191 results on '"Cheng, Zhuo"'
Search Results
2. Worst-case Power Integrity Prediction Using Convolutional Neural Network
- Author
-
Xiao Dong, Yufei Chen, Jun Chen, Yucheng Wang, Ji Li, Tianming Ni, Zhiguo Shi, Xunzhao Yin, and Cheng Zhuo
- Subjects
Electrical and Electronic Engineering ,Computer Graphics and Computer-Aided Design ,Computer Science Applications - Abstract
Power integrity analysis is an essential step in power distribution network (PDN) sign-off to ensure the performance and reliability of chips. However, with the growing PDN size and increasing scenarios to be validated, it becomes very time- and resource-consuming to conduct full-stack PDN simulation to check the power integrity for different test vectors. Recently, various works have proposed machine learning–based methods for PDN power integrity prediction, many of which still suffer from large training overhead, inefficiency, or non-scalability. Thus, this article proposed an efficient and scalable framework for the worst-case power integrity prediction, which can handle general tasks including dynamic noise prediction and bump current prediction. The framework first reduces the spatial and temporal redundancy in the PDN and input current vector and then employs efficient feature extraction as well as a novel convolutional neural network architecture to predict the worst-case power integrity. Experimental results show that the proposed framework consistently outperforms the commercial tool and the state-of-the-art machine learning method with only 0.63–1.02% mean relative error and 25–69× speedup for noise prediction and 0.22–1.06% mean relative error and 24–64× speedup for bump current prediction.
- Published
- 2023
3. Design of Ultracompact Content Addressable Memory Exploiting 1T-1MTJ Cell
- Author
-
Cheng Zhuo, Zeyu Yang, Kai Ni, Mohsen Imani, Yuxuan Luo, Shaodi Wang, Deming Zhang, and Xunzhao Yin
- Subjects
Electrical and Electronic Engineering ,Computer Graphics and Computer-Aided Design ,Software - Published
- 2023
4. A Fast Method to Estimate Through-Bump Current for Power Delivery Verification
- Author
-
Cheng Zhuo and Songyu Sun
- Subjects
Electrical and Electronic Engineering ,Computer Graphics and Computer-Aided Design ,Software - Published
- 2023
5. Ferroelectric Ternary Content Addressable Memories for Energy-Efficient Associative Search
- Author
-
Xunzhao Yin, Yu Qian, Mohsen Imani, Kai Ni, Chao Li, Grace Li Zhang, Bing Li, Ulf Schlichtmann, and Cheng Zhuo
- Subjects
Electrical and Electronic Engineering ,Computer Graphics and Computer-Aided Design ,Software - Published
- 2023
6. LIAS: A Lightweight Incentive Authentication Scheme for Forensic Services in IoV
- Author
-
Mingyue Zhang, Junlong Zhou, Peijin Cong, Gongxuan Zhang, Cheng Zhuo, and Shiyan Hu
- Subjects
Control and Systems Engineering ,Electrical and Electronic Engineering - Published
- 2023
7. A DVFS Design and Simulation Framework Using Machine Learning Models
- Author
-
Di Gao, Cheng Zhuo, Yuan Cao, Tianhao Shen, Jin-fang Zhou, Xunzhao Yin, and Li Zhang
- Subjects
Power management ,Profiling (computer programming) ,Computer science ,business.industry ,Machine learning ,computer.software_genre ,Power (physics) ,Hardware and Architecture ,Management methods ,Artificial intelligence ,Electrical and Electronic Engineering ,Performance improvement ,business ,computer ,Mobile device ,Design space ,Software - Abstract
Battery-powered mobile devices are typically featured with fast varying workloads and constrained power supply, demanding more efficient run-time power management. In this paper, we propose a DVFS design and simulation framework to explore the design space for DVFS. The framework leverages the existing tool chains and uses several machine learning models to support the architectural simulation and run-time profiling. When using the proposed framework to evaluate different management methods, the proposed deep-reinforcement-learning approach can achieve 5.8-7.3% performance improvement compared with the other alternatives.
- Published
- 2023
8. Amplification of dissymmetry factors by dihedral angle engineering in donor–acceptor type circularly polarized luminescence materials
- Author
-
Xing-Yu Chen, Ji-Kun Li, Wen-Long Zhao, Cheng-Zhuo Du, Meng Li, Chuan-Feng Chen, and Xiao-Ye Wang
- Subjects
Materials Chemistry ,General Chemistry - Abstract
A new donor–acceptor type circularly polarized luminescence material has been developed, and a dihedral angle engineering strategy has been demonstrated for the first time to significantly amplify the luminescence dissymmetry factors.
- Published
- 2023
9. A fine-grained mixed precision DNN accelerator using a two-stage big–little core RISC-V MCU
- Author
-
Li Zhang, Qishen Lv, Di Gao, Xian Zhou, Wenchao Meng, Qinmin Yang, and Cheng Zhuo
- Subjects
Hardware and Architecture ,Electrical and Electronic Engineering ,Software - Published
- 2023
10. Indole-fused BN-heteroarenes as narrowband blue emitters for organic light-emitting diodes
- Author
-
Cheng-Zhuo Du, Yang Lv, Hengyi Dai, Xiangchen Hong, Jianping Zhou, Ji-Kun Li, Rong-Rong Gao, Dongdong Zhang, Lian Duan, and Xiao-Ye Wang
- Subjects
Materials Chemistry ,General Chemistry - Abstract
Multi-resonance thermally activated delayed fluorescence (MR-TADF) emitters based on a novel indole-fused BN-heteroarene (InBN) are developed via a π-truncation strategy. Narrowband blue-emitting OLEDs are demonstrated with high EQEs of up to 16.8%.
- Published
- 2023
11. GoodFloorplan: Graph Convolutional Network and Reinforcement Learning-Based Floorplanning
- Author
-
Xiaoqing Wen, Yi Kang, Cheng Zhuo, Hao Geng, Qi Xu, Bo Yuan, and Song Chen
- Subjects
Theoretical computer science ,Optimization problem ,Computer science ,Heuristic ,Reinforcement learning ,Graph (abstract data type) ,Electronic design automation ,Markov decision process ,Electrical and Electronic Engineering ,Physical design ,Computer Graphics and Computer-Aided Design ,Software ,Floorplan - Abstract
Electronic Design Automation (EDA) comprises a series of computationally difficult optimization problems that require substantial specialized knowledge as well as a considerable amount of trial-and-error efforts. However, open challenges including long simulation runtime and lack of generalization continue to restrict the applications of existing EDA tools. Recently, learning-based algorithms especially reinforcement learning (RL) have been successfully applied to handle various combinatorial optimization problems by automatically acquiring knowledge from the past experience. In this paper, we formulate the floorplanning problem, the first stage of the physical design flow, as a Markov Decision Process (MDP). An end-toend learning-based floorplanning framework GoodFloorplan is proposed to explore the design space, which combines graph convolutional network (GCN) and RL. Experimental results demonstrate that, compared with state-of-the-art heuristic-based floorplanners, the proposed GoodFloorplan can provide better area and wirelength.
- Published
- 2022
12. Improving Fault Tolerance for Reliable DNN Using Boundary-Aware Activation
- Author
-
Wei Jiang, Cheng Zhuo, Jinyu Zhan, Xunzhao Yin, Ruoxu Sun, and Yucheng Jiang
- Subjects
Computer science ,Control theory ,Boundary (topology) ,Fault tolerance ,Electrical and Electronic Engineering ,Computer Graphics and Computer-Aided Design ,Software - Published
- 2022
13. PAM: A Piecewise-Linearly-Approximated Floating-Point Multiplier With Unbiasedness and Configurability
- Author
-
Cheng Zhuo, Xunzhao Yin, Chuangtao Chen, Mohsen Imani, and Weikang Qian
- Subjects
Floating point ,Optimization problem ,Computer science ,Topology ,Theoretical Computer Science ,Computational Theory and Mathematics ,Hardware and Architecture ,Piecewise ,Multiplier (economics) ,Multiplication ,Enhanced Data Rates for GSM Evolution ,Linear independence ,Hardware_ARITHMETICANDLOGICSTRUCTURES ,Software ,Efficient energy use - Abstract
Approximate computing is a promising alternative to improve energy efficiency for IoT devices on the edge. This work proposes a piecewise-linearly-approximated and unbiased floating-point approximate multiplier with run-time configurability. We provide a theoretically sound formulation that turns multiplication approximation to an optimization problem. With the formulation and findings, a multi-level architecture is proposed to easily incorporate run-time configurability and module execution parallelism. Finally, the proposed multiplier is further optimized to reduce the circuit implementation complexity, making the multiplier linearly dependent on the precision requirement, instead of quadratically or exponentially as in prior work. When compared to the prior state-of-the-art approximate floating-point multiplier, ApproxLP [1], the proposed multiplier outperforms in all the aspects including accuracy, area, and delay. By replacing a full-precision floating-point multiplier in GPU, the proposed design can improve the energy efficiency for various edge computing tasks. Even with Level 1 approximation, the proposed multiplier improves energy efficiency up to 20x for machine learning on CIFAR-10, with almost negligible accuracy loss.
- Published
- 2022
14. Comprehensive analysis of mitophagy in HPV-related head and neck squamous cell carcinoma
- Author
-
Li Yanan, Liang Hui, Cheng Zhuo, Ding Longqing, and Sun Ran
- Subjects
Multidisciplinary - Abstract
Head and neck squamous cell carcinoma (HNSCC) is a common tumour type in otorhinolaryngology, and its occurrence is related to long-term exposure to tobacco and alcohol. Recently, HPV infection has become an increasingly important contributor to HNSCC, and HPV-associated HNSCC has a different clinical course and better prognosis than non-HPV-associated HNSCC. However, the exact molecular mechanism of HNSCC is unclear. Here, we obtained data from The Cancer Genome Atlas (TCGA) and gene expression omnibus (GEO) to analyse the mitophagy process and related influencing factors of HPV-associated HNSCC via the integration of bioinformatics analysis and experimental validation. We found that in HPV-associated HNSCC, process of mitophagy affects tumour development, immune cell infiltration and prognosis. In the mitophagy process of HPV-related HNSCC: NOS2, IL17REL, TMSB15A, TUBB4A and other hub genes showed significantly higher expression levels than in non-HPV-related HNSCC. Furthermore, this was also confirmed by quantitative real-time PCR (qRT‒PCR), which was used to detect the expression of differentially expressed genes in HNSCC tissues. Furthermore, we found that the unique immunological characteristics by expressing CD8+ T cell in a high level in HPV-related HNSCC, and the scores obtained from the score model affected the prognosis of patients. In conclusion, our study revealed the unique biomolecular signature of mitophagy in HPV-associated HNSCC, which may contribute to the development of precise treatment regimens for HPV-associated HNSCC patients.
- Published
- 2023
15. Dynamic and probabilistic seismic performance assessment of precast prestressed reinforced concrete frames incorporating slab influence through three-dimensional spatial model
- Author
-
Xu-Yang Cao, Cheng-Zhuo Xiong, De-Cheng Feng, and Gang Wu
- Subjects
Geophysics ,Building and Construction ,Geotechnical Engineering and Engineering Geology ,Civil and Structural Engineering - Published
- 2022
16. Magnetic Core TSV-Inductor Design and Optimization for On-chip DC-DC Converter
- Author
-
Chenyi Wen, Xiao Dong, Baixin Chen, Umamaheswara Rao Tida, Yiyu Shi, and Cheng Zhuo
- Subjects
Electrical and Electronic Engineering ,Computer Graphics and Computer-Aided Design ,Computer Science Applications - Abstract
The conventional on-chip spiral inductor consumes a significant top-metal routing area, thereby preventing its popularity in many on-chip applications. Recently through-silicon-via– (TSV) based inductor (also known as a TSV-inductor) with a magnetic core has been proved to be a viable option for the on-chip DC-DC converter. The operating conditions of these inductors play a major role in maximizing the performance and efficiency of the DC-DC converter. However, there is a critical need to study the design and optimization details of magnetic core TSV-inductors with the unique three-dimensional structure embedding magnetic core. This article aims to provide a clear understanding of the modeling details of a magnetic core TSV-inductor and a design and optimization methodology to assist efficient inductor design. Moreover, a machine learning–assisted model combining physical details and artificial neural network is also proposed to extract the equivalent circuit to further facilitate DC-DC converter design. Experimental results show that the optimized TSV-inductor with the magnetic core and air-gap can achieve inductance density improvement of up to 7.7 \( \times \) and quality factor improvements of up to 1.6 \( \times \) for the same footprint compared with the TSV-inductor without a magnetic core. For on-chip DC-DC converter applications, the converter efficiency can be improved by up to 15.9% and 6.8% compared with the conventional spiral and TSV-inductor without magnetic core, respectively.
- Published
- 2022
17. An Ultracompact Single‐Ferroelectric Field‐Effect Transistor Binary and Multibit Associative Search Engine
- Author
-
Xunzhao Yin, Franz Müller, Qingrong Huang, Chao Li, Mohsen Imani, Zeyu Yang, Jiahao Cai, Maximilian Lederer, Ricardo Olivo, Nellie Laleni, Shan Deng, Zijian Zhao, Zhiguo Shi, Yiyu Shi, Cheng Zhuo, Thomas Kämpfe, and Kai Ni
- Subjects
General Economics, Econometrics and Finance - Published
- 2023
18. Computing-In-Memory Using Ferroelectrics: From Single- to Multi-Input Logic
- Author
-
Di Gao, Michael Niemier, Cheng Zhuo, Chao Li, Dayane Reis, Mohsen Imani, Qingrong Huang, Xunzhao Yin, and Xiaobo Sharon Hu
- Subjects
Out of memory ,CMOS ,Computer engineering ,Hardware and Architecture ,Computer science ,Computation ,Process (computing) ,Electrical and Electronic Engineering ,Performance improvement ,Software ,Energy (signal processing) ,Efficient energy use ,Data transmission - Abstract
As a promising solution to address memory wall, computing in memory (CiM) designs using CMOS or emerging non-volatile memories (NVMs) are proposed to support bit-wise Boolean logic and arithmetic operations. Unlike the conventional executions that read data out of memory, process sequentially and send the outputs back, CiM implementations fully utilize its parallel in-memory bit-wise computation nature and hence reduce the unnecessary data transfer, thereby saving both area and power consumption. This paper proposes CiM designs based on Ferroelectric FETs (FeFETs) for bit-wise Boolean logic and multi-input MAJ operations. By exploiting the merged memory and switch property of FeFETs, our design realizes both high storage density and energy efficiency in computation. Evaluation results demonstrate that our proposed CiM designs can achieve significant energy saving and performance improvement, up to ~31% for Boolean logic and ~11× for majority vote, when compared to other NVM counterparts.
- Published
- 2022
19. PKDGAN: Private Knowledge Distillation With Generative Adversarial Networks
- Author
-
Cheng Zhuo, Di Gao, and Liangwei Liu
- Subjects
Information Systems and Management ,Information Systems - Published
- 2022
20. Senputing: An Ultra-Low-Power Always-On Vision Perception Chip Featuring the Deep Fusion of Sensing and Computing
- Author
-
Qi Wei, Fei Qiao, Cheng Zhuo, Ningchao Lin, Xunzhao Yin, Han Xu, Li Luo, Runsheng Wang, and Huazhong Yang
- Subjects
Computer science ,business.industry ,Computation ,computer.file_format ,Chip ,Power (physics) ,Data conversion ,Transmission (telecommunications) ,Electrical and Electronic Engineering ,business ,computer ,Computer hardware ,MNIST database ,Efficient energy use ,Voltage - Abstract
Always-on intelligent visual perception applications are widely deployed in edges in the AIoT era. In order to eliminate power costs of data conversion and transmission, this paper proposes Senputing, an ultra-low-power processing-in-sensor chip that completely fuses sensing and computing together for a BNN-based hierarchical processing system. This chip could operate in two modes. In computation mode, photocurrents are directly utilized for computing without being converted into voltages, and the computation results of 1-st BNN layer are directly sent out to subsequent BNN processors for an always-on coarse classification, eliminating conversion power and storage cost of raw images. Once an interested objected is detected, this chip switches to sensor mode and sends raw images to potential full-precision processors or cloud servers for fine-grained recognition or segmentation. A 32x 32 prototype is fabricated with 180nm CMOS process. It accomplishes MNIST dataset classification task with the accuracy of 93.76% and the power consumption of 147nW at 156fps, achieving 13.1x energy efficiency compared with state-of-the-art work.
- Published
- 2022
21. Approximate Floating-Point FFT Design with Wide Precision-Range and High Energy Efficiency
- Author
-
Chenyi Wen, Ying Wu, Xunzhao Yin, and Cheng Zhuo
- Published
- 2023
22. ANT-UNet: Accurate and Noise-Tolerant Segmentation for Pathology Image Processing
- Author
-
Yufei Chen, Tingtao Li, Qinming Zhang, Wei Mao, Nan Guan, Mei Tian, Hao Yu, and Cheng Zhuo
- Subjects
Hardware and Architecture ,Electrical and Electronic Engineering ,Software - Abstract
Pathology image segmentation is an essential step in early detection and diagnosis for various diseases. Due to its complex nature, precise segmentation is not a trivial task. Recently, deep learning has been proved as an effective option for pathology image processing. However, its efficiency is highly restricted by inconsistent annotation quality. In this article, we propose an accurate and noise-tolerant segmentation approach to overcome the aforementioned issues. This approach consists of two main parts: a preprocessing module for data augmentation and a new neural network architecture, ANT-UNet. Experimental results demonstrate that, even on a noisy dataset, the proposed approach can achieve more accurate segmentation with 6% to 35% accuracy improvement versus other commonly used segmentation methods. In addition, the proposed architecture is hardware friendly, which can reduce the amount of parameters to one-tenth of the original and achieve 1.7× speed-up.
- Published
- 2021
23. A novel analytic approach for outcome prediction in diffuse large B-cell lymphoma by [18F]FDG PET/CT
- Author
-
Jing Wang, Mindi Ma, Xuexin He, Rui Zhou, Xiaohui Zhang, Lin Chen, Han Jiang, Shuang Wu, Wenbin Qian, Zexin Chen, Liu Feng, Mei Tian, Cheng Zhuo, Miaoqi Ni, Chentao Jin, Teng Zhang, Kai Zhang, and Hong Zhang
- Subjects
medicine.diagnostic_test ,Receiver operating characteristic ,business.industry ,Proportional hazards model ,Area under the curve ,General Medicine ,Nomogram ,medicine.disease ,International Prognostic Index ,Positron emission tomography ,medicine ,Radiology, Nuclear Medicine and imaging ,Fdg pet ct ,Nuclear medicine ,business ,Diffuse large B-cell lymphoma - Abstract
Purpose This study aimed to develop a novel analytic approach based on 2-deoxy-2-[18F]fluoro-D-glucose positron emission tomography/computed tomography ([18F]FDG PET/CT) radiomic signature (RS) and International Prognostic Index (IPI) to predict the progression-free survival (PFS) and overall survival (OS) of patients with diffuse large B-cell lymphoma (DLBCL). Methods We retrospectively enrolled 152 DLBCL patients and divided them into a training cohort (n = 100) and a validation cohort (n = 52). A total of 1245 radiomic features were extracted from the total metabolic tumor volume (TMTV) and the metabolic bulk volume (MBV) of pre-treatment PET/CT images. The least absolute shrinkage and selection operator (LASSO) algorithm was applied to develop the RS. Cox regression analysis was used to construct hybrid nomograms based on different RS and clinical variables. The performances of hybrid nomograms were evaluated using the time-dependent receiver operator characteristic (ROC) curve and the Hosmer–Lemeshow test. The clinical utilities of prediction nomograms were determined via decision curve analysis. The predictive efficiency of different RS, clinical variables, and hybrid nomograms was compared. Results The RS and IPI were identified as independent predictors of PFS and OS, and were selected to construct hybrid nomograms. Both TMTV- and MBV-based hybrid nomograms had significantly higher values of area under the curve (AUC) than IPI in training and validation cohorts (all P P > 0.05). The Hosmer–Lemeshow test showed that both TMTV- and MBV-based hybrid nomograms calibrated well in the training and validation cohorts (all P > 0.05). Decision curve analysis indicated that hybrid nomograms had higher net benefits than IPI. Conclusion The hybrid nomograms combining RS with IPI could significantly improve survival prediction in DLBCL. Radiomic analysis on MBV may serve as a potential approach for prognosis assessment in DLBCL. Trial registration NCT04317313. Registered March 16, 2020. Public site: https://clinicaltrials.gov/ct2/show/NCT04317313
- Published
- 2021
24. Attention cutting and padding learning for fine-grained image recognition
- Author
-
Hao Luo, Hongjian Li, Duan Xiaolin, He Mingxuan, Xiangyan Zeng, and Cheng Zhuo
- Subjects
Computer Networks and Communications ,Computer science ,business.industry ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Semantics ,Padding ,Convolutional neural network ,Field (computer science) ,Image (mathematics) ,Task (computing) ,Hardware and Architecture ,Media Technology ,Computer vision ,Saliency map ,Artificial intelligence ,business ,Intelligent transportation system ,Software - Abstract
Fine-grained image recognition is an important task in the field of computer vision. In fine-grained image recognition, the difference between different categories is very small. Thus, fine-grained image recognition highly depends on local features. In this paper, a novel “Attention Cutting And Padding Learning” method is proposed to learn the local features. Firstly, the image is fed to Convolutional Neural Networks, and a saliency map is gotten. According to the saliency map, the attention image is obtained. Secondly, the attention image is cut into $$N*N$$ sub-images. Every sub-image is padded by 0 and the padding size is P. All sub-images are spliced into a Cutting And Padding image. Finally, the Cutting And Padding image and the attention image are fed to CNNs to train. In this method, more local features can be learned, and the high-level semantics is not damaged. Experimental results show that the recognition accuracy of Attention Cutting And Padding Learning is 87.9%, 94.6%, and 92.4% respectively on CUB-200-2011, Stanford Cars, and FGVC-Aircraft dataset. Moreover, this method can be easily applied to biodiversity automatic monitoring, intelligent retail, intelligent transportation, and other fields to improve recognition accuracy without changing the network structure.
- Published
- 2021
25. In-Memory Multi-Bit Multiplication and Accumulation (MAC) Using FeFET for Energy Efficient IoT
- Author
-
Xudong Lu, Shuo Chen, Zhanxi Pang, Songyu Sun, Xunzhao Yin, and Cheng Zhuo
- Published
- 2022
26. Examining the moderating role of technostress and compatibility in EFL Learners’ mobile learning adoption: A perspective from the theory of planned behaviour
- Author
-
Wang, Qiong, Zhao, Guoqing, and Cheng, Zhuo
- Subjects
General Psychology - Abstract
Mobile English learning has multiple advantages and brings enormous benefits to EFL learners. However, not everyone adopts it, and the determinants of learners’ adoption intention have not yet been investigated fully. This study aimed to better understand learners’ adoption by employing the theory of planned behaviour (TPB) in conjunction with the influences of technostress and compatibility. Based on existing literature, a research model was proposed and verified with a sample of 409 undergraduates from a Chinese university. The results indicated that in the context of mobile English learning: (a) Individuals with higher adoption intention are more likely to engage in mobile English learning with higher frequency (b = 0.473, P < 0.001) and longer duration (b = 0.330, P < 0.001); (b) Individuals’ attitude toward mobile English learning (b = 0.171, P < 0.05), perceived behavioural control (b = 0.221, P < 0.001), subjective norms (b = 0.237, P < 0.05), and compatibility (b = 0.443, P < 0.001) are significantly positively associated with their adoption intention; (c) Compatibility is the strongest predictor of adoption intention (b = 0.443, P < 0.001) and negatively moderates the effect of subjective norms on adoption intention (b = –0.103, P < 0.005); (d) The influence of technostress on the adoption intention of mobile English learning is not significant (b = –0.041, P > 0.05). Practical implications related to mobile English learning were discussed.
- Published
- 2022
27. Local-to-global spatial learning for whole-slide image representation and classification
- Author
-
Jiahui Yu, Tianyu Ma, Yu Fu, Hang Chen, Maode Lai, Cheng Zhuo, and Yingke Xu
- Subjects
Radiological and Ultrasound Technology ,Health Informatics ,Radiology, Nuclear Medicine and imaging ,Computer Vision and Pattern Recognition ,Computer Graphics and Computer-Aided Design - Published
- 2023
28. AIGAN: Attention–encoding Integrated Generative Adversarial Network for the reconstruction of low-dose CT and low-dose PET images
- Author
-
Yu Fu, Shunjie Dong, Meng Niu, Le Xue, Hanning Guo, Yanyan Huang, Yuanfan Xu, Tianbai Yu, Kuangyu Shi, Qianqian Yang, Yiyu Shi, Hong Zhang, Mei Tian, and Cheng Zhuo
- Subjects
Radiological and Ultrasound Technology ,Health Informatics ,Radiology, Nuclear Medicine and imaging ,Computer Vision and Pattern Recognition ,Computer Graphics and Computer-Aided Design - Published
- 2023
29. A Reconfigurable Multiplier for Signed Multiplications with Asymmetric Bit-Widths
- Author
-
Bing Li, Xunzhao Yin, Grace Li Zhang, Cheng Zhuo, Chuliang Guo, Li Zhang, Weikang Qian, and Xian Zhou
- Subjects
Approximate computing ,Computer science ,020208 electrical & electronic engineering ,02 engineering and technology ,020202 computer hardware & architecture ,Embedded applications ,Bit (horse) ,Hardware and Architecture ,0202 electrical engineering, electronic engineering, information engineering ,Multiplier (economics) ,Hardware_ARITHMETICANDLOGICSTRUCTURES ,Electrical and Electronic Engineering ,Arithmetic ,Software - Abstract
Multiplications have been commonly conducted in quantized CNNs, filters, and reconfigurable cores, and so on, which are widely deployed in mobile and embedded applications. Most multipliers are designed to perform multiplications with symmetric bit-widths, i.e., n - by n -bit multiplication. Such features would cause extra area overhead and performance loss when m - by n -bit multiplications ( m > n ) are deployed in the same hardware design, resulting in inefficient multiplication operations. It is highly desired and challenging to propose a reconfigurable multiplier design to accommodate operands with both symmetric and asymmetric bit-widths. In this work, we propose a reconfigurable approximate multiplier to support multiplications at various precisions, i.e., bit-widths. Unlike prior works of approximate adders assuming a uniform weight distribution with bit-wise independence, scenarios like a quantized CNN may have a centralized weight distribution and hence follow a Gaussian-like distribution with correlated adjacent bits. Thus, a new block-based approximate adder is also proposed as part of the multiplier to ensure energy-efficient operation with an awareness of the bit-wise correlation. Our experimental results show that the proposed approximate adder significantly reduces the error rate by 76% to 98% over a state-of-the-art approximate adder for Gaussian-like distribution scenarios. Evaluation results show that the proposed multiplier is 19% faster and 22% more power saving than a Xilinx multiplier IP at the same bit precision and achieves a 23.94-dB peak signal-to-noise ratio, which is comparable to the accurate one of 24.10 dB when deployed in a Gaussian filter for image processing tasks.
- Published
- 2021
30. Altered nonlinear Granger causality interactions in the large-scale brain networks of patients with schizophrenia
- Author
-
Yu Fu, Meng Niu, Yuanhang Gao, Shunjie Dong, Yanyan Huang, Zhe Zhang, and Cheng Zhuo
- Subjects
Cellular and Molecular Neuroscience ,Biomedical Engineering - Abstract
Objective. It has been demonstrated that schizophrenia (SZ) is characterized by functional dysconnectivity involving extensive brain networks. However, the majority of previous studies utilizing resting-state functional magnetic resonance imaging (fMRI) to infer abnormal functional connectivity (FC) in patients with SZ have focused on the linear correlation that one brain region may influence another, ignoring the inherently nonlinear properties of fMRI signals. Approach. In this paper, we present a neural Granger causality (NGC) technique for examining the changes in SZ’s nonlinear causal couplings. We develop static and dynamic NGC-based analyses of large-scale brain networks at several network levels, estimating complicated temporal and causal relationships in SZ patients. Main results. We find that the NGC-based FC matrices can detect large and significant differences between the SZ and healthy control groups at both the regional and subnetwork scales. These differences are persistent and significantly overlapped at various network sparsities regardless of whether the brain networks were built using static or dynamic techniques. In addition, compared to controls, patients with SZ exhibited extensive NGC confusion patterns throughout the entire brain. Significance. These findings imply that the NGC-based FCs may be a useful method for quantifying the abnormalities in the causal influences of patients with SZ, hence shedding fresh light on the pathophysiology of this disorder.
- Published
- 2022
31. PIM-DH
- Author
-
Fangxin Liu, Wenbo Zhao, Yongbiao Chen, Zongwu Wang, Zhezhi He, Rui Yang, Qidong Tang, Tao Yang, Cheng Zhuo, and Li Jiang
- Published
- 2022
32. Energy efficient data search design and optimization based on a compact ferroelectric FET content addressable memory
- Author
-
Jiahao Cai, Mohsen Imani, Kai Ni, Grace Li Zhang, Bing Li, Ulf Schlichtmann, Cheng Zhuo, and Xunzhao Yin
- Published
- 2022
33. Aging Aware Retraining for Memristor-based Neuromorphic Computing
- Author
-
Wenwen Ye, Grace Li Zhang, Bing Li, Ulf Schlichtmann, Cheng Zhuo, and Xunzhao Yin
- Published
- 2022
34. A deep learning framework for 18F-FDG PET imaging diagnosis in pediatric patients with temporal lobe epilepsy
- Author
-
Mindi Ma, Qinming Zhang, Kexin Shi, Jianhua Feng, Haifeng Hou, Zexin Chen, Lin Chen, Lei Ren, Cheng Zhuo, Liu Feng, Yufei Chen, Shuang Wu, Liao Yi, Teng Zhang, Jianing Deng, Xiaofeng Dou, Wang Xiawan, Yao Ding, Hong Zhang, Le Xue, Congcong Yu, and Mei Tian
- Subjects
medicine.medical_specialty ,Focus (geometry) ,Statistical parametric mapping ,Logistic regression ,Pediatrics ,030218 nuclear medicine & medical imaging ,Temporal lobe ,03 medical and health sciences ,Epilepsy ,0302 clinical medicine ,Sørensen–Dice coefficient ,Fluorodeoxyglucose F18 ,Positron Emission Tomography Computed Tomography ,medicine ,Humans ,Radiology, Nuclear Medicine and imaging ,Child ,Retrospective Studies ,Glucose metabolism ,medicine.diagnostic_test ,business.industry ,Deep learning ,General Medicine ,medicine.disease ,Magnetic Resonance Imaging ,Epilepsy, Temporal Lobe ,Positron emission tomography ,Positron emission tomography (PET) ,Positron-Emission Tomography ,Original Article ,Radiology ,Abnormality ,business ,030217 neurology & neurosurgery - Abstract
Purpose Epilepsy is one of the most disabling neurological disorders, which affects all age groups and often results in severe consequences. Since misdiagnoses are common, many pediatric patients fail to receive the correct treatment. Recently, 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) imaging has been used for the evaluation of pediatric epilepsy. However, the epileptic focus is very difficult to be identified by visual assessment since it may present either hypo- or hyper-metabolic abnormality with unclear boundary. This study aimed to develop a novel symmetricity-driven deep learning framework of PET imaging for the identification of epileptic foci in pediatric patients with temporal lobe epilepsy (TLE). Methods We retrospectively included 201 pediatric patients with TLE and 24 age-matched controls who underwent 18F-FDG PET-CT studies. 18F-FDG PET images were quantitatively investigated using 386 symmetricity features, and a pair-of-cube (PoC)-based Siamese convolutional neural network (CNN) was proposed for precise localization of epileptic focus, and then metabolic abnormality level of the predicted focus was calculated automatically by asymmetric index (AI). Performances of the proposed framework were compared with visual assessment, statistical parametric mapping (SPM) software, and Jensen-Shannon divergence-based logistic regression (JS-LR) analysis. Results The proposed deep learning framework could detect the epileptic foci accurately with the dice coefficient of 0.51, which was significantly higher than that of SPM (0.24, P < 0.01) and significantly (or marginally) higher than that of visual assessment (0.31–0.44, P = 0.005–0.27). The area under the curve (AUC) of the PoC classification was higher than that of the JS-LR (0.93 vs. 0.72). The metabolic level detection accuracy of the proposed method was significantly higher than that of visual assessment blinded or unblinded to clinical information (90% vs. 56% or 68%, P < 0.01). Conclusion The proposed deep learning framework for 18F-FDG PET imaging could identify epileptic foci accurately and efficiently, which might be applied as a computer-assisted approach for the future diagnosis of epilepsy patients. Trial registration NCT04169581. Registered November 13, 2019 Public site: https://clinicaltrials.gov/ct2/show/NCT04169581
- Published
- 2021
35. Active Index: An Integrated Index to Reveal Disrupted Brain Network Organizations of Major Depressive Disorder Patients
- Author
-
Yu Fu, Yanyan Huang, Meng Niu, Le Xue, Shunjie Dong, Shunlin Guo, Junqiang Lei, and Cheng Zhuo
- Published
- 2022
36. A Resource-Efficient Deep Learning Framework for Low-Dose Brain Pet Image Reconstruction and Analysis
- Author
-
Yu Fu, Shunjie Dong, Yi Liao, Le Xue, Yuanfan Xu, Feng Li, Qianqian Yang, Tianbai Yu, Mei Tian, and Cheng Zhuo
- Subjects
FOS: Computer and information sciences ,Computer Science - Machine Learning ,Image and Video Processing (eess.IV) ,FOS: Electrical engineering, electronic engineering, information engineering ,Electrical Engineering and Systems Science - Image and Video Processing ,Machine Learning (cs.LG) - Abstract
18F-fluorodeoxyglucose (18F-FDG) Positron Emission Tomography (PET) imaging usually needs a full-dose radioactive tracer to obtain satisfactory diagnostic results, which raises concerns about the potential health risks of radiation exposure, especially for pediatric patients. Reconstructing the low-dose PET (L-PET) images to the high-quality full-dose PET (F-PET) ones is an effective way that both reduces the radiation exposure and remains diagnostic accuracy. In this paper, we propose a resource-efficient deep learning framework for L-PET reconstruction and analysis, referred to as transGAN-SDAM, to generate F-PET from corresponding L-PET, and quantify the standard uptake value ratios (SUVRs) of these generated F-PET at whole brain. The transGAN-SDAM consists of two modules: a transformer-encoded Generative Adversarial Network (transGAN) and a Spatial Deformable Aggregation Module (SDAM). The transGAN generates higher quality F-PET images, and then the SDAM integrates the spatial information of a sequence of generated F-PET slices to synthesize whole-brain F-PET images. Experimental results demonstrate the superiority and rationality of our approach.
- Published
- 2022
37. OPACT: Optimization of Approximate Compressor Tree for Approximate Multiplier
- Author
-
Weihua Xiao, Cheng Zhuo, and Weikang Qian
- Published
- 2022
38. Energy-Efficient Real-Time UAV Object Detection on Embedded Platforms
- Author
-
Zhiguo Shi, Jianing Deng, and Cheng Zhuo
- Subjects
Computer science ,Detector ,Feature extraction ,Real-time computing ,02 engineering and technology ,Energy consumption ,Computer Graphics and Computer-Aided Design ,Object detection ,020202 computer hardware & architecture ,Task (computing) ,0202 electrical engineering, electronic engineering, information engineering ,Task analysis ,Key (cryptography) ,Electrical and Electronic Engineering ,Software ,Efficient energy use - Abstract
The recent technology advancement on unmanned aerial vehicle (UAV) has enabled diverse applications in vision-related outdoor tasks. Visual object detection is a crucial task among them. However, it is difficult to actually deploy detectors on embedded devices due to the challenges among energy consumption, accuracy, and speed. In this article, we address a few key challenges from the platform, application to the system, and propose an energy-efficient system for real-time UAV object detection on an embedded platform. The proposed system can achieve speed of 28.5 FPS and 2.7-FPS/W energy efficiency on the data set from 2018 low-power object detection challenges (LPODCs).
- Published
- 2020
39. Hierarchical saliency mapping for weakly supervised object localization based on class activation mapping
- Author
-
Hongjian Li, Cheng Zhuo, Duan Xiaolin, Meiqi Wang, and Xiangyan Zeng
- Subjects
Computer Networks and Communications ,Computer science ,business.industry ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,020207 software engineering ,Pattern recognition ,02 engineering and technology ,Object (computer science) ,Class (biology) ,Field (computer science) ,Hardware and Architecture ,Salience (neuroscience) ,Video tracking ,0202 electrical engineering, electronic engineering, information engineering ,Media Technology ,Saliency map ,Artificial intelligence ,Pyramid (image processing) ,business ,Software - Abstract
Weakly supervised object localization is a basic research in the field of computer vision. In this paper, a hierarchical saliency mapping network for object localization is proposed and designed to avoid missing detailed information of potential object. Based on the classical convolution network, we remove the fully connected part and add multiple information extraction branches. The network extracts information from convolution layers of different scales to generate Hierarchical Saliency Map. Hierarchical Saliency Maps that include Hierarchical-Class Activation Map and Hierarchical-Spatial Pyramid Saliency Map fuse deep-level features and low-level features to locate object. The datasets used for testing are Caltech-UCSD Birds 200, Caltech101 and ImageNet. Compared with Class Activation Map and Spatial Pyramid Saliency Map, the localization accuracy has been improved. This method can be used for fine-grained classification, object tracking and other fields.
- Published
- 2020
40. Noise-Aware DVFS for Efficient Transitions on Battery-Powered IoT Devices
- Author
-
Shaoheng Luo, Jiang Hu, Houle Gan, Cheng Zhuo, and Zhiguo Shi
- Subjects
Schedule ,business.industry ,Computer science ,Clock rate ,Electrical engineering ,02 engineering and technology ,Computer Graphics and Computer-Aided Design ,Capacitance ,020202 computer hardware & architecture ,0202 electrical engineering, electronic engineering, information engineering ,Electrical and Electronic Engineering ,Internet of Things ,business ,Software ,Decoupling (electronics) - Abstract
Low power system-on-chips (SoCs) are now at the heart of Internet-of-Things (IoT) devices, which are well-known for their bursty workloads and limited energy storage—usually in the form of tiny batteries. To ensure battery lifetime, dynamic voltage frequency scaling (DVFS) has become an essential technique in such SoC chips. With continuously decreasing supply level, noise margins in these devices are already being squeezed. During DVFS transition, large current that accompanies the clock speed transition runs into or out of clock networks in a few clock cycles, induces large ${\text {L}di}{/}{\mathrm {d}t}$ noise, thereby stressing the power delivery system (PDS). Due to the limited area and cost target, adding additional decoupling capacitance to mitigate such noise is usually challenging. A common approach is to gradually introduce/remove the additional clock cycles to increase/decrease the clock frequency in steps, also known as, clock skipping. However, such a technique may increase DVFS transition time, and still cannot guarantee minimal noise. In this paper, we propose a new noise-aware DVFS sequence optimization technique by formulating a mixed 0/1 programming to resolve the problems of clock skipping sequence optimization. Moreover, the method is also extended to schedule extensive wake-up activities on different clock domains for the same purpose. The experiments show that the optimized sequence is able to significantly mitigate noise within the desired transition time, thereby saving both power and energy.
- Published
- 2020
41. Spatio-Temporal Deformable Convolution for Compressed Video Quality Enhancement
- Author
-
Cheng Zhuo, Jianing Deng, Li Wang, and Shiliang Pu
- Subjects
Motion compensation ,Compression artifact ,Computer science ,business.industry ,Deep learning ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Optical flow ,General Medicine ,Video quality ,Optical flow estimation ,Computer vision ,Artificial intelligence ,business ,Reference frame - Abstract
Recent years have witnessed remarkable success of deep learning methods in quality enhancement for compressed video. To better explore temporal information, existing methods usually estimate optical flow for temporal motion compensation. However, since compressed video could be seriously distorted by various compression artifacts, the estimated optical flow tends to be inaccurate and unreliable, thereby resulting in ineffective quality enhancement. In addition, optical flow estimation for consecutive frames is generally conducted in a pairwise manner, which is computational expensive and inefficient. In this paper, we propose a fast yet effective method for compressed video quality enhancement by incorporating a novel Spatio-Temporal Deformable Fusion (STDF) scheme to aggregate temporal information. Specifically, the proposed STDF takes a target frame along with its neighboring reference frames as input to jointly predict an offset field to deform the spatio-temporal sampling positions of convolution. As a result, complementary information from both target and reference frames can be fused within a single Spatio-Temporal Deformable Convolution (STDC) operation. Extensive experiments show that our method achieves the state-of-the-art performance of compressed video quality enhancement in terms of both accuracy and efficiency.
- Published
- 2020
42. Dynamic Frequency Scaling Aware Opportunistic Through-Silicon-Via Inductor Utilization in Resonant Clocking
- Author
-
Cheng Zhuo, Leibo Liu, Yiyu Shi, and Umamaheswara Rao Tida
- Subjects
Through-silicon via ,Maximum power principle ,Computer science ,Dynamic frequency scaling ,Integrated circuit ,Inductor ,Computer Graphics and Computer-Aided Design ,Noise (electronics) ,law.invention ,Inductance ,Capacitor ,law ,Electronic engineering ,Electrical and Electronic Engineering ,Software - Abstract
LC resonant clock is a viable option for low power on-chip clock distributions. A major limiting factor to its implementation is the large area overhead due to the use of conventional spiral inductors. On the other hand, idle through-silicon-vias (TSVs) in 3-D integrated circuits (3-D ICs) can form vertical inductors with minimal footprint and have little noise coupling with horizontal traces, particularly suitable for the application of LC resonant clock. However, due to the strict constraints on the location of idle TSVs, the use of the TSV inductor is constrained by its location, inductance, and quality factor. The problem is further complicated by dynamic frequency scaling (DFS), where the resonant tanks need to accommodate multiple clock frequencies. Moreover, these TSV inductors can be in any orientation with any distance apart, thereby causing complicated coupling effects. In this paper, we first present a novel scheme to opportunistically use idle TSVs to form inductors in LC resonant clock of 3-D ICs for maximum power reduction in clock-distribution network (CDN) at a fixed frequency, and then extend it to DFS schemes. Experimental results on a few industrial designs for the resonant CDNs operated at a fixed frequency of 3 GHz show that the power consumption is reduced by up to 47.9% compared with the conventional CDNs without resonant clocking. In addition, for the resonant CDNs with DFS scheme, the power consumption reduced by up to 42.3%, 39.0%, 38.3%, 34.3%, and 28.6% at 3, 2.5, 2, 1.5, and 1 GHz frequency, respectively, compared with the CDNs without resonant clocking. When compared with CDNs with conventional spiral inductors, our scheme with TSV inductors can reduce the inductor footprint by up to $6.30 \times$ with the same power consumption.
- Published
- 2020
43. Early-Stage Planning of Switched-Capacitor Converters in a Heterogeneous Chip
- Author
-
Lu Wang, Cheng Zhuo, Leilei Wang, and Pingqiang Zhou
- Subjects
General Computer Science ,Computer science ,Hardware_PERFORMANCEANDRELIABILITY ,02 engineering and technology ,Capacitance ,MIM capacitance ,law.invention ,multi-core ,law ,Hardware_INTEGRATEDCIRCUITS ,0202 electrical engineering, electronic engineering, information engineering ,Electronic engineering ,Overhead (computing) ,General Materials Science ,Multi-core processor ,Hardware_MEMORYSTRUCTURES ,020208 electrical & electronic engineering ,General Engineering ,Converters ,Chip ,Switched capacitor ,020202 computer hardware & architecture ,Capacitor ,Energy efficiency ,switched-capacitor converter ,lcsh:Electrical engineering. Electronics. Nuclear engineering ,Voltage regulation ,lcsh:TK1-9971 ,Efficient energy use - Abstract
The switched-capacitor converter (SCC) has been widely used for voltage regulation in multicore chips, where energy efficiency is the major concern. However as the overhead to integrate SCCs in a chip is non-negligible, the SCCs could not be overused. Hence in this paper we propose an early stage SCCs planning framework to obtain the SCC supply scheme together with the optimized Metal-Insulator-Metal (MIM) capacitance allocation and converter ratio selection for each SCC when the given number of SCCs is less than the number of cores . Besides, our method could also explore to find the best number of used SCCs for a given chip. The experiments show the results of our SCC planning methods.
- Published
- 2020
44. Application of Deep Learning in Back-End Simulation: Challenges and Opportunities
- Author
-
Yufei Chen, Haojie Pei, Xiao Dong, Zhou Jin, and Cheng Zhuo
- Published
- 2022
45. Growth optimization and device integration of narrow-bandgap graphene nanoribbons
- Author
-
Gabriela Borin Barin, Qiang Sun, Marco Di Giovannantonio, Cheng‐Zhuo Du, Xiao‐Ye Wang, Juan Pablo Llinas, Zafer Mutlu, Yuxuan Lin, Jan Wilhelm, Jan Overbeck, Colin Daniels, Michael Lamparski, Hafeesudeen Sahabudeen, Mickael L. Perrin, José I. Urgel, Shantanu Mishra, Amogh Kinikar, Roland Widmer, Samuel Stolz, Max Bommert, Carlo Pignedoli, Xinliang Feng, Michel Calame, Klaus Müllen, Akimitsu Narita, Vincent Meunier, Jeffrey Bokor, Roman Fasel, and Pascal Ruffieux
- Subjects
Condensed Matter - Materials Science ,field-effect transistors ,ddc:530 ,Materials Science (cond-mat.mtrl-sci) ,FOS: Physical sciences ,on-surface synthesis, graphene nanoribbons, scanning tunneling microscopy, temperature programmed X-ray photoelectron spectroscopy, Raman spectroscopy, field-effect transistors ,temperature programmed X-ray photoelectron spectroscopy ,General Chemistry ,530 Physik ,Biomaterials ,Raman spectroscopy ,540 Chemistry ,scanning tunneling microscopy ,570 Life sciences ,biology ,on-surface synthesis ,General Materials Science ,graphene nanoribbons ,Biotechnology - Abstract
The electronic, optical, and magnetic properties of graphene nanoribbons (GNRs) can be engineered by controlling their edge structure and width with atomic precision through bottom-up fabrication based on molecular precursors. This approach offers a unique platform for all-carbon electronic devices but requires careful optimization of the growth conditions to match structural requirements for successful device integration, with GNR length being the most critical parameter. In this work, the growth, characterization, and device integration of 5-atom wide armchair GNRs (5-AGNRs) are studied, which are expected to have an optimal bandgap as active material in switching devices. 5-AGNRs are obtained via on-surface synthesis under ultrahigh vacuum conditions from Br- and I-substituted precursors. It is shown that the use of I-substituted precursors and the optimization of the initial precursor coverage quintupled the average 5-AGNR length. This significant length increase allowed the integration of 5-AGNRs into devices and the realization of the first field-effect transistor based on narrow bandgap AGNRs that shows switching behavior at room temperature. The study highlights that the optimized growth protocols can successfully bridge between the sub-nanometer scale, where atomic precision is needed to control the electronic properties, and the scale of tens of nanometers relevant for successful device integration of GNRs.
- Published
- 2022
- Full Text
- View/download PDF
46. RT-DNAS: Real-Time Constrained Differentiable Neural Architecture Search for 3D Cardiac Cine MRI Segmentation
- Author
-
Qing Lu, Xiaowei Xu, Shunjie Dong, Cong Hao, Lei Yang, Cheng Zhuo, and Yiyu Shi
- Published
- 2022
47. VirtualSync+: Timing Optimization with Virtual Synchronization
- Author
-
Grace Li Zhang, Bing Li, Xing Huang, Xunzhao Yin, Cheng Zhuo, Masanori Hashimoto, and Ulf Schlichtmann
- Subjects
FOS: Computer and information sciences ,Hardware Architecture (cs.AR) ,Electrical and Electronic Engineering ,Computer Science - Hardware Architecture ,Computer Graphics and Computer-Aided Design ,Software ,Hardware_LOGICDESIGN - Abstract
In digital circuit designs, sequential components such as flip-flops are used to synchronize signal propagations. Logic computations are aligned at and thus isolated by flip-flop stages. Although this fully synchronous style can reduce design efforts significantly, it may affect circuit performance negatively, because sequential components can only introduce delays into signal propagations but never accelerate them. In this paper, we propose a new timing model, VirtualSync+, in which signals, specially those along critical paths, are allowed to propagate through several sequential stages without flip-flops. Timing constraints are still satisfied at the boundary of the optimized circuit to maintain a consistent interface with existing designs. By removing clock-to-q delays and setup time requirements of flip-flops on critical paths, the performance of a circuit can be pushed even beyond the limit of traditional sequential designs. In addition, we further enhance the optimization with VirtualSync+ by fine-tuning with commercial design tools, e.g., Design Compiler from Synopsys, to achieve more accurate result. Experimental results demonstrate that circuit performance can be improved by up to 4% (average 1.5%) compared with that after extreme retiming and sizing, while the increase of area is still negligible. This timing performance is enhanced beyond the limit of traditional sequential designs. It also demonstrates that compared with those after retiming and sizing, the circuits with VirtualSync+ can achieve better timing performance under the same area cost or smaller area cost under the same clock period, respectively.
- Published
- 2022
- Full Text
- View/download PDF
48. LQoCo: Learning to Optimize Cache Capacity Overloading in Storage Systems
- Author
-
Zhang, Ji, Li, Xijun, Zhou, Xiyao, Yuan, Mingxuan, Cheng, Zhuo, Huang, Keji, and Li, Yifan
- Subjects
FOS: Computer and information sciences ,Hardware_MEMORYSTRUCTURES ,Artificial Intelligence (cs.AI) ,Computer Science - Artificial Intelligence ,Hardware Architecture (cs.AR) ,FOS: Electrical engineering, electronic engineering, information engineering ,Systems and Control (eess.SY) ,Computer Science - Hardware Architecture ,Electrical Engineering and Systems Science - Systems and Control - Abstract
Cache plays an important role to maintain high and stable performance (i.e. high throughput, low tail latency and throughput jitter) in storage systems. Existing rule-based cache management methods, coupled with engineers' manual configurations, cannot meet ever-growing requirements of both time-varying workloads and complex storage systems, leading to frequent cache overloading. In this paper, we for the first time propose a light-weight learning-based cache bandwidth control technique, called \LQoCo which can adaptively control the cache bandwidth so as to effectively prevent cache overloading in storage systems. Extensive experiments with various workloads on real systems show that LQoCo, with its strong adaptability and fast learning ability, can adapt to various workloads to effectively control cache bandwidth, thereby significantly improving the storage performance (e.g. increasing the throughput by 10\%-20\% and reducing the throughput jitter and tail latency by 2X-6X and 1.5X-4X, respectively, compared with two representative rule-based methods)., Comment: This paper has been accepted by DAC 2022. Xijun is the correspoonding author
- Published
- 2022
- Full Text
- View/download PDF
49. Otfpf: Optimal Transport Based Feature Pyramid Fusion Network for Brain Age Estimation
- Author
-
Yu Fu, Yanyan Huang, Zhe Zhang, Shunjie Dong, Le Xue, Meng Niu, Yunxin Li, Zhiguo Shi, Yalin Wang, Hong Zhang, Mei Tian, and Cheng Zhuo
- Published
- 2022
50. FeFET Based In-Memory Hyperdimensional Encoding Design
- Author
-
Qingrong Huang, Zeyu Yang, Kai Ni, Mohsen Imani, Cheng Zhuo, and Xunzhao Yin
- Subjects
Electrical and Electronic Engineering ,Computer Graphics and Computer-Aided Design ,Software - Published
- 2023
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.