Liquid Silicon: A Nonvolatile Fully Programmable Processing-in-Memory Processor with Monolithically Integrated ReRAM Yu e Z h a , Student Member , IEEE

Abstract

The slowdown of the CMOS technology scaling, and the trade-off between efficiency and flexibility have fueled the exploration into novel architectures with emerging post- CMOS technology [e.g., resistive-RAM (RRAM)]. In this article, a nonvolatile fully programmable processing-in-memory (PIM) processor named Liquid Silicon is demonstrated, which com- bines the superior programmability of general-purpose com- puting devices [e.g., field-programmable gate array (FPGA)] and the high efficiency of domain-specific accelerators. Besides the general computing applications, Liquid Silicon is par- ticularly well suited for artificial intelligence (AI)/machine learning and big data applications, which not only poses high computational/memory demand but also evolves rapidly. To fabricate the Liquid Silicon chip, the HfO 2 RRAM is monolithically integrated on top of the commercial 130 nm CMOS. Our measurement confirms that Liquid Silicon chip can operate reliably at a low voltage of 650 mV . It achieves 60.9 TOPS/W in performing neural network (NN) inferences, and 480 GOPS/W in performing content-based similarity search (a key big data application) at a nominal voltage supply of 1.2 V , showing 3 × and 100 × improvement over the state-of-the-art domain-specific CMOS-/RRAM-based accelerators. In addition, it outperforms the latest nonvolatile FPGA in energy efficiency by 3 × in general computing applications.