检索结果-内蒙古大学图书馆

7th ieee/acm Workshop on machine learning in High Performance Computing environments (mlhpc)

作者： Wyatt, Michael R., II Yamamoto, Valen Tosi, Zoe Karlin, Ian Van Essen, Brian Lawrence Livermore Natl Lab Tenter Appl Sci Comp Livermore CA 94550 USA Intel Corp Santa Clara CA 95051 USA

ISBN: (纸本)9781665411240

Cognitive simulation (CogSim) is an important and emerging workflow for hpc scientific exploration and scientific machine learning (SciML). One challenging workload for CogSim is the replacement of one component in a complex physical simulation with a fast, learned, surrogate model that is "inside" of the computational loop. The execution of this in-the-loop inference is particularly challenging because it requires frequent inference across multiple possible target models, can be on the simulation's critical path (latency bound), is subject to requests from multiple MPI ranks, and typically contains a small number of samples per request. In this paper we explore the use of large, dedicated Deep learning / AI accelerators that are disaggregated from compute nodes for this CogSim workload. We compare the trade-offs of using these accelerators versus the node-local GPU accelerators on leadership-class hpc systems.

关键词： deep learning cognitive simulation surrogate models accelerator performance

来源：评论

学校读者我要写书评

暂无评论

High-Performance Deep learning Toolbox for Genome-Scale Prediction of Protein Structure and Function 7

High-Performance Deep Learning Toolbox for Genome-Scale Pred...

引用

7th ieee/acm Workshop on machine learning in High Performance Computing environments (mlhpc)

作者： Gao, Mu Lund-Andersen, Peik Morehead, Alex Mahmud, Sajid Chen, Chen Chen, Xiao Giri, Nabin Roy, Raj S. Quadir, Farhan Effler, T. Chad Prout, Ryan Abraham, Subil Elwasif, Wael Haas, N. Quentin Skolnick, Jeffrey Cheng, Jianlin Sedova, Ada Georgia Inst Technol Atlanta GA 30332 USA Univ Idaho Moscow ID 83843 USA Oak Ridge Natl Lab Oak Ridge TN 37830 USA Univ Missouri Columbia MO 65211 USA

ISBN: (纸本)9781665411240

Computational biology is one of many scientific disciplines ripe for innovation and acceleration with the advent of high-performance computing (hpc). In recent years, the field of machine learning has also seen significant benefits from adopting hpc practices. In this work, we present a novel hpc pipeline that incorporates various machine-learning approaches for structure-based functional annotation of proteins on the scale of whole genomes. Our pipeline makes extensive use of deep learning and provides computational insights into best practices for training advanced deep-learning models for high-throughput data such as proteomics data. We showcase methodologies our pipeline currently supports and detail future tasks for our pipeline to envelop, including large-scale sequence comparison using SAdLSA and prediction of protein tertiary structures using AlphaFold2.

关键词： high-performance computing computational biology machine learning deep learning protein sequence alignment protein structure prediction

来源：评论

学校读者我要写书评

暂无评论

Colmena: Scalable machine-learning-Based Steering of Ensemble Simulations for High Performance Computing 7

Colmena: Scalable Machine-Learning-Based Steering of Ensembl...

引用

7th ieee/acm Workshop on machine learning in High Performance Computing environments (mlhpc)

作者： Ward, Logan Sivaraman, Ganesh Pauloski, J. Gregory Babuji, Yadu Chard, Ryan Dandu, Naveen Redfern, Paul C. Assary, Rajeev S. Chard, Kyle Curtiss, Larry A. Thakur, Rajeev Foster, Ian Argonne Natl Lab Data Sci & Learning Div Lemont IL 60439 USA Univ Chicago Dept Comp Sci Chicago IL 60637 USA Univ Chicago Joint Ctr Energy Storage Res Chicago IL 60637 USA

ISBN: (纸本)9781665411240

Scientific applications that involve simulation ensembles can be accelerated greatly by using experiment design methods to select the best simulations to perform. Methods that use machine learning (ML) to create proxy models of simulations show particular promise for guiding ensembles but are challenging to deploy because of the need to coordinate dynamic mixes of simulation and learning tasks. We present Colmena, an open-source Python framework that allows users to steer campaigns by providing just the implementations of individual tasks plus the logic used to choose which tasks to execute when. Colmena handles task dispatch, results collation, ML model invocation, and ML model (re)training, using Parsl to execute tasks on hpc systems. We describe the design of Colmena and illustrate its capabilities by applying it to electrolyte design, where it both scales to 65 536 CPUs and accelerates the discovery rate for high-performance molecules by a factor of 100 over unguided searches.

关键词： machine learning Computational Steering Many Task Computing

来源：评论

学校读者我要写书评

暂无评论

MLPerf™ hpc: A Holistic Benchmark Suite for Scientific machine learning on hpc Systems 7

MLPerf™ HPC: A Holistic Benchmark Suite for Scientific Mach...

引用

7th ieee/acm Workshop on machine learning in High Performance Computing environments (mlhpc)

作者： Farrell, Steven Emani, Murali Balma, Jacob Drescher, Lukas Drozd, Aleksandr Fink, Andreas Fox, Geoffrey Kanter, David Kurth, Thorsten Mattson, Peter Mu, Dawei Ruhela, Amit Sato, Kento Shirahata, Koichi Tabaru, Tsuguchika Tsaris, Aristeidis Balewski, Jan Cumming, Ben Danjo, Takumi Domke, Jens Fukai, Takaaki Fukumoto, Naoto Fukushi, Tatsuya Gerofi, Balazs Honda, Takumi Imamura, Toshiyuki Kasagi, Akihiko Kawakami, Kentaro Kudo, Shuhei Kuroda, Akiyoshi Martinasso, Maxime Matsuoka, Satoshi Mendonca, Henrique Minami, Kazuki Ram, Prabhat Sawada, Takashi Shankar, Mallikarjun St John, Tom Tabuchi, Akihiro Vishwanath, Venkatram Wahib, Mohamed Yamazaki, Masafumi Yin, Junqi Lawrence Berkeley Natl Lab Berkeley CA 94720 USA Argonne Natl Lab Argonne IL 60439 USA Maxwell Labs Inc St Louis Pk MN USA Swiss Natl Supercomp Ctr Porza Switzerland RIKEN Ctr Computat Sci Wako Saitama Japan Univ Virginia Charlottesville VA 22903 USA MLCommons San Francisco CA USA NVIDIA Zurich Switzerland Google Mountain View CA 94043 USA Natl Ctr Supercomp Applicat Urbana IL USA Texas Adv Comp Ctr Austin TX USA Fujitsu Ltd Tokyo Japan Oak Ridge Natl Lab Oak Ridge TN USA Microsoft Redmond WA USA Cruise Miami FL USA Natl Inst Adv Ind Sci & Technol Tokyo Japan

ISBN: (纸本)9781665411240

Scientific communities are increasingly adopting machine learning and deep learning models in their applications to accelerate scientific insights. High performance computing systems are pushing the frontiers of performance with a rich diversity of hardware resources and massive scale-out capabilities. There is a critical need to understand fair and effective benchmarking of machine learning applications that are representative of real-world scientific use cases. MLPerf (TM) is a community-driven standard to benchmark machine learning workloads, focusing on end-to-end performance metrics. In this paper, we introduce MLPerf hpc, a benchmark suite of largescale scientific machine learning training applications, driven by the MLPerf (TM) Association. We present the results from the first submission round including a diverse set of some of the world's largest hpc systems. We develop a systematic framework for their joint analysis and compare them in terms of data staging, algorithmic convergence and compute performance. As a result, we gain a quantitative understanding of optimizations on different subsystems such as staging and on-node loading of data, compute-unit utilization and communication scheduling enabling overall > 10x (end-to-end) performance improvements through system scaling. Notably, our analysis shows a scale-dependent interplay between the dataset size, a system's memory hierarchy and training convergence that underlines the importance of near-compute storage. To overcome the data-parallel scalability challenge at large batch-sizes, we discuss specific learning techniques and hybrid data-and-model parallelism that are effective on large systems. We conclude by characterizing each benchmark with respect to low-level memory, I/O and network behaviour to parameterize extended roofline performance models in future rounds.

关键词： Deep learning Benchmarks Supercomputers Scientific Applications

来源：评论

学校读者我要写书评

暂无评论

Proceedings of mlhpc 2021: Workshop on machine learning in High Performance Computing environments, Held in conjunction with SC 2021: The International Conference for High Performance Computing, Networking, Storage and Analysis

Proceedings of MLHPC 2021: Workshop on Machine Learning in H...

引用

7th ieee/acm Workshop on machine learning in High Performance Computing environments, mlhpc 2021

ISBN: (纸本)9781665411240

The proceedings contain 9 papers. The topics discussed include: semantic-aware lossless data compression for deep learning recommendation model (DLRM);Colmena: scalable machine-learning-based steering of ensemble simulations for high performance computing;production deployment of machine-learned rotorcraft surrogate models on hpc;high-performance deep learning toolbox for genome-scale prediction of protein structure and function;hpcFAIR: enabling FAIR AI for hpc applications;hpc ontology: towards a unified ontology for managing training datasets and AI models for high-performance computing;HYPPO: a surrogate-based multi-level parallelism tool for hyperparameter optimization;and is disaggregation possible for hpc cognitive simulation?.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ensemble Deep Random Vector Functional Link Network Using Privileged Information for Alzheimer's Disease Diagnosis

引用

ieee-acm TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2024年第4期21卷 534-545页

作者： Ganaie, M. A. Tanveer, M. Indian Inst Technol IIT Indore Dept Math Indore Madhya Pradesh India

Alzheimer's disease (AD) is a progressive brain disorder. machine learning models have been proposed for the diagnosis of AD at early stage. Recently, deep learning architectures have received quite a lot attention. Most of the deep learning architectures suffer from the issues of local minima, slow convergence and sensitivity to learning rate. To overcome these issues, non-iterative learning based deep randomized models especially random vector functional link network (RVFL) with direct links have proven to be successful. However, deep RVFL and its ensemble models are trained only on normal samples. In this paper, deep RVFL and its ensembles are enabled to incorporate privileged information, as the standard RVFL model and its deep models are unable to use privileged information. To fill this gap, we have incorporated learning using privileged information (LUPI) in deep RVFL model, and propose deep RVFL with LUPI framework (dRVFL+). Privileged information is available while training the models. As RVFL is an unstable classifier, we propose ensemble deep RVFL+ with LUPI framework (edRVFL+) which exploits the LUPI as well as the diversity among the base leaners for better classification. Unlike traditional ensemble approach wherein multiple base learners are trained, the proposed edRVFL+ model optimises a single network and generates an ensemble via optimization at different levels of random projections of the data. Both dRVFL+ and edRVFL+ efficiently utilise the privileged information which results in better generalization performance. In LUPI framework, half of the available features are used as normal features and rest as the privileged features. However, we propose a novel approach for generating the privileged information. We utilise different activation functions while processing the normal and privileged information in the proposed deep architectures. To the best of our knowledge, this is first time that a separate privileged information is generated. The propo

关键词： Diseases Deep learning Standards Brain modeling Training Support vector machines Alzheimer's disease ensemble deep learning random vector functional link (RVFL) deep RVFL magnetic resonance imaging (MRI) magnetic resonance imaging (MRI)

来源：评论

学校读者我要写书评

暂无评论

SDN Lullaby: VM Consolidation for SDN using Transformer-Based Deep Reinforcement learning 19

SDN Lullaby: VM Consolidation for SDN using Transformer-Base...

引用

19th International Conference on Network and Service Management (CNSM) - Network and Service Management in the Era of Generative AI and Digital Twins

作者： Jeong, Eui-Dong Yoo, Jae-Hyoung Hong, James Won-Ki POSTECH Dept Comp Sci & Engn Pohang South Korea

ISBN: (纸本)9783903176591

This study introduces Virtual machine (VM) Consolidation using a Transformer-based Deep Reinforcement learning (DRL) method, to address the complexity and inefficiency in operating Software Defined Networks-enabled Network Function Virtualization (SDN-enabled NFV). The distribution of Virtual Network Functions (VNFs) as VMs across servers often leads to energy loss due to irregular deployment. The proposed approach enhances energy efficiency while maintaining the performance of Service Function Chains (SFCs). By refining the VM consolidation process and leveraging a more sophisticated DRL method, this approach promises a more efficient solution to VM consolidation in SDN-enabled NFV environments.

关键词： SDN NFV Energy Efficiency VM Consolidation Deep Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Seeking the Truth in a Decentralized Manner

引用

ieee-acm TRANSACTIONS ON NETWORKING 2021年第5期29卷 2296-2312页

作者： Fu, Luoyi Xu, Jiasheng Qu, Shan Xu, Zhiying Wang, Xinbing Chen, Guihai Shanghai Jiao Tong Univ Dept Elect Informat & Elect Engn Shanghai 200240 Peoples R China

In networks where massive sources make observations of same entities, we intend to seek the truth - the most trustworthy value of each entity from conflicting information claimed by multiple sources. Various methods are proposed for accurately inferring both source reliability and truths, yet relying heavily on centralized settings that incur tremendous overhead to source side. In this paper, we offer a decentralized design of truth discovery task that can fit favorably to the environments with limited resources. Considering that sources forming the connected network and making individual observations, we undertake the joint maximum likelihood estimation (MLE) of truth and source reliability. Our decentralization framework simply allows each source to maintain local information exchange at a time, and computes very basic functions of data observations. To this end, we facilitate the decentralization by simplifying the MLE problem into optimizing an objective function. Upon the proof of NP-hardness, two proposed decentralized algorithms (exact and approximation) are decentralized and randomized via a combination of algorithms from their centralized counterparts that ensure performance guarantee. The derived time complexity features explicit data/network dependent terms, which leads to further acceleration in truth finding. Remarkably, in two well connected networks like random geometric and preferential attachment graphs, the accelerated approximation method enjoys logarithmic time complexity while preserving comparable accuracy to the centralized counterparts. The effectiveness of the proposed decentralizations are further empirically confirmed.

关键词： Approximation algorithms Reliability machine learning algorithms Task analysis machine learning Maximum likelihood estimation Data mining Truth discovery source reliability maximum likelihood estimation decentralization

来源：评论

学校读者我要写书评

暂无评论

Accelerating GPU-based machine learning in Python using MPI Library: A Case Study with MVAPICH2-GDR 6

Accelerating GPU-based Machine Learning in Python using MPI ...

引用

ieee/acm Workshop on machine learning in High Performance Computing environments (mlhpc) / Workshop on Artificial Intelligence and machine learning for Scientific Applications (AI4S)

作者： Ghazimirsaeed, S. Mahdieh Anthony, Quentin Shafi, Aamir Subramoni, Hari Panda, Dhabaleswar K. Dk Ohio State Univ Columbus OH 43210 USA

ISBN: (纸本)9781665422918

The growth of big data applications during the last decade has led to a surge in the deployment and popularity of machine learning (ML) libraries. On the other hand, the high performance offered by GPUs makes them well suited for ML problems. To take advantage of GPU performance for ML, NVIDIA has recently developed the cuML library. cuML is the GPU counterpart of Scikit-learn, and provides similar Pythonic interfaces to Scikit-learn while hiding the complexities of writing GPU compute kernels directly using CUDA. To support execution of ML workloads on Multi-Node Multi-GPU (MNMG) systems, the cuML library exploits the NVIDIA Collective Communications Library (NCCL) as a backend for collective communications between processes. On the other hand, MPI is a de facto standard for communication in hpc systems. Among various MPI libraries, MVAPICH2-GDR is the pioneer in optimizing GPU communication. This paper explores various aspects and challenges of providing MPI-based communication support for GPU-accelerated cuML applications. More specifically, it proposes a Python API to take advantage of MPI-based communications for cuML applications. It also gives an in-depth analysis, characterization, and benchmarking of the cuML algorithms such as K-Means, Nearest Neighbors, Random Forest, and tSVD. Moreover, it provides a comprehensive performance evaluation and profiling study for MPI-based versus NCCL-based communication for these algorithms. The evaluation results show that the proposed MPI-based communication approach achieves up to 1.6x, 1.25x, 1.25x, and 1.36x speedup for K-Means, Nearest Neighbors, Linear Regression, and tSVD, respectively on up to 32 GPUs.

关键词： machine learning cuML MPI GPUs

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of machine learning-Based Systems for Detecting Deforestation 11

Performance Analysis of Machine Learning-Based Systems for D...

引用

11th Brazilian Symposium on Computing Systems Engineering (SBESC)

作者： de Araujo, Michel Andrade, Ermeson Machida, Fumio Univ Fed Rural Pernambuco Dept Comp Recife PE Brazil Univ Tsukuba Dept Comp Sci Tsukuba Ibaraki Japan

ISBN: (纸本)9781665443111

Remote monitoring has become an important tool for recognizing land and ground objects through sensor data analysis. The use of machine learning (ML) algorithms for classification of remote monitoring images has increased in recent years. ML-based image classifiers have played an important role in detecting deforestation, illegal mining or fire. However, the precise classification of land use is a huge challenging task, especially in remote tropical regions, due to the complex biophysical environment and the limitations of the remote monitoring infrastructure. This work aims at studying the trade-offs between performance and accuracy of classification systems for the Brazilian Amazon rainforest, taking into account different computing platforms (server and edge), ML algorithms and images sizes. Although there is a direct relationship between image accuracy and quality, our experimental study shows that it is possible to use low-cost computational environments to perform image classification. The results indicate that Amazon rainforest can be monitored with affordable computing resources such as drones.

关键词： Performance machine learning Deforestation

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：