Bing Li

Bing Li

Auto-generated profile, based on publicly available information

Bing Li

Institute of Microelectronics of the Chinese Academy of Sciences, Beijing, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 February 2023 in Science China Information Sciences
Verified
Journal Article
Closed access
PDF file
YZYinglin Zhao
Yinglin Zhao
JYJianlei Yang
Jianlei Yang
BLBing Li
Bing Li
XCXingzhou Cheng
Xingzhou Cheng
XYXucheng Ye
Xucheng Ye
WZWeisheng Zhao
Weisheng Zhao

23 February 2021 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
BLBing Li
Bing Li
SQSongyun Qu
Songyun Qu
YWYing Wang
Ying Wang
With the advancement of deep neural networks (DNNs), the applications driven by DNNs have been spread from the cloud to the edge. However, the intensive computations and data movements in CNNs impede the adoption of DNNs in resource-constraint edge devices. Quantization , a common model compression method, has attracted a lot of attention as it enables efficient inference by lowering the data bit-width of CNN parameters. Due to the features of massive storage and computing-in-memory array, resistive memory (RRAM) has established the energy efficiency and small area processing-in-memory (PIM) for the acceleration of DNNs at the edge end. However, when deploying the network onto resistive-memory-based PIM (RRAM-based PIM), there will be tremendous unused cells due to the mismatch between the structure of the neural network layer and memory array, resulting in the resource under-utilization and low computation efficiency. In this work, we observed prior quantization approaches fail to improve hardware resource utilization as they ignored the hardware structure information in RRAM. Thus, combining the information of the neural network model and hardware information is essential for a high-utilization RRAM-based PIM design. Considering the vast model parameters and heterogeneous RRAM crossbar structure, we develop a novel quantization framework by leveraging the AutoML technique, i.e., RaQu, which automatically generates a fine-grained quantization strategy for any model that fully utilizes the resource of RRAM-based PIM. The experimental results show that RaQu achieves at most 29.2%–37.4% and 1.8%–3.3% improvement in resource utilization and model accuracy, respectively, compared to prior coarse-grained quantization methods.

30 January 2020 in ACM Journal on Emerging Technologies in Computing Systems
Verified
Journal Article
Open access
BLBing Li
Bing Li
JDJanardhan Rao Doppa
Janardhan Rao Doppa
PPPartha Pratim Pande
Partha Pratim Pande
KCKrishnendu Chakrabarty
Krishnendu Chakrabarty
JQJoe X. Qiu
Joe X. Qiu
HLHai (Helen) Li
Hai (Helen) Li
Deep neural network (DNN) models are being expanded to a broader range of applications. The computational capability of traditional hardware platforms cannot accommodate the growth of model complexity. Among recent technologies to accelerate DNN, resistive memory (ReRAM)-based processing-in-memory (PIM) emerged as a promising solution for DNN inference due to its high efficiency for matrix-based computation. We face two major technical challenges in extending the use of ReRAM-based accelerators for training: (1) full-precision data is essential in back-propagation; (2) the need to support both feed-forward and back-propagation aggravates the data-movement burden. We propose a heterogeneous architecture named as 3D-ReG, which leverages full-precision GPU to ensure training accuracy and low-overhead 3D integration to provide low-cost data movements. Moreover, we introduce conservative and aggressive task-mapping schemes, which partition the computation phases in different ways to balance execution efficiency and training accuracy. We evaluate 3D-ReG implemented with two 3D integration technologies, through-silicon vias (TSVs) and monolithic inter-tier vias (MIVs), and compare them with GPU-only and PIM-only counterparts. Various GPU-only platforms using two main-memory technologies (DRAM, ReRAM) and three interconnect technologies (2D, TSV, MIV) are evaluated as well. Experimental results show that 3D-ReG can achieve on average 5.64× training speedup and 3.56× higher energy efficiency compared with the GPU with DRAM as main memory, at the cost of 0.05%–3.39% accuracy drop. We define a new metric, gain-loss ratio (GLR), which quantitatively evaluates the capability of a DNN training hardware in terms of the model accuracy and hardware efficiency. The results of our comparison show that the aggressive task-mapping scheme on MIV-based 3D-ReG outperforms the other methods.

27 April 2024
Verified
Conference Paper
Open access
SQSongyun Qu
Songyun Qu
SZShixin Zhao
Shixin Zhao
BLBing Li
Bing Li
YHYintao He
Yintao He
XCXuyi Cai
Xuyi Cai
YWYing Wang
Ying Wang

16 March 2020 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
ZLZiru Li
Ziru Li
BLBing Li
Bing Li
ZFZichen Fan
Zichen Fan
HLHai Li
Hai Li

1 January 2019 in Integration
Verified
Journal Article
Closed access
QGQingli Guo
Qingli Guo
JYJing Ye
Jing Ye
BLBing Li
Bing Li
YHYu Hu
Yu Hu
XLXiaowei Li
Xiaowei Li
GZGuohe Zhang
Guohe Zhang