检索结果-内蒙古大学图书馆

38th ACM International Conference on Supercomputing (ACM ICS)

作者： Petit, Quentin Li, Chong Emad, Nahid Univ Paris Saclay Gif Sur Yvette France Huawei Technol France Gif Sur Yvette France Paris Distributed & Parallel Technol Lab Boulogne France Huawei Technol France Boulogne France Maison Simulat Gif Sur Yvette France LI PaRAD Gif Sur Yvette France

ISBN: (纸本)9798400706103

Embedding is a crucial step for deep neural networks. Datasets, from different applications, with different structures, can all be processed through an embedding layer and transformed into a dense matrix. The transformation must minimize both the loss of information and the redundancy of data. Extracting appropriate data features ensures the efficiency of the transformation. The co-occurrence matrix is an excellent way of representing the links between elements in a dataset. However, the dataset size becomes a problem in terms of computation power and memory footprint for using the co-occurrence matrix. In this paper, we propose a parallel and distributed approach to efficiently constructing the co-occurrence matrix in a scalable way. Our solution takes advantage of different features of boolean datasets to minimize the construction time of the co-occurrence matrix. Our experimental results show that our solution outperforms traditional approaches up to 34x. We also demonstrate the efficacy of our approach with a cost model.

关键词： Deep Learning distributed computing Embedding Sparse matrix Co-occurrence matrix Large-scale data analytics

来源：评论

学校读者我要写书评

暂无评论

Optimizing High-Throughput Inference on Graph Neural Networks at Shared computing Facilities with the NVIDIA Triton Inference Server

引用

computing and Software for Big Science 2024年第1期8卷 1-14页

作者： Savard, Claire Manganelli, Nicholas Holzman, Burt Gray, Lindsey Perloff, Alexx Pedro, Kevin Stenson, Kevin Ulmer, Keith Department of Physics University of Colorado Boulder Fermi National Accelerator Laboratory Lawrence Livermore National Laboratory

With machine learning applications now spanning a variety of computational tasks, multi-user shared computing facilities are devoting a rapidly increasing proportion of their resources to such algorithms. Graph neural networks (GNNs), for example, have provided astounding improvements in extracting complex signatures from data and are now widely used in a variety of applications, such as particle jet classification in high energy physics (HEP). However, GNNs also come with an enormous computational penalty that requires the use of GPUs to maintain reasonable throughput. At shared computing facilities, such as those used by physicists at Fermi National Accelerator Laboratory (Fermilab), methodical resource allocation and high throughput at the many-user scale are key to ensuring that resources are being used as efficiently as possible. These facilities, however, primarily provide CPU-only nodes, which proves detrimental to time-to-insight and computational throughput for workflows that include machine learning inference. In this work, we describe how a shared computing facility can use the NVIDIA Triton Inference Server to optimize its resource allocation and computing structure, recovering high throughput while scaling out to multiple users by massively parallelizing their machine learning inference. To demonstrate the effectiveness of this system in a realistic multi-user environment, we use the Fermilab Elastic Analysis Facility augmented with the Triton Inference Server to provide scalable and high-throughput access to a HEP-specific GNN and report on the outcome. © The Author(s) 2024.

关键词： distributed computing Graph neural network Heterogeneous computing Inference-as-a-service Machine learning Particle physics

来源：评论

学校读者我要写书评

暂无评论

Co-Design of Decision Trees for Network Intrusion Detection at the Edge on Digital vs. Analog Hardware

Co-Design of Decision Trees for Network Intrusion Detection ...

引用

2024 Military Communications Conference

作者： Riem, Joseph Zhang, Lei Chen, Jingdi Mackay, Henry Lan, Tian Bastian, Nathaniel D. Adam, Gina C. George Washington Univ Elect & Comp Engn Washington DC 20052 USA US Mil Acad Army Cyber Inst West Point NY USA

ISBN: (纸本)9798350374247;9798350374230

Enabling cybersecurity at the network edge requires energy-efficient and lightweight implementations of explainable network intrusion detection in constrained environments, such as the Internet of Battlefield Things (IoBT). Hardware solutions can support the efficient operation of algorithms for network intrusion detection, but these algorithms must consider the limited resources available at the network edge. To this end, we show two possible hardware implementations, one digital on an FPGA and one analog on a memristor/130nm CMOS design, of 9-node decision trees for three relevant datasets, the UNSW-NB15, the CIC-IDS 2017, and the ACI-IoT 2023. The decision tree boundaries are digitally implemented using LUTs with quantized 6-bit values on the FPGA. For the analog implementation, each leaf unit in the decision trees is naturally mapped to a chiplet, where the boundaries have a physical value stored in the programmable 6-bit resistance of a memristor device. Quantization in such novel computing architectures is necessary due to the limited bit precision of emerging nanoscale memristor devices. The corresponding boundaries are obtained by training the decision tree on respective datasets. The obtained accuracy on the digital implementation on the FPGA is 84%, 93%, and 79%, respectively, for the three datasets. The accuracy of the analog implementation is 79%, 83%, and 73%, respectively, impacted by the memristor non-idealities. Analog non-idealities can be mitigated by developing better devices in the future or by additional circuitry. The power consumption of these implemented trees shows 101mW for the FPGA implementation and 3.4mW for the analog chiplet approach. The 30x reduction in energy consumption shows the potential for analog hardware co-designed with explainable algorithms to provide efficient inference for network intrusion detection at the edge.

关键词： network intrusion detection decision tree internet of things FPGA memristor distributed computing

来源：评论

学校读者我要写书评

暂无评论

Deterministic distributed Sparse and Ultra-Sparse Spanners and Connectivity Certificates 22

Deterministic Distributed Sparse and Ultra-Sparse Spanners a...

引用

34th ACM Symposium on Parallelism in Algorithms and Architectures (SPAA)

作者： Bezdrighin, Marcel Elkin, Michael Ghaffari, Mohsen Grunau, Christoph Haeupler, Bernhard Ilchi, Saeed Rozhon, Vaclav Swiss Fed Inst Technol Zurich Switzerland Ben Gurion Univ Negev Beer Sheva Israel Carnegie Mellon Univ Pittsburgh PA USA

ISBN: (纸本)9781450391467

This paper presents efficient distributed algorithms for a number of fundamental problems in the area of graph sparsification: circle We provide the first deterministic distributed algorithm that computes an ultra-sparse spanner in polylog(n) rounds in weighted graphs. Concretely, our algorithm outputs a spanning subgraph with only n +o (n) edges in which the pairwise distances are stretched by a factor of at most O ( log n center dot 2(O (log*n))). circle We provide a polylog(n)-round deterministic distributed algorithm that computes a spanner with stretch (2k - 1) and O (nk +n(1+1/k) logk) edges in unweighted graphs and with O(n(1+1/k)k) edges in weighted graphs. circle We present the first polylog(n) round randomized distributed algorithm that computes a sparse connectivity certificate. For an n-node graph G, a certificate for connectivity kappa is a spanning subgraph H that is kappa-edge-connected if and only if G is kappa-edge-connected, and this subgraph.. is called sparse if it has O(nk) edges. Our algorithm achieves a sparsity of (1 +o (1))nk edges, which is within a 2(1 +o(1)) factor of the best possible.

关键词： distributed computing Spanners Ultra-Sparse Spanners LowDiameter Clustering Connectivity Certificates

来源：评论

学校读者我要写书评

暂无评论

Fast-tunable Graphene-based AWGR for Deep Learning Training Networks 1

Fast-tunable Graphene-based AWGR for Deep Learning Training ...

引用

1st Workshop on Hot Topics in Optical Technologies and Applications in Networking (HotOptics)

作者： Zhang, Shicheng Xue, Xuwei Guo, Bingli Li, Yixuan Li, Wenzhe Shen, Shikui Qian, Haoze Yin, Xiaojie Wei, Buzheng Yuan, Guojun Tang, Xiongyan Huang, Shanguo Beijing Univ Posts & Telecommun State Key Lab Informat Photon & Opt Commun Beijing Peoples R China Chinese Acad Sci Inst Comp Technol Beijing Peoples R China China Unicom Res Inst Beijing Beijing Peoples R China Chinese Acad Sci Key Lab Optoelect Mat & Devices Beijing Peoples R China

ISBN: (纸本)9798400707162

Optical interconnection networks are often cited as ways to break through the energy-bandwidth limitations of conventional electrical wires and improve interconnect performance in data centers and high-performance computing (HPC). However, due to the rigorous demands on latency and bandwidth imposed by the trillions of parameters synchronization in the distributed training, current optical interconnect technologies, such as those based on Arrayed Waveguide Grating Routers (AWGR) or MEMS optical switches, have become critical performance bottlenecks in Deep Learning. In this paper, targeting the periodic patterns of internode interconnectivity and the multiple iterative feature in distributed training, we propose a graphene-based fast-tunable AWGR device. The switching characteristics of this device are highly compatible with the traffic features of distributed computing, which is expected to significantly improve the training efficiency of large-scale deep learning. Leveraging the strong electromagnetic wave confinement achieved with multilayer graphene, we achieve picosecond-level tuning speeds and center wavelength shifts across the full Free Spectral Range (FSR). Theoretical calculations and simulation results indicate that our optical interconnect approach speeds up the training times of deep learning applications around 33%.

关键词： optical switching optical interconnection distributed computing arrayed waveguide grating router

来源：评论

学校读者我要写书评

暂无评论

OsirisBFT: Say No to Task Replication for Scalable Byzantine Fault Tolerant Analytics 24

OsirisBFT: Say No to Task Replication for Scalable Byzantine...

引用

29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming (PPoPP)

作者： Jamshidi, Kasra Vora, Keval Simon Fraser Univ Sch Comp Sci Burnaby BC Canada

ISBN: (纸本)9798400704352

We present a verification-based Byzantine Fault Tolerant processing system, called OsirisBFT, for distributed taskparallel applications. OsirisBFT treats computation tasks differently from state update tasks, allowing the application to scale independently from number of expected failures. OsirisBFT captures application-specific verification semantics via generic verification operators and employs lightweight verification strategies with little coordination during graceful execution. Evaluation across multiple applications and workloads shows that OsirisBFT delivers high processing throughput and scalability compared to replicated processing. Importantly, the scalable nature of OsirisBFT enables it to reduce the performance gap compared to baseline with no fault tolerance by simply scaling out.

关键词： distributed computing Byzantine Fault Tolerance Data Processing Systems Resilient Systems.

来源：评论

学校读者我要写书评

暂无评论

Energy performance of Internet of Things (IoT) networks for pipeline monitoring 20

Energy performance of Internet of Things (IoT) networks for ...

引用

20th IEEE International Wireless Communications and Mobile computing (IEEE IWCMC) - Green and Intelligent Communications

作者： Kuaban, Godlove Suila Czachorski, Tadeusz Gelenbe, Erol Pecka, Piotr Nkemeni, Valery Czekalski, Piotr Polish Acad Sci IITiS PAN Inst Theoret & Appl Informat Gliwice Poland Univ Buea Fac Engn & Technol Lab Elect Engn & Comp Buea Cameroon Silesian Tech Univ Fac Automat Control Elect & Informat Gliwice Poland

ISBN: (纸本)9798350361261;9798350361278

Pipelines are the most convenient ways to transport fluids (e.g., water, oil, and gas). However, leakage of fluids into the environment results in resource wastage (primarily water, which is becoming a scarce resource) and environmental pollution (in the case of leakage of toxic fluids like oil and gas). Emerging technologies like the Internet of Things (IoT), Wireless Sensor Networks (WSNs), Artificial Intelligence (AI), distributed computing, and cloud computing enable continuous monitoring of pipelines to detect leakages and corrosion on the pipeline. The main challenge with using battery-powered sensor nodes to monitor pipelines is the energy constraint, necessitating frequent battery replacement. Thus, there is a need to develop energy-saving mechanisms to prolong the lifetime of these sensor nodes. In this paper, we use the diffusion approximation modelling framework in which the data from the experimental testbed are used to model the dynamics of the battery's energy content and to estimate the mean and variance of the device's lifetime. The novelty in the proposed diffusion model of the battery of an IoT node is the introduction of multiple energy thresholds that split the energy state-space of the battery into multiple energysaving regimes. As the battery discharges, the node gradually transitions into energy-saving regimes by reconfiguring some of its parameters to reduce energy consumption (sometimes at the cost of trading off some performance metrics). We investigate the impact of energy-saving regimes or the number of thresholds on the node's lifetime.

关键词： Green Internet of Things (IoT) energy performance diffusion models adaptive sensing distributed computing duty cycling

来源：评论

学校读者我要写书评

暂无评论

Cliffhanger: An Experimental Evaluation of Stateful Serverless at the Edge 19

Cliffhanger: An Experimental Evaluation of Stateful Serverle...

引用

19th Wireless On-Demand Network Systems and Services Conference (WONS)

作者： Hasselberg, Adam Timoudas, Thomas Ohlson Carbone, Paris Dan, Gyorgy RISE Gothenburg Sweden KTH Stockholm Sweden

ISBN: (纸本)9783903176614

The serverless computing paradigm has transformed cloud service deployment by enabling automatic scaling of resources in response to varying demand. Building on this, stateful serverless computing introduces critical capabilities for data management, fault tolerance, and consistency, which are particularly relevant in the context of distributed deployments, notably in edge computing environments. In this work, we explore the feasibility of stateful serverless computing in resource-limited edge environments through an empirical study utilizing a multi-view object tracking application. Our results show that while these systems perform well in cloud environments, their effectiveness is severely affected at the edge due to state, application, and resource management solutions optimized for cloud environments. Existing solutions are most detrimental to applications with intermittent workloads, as typical combinations of concurrency handling and resource reservation can lead to minutes of unstable system behavior due to cold starts. Our results highlight the need for a tailored approach in stateful serverless systems for edge computing scenarios.

关键词： distributed computing Edge computing Fog computing

来源：评论

学校读者我要写书评

暂无评论

IPU-EpiDet: Identifying Gene Interactions on Massively Parallel Graph-Based AI Accelerators 38

IPU-EpiDet: Identifying Gene Interactions on Massively Paral...

引用

International Parallel and distributed Processing Symposium (IPDPS)

作者： Nobre, Ricardo Ilic, Aleksandar Santander-Jimenez, Sergio Sousa, Leonel Univ Lisbon INESC ID Inst Super Tecn Lisbon Portugal Univ Extremadura UNEX Caceres Spain

ISBN: (纸本)9798350387117;9798350387124

Epistasis detection is a bioinformatics application that searches for associations between sets of single nucleotide polymorphisms (SNPs) and a given trait of a population. Epistasis detection is a computationally complex problem, especially when tackling interaction orders above two. This paper presents a pioneering approach for performing third-order epistasis searches that has been devised around the bulk-synchronous parallel (BSP) model of execution, which is used in processor designs that target artificial intelligence (AI) workloads, such as Graphcore's Intelligence Processing Unit (IPU). We propose a parallelization approach and a set of optimizations to efficiently exploit the computation and communication resources of these novel AI processors to perform precise bioinformatics searches. The proposed approach achieves a performance of 3.9 Tera SNP combinations evaluated per second, scaled to sample size, on an IPU-M2000 AI accelerator, while close to a linear speedup (up to 15.01x) is achieved with 16 IPU-M2000 accelerators.

关键词： bioinformatics epistasis detection distributed computing IPU

来源：评论

学校读者我要写书评

暂无评论

Byzantine Attack Identification in distributed Matrix Multiplication via locally testable codes

Byzantine Attack Identification in Distributed Matrix Multip...

引用

IEEE International Symposium on Information Theory (ISIT)

作者： Hong, Sangwoo Yang, Heecheol Lee, Jungwoo Seoul Natl Univ Dept Elect & Comp Engn Seoul South Korea Chungnam Natl Univ Div Comp Convergence Daejeon South Korea

ISBN: (纸本)9781665421607;9781665421591

Coded computing has proved its efficiency in handling a straggler issue in distributed computing framework. However, in a coded distributed computing framework, there may exist Byzantine workers who send the wrong computation results to a master to contaminate the overall computation output. Therefore, it is essential to identify Byzantine workers from their computation results in coded computing. In this paper, we consider Byzantine attack identification problem in coded computing for distributed matrix multiplication tasks. We propose locally testable codes which facilitate the efficient Byzantine attack identification, and suggest a hierarchical group testing method for Byzantine attack identification. We show that our scheme requires smaller number of tests than the conventional group testing methods for the existing coded computing schemes.

关键词： distributed computing Byzantine attack coded computation matrix multiplication group testing

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：