and Variation-Tolerant 3D In-memory Compute System for Deep Convolutional Neural Networks

Untethered computing using Deep Convolutional Neural Networks at the edge of IoT with limited resources requires systems that are exceedingly power and area-efficient. Analog in-memory matrix-matrix multiplications enabled by emerging memories can significantly reduce the energy budget of such systems and result in compact accelerators. In this paper, we report a high-throughput RRAM-based DCNN processor that boasts 7.12× area-efficiency (AE) and 6.52× power-efficiency (PE) enhancements over state-of-the-art accelerators. We achieve this by coupling a novel in-memory computing methodology with a staggered-3D memristor array. Our variation-tolerant in-memory compute method, which performs operations on signed floating-point numbers within a single array, leverages charge domain operations and conductance discretization to reduce peripheral overheads. Voltage pulses applied at the staggered bottom electrodes of the 3D-array generate a concurrent input shift and parallelize convolution operations to boost throughput. The high density and low footprint of the 3D-array, along with the modified in-memory M2M execution, improve peak AE to 9.1TOPsmm-2 while the elimination of input regeneration improves PE to 10.6TOPsW-1. This work provides a path towards infallible RRAM-based hardware accelerators that are fast, low-power, and low-area.