检索结果-内蒙古大学图书馆

34th ACM international conference on Supercomputing, ICS 2020

ISBN: (纸本)9781450379830

the proceedings contain 40 papers. the topics discussed include: a scalable framework for solving fractional diffusion equations;fast distributed bandits for online recommendation systems;wavefront parallelization of recurrent neural networks on multi-core architectures;NV-group: link-efficient reduction for distributed deep learning on modern dense GPU systems;a coordinate-oblivious index for high-dimensional distance similarity searches on the GPU;V-combiner: speeding-up iterative graph processing on a shared-memory platform with vertex merging;efficient parallel algorithms for betweenness- and closeness-centrality in dynamic graphs;parallelizing pruned landmark labeling: dealing with dependencies in graph algorithms;Graptor: efficient pull and push style vectorized graph processing;and SB-fetch: synchronization aware hardware prefetching for chip multiprocessors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

parallel methods for linear systems solution in extreme learning machines: An overview 7

Parallel methods for linear systems solution in extreme lear...

引用

7th international conference Days of Applied Mathematics, ICDAM 2020

作者： Gelvez-Almeida, E. Baldera-Moreno, Y. Huérfano, Y. Vera, M. Mora, M. Barrientos, R. Laboratorio de Investigaciones Tecnologicas en Reconocimiento de Patrones Universidad Católica Del Maule Talca Chile Facultad de Ciencias Básicas y Biomédicas Universidad Simón Bolívar San José de Cúcuta Colombia Grupo de Investigación en Procesamiento Computacional de Datos Universidad de Los Andes San Cristóbal Venezuela

this paper aims to present an updated review of parallel algorithms for solving square and rectangular single and double precision matrix linear systems using multi-core central processing units and graphic processing units. A brief description of the methods for the solution of linear systems based on operations, factorization and iterations was made. the methodology implemented, in this article, is a documentary and it was based on the review of about 17 papers reported in the literature during the last five years (2016-2020). the disclosed findings demonstrate the potential of parallelism to significantly decrease extreme learning machines training times for problems with large amounts of data given the calculation of the Moore Penrose pseudo inverse. the implementation of parallel algorithms in the calculation of the pseudo-inverse will allow to contribute significantly in the applications of diversifying areas, since it can accelerate the training time of the extreme learning machines with optimal results. © 2020 Published under licence by IOP Publishing Ltd.

关键词： parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Alternative of high voltage multipliers utilizing Cockcroft-Walton multiplier blocks for 220 V and 50 Hz input

引用

ENERGY REPORTS 2020年 6卷 909-913页

作者： Jaiwanglok, Anurak Eguchi, Kei Julsereewong, Amphawan Pannil, Pittaya King Mongkuts Inst Technol Ladkrabang Fac Engn Bangkok 10520 Thailand Fukuoka Inst Technol Dept Informat Elect Fukuoka 8110295 Japan

In order to be practical for converting 220 V and 50 Hz AC input into high DC output ranged between 3.5 and 4.0 kV to create underwater shockwaves in non-thermal technique for processing foods, this article presents an alternative approach for modifying conventional high voltage multipliers without magnetic elements, which are based on the use of parallel-connected Cockcroft-Walton multiplier blocks (CWMBs) in bipolar structure. the basic three-stage CWMB scheme as well as the effect of different capacitor values on its output is described. the modified high voltage multiplier with improved response speed consists of a full-wave rectifier (FWR), a two-phase driver block, a parallel-connected positive CWMB, and a parallel-connected negative CWMB. Both output voltage and power efficiency of the proposed scheme can be demonstrated by theoretical analysis results. Moreover, simulation results showing the characteristics of the proposed high voltage multiplier are also included. (C) 2020 the Author(s). Published by Elsevier Ltd.

关键词： Cockcroft-Walton multiplier block Full-wave rectifier High voltage multiplier Non-thermal food processing Underwater shockwave

来源：评论

学校读者我要写书评

暂无评论

Designing a Deep Neural Network Model for Finding Semantic Similarity Between Short Persian Texts Using a parallel Corpus

Designing a Deep Neural Network Model for Finding Semantic S...

引用

international conference on Web Research (ICWR)

作者： Zahra Sadat Hosseini Moghadam Emami Shohreh Tabatabayiseifi Mohammad Izadi Mohammad Tavakoli Computer Engineering Science and Culture University Tehran Iran Artificial Intelligence Sharif University of Technology Tehran Iran Computer Engineering Sharif University of Technology Tehran Iran Computational Linguistics Sharif University of Technology Tehran Iran

Text processing, as one of the main issues in the field of artificial intelligence, has received a lot of attention in recent decades. Numerous methods and algorithms are proposed to address the task of semantic textual similarity which is one of the sub-branches of text processing. Due to the special features of the Persian language and its non-standard writing system, finding semantic similarity is an even more challenging task in Persian. On the other hand, producing a proper corpus that can be used for training a model for finding semantic similarities, is of great importance. In this study, the main purpose is to propose a method for measuring the semantic similarity between short Persian texts. To do so, first, we try to build an appropriate corpus, and then propose an efficient approach based on neural networks. the proposed method involves three steps. the first step is data collection and building a parallel corpus. In the next step, namely the pre-processing step, the data is normalized. Finally, Semantic similarity recognition is done by the neural network using vector representations of the words. the suggested model is built upon the produced corpus made of movie and tv show subtitles containing 35266 sentence pairs. the F-measure of the proposed approach on PAN2016 is 75.98% with 4 tags and 98.87% with 2 tags. We also achieved an F-measure of 98.86% for our model tested on the parallel corpus with 2 tags.

关键词： Deep learning Training TV Text recognition Semantics Neural networks Writing

来源：评论

学校读者我要写书评

暂无评论

Multi-scaled Non-local Means parallel Filters for Medical Image Denoising 20th

Multi-scaled Non-local Means Parallel Filters for Medical Im...

引用

20th international conference on algorithms and architectures for parallel processing (ICA3PP)

作者： Rabbouch, Hana Ben Messaoud, Othman Saadaoui, Foued Fac Sci Lab LR18ES15 Algebre Theorie Nombres & Anal Nonli Monastir 5019 Tunisia Compagnie Phosphates Gafsa CPG Cite Bayech 2100 Gafsa Tunisia King Abdulaziz Univ POB 80203 Jeddah 21589 Saudi Arabia

ISBN: (纸本)9783030602451;9783030602444

In recent years, there has been an increased interest in denoising techniques that are applicable in various medical imaging fields. the extraordinary development of the denoising area is no doubt due to the ever expanding and successful computing technology, but also to the emergence of the multi-resolution analysis (MRA) on both mathematical and algorithmic levels. However, many denoising techniques still remain ineffective in dealing with certain types of noise. Other methods can be too expensive, given their nested and complicated structure. therefore, in this paper, A new multi-scale parallel denoising paradigm is defined and tested. A comparative study is conducted between the two best-known MRA-based decomposition techniques: the Empirical Mode Decomposition (EMD) and the Discrete Wavelet Transform (DWT). the comparison is carried out in this framework of multi-scaled parallel denoising, where a Non-Local Means (NLM) filter is implemented and adjusted scale-by-scale to a sample of X-ray benchmark images. Some state-of-the-art denoising methods were also used in the evaluation. the numerical results proved the effectiveness of the multi-scaled parallel denoising in terms of accuracy and speed of convergence, especially when the NLM filtering is coupled with the EMD. this shows a bright future for their medical use in the next few years.

关键词： Medical imaging Non-local means Multi-scaled denoising Empirical mode decomposition Wavelets

来源：评论

学校读者我要写书评

暂无评论

CHEAPS2AGA: Bounding Space Usage in Variance-Reduced Stochastic Gradient Descent over Streaming Data and Its Asynchronous parallel Variants 20th

CHEAPS2AGA: Bounding Space Usage in Variance-Reduced Stochas...

引用

20th international conference on algorithms and architectures for parallel processing (ICA3PP)

作者： Peng, Yaqiong Fei, Haiqiang Li, Lun Ding, Zhenquan Hao, Zhiyu Chinese Acad Sci Inst Informat Engn Beijing 100093 Peoples R China

ISBN: (纸本)9783030602390;9783030602383

Stochastic Gradient Descent (SGD) is widely used to train a machine learning model over large datasets, yet its slow convergence rate can be a bottleneck. As a remarkable family of variance reduction techniques, memory algorithms such as SAG and SAGA have been proposed to accelerate the convergence rate of SGD. However, these algorithms need to store per training data point corrections in memory. the unlimited space usage feature is impractical for modern large-scale applications, especially over data points that arrive over time (referred to as streaming data in this paper). To overcome this weakness, this paper investigates the methods that bound the space usage in the state-of-the-art family of variance-reduced stochastic gradient descent over streaming data, and presents CHEAPS2AGA. At each step of updating the model, the key idea of CHEAPS2AGA is always reserving N random data points as samples, while re-using information about past stochastic gradients across all the observed data points with limited space usage. In addition, training an accurate model over streaming data requires the algorithm to be time-efficient. To accelerate the model training phase, CHEAPS2AGA embraces a lock-free data structure to insert new data points and remove unused data points in parallel, and updates the model parameters without using any locking. We conduct comprehensive experiments to compare CHEAPS2AGA to prior related algorithms suited for streaming data. the experimental results demonstrate the practical competitiveness of CHEAPS2AGA in terms of scalability and accuracy.

关键词： Machine learning Stochastic gradient descent Streaming data parallel algorithm Multicore

来源：评论

学校读者我要写书评

暂无评论

Evaluating the performance and improving the usability of parallel and distributed Word Embeddings tools 28

Evaluating the performance and improving the usability of pa...

引用

28th Euromicro international conference on parallel, Distributed and Network-Based processing (PDP)

作者： da Silva, Matheus L. Meyer, Vinicius Kirchoff, Dionatra F. Nero, Joaquim F. S. Vieira, Renata De Rose, Cesar A. F. Pontific Catholic Univ Rio Grande PUCKS Polytech Sch Ipiranga Ave 6681 BR-90619900 Porto Alegre RS Brazil

ISBN: (纸本)9781728165820

the representation of words by means of vectors, also called Word Embeddings (WE), has been receiving great attention from the Natural Language processing (NLP) field. WE models are able to express syntactic and semantic similarities, as well as relationships and contexts of words within a given corpus. Although the most popular implementations of WE algorithms present low scalability, there are new approaches that apply High-Performance Computing (HPC) techniques. this is an opportunity for an analysis of the main differences among the existing implementations, based on performance and scalability metrics. In this paper, we present a study which addresses resource utilization and performance aspects of known WE algorithms foetid in the literature. To improve scalability and usability we propose a wrapper library for local and remote execution environments that contains a set of optimizations such as the pWord2vec, pWord2vec_MPI, Wang2vec and the original Word2vec algorithm. Utilizing these optimizations it is possible to achieve an average performance gain of 15x for multicores and 105x for multinodes compared to the original version. there is also a big reduction in the memory footprint compared to the most popular python versions.

关键词： Natural Language processing Word2vec Performance Evaluation

来源：评论

学校读者我要写书评

暂无评论

Pimiento: A Vertex-Centric Graph-processing Framework on a Single Machine 19th

Pimiento: A Vertex-Centric Graph-Processing Framework on a S...

引用

19th international conference on algorithms and architectures for parallel processing (ICA3PP)

作者： Huang, Jianqiang Qin, Wei Wang, Xiaoying Chen, Wenguang Tsinghua Univ Dept Comp Sci & Technol Beijing 100084 Peoples R China Qinghai Univ Dept Comp Technol & Applicat Xining 810016 Peoples R China

ISBN: (纸本)9783030389611;9783030389604

Here, we describe a method for handling large graphs with data sizes exceeding memory capacity using minimal hardware resources. this method (called Pimiento) is a vertex-centric graph-processing framework on a single machine and represents a semi-external graph-computing system, where all vertices are stored in memory, and all edges are stored externally in compressed sparse row data-storage format. Pimiento uses a multi-core CPU, memory, and multi-threaded data preprocessing to optimize disk I/O in order to reduce random-access overhead in the graph-algorithm implementation process. An on-the-fly update-accumulated mechanism was designed to reduce the time that the graph algorithm accesses disks during execution. Our experiments compared external this method with other graph-processing systems, including GraphChi, X-Stream, and FlashGraph, revealing that Pimiento achieved 7.5x, 4x, 1.6x better performance on large real-world graphs and synthetic graphs in the same experimental environment.

关键词： Vertex-centric Graph processing Semi-external Passing message Asynchronous update accumulation

来源：评论

学校读者我要写书评

暂无评论

parallel SCC Detection Based on Reusing Warps and Coloring Partitions on GPUs 20th

Parallel SCC Detection Based on Reusing Warps and Coloring P...

引用

20th international conference on algorithms and architectures for parallel processing (ICA3PP)

作者： Hou, Junteng Wang, Shupeng Wu, Guangjun Ma, Bingnan Zhang, Lei Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China Natl Comp Network Emergency Response Tech Team Coordinat Ctr China Beijing Peoples R China

ISBN: (纸本)9783030602451;9783030602444

Detecting strongly connected components (SCCs) in directed graphs is crucial for analyzing the structure of graphs. It can accelerate the process of large-scale graphs with applying GPUs to graph computation. However, GPU-based SCC detection still faces the challenge from graphs, especially real-world graphs, skewing and strict synchronization requirement. In this paper, we proposed a new paradigm of identifying SCCs with reusing warps and coloring partitions. the scheme of reusing warps assigns multiple vertices to each virtual warp at one time, which greatly reduces the number of warps that are applied but assigned few tasks. Furthermore, we proved that the partitions formed by coloring independently contains all SCCs in them, so we use coloring to identify more partitions and parallel detect SCCs in each partition to get more SCCs. Finally, the colored partitions are deeply combined with the following traversal to optimize the algorithm. We conduct extensive theoretical and experimental analysis to demonstrate the efficiency and accuracy of our approach. the experimental results expose that our approach can achieve 7.23x, 30.55x, 1.75x and 1.26x speedup for SCC detection using NVIDIA K80 compared with algorithms of Tarjan, Barnat, Hong and Slota respectively.

关键词： Strongly connected components detection GPUs Reusing warps Coloring partitions Partitions combined with traversal

来源：评论

学校读者我要写书评

暂无评论

Rise the Momentum: A Method for Reducing the Training Error on Multiple GPUs 19th

Rise the Momentum: A Method for Reducing the Training Error ...

引用

19th international conference on algorithms and architectures for parallel processing (ICA3PP)

作者： Tang, Yu Yin, Lujia Zhang, Zhaoning Li, Dongsheng Natl Univ Def Technol Sci & Technol Parallel & Distributed Lab Changsha Peoples R China

ISBN: (纸本)9783030389611;9783030389604

Deep neural network training is a common issue that is receiving increasing attention in recent years and basically performed on Stochastic Gradient Descent or its variants. Distributed training increases training speed significantly but causes precision loss at the mean time. Increasing batchsize can improve training parallelism in distributed training. However, if the batchsize is too large, it will bring difficulty to training process and introduce more training error. In this paper, we consider controlling the total batchsize and lowering batchsize on each GPU by increasing the number of GPUs in distributed training. We train Resnet50 [4] on CIFAR-10 dataset by different optimizers, such as SGD, Adam and NAG. the experimental results show that large batchsize speeds up convergence to some degree. However, if the batchsize of per GPU is too small, training process fails to converge. Large number of GPUs, which means a small batchsize on each GPU declines the training performance in distributed training. We tried several ways to reduce the training error on multiple GPUs. According to our results, increasing momentum is a well-behaved method in distributed training to improve training performance on condition of multiple GPUs of constant large batchsize.

关键词： Multiple GPUs Batchsize Distributed training Momentum

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：