A 28-nm 19.9-to-258.5-TOPS/W 8b Digital Computing-in-Memory Processor With Two-Cycle Macro Featuring Winograd-Domain Convolution and Macro-Level Parallel Dual-Side Sparsity
- 18 June 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 60 (1) , 347-361
Abstract
Recently, computing in memory (CiM) has been proven to be an energy-efficient and promising architecture for artificial intelligence (AI) algorithms. And yet, current CiM schemes generally suffer from limited throughput compared to their digital counterparts, and the key reason is that the CiM macro calculation must iterate through multiple cycles. Thus, the need to reduce the calculation cycle of the macro while keeping high energy efficiency and the necessity of developing acceleration methods for the universal CiM-based processor have become major issues faced by the current CiM architectures. To surmount these critical problems, we propose a processor based on a two-cycle CiM macro. Our work makes three main contributions: 1) we present a Radix16-based digital-CiM macro with look-up table (LUT) optimization to reduce dynamic power consumption; 2) we devise a hybrid Winograd microarchitecture and dataflow that supports (2, 3) and (4, 3) Winograd convolution, meaning that a good compromise can be reached between the accuracy of the algorithm and the reduction in workload; and 3) we propose a macrolevel parallel dual-side sparse CiM core that uses a horizontal direction compression method to reduce the input cycle of activation data and improve the mapping efficiency of the weight data in the macros. A prototype of the processor is fabricated in a 28-nm CMOS, which achieves a peak system energy efficiency of 19.9–258.5-TOPS/W for a voltage supply of 0.6–1.1 V, and an operating frequency of 78–287 MHz, a 2.55–7.08 $\times$ higher than other state-of-the-art CiM processors.Keywords
Funding Information
- National Key Research Plan of China (2023YFB4402400)
- Strategic Priority Research Program of the Chinese Academy of Sciences China (XDB44000000, XDA330100)
- National Natural Science Foundation of China (U2341218, 62101038)
- Science and Technology Development Fund (0036/2020/AGJ, MYRG2020-00209-IME)
This publication has 29 references indexed in Scilit:
- Channel Balancing for Accurate Quantization of Winograd Convolutions2022
- Griffin: Rethinking Sparse Optimization for Deep Learning Architectures2022
- RePIM: Joint Exploitation of Activation and Weight Repetitions for In-ReRAM DNN Acceleration2021
- Cambricon-Q: A Hybrid Architecture for Efficient Training2021
- Ten Lessons From Three Generations Shaped Google’s TPUv4i : Industrial Product2021
- Dual-side Sparse Tensor Core2021
- Sparsity-Aware and Re-configurable NPU Architecture for Samsung Flagship Mobile SoC2021
- 16.4 An 89TOPS/W and 16.3TOPS/mm2 All-Digital SRAM-Based Full-Precision Compute-In Memory Macro in 22nm for Machine-Learning Edge Applications2021
- Exploring the Granularity of Sparsity in Convolutional Neural Networks2017
- Fast Algorithms for Convolutional Neural Networks2016