检索结果-内蒙古大学图书馆

31st IEEE International Symposium on High Performance computer Architecture, HPCA 2025

作者： Lee, Jiwon Ko, Gun Yoon, Myung Kuk Jeong, Ipoom Oh, Yunho Ro, Won Woo Ewha Womans University Department of Computer Science and Engineering Seoul Korea Republic of Yonsei University Department of System Semiconductor Engineering Seoul Korea Republic of Yonsei University Department of Electrical and Electronic Engineering Seoul Korea Republic of Korea University School of Electrical Engineering Seoul Korea Republic of

ISBN: (纸本)9798331506476

Virtual memory, with the support of address translation hardware, is a key technique in expanding programmability and memory management in GPUs. However, the nature of the GPU execution model heavily pressures its translation hardware, particularly due to a discrepancy in the behavior of page table walkers and thousands of concurrently running threads. In GPU workloads, multiple threads simultaneously access a number of pages necessitating a substantial number of translations whereas each walker handles only a single walk request at a time. Such a limitation significantly increases the queueing latency of walk requests, which we observe as a major bottleneck for servicing page table walks in GPUs. To tackle this challenge, we investigate a design of page walkers that facilitates multiple walk requests to be handled together in batches. Then, we make the following observations: 1) allowing a page walker to issue beyond a single memory request significantly improves the throughput of walkers, and 2) GPU applications tend to concurrently access pages in wide address ranges. By leveraging the above implications, we propose Marching Page Walks (MPW) that effectively mitigate the contention in GPU page table walkers. MPW scans pending walk requests to identify ones that can be grouped together. Then, MPW batches these requests and concurrently handles them by issuing multiple memory instructions. Experiments show that MPW reduces the queueing latency of page walks by 86.7% and improves GPU performance by 55.6% over the baseline design. © 2025 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Sustainable Optimization of Construction Project Portfolio Management Through a Data-Driven Approach 2nd

Sustainable Optimization of Construction Project Portfolio ...

引用

2nd Decision science Alliance International Summer Conference, DSA ISC 2024

作者： Lostumbo, Marisa A. Iniesta, Marc Bara Calvet, Laura Computer Science Department Universitat Oberta de Catalunya Barcelona Spain EAE Business School Barcelona Spain Telecommunication and System Engineering Department Universitat Autónoma de Barcelona Sabadell Spain

ISBN: (纸本)9783031782374

Effective management of construction project portfolios demands informed decisions driven by data and mathematical models, aiming to enhance decision-making and address complex decision problems. This article introduces an innovative approach that prioritizes sustainability criteria selection, utilizing data-driven insights and mathematical optimization to optimize project portfolio management. Through multi-objective optimization, our study targets improved resource efficiency, time reduction, and minimized environmental impact, offering portfolio managers a powerful tool for decision-making. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Project management

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Workload Prediction and Distribution in Cloud Computing using Deep Reinforcement Learning and LSTM

引用

Journal of Harbin Institute of Technology(New series) 2025年

作者： Nampally Vijay Kumar Satarupa Mohanty Prasant Kumar Pattnaik School of Computer Engineering KIIT Deemed to be University Department of Computer Science and Business System B V RAJU Institute of Technology

Maintaining high-quality service supply and sustainability in modern cloud computing is essential to ensuring optimal system performance and energy efficiency. A novel approach is introduced in this study to decrease a system.s overall delay and energy consumption by utilising a deep reinforcement learning(DRL)model to predict and allocate incoming workloads flexibly. The proposed methodology integrates workload prediction utilising long short-term memory(LSTM)networks with efficient load-balancing techniques led by deep Q-learning and Actor-Critic algorithms. By continuously analysing current and historical data,the model can efficiently allocate resources,prioritizing speed and energy preservation. The experimental findings demonstrate that our load balancing system,which utilises DRL,significantly reduces average response times and energy usage compared to traditional methods. This approach provides a scalable and adaptable strategy for enhancing cloud infrastructure performance. It consistently provides reliable and durable performance across a range of dynamic workloads.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Online Credibility Assessment of Equipment Digital Twin for Discrete Manufacturing

引用

IEEE Transactions on Automation science and engineering 2025年 22卷 14763-14774页

作者： Lu, Han Zhang, Lin Deen, M. Jamal Wang, Kunyu Cheng, Hongbo Yang, Laurence T. Beihang University Hangzhou International Innovation Institute Zhejiang 311115 China Beihang University School of Automation Science and Electrical Engineering Beijing100191 China State Key Laboratory of Intelligent Manufacturing System Technology Beijing100854 China AI Atlas Inc Canada Zhengzhou University School of Computer and Artificial Intelligence School of Software Engineering Zhengzhou China St. Francis Xavier University Department of Computer Science Antigonish Canada

The equipment digital twins (EDTs) for discrete manufacturing should be calibrated quickly to avoid irreversible physical damage to the equipment caused by biased control commands. Therefore, an online credibility assessment method for EDTs is urgently needed. However, existing assessment approaches consume too much time, and thus could not reveal dynamic faults in time. In this paper, the dynamic relationship between online evolution and actual applications of EDTs is investigated. Then, two steps are proposed to accelerate the assessment process significantly. One involves pre-constructing a performance-deviation-agent (PDA), and the other involves dynamically fitting the application-time-window (ATW) probability distribution. The methodology is applicable to discrete manufacturing processes. The dynamic credibility of EDT evolution process can be updated after every iteration of the model evolution. Sorting manufacturing equipment was used as a case study to demonstrate the effectiveness of this method. The time consumption was reduced by 90% compared with traditional assessment methods in the case. © 2025 IEEE.

关键词： Fabrication

来源：评论

学校读者我要写书评

暂无评论

FDSOI-Based Reconfigurable FETs: A Ferroelectric Approach

引用

IEEE Transactions on Nanotechnology 2025年 24卷 277-281页

作者： Lee, Donghyeok Das, Suprem R. Kwon, Jiseok Chang, Jiwon Yonsei University Department of System Semiconductor Engineering Department of Materials Science and Engineering Seoul03722 Korea Republic of Kansas State University Department of Industrial and Manufacturing Systems Engineering Department of Electrical and Computer Engineering ManhattanKS66506 United States The Catholic University of Korea School of Information Communications and Electronic Engineering Gyeonggi-do14662 Korea Republic of

In this study, we propose ferroelectric-based reconfigurable field-effect transistors (FeRFETs) that utilizes the structure of a fully depleted silicon-on-insulator field-effect transistors (FDSOI FETs). In FeRFETs, the non-volatile and reconfigurable electrostatic doping facilitated by ferroelectric enables type conversion. Through the TCAD simulations calibrated with the experimental data, we confirm a reconfigurable high doping level (> 1×1021 cm-3), a clear type conversion and highly tunable performance in FeRFETs. It is also found that carefully tailoring coercive field (EC) is important to maximize the performance of FeRFETs. © 2002-2012 IEEE.

关键词： Reconfigurable hardware

来源：评论

学校读者我要写书评

暂无评论

Warped-Compaction: Maximizing GPU Register File Bandwidth Utilization via Operand Compaction 31

Warped-Compaction: Maximizing GPU Register File Bandwidth Ut...

引用

31st IEEE International Symposium on High Performance computer Architecture, HPCA 2025

作者： Jeong, Eunbi Jeong, Ipoom Yoon, Myung Kuk Kim, Nam Sung Ewha Womans University Department of Computer Science and Engineering Seoul Korea Republic of Yonsei University Department of System Semiconductor Engineering Seoul Korea Republic of Yonsei University Department of Electrical and Electronic Engineering Seoul Korea Republic of University of Illinois Urbana-Champaign Urbana United States

ISBN: (纸本)9798331506476

The GPU has been successfully used for diverse emerging compute-intensive applications, including imaging, computer vision, and more recently, deep learning, to name a few. To offer high performance for such applications, it is provisioned with massive Register Files (RFs) to exploit high Thread-Level Parallelism (TLP). As RFs are designed to store thousands of contexts and provide very high bandwidth for uninterrupted supply of operands to hundreds of compute units for high TLP, they have become one of the most power-hungry components in the GPU. Meanwhile, faced with the end of Dennard scaling, it is more important than ever to innovate the microarchitecture of (power-constrained) GPUs to continuously improve the performance of future compute-intensive *** this work, we propose a GPU microarchitecture, WarpedCompaction, designed to utilize given RFs more efficiently, instead of relying on larger-capacity and/or higher-bandwidth RFs to further improve GPU performance. Specifically, first, we reverse-engineer the latest GPU's RF organization through microbenchmarking. This uncovers that each sub-core within a streaming multiprocessor contains only two dual-ported RF banks, and accesses to these banks are arbitrated solely based on register IDs. We also reveal that, despite the modest configurations, RF banks are largely underutilized, staying inactive for 33.5% of the time. Second, we observe that previously proposed RF optimization techniques, data forwarding and dead register elimination, cannot address this underutilization problem. This is mainly due to the (R1) insufficient RF access requests from a limited number of Operand Collector Units (OCUs) and (R2) inefficient operand distribution by the conventional RF bank arbitration. Third, we present two architectural solutions to tackle the observed inefficiency: (S1) OCU sharing and (S2) skewed arbitrator. Building on enhanced OCU early allocation for partially ready instructions and operand forwardin

关键词： Compaction

来源：评论

学校读者我要写书评

暂无评论

Leveraging Cross-Project Similarity for Data Augmentation and Security Bug Report Prediction

引用

IEEE Access 2025年 13卷 80416-80428页

作者： Ji, Jinfeng Yang, Geunseok Hankyong National University Department of Computer Science and Engineering Korea Republic of Hankyong National University Computer System Institute Department of Computer Applied Mathematics Korea Republic of

Introduction: Bug reports are typically classified into two categories: security and non-security. However, due to the varying levels of expertise among bug reporters, some security-related bug reports are misclassified as non-security, leading to an increased workload for developers and potential security risks. This issue highlights the need for an effective method to identify security bug reports. Methods: To address this challenge, we propose a predictive approach that based deep learning models for security bug report classification. We extract data from four open-source projects—Ambari, Camel, Derby, and Wicket—containing 56, 74, 179, and 47 security bug reports, respectively, alongside 944, 926, 821, and 953 non-security reports. Given the imbalanced dataset, we employ cross-project similarity-based data augmentation to enhance model training. We evaluate multiple deep learning models, including CNN, LSTM, GRU, Transformer, and BERT, to improve classification accuracy. Results: The experimental results demonstrate the effectiveness of our approach, achieving F1 scores ranging from 0.60 to 0.98. LSTM on Ambari and GRU on both Ambari and Camel achieved the highest performance of 0.98. The overall average F1 score across all models and datasets is 0.77, indicating a notable improvement in classification accuracy. Discussion: The results suggest that cross-project data augmentation effectively mitigates the class imbalance issue and enhances model performance. The variation in F1 scores across different models and datasets highlights the impact of model selection on classification effectiveness. LSTM and GRU consistently outperform other models, demonstrating their suitability for security bug classification tasks. Conclusion: Incorporating cross-project similarity-based data augmentation significantly improves the identification of security bug reports. This approach can help developers more effectively detect security-related issues, reducing misclassification

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Prescribing Decision Conservativeness in Two-Stage Power Markets: A Distributionally Robust End-to-End Approach 59

Prescribing Decision Conservativeness in Two-Stage Power Mar...

引用

59th Annual Conference on Information sciences and systems, CISS 2025

作者： Liang, Zhirui Li, Qi Liu, Anqi Dvorkin, Yury Johns Hopkins University Department of Applied Mathematics and Statistics BaltimoreMD United States Johns Hopkins University Department of Computer Science BaltimoreMD United States Johns Hopkins University Department of Electrical and Computer Engineering BaltimoreMD United States Johns Hopkins University Department of Civil and System Engineering BaltimoreMD United States

ISBN: (纸本)9798331513269

This paper presents an end-to-end framework for calibrating wind power forecast models to minimize operational costs in two-stage power markets, where the first stage involves a distributionally robust optimal power flow (DR-OPF) model. Unlike traditional methods that adjust forecast parameters and uncertainty quantification (UQ) separately, this framework jointly optimizes both the forecast model parameters and the decision conservativeness, which determines the size of the ambiguity set in the DR-OPF model. The framework aligns UQ with actual uncertainty realizations by directly optimizing downstream operational costs, a process referred to as cost-oriented calibration. The calibration is achieved using a gradient descent approach. To enable efficient differentiation, the DR-OPF problem is reformulated into a convex form, and the Envelope Theorem is leveraged to simplify gradient derivation in the two-stage setting. Additionally, the framework supports distributed implementation, effectively reducing computational overhead and enhancing efficiency. By proactively calibrating forecast parameters and prescribing optimal decision conservativeness, the framework significantly enhances cost efficiency and reliability in power system operations. Numerical experiments on an IEEE 5-bus system demonstrate the effectiveness and efficiency of the proposed approach. © 2025 IEEE.

关键词： Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis of Hate Speech Detection and Recognition Utilising Advanced Machine Learning Algorithms and Techniques

A Comprehensive Analysis of Hate Speech Detection and Recogn...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Praveen Kumar Mannepalli Saurabh Sharma Neha Rajput Sanjay Kalamdhad Department of Computer Science & Engineering Chandigarh University Mohali Department of Computer Science and Engineering Chandigarh University Mohali India Department of Computer Science and Engineering Chandigarh University Punjab Department of Computer Science & Business System St. Vincent Pallotti College of Engineering and Technology Nagpur

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

Social networking sites have come into demand as a way of sharing ideas and opinions with other people. But unfortunately, people tend to misuse social media to write nasty comments. Victims' lives might be negatively impacted by behaviours that are abusive and humiliating. Social networks give people a great tool to share information on ideas on multiple topics and opinions. However, these platforms are often abused to announce toxic and offensive comments, which eventually negatively affect victims and demographics. This study offers a thorough method for identifying hate speech (HS) on social media by utilising cutting-edge ML algorithms. A publicly available Twitter dataset containing 159,571 tweets classified into six categories, including toxic and identity hatred, was utilised. The methodology comprises data collection, conditioning, and categorisation that employs BiLSTM, which is particularly appropriate for the tasks demanding contextual sensitivity. These operations include symbol removing, stemming and stop-word eliminating, feature extraction using TF-IDF, and using the Bag-of-Words model. For classification of the data between hate and non-hate, the dataset is then split into training and testing datasets and the BiLSTM model used to provide classifications for the text. The evaluation of the BiLSTM model demonstrates superior performance, achieving an accuracy86%, a precision90%, a recall86%, and an F1-score88% • A comparison between the model and other models such as SVM and CNN reveals the strength of the BiLSTM in contextual classification tasks. The results demonstrate that BiLSTM can tackle problems with hate speech detection, providing a strong answer to the problem of harmful content on social media and helping to make the internet a better place for everyone.

关键词： Training Support vector machines Social networking (online) Text recognition Hate speech Bidirectional long short term memory Symbols Speech recognition Context modeling Testing

来源：评论

学校读者我要写书评

暂无评论

Real-Time Myanmar Hand Gestures Recognition Using Deep Learning Models 8th

Real-Time Myanmar Hand Gestures Recognition Using Deep Learn...

引用

8th International Conference on Intelligent Technologies, ICIT 2023

作者： Kyaw, Nwe Ni Mitra, Pabitra Sinha, G.R. Department of Computer Science and Engineering Indian Institute of Technology Kharagpur West Bengal721302 India Indian Knowledge System Lab International Institute of Information Technology Bangalore Karnataka Bengaluru560100 India

ISBN: (纸本)9789819738588

The proposed system for recognizing Myanmar sign language between individuals who are deaf. The aim of this study is to develop deep learning models for the purpose of accurately identifying dynamic hand gesture images depicting 14 classes of Myanmar words and numbers. The present system utilizes a new dataset comprising 7834 images for 14 classes obtained through Webcam. The objective of this study is to enhance the robustness of the new model. Next, we proceed to evaluate the proposed model by comparing them to those of existing convolutional neural network models. These models are generally recognized as effective deep-learning approaches for recognition tasks. The proposed model exhibits a performance level of 96% for both validation and testing accuracies. Furthermore, the experimental finding demonstrates that the model, convolutional layers, achieved an accuracy of 100% in recognizing Myanmar Sign Language (MSL). © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：