Litcius/Paper detail

A 32.2 TOPS/W SRAM Compute-in-Memory Macro Employing a Linear 8-bit C-2C Ladder for Charge Domain Computation in 22nm for Edge Inference

Hechen Wang, Renzhi Liu, Richard Dorrance, Deepak Dasalukunte, Xiaosen Liu, Dan Lake, Brent Carlton, May Wu

20222022 IEEE Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits)41 citationsDOI

Abstract

This paper presents an SRAM-based analog Compute-in-Memory (CiM) macro in 22 nm CMOS process. By introducing a C-2C capacitor ladder-based charge domain computing scheme, the CiM prototype chip demonstrates 2k multiply-accumulation (MAC) operations in one clock cycle and achieves 32.2 TOPS/W peak energy efficiency and 4.0 TOPS/mm <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> peak area efficiency with 8-bit precision in both input activation and weight. A variety of analog impairment factors were analyzed during the testchip implementation to ensure sufficiently high multibit linearity.

Topics & Concepts

Static random-access memoryCMOSComputationMacroTOPSChipCapacitorDomain (mathematical analysis)Energy (signal processing)Charge (physics)Parallel computingComputer hardwareComputer scienceComputational sciencePhysicsElectronic engineeringElectrical engineeringAlgorithmVoltageEngineeringMathematicsQuantum mechanicsAstronomyProgramming languageMathematical analysisAzimuthAdvanced Memory and Neural ComputingFerroelectric and Negative Capacitance DevicesSemiconductor materials and devices