In-Memory Computation With Improved Linearity Using Adaptive Sparsity-Based Compact Thermometric Code

• Published in: IEEE transactions on very large scale integration (VLSI) systems Vol. 30; no. 10; pp. 1473 - 1483
• Main Authors: Saragada, Prasanna Kumar, Das, Bishnu Prasad
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.10.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Codes; Computer architecture; Discharges (electric); Image classification; In-memory computation (IMC); integral nonlinearity (INL); Linearity; machine learning (ML) classifier; process variation; Random access memory; Sparsity; sparsity-aware design; static random access memories (SRAMs); Static random access memory; thermometer code; Thermometers; Voltage
• ISSN: 1063-8210; 1557-9999
• DOI: 10.1109/TVLSI.2022.3199396

The article presents an efficient static random access memory (SRAM)-based in-memory computation (IMC) architecture which is capable of performing image classification with improved linearity. In this work, we proposed a thermometric code-based IMC (TC-IMC) to perform multibit multiply-and-accumulate (MAC) operations with improved linearity. An input sparsity-aware compact thermometric code approach is proposed to reduce the number of SRAM bitcells compared to the thermometric code-based encoding without loss of accuracy in the MAC operation. We proposed an optimal sampling time to improve the linearity of the TC-IMC MAC operation with maximum signal margin (SM) based on the detailed nonlinearity analysis of 8T SRAM-based TC-IMC architecture. The test chip measurement results in 180 nm process show that the proposed TC-IMC has 72% better linearity than the traditional IMC. The measured results on 100 Modified National Institute of Standards and Technology (MNIST) and CIFAR-10 test images show an accuracy of 97% and 87%, respectively. In addition, the proposed TC-IMC architecture achieves MAC compute latency of 25 ns, GOPS/kb (normalized to 1 b <inline-formula> <tex-math notation="LaTeX">\times </tex-math></inline-formula> 1 b) of 29.8, and energy efficiency of 2.3 TOPS/W. The simulation result of the entire 10000 MNIST and CIFAR-10 images considering process variation effects shows an accuracy of 98.7% and 90.4%, respectively.