A Charge-Domain 4T2C eDRAM Compute-in-Memory Macro With Enhanced Variation Tolerance and Low-Overhead Data Conversion Schemes
- 15 November 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 71 (4) , 1824-1828
Abstract
In this brief, a novel charge-domain 4T2C eDRAM-CIM macro is proposed that has three key features: 1) a novel 4T2C eDRAM cell with an enhanced PVT variation tolerance that resolves the limitations of previous eDRAM-CIM macros such as current domain operation, large bit-cell size, cell leakage, and low energy- and area-efficiency, resulting in high linearity (R2 = 0.9998) and 76.8% reduction in $3\sigma $ PVT variation, 2) a quarter-ADC-reduction scheme with an offset-calibration comparator that reduces the number of ADC by 73% while improving the accuracy drop by 7.82%, and 3) an array-embedded DAC that reduces the area overhead by 64.2% compared to current-based DAC. The proposed 4T2C eDRAM-CIM macro is fabricated in 65nm LP technology and achieves 43.02- to 49.20-TOPS/W and 2.4-TOPS/mm 2 when 4b $\times 4\text{b}$ MAC operation is performed with 250MHz. In addition, an 90.03% accuracy at the CIFAR-10 dataset with the ResNet-20 network is achieved.
Keywords
Funding Information
- Institute for Information and Communications Technology Promotion (IITP) Grant funded by the Korea Government (2021-0-00871)
This publication has 16 references indexed in Scilit:
- A 177 TOPS/W, Capacitor-based In-Memory Computing SRAM Macro with Stepwise-Charging/Discharging DACs and Sparsity-Optimized Bitcells for 4-Bit Deep Convolutional Neural Networks2022
- MC2-RAM: An In-8T-SRAM Computing Macro Featuring Multi-Bit Charge-Domain Computing and ADC-Reduction Weight Encoding2021
- CAP-RAM: A Charge-Domain In-Memory Computing 6T-SRAM for Accurate and Precision-Programmable CNN InferenceIEEE Journal of Solid-State Circuits, 2021
- 16.2 eDRAM-CIM: Compute-In-Memory Design with Reconfigurable Embedded-Dynamic-Memory Array Realizing Adaptive Data Converters and Charge-Domain Computing2021
- 15.3 A 65nm 3T Dynamic Analog RAM-Based Computing-in-Memory Macro and CNN Accelerator with Retention Enhancement, Adaptive Analog Sparsity and 44TOPS/W System Energy Efficiency2021
- A 7-nm Compute-in-Memory SRAM Macro Supporting Multi-Bit Input, Weight and Output and Achieving 351 TOPS/W and 372.4 GOPSIEEE Journal of Solid-State Circuits, 2020
- XNOR-SRAM: In-Memory Computing SRAM Macro for Binary/Ternary Deep Neural NetworksIEEE Journal of Solid-State Circuits, 2020
- A Multi-Functional In-Memory Inference Processor Using a Standard 6T SRAM ArrayIEEE Journal of Solid-State Circuits, 2018
- A 2T1C Embedded DRAM Macro With No Boosted Supplies Featuring a 7T SRAM Based Repair and a Cell Storage MonitorIEEE Journal of Solid-State Circuits, 2012
- A 667 MHz Logic-Compatible Embedded DRAM Featuring an Asymmetric 2T Gain Cell for High Speed On-Die CachesIEEE Journal of Solid-State Circuits, 2011