检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Agostinho de Souza Filho, Reinaldo Cirilo do Nascimento, Diego V. Xavier-de-Souza, Samuel Universidade Federal do Rio Grande do Norte Natal-RN Brazil Instituto Federal do Rio Grande do Norte Natal-RN Brazil

One of the barriers to the adoption of parallel computing is the inherent complexity of its programming. The Open Multi-Processing (OpenMP) Application programming Interface (API) facilitates such implementations, providing high abstraction level directives. On another front, new architectures aimed at low energy consumption have been developed, such as the Greenwaves Technologies GAP8, a Multi-Processor System-on-Chip (MPSoC) based on the parallel Ultra Low Power (PULP) Platform. The GAP8 has an 8-core cluster and a Fabric Controller(FC) master core. parallel programming with GAP8 is very promising on the efficiency side, but its recent development and lack of a robust OS to handle threads and core scheduling complicate a simple implementation of the OpenMP APIs. This project implements a source to source translator that interprets a limited set of OpenMP directives, and is capable of generating parallel microcontroller code manipulating the cores directly. The preliminary results obtained in this work shows a reduction of the code size, if compared with the base implementation, proving the efficiency of the project to ease the programming of the GAP8. Further work is need in order to implement more OpenMP directives. Copyright © 2020, The Authors. All rights reserved.

关键词： parallel programming

来源：评论

学校读者我要写书评

暂无评论

AMCilk: A Framework for Multiprogrammed parallel Workloads

AMCilk: A Framework for Multiprogrammed Parallel Workloads

引用

International Conference on High Performance Computing

作者： Zhe Wang Chen Xu Kunal Agrawal Jing Li Washington University in St. Louis New Jersey Institute of Technology

Modern parallel platforms, such as clouds or servers, are often shared among many different jobs. However, existing parallel programming runtime systems are designed and optimized for running a single parallel job, so it is generally hard to directly use them to schedule multiple parallel jobs without incurring high overhead and inefficiency. In this work, we develop AMCilk (Adaptive Multiprogrammed Cilk), a novel runtime system framework, designed to support multiprogrammed parallel workloads. AMCilk has client-server architecture where users can dynamically submit parallel jobs to the system. AMCilk has a single runtime system that runs these jobs while dynamically reallocating cores, last-level cache, and memory bandwidth among these jobs according to the scheduling policy. AMCilk exposes the interface to the system designer, which allows the designer to easily build different scheduling policies meeting the requirements of various application scenarios and performance metrics, while AMCilk transparently (to designers) enforces the scheduling policy. The primary feature of AMCilk is the low-overhead and responsive preemption mechanism that allows fast reallocation of cores between jobs. Our empirical evaluation indicates that AMCilk incurs small overheads and provides significant benefits on application-specific criteria for a set of 4 practical applications due to its fast and low-overhead core reallocation mechanism.

关键词： Performance evaluation Schedules Runtime parallel programming High performance computing Conferences Bandwidth

来源：评论

学校读者我要写书评

暂无评论

NASA Technical Reports Server (Ntrs) 19890012171: parallel Solution of Sparse One-Dimensional Dynamic programming Problems

引用

2017年

NASA Technical Reports Server (Ntrs) 19890012171: parallel Solution of Sparse One-Dimensional Dynamic programming Problems by NASA Technical Reports Server (Ntrs); published by

关键词： (ntrs) 19890012171: computer programming computer techniques concurrent processing data processing equipment dynamic multiprocessing (computers) nasa technical reports server (ntrs) nicol, david m. one-dimensional parallel parallel programming time sharing

来源：评论

学校读者我要写书评

暂无评论

Face Anti-Spoofing Using CNN Classifier & Face liveness Detection

Face Anti-Spoofing Using CNN Classifier & Face liveness Dete...

引用

International Conference on Information and Communications Technology (ICOIACT)

作者： Raden Budiarto Hadiprakoso Hermawan Setiawan Girinoto Cryptographic Engineering Poltek Siber dan Sandi Negara Bogor Indonesia

ISBN: (数字)9781728173566

ISBN: (纸本)9781728173573

Biometrics with facial recognition is now widely used. A face identification system should identify not only someone's faces but also detect spoofing attempts with printed face or digital presentations. A sincere spoofing prevention approach is to examine face liveness, such as eye blinking and lips movement. Nevertheless, this approach is helpless when dealing with video-based replay attacks. For this reason, this paper proposes a combined method of face liveness detection and CNN (Convolutional Neural Network) classifier. The anti-spoofing method is designed with two modules, the blinking eye module that evaluates eye openness and lip movement, and the CCN classifier module. The dataset for training our CNN classification can be from a variety of publicly available sources. We combined these two modules sequentially and implemented them into a simple facial recognition application using the Android platform. The test results show that the module created can recognize various kinds of facial spoof attacks, such as using posters, masks, or smartphones.

关键词： Training parallel programming Face recognition Lips Information and communication technology Smart phones Testing

来源：评论

学校读者我要写书评

暂无评论

LuNA-ICLU compiler for automated generation of iterative fragmented programs 1

引用

15th International Conference on parallel Computing Technologies, PaCT 2019

作者： Belyaev, Nikolay Kireev, Sergey ICMMG SB RAS Novosibirsk Russia Novosibirsk State University Novosibirsk Russia

ISBN: (数字)9783030256364

ISBN: (纸本)9783030256357

The work focuses on the application of Fragmented programming approach to automated generation of a parallel programs for solving applied numerical problems. A new parallel programming system LuNA-ICLU applying this approach was introduced. The LuNA-ICLU compiler translates a fragmented program of a particular type written in the LuNA language to an MPI program with dynamic load balancing support. The application algorithm representation and the system algorithms used in the LuNA-ICLU system are described. Performance comparison results show a speedup compared to the previous implementation of the LuNA programming system. © 2019, Springer Nature Switzerland AG.

关键词： parallel programming

来源：评论

学校读者我要写书评

暂无评论

Research on parallel Computing Teaching: state of the art and future directions

Research on Parallel Computing Teaching: state of the art an...

引用

Frontiers in Education (FIE) Conference

作者： Thiago de Jesus Oliveira Duraes Paulo Sergio Lopes de Souza Guilherme Martins Davi Jose Conte Naylor Garcia Bachiega Sarita Mazzini Bruschi ICMC University of Sao Paulo Sao Carlos Brazil

ISBN: (数字)9781728189611

ISBN: (纸本)9781728189628

This research full paper identifies how the teaching of parallel computing has been developing over the years. The learning of parallel and distributed computing is fundamental for computing professionals, due to the popularization of parallel architectures. Teaching parallel computing involves theoretical concepts and the development of practical skills. Its content is dense and comprises different disciplines in computer courses. Although there is growing concerned about this type of teaching, the organization and depth of parallel computing teaching at universities change widely. The available literature on the teaching of parallel computing shows some experiences about how to teach parallel computing; however, it is not easy to determine the state of the art with challenges and gaps. Our objective is to identify essential aspects related to the teaching of parallel computing as methodologies, supporting resources, subjects taught, the satisfaction of students with learning and curricula. We carried out a systematic mapping to extract information from the literature, which is composed of three phases: planning, conduction, and reporting. We initially selected 819 papers from the Scopus, IEEE, ACM, and Google Scholar databases. After a previous analysis, we performed a full read of 94 papers. The use of different teaching methodologies appears in the publications, however, the traditional teaching methodology still is the most used. There is a small number of students in parallel computing courses, a concern of different authors. Educational software or hardware resources are reported, with software proposals corresponding to most of them. The teaching of parallel computing at the beginning of undergraduate courses appear in different papers. This paper contributes to research in teaching parallel computing, pointing out the state of the art of this area, highlighting challenges that should be the focus of investigations.

关键词： Education parallel processing Databases Systematics Proposals Software parallel programming

来源：评论

学校读者我要写书评

暂无评论

A parallel-computing algorithm for high-energy physics particle tracking and decoding using GPU architectures

arXiv

引用

arXiv 2020年

作者： Declara, Placido Fernandez Cámpora Pérez, Daniel Hugo Garcia-Blas, Javier Bruch, Dorothea V.O.M. Garcia, J. Daniel Neufeld, Niko EP-LBC CERN Geneve 231211– Switzerland Department of Computer Science and Engineering University Carlos III of Madrid Madrid Spain Universidad de Sevilla ETSI Informática Av. Reina Mercedes s/n Sevilla41012 Spain LPNHE Sorbonne Université Paris Diderot Sorbonne Paris Cité CNRS/IN2P3 Paris France

Real-time data processing is one of the central processes of particle physics experiments which require large computing resources. The LHCb (Large Hadron Collider beauty) experiment will be upgraded to cope with a particle bunch collision rate of 30 million times per second, producing 109 particles/s. 40 Tbits/s need to be processed in real-time to make filtering decisions to store data. This poses a computing challenge that requires exploration of modern hardware and software solutions. We present Compass, a particle tracking algorithm and a parallel raw input decoding optimised for GPUs. It is designed for highly parallel architectures, data-oriented and optimised for fast and localised data access. Our algorithm is configurable, and we explore the trade-off in computing and physics performance of various configurations. A CPU implementation that delivers the same physics performance as our GPU implementation is presented. We discuss the achieved physics performance and validate it with Monte Carlo simulated data. We show a computing performance analysis comparing consumer and server grade GPUs, and a CPU. We show the feasibility of using a full GPU decoding and particle tracking algorithm for high-throughput particle trajectories reconstruction, where our algorithm improves the throughput up to 7.4× compared to the LHCb baseline. Copyright © 2020, The Authors. All rights reserved.

关键词： parallel programming

来源：评论

学校读者我要写书评

暂无评论

Generic parallel programming for Massive Remote Sensing Data Processing

Generic Parallel Programming for Massive Remote Sensing Data...

引用

IEEE International Conference on Cluster Computing

作者： Ma, Yan Wang, Lizhe Liu, Dingsheng Liu, Peng Wang, Jun Tao, Jie Chinese Acad Sci Ctr Earth Observat & Digital Earth Beijing 100864 Peoples R China Univ Cent Florida Dept Elect Engn & Comp Sci Orlando FL USA Karlsruhe Inst Technol Steinbuch Ctr Comp Karlsruhe Germany

ISBN: (纸本)9781467324229

Remote Sensing (RS) data processing is characterized by massive remote sensing images and increasing amount of algorithms of higher complexity. parallel programming for data-intensive applications like massive remote sensing image processing on parallel systems is bound to be especially trivial and challenging. We propose a C++ template mechanism enabled generic parallel programming skeleton for these remote sensing applications in high performance clusters. It provides both programming templates for distributed RS data and generic parallel skeletons for RS algorithms. Through one-side communication primitives provided by MPI, the distributed RS data template could provide a global view of the big RS data whose sliced data blocks are scattered among the distributed memory of cluster nodes. Moreover, by data serialization and RMA (Remote Memory Access), the data templates could also offer a simple and effective way to distribute and communicate massive remote sensing data with complex data structures. Furthermore, the generic parallel skeletons implement the recurring patterns of computation, performance optimization and pass the user-defined sequential functions as parameters of templates for type genericity. With the implemented skeletons, Developers without extensive parallel computing technologies can implement efficient parallel remote sensing programs without concerning for parallel computing details. Through experiments on remote sensing applications, we confirmed that our templates were productive and efficient.

关键词： parallel programming generic programming data-intensive computing remote sensing image processing

来源：评论

学校读者我要写书评

暂无评论

Methods and Tools for Formal Verification of Cloud Sisal Programs

Methods and Tools for Formal Verification of Cloud Sisal Pro...

引用

International Conference on Mathematics and Computers in Science and Engineering (MACISE)

作者： Victor N. Kasyanov Elena V. Kasyanova Institute of Informatics Systems Novosibirsk 630090 Russia

ISBN: (数字)9781728166957

ISBN: (纸本)9781728166964

A cloud parallel programming system CPPS being under development at the Institute of Informatics Systems is aimed to be an interactive visual environment of functional and parallel programming for supporting of computer science teaching and learning. The system will support the development, verification and debugging of architecture-independent parallel Cloud Sisal programs and their correct conversion into efficient code of parallel computing systems for its execution in clouds. In the paper, methods and tools of the CPPS system intended for formal verification of Cloud Sisal programs are described.

关键词： Cloud computing Visualization C languages Computers Informatics parallel programming Debugging

来源：评论

学校读者我要写书评

暂无评论

Gadara: Dynamic deadlock avoidance for multithreaded programs 8

Gadara: Dynamic deadlock avoidance for multithreaded program...

引用

8th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2008

作者： Wang, Yin Kelly, Terence Kudlur, Manjunath Lafortune, Stéphane Mahlke, Scott EECS Department University of Michigan United States Hewlett-Packard Laboratories United States

ISBN: (纸本)9781931971652

Deadlock is an increasingly pressing concern as the multicore revolution forces parallel programming upon the average programmer. Existing approaches to deadlock impose onerous burdens on developers, entail high runtime performance overheads, or offer no help for unmodified legacy code. Gadara automates dynamic deadlock avoidance for conventional multithreaded programs. It employs whole-program static analysis to model programs, and Discrete Control Theory to synthesize lightweight, decentralized, highly concurrent logic that controls them at runtime. Gadara is safe, and can be applied to legacy code with modest programmer effort. Gadara is efficient because it performs expensive deadlock-avoidance computations offline rather than online. We have implemented Gadara for C/Pthreads programs. In benchmark tests, Gadara successfully avoids injected deadlock faults, imposes negligible to modest performance overheads (at most 18%), and outperforms a software transactional memory system. Tests on a real application show that Gadara identifies and avoids both previously known and unknown deadlocks while adding performance overheads ranging from negligible to 10%.

关键词： parallel programming

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：