HPSW-CIM: A Novel ReRAM-Based Computing-in-Memory Architecture with Constant-Term Circuit for Full Parallel Hybrid-Precision-Signed-Weight MAC Operation
- 28 May 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3274-3278
Abstract
Non-volatile memory (NVM) based computing-- (CIM) systems can provide low-latency and high-efficiency parallel multiply-accumulate (MAC) operations, which shows great potential in accelerating edge AI computing. In response to the limitations of miniaturization, parallelism, and low-power consumption of edge AI devices, this work proposes: 1. A hybrid-precision-signed-weight ITIR (HPSWITIR) sub-array realizes the signed-weight by constant-term resistor circuit without additional ReRAM array overhead. 2. A computing array reduces the IR-drop and transistor errors of the array by assembling a series of HPSW-1T1R sub-arrays and achieve high-density array integration. 3. Global-share ADCs (GS-ADCs) optimize the analog signals conversion process to improve computing parallelism. 4. Odd-Channel-Input-WeightInverse Coding (ORIWI) can further reduce IR drop by decreasing the accumulative SL current (ISL) inside the HPSWITIR sub-array. In these manners, this work constructed a high computing-density HPSW-CIM calculation core for fully parallel MAC operation. The circuit-level evaluation shows that the energy cost of data conversion reduced by 2×-2.7×, reduces the peak column average current by 3.1×-6.2×, and improves array computing density by at least twice. The system-level evaluation shows that, in an HPSW-CIM core with 256KB memory in the 28nm process, the peak energy efficiency reaches 95.8TOPS/W@8bIN-4bW-8bO.Keywords
Funding Information
- Chinese Academy of Sciences
This publication has 12 references indexed in Scilit:
- Analog architectures for neural network acceleration based on non-volatile memoryApplied Physics Reviews, 2020
- Timely: Pushing Data Movements And Interfaces In Pim Accelerators Towards Local And In Time Domain2020
- 33.2 A Fully Integrated Analog ReRAM Based 78.4TOPS/W Compute-In-Memory Chip with Fully Parallel MAC Computing2020
- Brain-inspired computing with memristors: Challenges in devices, circuits, and systemsApplied Physics Reviews, 2020
- The building blocks of a brain-inspired computerApplied Physics Reviews, 2020
- FloatPIM2019
- Memristor-Based Circuit Design for Multilayer Neural NetworksIEEE Transactions on Circuits and Systems I: Regular Papers, 2017
- PRIMEACM SIGARCH Computer Architecture News, 2016
- RRAM-Based Analog Approximate ComputingIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2015
- A CMOS Image Sensor with a Column-Level Multiple-Ramp Single-Slope ADC2007