A 28 nm 16 Kb Bit-Scalable Charge-Domain Transpose 6T SRAM In-Memory Computing Macro
- 14 February 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 70 (5) , 1835-1845
Abstract
This article presents a compact, robust, and transposable SRAM in-memory computing (IMC) macro to support feed forward (FF) and back propagation (BP) computation within a single macro. The transpose macro is created with a clustering structure, and eight 6T bitcells are shared with one charge-domain computing unit (CCU) to efficiently deploy the DNNs weights. The normalized area overhead of clustering structure compared to 6T SRAM cell is only 0.37. During computation, the CCU performs robust charge-domain operations on the parasitic capacitances of the local bitlines in the IMC cluster. In the FF mode, the proposed design supports 128-input 1b XNOR and 1b AND multiplications and accumulations (MACs). The 1b AND can be extended to multi-bit MAC via bit-serial (BS) mapping, which can support DNNs with various precision. A power-gated auto-zero Flash analog-to-digital converter (ADC) reducing the input offset voltage maintains the overall energy efficiency and throughput. The proposed macro is prototyped in a 28-nm CMOS process. It demonstrates a 1b energy efficiency of $166\vert 257$ TOPS/W in FF-XNOR $\vert $ AND mode, and 31.8 TOPS/W in BP mode, respectively. The macro achieves $80.26\% \vert 85.07\%$ classification accuracy for the CIFAR-10 dataset with 1b $\vert 4\text{b}$ CNN models. Besides, 95.50% MNIST dataset classification accuracy (95.66% software accuracy) is achieved by the BP mode of the proposed transpose IMC macro.
Keywords
Funding Information
- National Key Research and Development Program of China (2020YFB2205502)
- Joint Funds of the National Natural Science Foundation of China (U20A20204)
- 111 Project (B18001)
This publication has 43 references indexed in Scilit:
- XNOR-SRAM: In-Memory Computing SRAM Macro for Binary/Ternary Deep Neural NetworksIEEE Journal of Solid-State Circuits, 2020
- In-Memory Computing: Advances and ProspectsIEEE Solid-State Circuits Magazine, 2019
- Area-Efficient and Variation-Tolerant In-Memory BNN Computing using 6T SRAM Array2019
- Optimizing Weight Mapping and Data Flow for Convolutional Neural Networks on RRAM Based Processing-In-Memory Architecture2019
- A 64-Tile 2.4-Mb In-Memory-Computing CNN Accelerator Employing Charge-Domain ComputeIEEE Journal of Solid-State Circuits, 2019
- 24.4 Sandwich-RAM: An Energy-Efficient In-Memory BWN Architecture with Pulse-Width Modulation2019
- Conv-RAM: An energy-efficient SRAM with embedded convolution computation for low-power CNN-based machine learning applications2018
- A Multi-Functional In-Memory Inference Processor Using a Standard 6T SRAM ArrayIEEE Journal of Solid-State Circuits, 2018
- In-Memory Computation of a Machine-Learning Classifier in a Standard 6T SRAM ArrayIEEE Journal of Solid-State Circuits, 2017
- XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks2016