Litcius/Paper detail

A 40-nm, 2M-Cell, 8b-Precision, Hybrid SLC-MLC PCM Computing-in-Memory Macro with 20.5 - 65.0TOPS/W for Tiny-Al Edge Devices

Win-San Khwa, Yen-Cheng Chiu, Chuan-Jia Jhang, Sheng-Po Huang, Chun‐Ying Lee, Tai-Hao Wen, Fu-Chun Chang, S. M. Yu, Tung-Yin Lee, Meng‐Fan Chang

20222022 IEEE International Solid- State Circuits Conference (ISSCC)118 citationsDOI

Abstract

Efficient edge computing, with sufficiently large on-chip memory capacity, is essential in the internet-of-everything era. Nonvolatile computing-in-memory (nvCIM) reduces the data transfer overhead by bringing computation closer, in proximity, to the memory [1]–[4]. While the multi-level cell (MLC) has higher storage density than the single-level cell (SLC). A few MLC or analog nvCIM designs had been proposed, but they either target simpler neural-net models [5] or are implemented using a less area-efficient differential cell [6]. Furthermore, representing the entire weight vector using one storage type does not exploit the drastic accuracy difference between the upper and the lower bits.

Topics & Concepts

Computer scienceOverhead (engineering)Enhanced Data Rates for GSM EvolutionParallel computingComputationMacroNon-volatile memoryComputer data storageExploitEdge deviceEdge computingComputer hardwareEmbedded systemComputational scienceAlgorithmTelecommunicationsProgramming languageCloud computingComputer securityOperating systemAdvanced Memory and Neural ComputingSemiconductor materials and devicesFerroelectric and Negative Capacitance Devices