检索结果-内蒙古大学图书馆

International Conference on computer and Communications (ICCC)

作者： Bowen Zheng Fan Yang Cenman Wang Ye Tian Anhui Key Laboratory on High Performance Computing School of Computer Science and Technology University of Science and Technology of China Hefei China

ISBN: (数字)9798331507077

ISBN: (纸本)9798331507084

Combining optical circuit switches (OCSes) and electrical packet switches (EPSes) has emerged as an appealing architecture for data centers. However, in this hybrid data center network architecture with widespread application, challenges persist in data packet scheduling and buffer management for OCS-based matching patterns due to spatial and temporal traffic pattern constraints. Given the demand-agnostic way for OCS configurations, where each switch can only provide matching between input and output ports at any given time. In other words, the availability of optical circuits is intermittent, resulting in potential blockage of flows between them when optical circuits are unavailable. Traditionally, in the event of flow blockage, multiple queue buffers are maintained at Top-of- Rack (ToR) switches, with the number of queues corresponding to the number of destinations. Unfortunately, the “per-destination queue” approach suffers from poor scalability. To address this issue, we propose HSToR, a novel design for ToR switches, aimed at enhancing scalability and data transfer efficiency in optical circuit switched networks. Experimental results demonstrate that HSToR achieves high scalability, maintains lower latency as the network scales, better addresses packet loss during buffering, and sustains high throughput and link utilization.

关键词： Integrated optics Scheduling algorithms Optical switches Scalability Optical buffering Packet loss Optical fiber networks Throughput Optical packet switching Switching circuits

来源：评论

学校读者我要写书评

暂无评论

Accurate Detection of Superspreaders on Multi-Pipeline Switches

Accurate Detection of Superspreaders on Multi-Pipeline Switc...

引用

International Conference on computer and Communications (ICCC)

作者： Cenman Wang Bowen Zheng Fan Yang Ye Tian Anhui Key Laboratory on High Performance Computing School of Computer Science and Technology University of Science and Technology of China Hefei China

ISBN: (数字)9798331507077

ISBN: (纸本)9798331507084

In various network monitoring tasks, the detection of superspreaders has become increasingly crucial. However, latest superspreader detection algorithms and data structures assume the target switch with a single pipeline, while state-of-the-art programmable switches actually comprise multiple independent pipelines. In current method for deploying super-spreader detection applications on multi-pipeline switches, a separate measurement data structure instance is employed for each pipeline. However, under multi-path routing, this simplistic approach leads to lower detection accuracy due to hash collisions. To address this issue, in this paper, we present PipelineAlloc, a HyperLogLog-based superspreader detection system designed for multi-pipeline switches. In order to reduce hash collisions in measurement data structures, PipelineAlloc assigns an egress pipeline as the monitor pipeline for each source IP address. PipelineAlloc introduces novel measurement data structures in the ingress pipelines for temporarily storing statistics of the source and destination IP addresses of packets, and uses packets to carry these measurement data to egress pipelines, which serve as the monitor pipelines. The HyperLogLog-based measurement data structures in egress pipelines are updated using data carried by packets. Experiments driven by real-world traffic traces show that PipelineAlloc outperforms existing solutions in terms of detection accuracy.

关键词： Accuracy Scalability Current measurement Pipelines Switches Data structures Routing IP networks Detection algorithms Monitoring

来源：评论

学校读者我要写书评

暂无评论

Coupled-mode phase matching on a silicon chip

引用

Physical Review A 2025年第3期111卷 033504-033504页

作者： Chao Wu Pingyu Zhu Miaomiao Yu Weihong Luo Qilin Zheng Kaikai Zhang Yingwen Liu Ping Xu Institute for Quantum Information & State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha 410073 China Hefei National Laboratory Hefei 230088 China

Phase matching lies at the heart of the classical nonlinear process for frequency conversion and all-optical processing, as well as the spontaneous parametric process for the quantum light sources generation. In this work, we experimentally demonstrate the coupled-mode phase-matching (CMPM) engineered by the two-paralleled-coupled waveguides on a silicon-on-insulator (SOI) chip, extending the converted beam and entangled photons to the S band and L band. We measure the spectrum and efficiency of wavelength conversion, which successfully validates the designed CMPM scheme. We further measure the pairs generation rate of the biphoton based on the spontaneous four-wave mixing, which features a narrow bandwidth consistent well with the theoretical simulations. Multiple CMPM conditions can be achieved by exploiting the combinations of even and odd supermodes of the coupled system and tuned by designing a proper coupling gap between the two waveguides. The CMPM can extend the FWM nonlinear process ranging from the O band to the U band and even the midinfrared, enriching the working wavelength to a large extent. In addition, the CMPM features a discrete-band narrow bandwidth, which will greatly enhance the encoding density of frequency and the spectral purity of generated photon. In addition, our methods can be easily extended to a wide range of materials such as silicon nitride, dispensing with the dispersion engineering for phase matching.

关键词： Silicon nitride

来源：评论

学校读者我要写书评

暂无评论

Generative Methods for Out-of-distribution Prediction and Applications for Threat Detection and Analysis: A Short Review 1st

Generative Methods for Out-of-distribution Prediction and Ap...

引用

1st International Workshop on Digital Sovereignty in Cyber Security: New Challenges in Future Vision, CyberSec4Europe 2022

作者： Coppolillo, Erica Liguori, Angelica Guarascio, Massimo Pisani, Francesco Sergio Manco, Giuseppe Department of Mathematics and Computer Science University of Calabria Rende Italy Department of Computer Engineering Modeling Electronics an d Systems University of Calabria Rende Italy Institute for High Performance Computing and Networking of Italian National Research Council Rende Italy

ISBN: (纸本)9783031360954

In recent times, Machine Learning has played an important role in developing novel advanced tools for threat detection and mitigation. Intrusion Detection, Misinformation, Malware, and Fraud Detection are just some examples of cybersecurity fields in which Machine Learning techniques are used to reveal the presence of malicious behaviors. However, Out-of-Distribution, i.e., the potential distribution gap between training and test set, can heavily affect the performances of the traditional Machine Learning based methods. Indeed, they could fail in identifying out-of-samples as possible threats, therefore devising robust approaches to cope with this issue is a crucial and relevant challenge to mitigate the risk of undetected attacks. Moreover, a recent emerging line proposes to use generative models to yield synthetic likely examples to feed the learning algorithms. In this work, we first survey recent Machine Learning and Deep Learning based solutions to face both the problems, i.e., outlier detection and generation;then we illustrate the main cybersecurity application scenarios in which these approaches have been adopted successfully. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Disentangled latent factors for muti-cause treatment effect estimation 6

Disentangled latent factors for muti-cause treatment effect ...

引用

2024 6th International Conference on Artificial Intelligence Technologies and Applications, ICAITA 2024

作者： Zhao, Zhuoyue Wang, Haotian Xu, Liyang Wang, Qian Tang, Yuhua Department of Intelligent Data Science National University of Defense Technology Changsha410073 China Intelligent Game and Decision Lab. Academy of Military Science Beijing100071 China Institute for Quantum Information State Key Laboratory of High-Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha410073 China

Existing methods estimate treatment effects from observational data and assume that covariates are all confounders. However, observed covariates may not directly represent confounding variables that influence both treatment and outcome. They always include variables that only affect the treatment or the outcome. In addition, for multi-dimensional binary treatments, disentangled methods are mainly designed for binary variables and ignore the impact of multi-cause treatment variables on the inference of latent factors. To address these two issues, based on variable decomposition and proxy inference, we propose the Disentangled Latent Factors for Multi-cause Treatment Estimation (DEMTE) algorithm. It utilizes an identifiable autoencoder to infer and disentangle latent factors based on the joint distribution of variables in observational data. DEMTE evaluates the treatment effect on the disentangled factors. Synthetic experiments and semi-synthetic experiments demonstrate the effectiveness of the inference and disentanglement techniques and our method achieves more accurate treatment effect estimation. © 2024 Institute of Physics Publishing. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluating Energy Efficiency of GPUs using Machine Learning Benchmarks

Evaluating Energy Efficiency of GPUs using Machine Learning ...

引用

IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum (IPDPSW)

作者： Brett Foster Shubbhi Taneja Joseph Manzano Kevin Barker Department of Computer Science Worcester Polytechnic Institute High Performance Computing Group Pacific Northwest National Laboratory

As we enter the exascale era, the energy efficiency and performance of high-performance computing (HPC) systems, especially running Machine Learning (ML) applications, are becoming increasingly important. Nvidia recently released its 9th-generation HPC-grade Graphics Processing Unit (GPU) microarchitecture, Ampere, claiming significant improvements over the previous generation’s Volta architecture. In this paper, we perform fine-grained power collection and assess the performance of these two HPC architectures’ performance by profiling ML benchmarks. In addition, we analyze various hyperparameters, primarily the batch size and the number of GPUs, to determine their impact on these systems’ performance and power efficiency. While Ampere is 3.16x more energy-efficient than Volta in isolation, this is counteracted by the PCIe interconnects of the A100s as the ML tasks are parallelized to run on more GPUs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Investigation of metabolic pathways from gut microbiome analyses regarding type 2 diabetes mellitus using artificial neural networks

引用

Discover Artificial Intelligence 2023年第1期3卷 19页

作者： Siptroth, Julienne Moskalenko, Olga Krumbiegel, Carsten Ackermann, Jörg Koch, Ina Pospisil, Heike High Performance Computing in Life Sciences Technical University of Applied Sciences Wildau Wildau15745 Germany BIOMES NGS GmbH Schwartzkopfstraße 1 Wildau15745 Germany Department of Molecular Bioinformatics Institute of Computer Science Goethe University Frankfurt Frankfurt am Main60325 Germany

Background: Type 2 diabetes mellitus is a prevalent disease that contributes to the development of various health issues, including kidney failure and strokes. As a result, it poses a significant challenge to the worldwide healthcare system. Research into the gut microbiome has enabled the identification and description of various diseases, with bacterial pathways playing a critical role in this context. These pathways link individual bacteria based on their biological functions. This study deals with the classification of microbiome pathway profiles of type 2 diabetes mellitus patients. Methods: Pathway profiles were determined by next-generation sequencing of 16S rDNA from stool samples, which were subsequently assigned to bacteria. Then, the involved pathways were assigned by the identified gene families. The classification of type 2 diabetes mellitus is enabled by a constructed neural network. Furthermore, a feature importance analysis was performed via a game theoretic approach (SHapley Additive exPlanations). The study not only focuses on the classification using neural networks, but also on identifying crucial bacterial pathways. Results: It could be shown that a neural network classification of type 2 diabetes mellitus and a healthy comparison group is possible with an excellent prediction accuracy. It was possible to create a ranking to identify the pathways that have a high impact on the model prediction accuracy. In this way, new associations between the alteration of, e.g. a biosynthetic pathway and the presence of diabetes mellitus type 2 disease can also be discovered. The basis is formed by 946 microbiome pathway profiles from diabetes mellitus type 2 patients (272) and healthy comparison persons (674). Conclusion: With this study of the gut microbiome, we present an approach using a neural network to obtain a classification of healthy and type 2 diabetes mellitus and to identify the critical features. Intestinal bacteria pathway profiles form the bas

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

BioNet+: A Comprehensive Interaction Model of Finding Therapeutics for Diseases with Graph Deep Learning 25

BioNet+: A Comprehensive Interaction Model of Finding Therap...

引用

25th IEEE International Conferences on high performance computing and Communications, 9th International Conference on Data science and Systems, 21st IEEE International Conference on Smart City and 9th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC/DSS/SmartCity/DependSys 2023

作者： Ma, Jinglun Qiu, Yanlong Yang, Canqun Wu, Chengkun Institute for Quantum Information State Key Laboratory of High Performance Computing National University of Defense Technology Changsha410073 China College of Computer Science and Techology National University of Defense Technology Changsha410073 China

ISBN: (纸本)9798350330014

The prediction of interactions between biomedical entities is crucial for the discovery of therapeutics for diseases. The fundamental step is to build an interaction model with a comprehensive coverage on literature and curated databases. The massive amount of heterogeneous data in interaction networks of biomedical entities poses significant challenges to relevant prediction tasks. Previous research has mainly focused on constructing networks with limited types of entity relations. In this paper, we construct a large-scale heterogeneous graph model, BioNet+, using a data-driven approach to extract latent information and predict various relations among biomedical entities. BioNet+ provides a crucial update to our previous BioNet model, with the addition of disease entities. The model employs a graph convolution encoder to learn embedding information from the intricate interactions among chemicals (C), genes (G), diseases (D), and biological pathways (P). Furthermore, a decoder that applies two tensor decomposition methods is deployed to predict multiple types of relations, including CG, CD, and GD interactions. The model constructs a graph network consisting of 81,987 entity nodes and 206,195,703 interaction edges. To handle this massive model, BioNet+ reduces the computational complexity via data categorization and proposes a parallel model training algorithm for cross-node GPUs. Evaluation experiments demonstrate that BioNet+ achieves superior predictive performance, as demonstrated by its highest area under the receiver operating characteristic curve (AUROC) of 0.964. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

From Failure to Insight: Analyzing Disk Breakdowns in Large-Scale HPC Environments

From Failure to Insight: Analyzing Disk Breakdowns in Large-...

引用

2024 Workshops of the International Conference for high performance computing, Networking, Storage and Analysis, SC Workshops 2024

作者： George, Anjus Wang, Meng Hanley, Jesse Ransom, Garrett Wilson Bent, John Zimmer, Christopher Oak Ridge National Laboratory National Center for Computational Sciences Oak RidgeTN United States University of Chicago Department of Computer Science ChicagoIL United States Los Alamos National Laboratory HPC Infrastructure Los AlamosNM United States Los Alamos National Laboratory High Performance Computing Los AlamosNM United States

ISBN: (纸本)9798350355543

Disk failure data provides valuable insights for preventing failures, enhancing storage robustness, guiding system design and deployment, and ensuring reliable operations at data centers. This paper introduces two disk failure datasets collected from large-scale HPC production environments over the past five years, comprising over 5,000 failure records from more than 40,000 disks. We analyzed these datasets across multiple dimensions, including temporal, spatial, and relational trends, and performed a comprehensive reliability assessment. Our analysis yielded numerous observations and insights that influence various operational aspects of HPC storage systems. We believe this study offers a holistic understanding of disk failure trends likely to interest the HPC storage community. © 2024 IEEE.

关键词： Cause effect analysis Failure data analysis Hard disk drives HPC storage Reliability Summit Supercomputer

来源：评论

学校读者我要写书评

暂无评论

On Error-Based Step Size Control for Discontinuous Galerkin Methods for Compressible Fluid Dynamics

引用

应用数学与计算数学学报 2025年第1期7卷 3-39页

作者： Hendrik Ranocha Andrew R.Winters Hugo Guillermo Castro Lisandro Dalcin Michael Schlottke-Lakemper Gregor J.Gassner Matteo Parsani Applied Mathematics University of HamburgBundesstr.5520146 HamburgGermany Department of Mathematics Applied Mathematics Linköping UniversityLinköpingSweden Extreme Computing Research Center(ECRC) Computer Electrical and Mathematical Science and Engineering Division(CEMSE)King Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Saudi Arabia Applied and Computational Mathematics RWTH Aachen UniversityAachenGermany High-Performance Computing Center Stuttgart University of StuttgartStuttgartGermany Department of Mathematics and Computer Science University of CologneCologneGermany Center for Data and Simulation Science University of CologneCologneGermany Extreme Computing Research Center(ECRC) Computer Electrical and Mathematical Science and Engineering Division(CEMSE)King Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Saudi Arabia Physical Science and Engineering Division(PSE) King Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Saudi Arabia

We study a temporal step size control of explicit Runge-Kutta(RK)methods for com-pressible computational fluid dynamics(CFD),including the Navier-Stokes equations and hyperbolic systems of conservation laws such as the Euler *** demonstrate that error-based approaches are convenient in a wide range of applications and compare them to more classical step size control based on a Courant-Friedrichs-Lewy(CFL)*** numerical examples show that the error-based step size control is easy to use,robust,and efficient,e.g.,for(initial)transient periods,complex geometries,nonlinear shock captur-ing approaches,and schemes that use nonlinear entropy *** demonstrate these properties for problems ranging from well-understood academic test cases to industrially relevant large-scale computations with two disjoint code bases,the open source Julia pack-ages *** with *** and the C/Fortran code SSDC based on PETSc.

关键词： Explicit Runge-Kutta(RK)methods Step size control Compressible fluid dynamics Adaptivity in space and time Shock capturing

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：