A Novel DRAM-Based Process-in-Memory Architecture and its Implementation for CNNs
Chirag Sudarshan, Taha Soliman, Cecilia De la Parra, Christian Weis, Leonardo Ecco, Matthias Jung, Norbert Wehn, Andre Guntoro
Abstract
Processing-in-Memory (PIM) is an emerging approach to bridge the memory-computation gap. One of the key challenges of PIM architectures in the scope of neural network inference is the deployment of traditional area-intensive arithmetic multipliers in memory technology, especially for DRAM-based PIM architectures. Hence, existing DRAM PIM architectures are either confined to binary networks or exploit the analog property of the sub-array bitlines to perform bulk bit-wise logic operations. The former reduces the accuracy of predictions, i.e. Quality-of-results, while the latter increases overall latency and power consumption.