检索结果-内蒙古大学图书馆

12th international conference on algorithms and architectures for parallel processing, ICA3PP 2012

作者： Liu, Jie Chi, Lihua Gong, Chunye Xu, Han Jiang, Jie Yan, Yihui Hu, Qingfeng College of Computer Science National University of Defense Technology Changsha 410073 China

ISBN: (纸本)9783642330643

Matrix multiplication is an essential building block of many linear algebra operations and applications. this paper presents parallel algorithms with shared A or B matrix in the memory for the special massively multithreaded Fiteng1000 processor. We discuss the implementations of parallel matrix multiplication algorithms on the multi-core processor with many threads. To gain better performance, it is important to choose the 2D thread spatial topography, the memory layer for the placement and the sizes of the matrices. parallel codes using C and assembly language under OpenMP parallel programming environment are designed. Performance results on Fiteng1000 processor show that the algorithms have well good parallel performance and achieve near-peak performance. © 2012 Springer-Verlag.

关键词： parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-target vectorization with MTPS C++ generic library

引用

10th international conference on Applied parallel and Scientific Computing, PARA 2010

作者： Kirschenmann, Wilfried Plagne, Laurent Vialle, Stéphane SINETICS Department EDF R and D France SUPELEC - UMI 2958 France AlGorille INRIA Project Team France

ISBN: (纸本)9783642281440

this article introduces a C++ template library dedicated at vectorizing algorithms for different target architectures: Multi-Target parallel Skeleton (MTPS). Skeletons describing the data structures and algorithms are provided and allow MTPS to generate a code with optimized memory access patterns for the choosen architecture. MTPS currently supports x86-64 multicore CPUs and CUDA enabled GPUs. On these architectures, performances close to hardware limits are observed. © 2012 Springer-Verlag.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient Execution of Erasure Codes on Multicore architectures

引用

10th Nordic international conference on Applied parallel Computing - State of the Art in Scientific and parallel Computing (PARA)

作者： Wyrzykowski, Roman Kuczynski, Lukasz Wozniak, Marcin Czestochowa Tech Univ Inst Comp & Informat Sci PL-42201 Czestochowa Poland

ISBN: (纸本)9783642281440;9783642281457

Erasure codes can improve the availability of distributed storage in comparison with replication systems. In this paper, we focus on investigating how to map systematically the Reed-Solomon and Cauchy Reed-Solomon erasure codes onto the Cell/B.E. and GPU multicore architecture. A method for the systematic mapping of computation kernels of encoding/decoding algorithms onto the Cell/B.E. architecture is proposed. this method takes into account properties of the architecture on all three levels of its parallel processing hierarchy. the performance results are shown to be very promising. the possibility of using GPUs is studied as well, based on the Cauchy version of Reed-Solomon codes.

关键词： Erasure codes Reed-Solomon codes Cauchy Reed-Solomon codes multicore architectures Cell/BE GPU

来源：评论

学校读者我要写书评

暂无评论

the research of multi-core parallel technology

The research of multi-core parallel technology

引用

2012 8th international conference on Natural Computation, ICNC 2012

作者： Pan, Yang Qiu, Jianlin Chen, Li Gu, Xiang Chen, Jianping Chen, Yanyun College of Computer Science and Technology Nantong University Nantong China

ISBN: (纸本)9781457721311

In order to take full advantage of multi-core resources to enhance the parallel performance, we study the architecture of multi-core processor and point out that the heterogeneous multi-core processor is the mainstream of development. With Amdahl's law, only by developing a new parallel programming model can solve the contradiction between traditional programming model and multi-core parallel structure. © 2012 IEEE.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Automated B-H curve identification algorithm combining field simulation with optimisation methods and exploiting parallel computation

引用

IET SCIENCE MEASUREMENT & TECHNOLOGY 2012年第5期6卷 369-375页

作者： Di Barba, P. Komeza, K. Juszczak, E. N. Lecointe, J. P. Napieralski, P. Hihat, N. Univ Pavia Dept Elect Engn I-27100 Pavia Italy Tech Univ Lodz Inst Mechatron & Informat Syst PL-90924 Lodz Poland Univ Lille Nord France F-59000 Lille France UA LSEE F-62400 Bethune France Tech Univ Lodz Inst Informat Technol PL-90924 Lodz Poland

the study proposes an automated procedure for linking an identification algorithm implemented in a general-purpose environment (MatLab) with a commercial finite-element code for magnetic field analysis (VF-Opera). the method is used to identify the B-H curves of anisotropic magnetic laminations in the direction normal to the sheet surface with the aid of a multiprocessor computer to benefit from parallel computing. the proposed approach, based on a non-deterministic algorithm, makes it possible to determine the entire B-H curve and is therefore an advancement on the commonly used assumption of constant permeability.

关键词： anisotropic magnetic lamination magnetic fields Finite element analysis magnetic field analysis Optimisation techniques sheet surface parallel processing parallel computation optimisation computational electromagnetics permeability multiprocessor computer finite element code Electrical engineering computing laminations constant permeability Magnetostatics Magnetic cores magnetic hysteresis magnetic field simulation parallel software nondeterministic algorithm curve fitting automated B-H curve identification finite element analysis

来源：评论

学校读者我要写书评

暂无评论

Investigating Memory Optimization of Hash-index for Next Generation Sequencing on Multi-core Architecture

Investigating Memory Optimization of Hash-index for Next Gen...

引用

26th IEEE international parallel and Distributed processing Symposium (IPDPS) / Workshop on High Performance Data Intensive Computing

作者： Wang, Wendi Tang, Wen Li, Linchuan Tan, Guangming Zhang, Peiheng Sun, Ninghui Chinese Acad Sci Inst Comp Technol High Performance Comp Res Ctr Beijing 100864 Peoples R China

ISBN: (纸本)9780769546766

Next Generation Sequencing (NGS) is gaining interests due to the increased requirements and the decreased sequencing cost. the important and prerequisite step of most NGS applications is the mapping of short sequences, called reads, to the template reference sequences. Both the explosion of NGS data with over billions of reads generated each day and the data-intensive computations pose great challenges to the capability of existing computing systems. In this paper, we take a hash-index based algorithm (PerM) as an example to investigate the optimization approaches for accelerating NGS reads mapping on multi-core architectures. First, we propose a new parallel algorithm that reorders bucket access in hash index among multiple threads so that data locality in shared cache is improved. Second, in order to reduce the number of empty hash bucket, we propose a serialized hash index compression algorithm, which coincides with the sequential access nature of our new parallel algorithm. With reduced hash index size, it also becomes possible for us to use longer hash keys, which alleviates the hash conflicts and improves the query performance. Our experiment on an 8-socket 8-cores Intel Xeon X7550 SMP with 128 GB memory shows that the new parallel algorithm reduces LLC miss ratio to be 8% similar to 15% of the original algorithm and the overall performance is improved by 4 similar to 11 times (6 times avg.).

关键词： hashing parallel algorithms core construction next generation sequencing locality data reading buckets

来源：评论

学校读者我要写书评

暂无评论

A new low latency parallel turbo decoder employing parallel phase decoding method

A new low latency parallel turbo decoder employing parallel ...

引用

12th international conference on algorithms and architectures for parallel processing, ICA3PP 2012

作者： Lee, Wen-Ta Chang, Min-Sheng Shen, Wei-Chieh Institute of Computer and Communication National Taipei University of Technology Taipei Taiwan

ISBN: (纸本)9783642330643

In this paper, a new parallel phase algorithm for parallel turbo decoder is proposed. Traditional sliding window turbo algorithm exchanges extrinsic information phase by phase, it will induce long decoding latency. the proposed algorithm exchanges extrinsic information as soon as it had been calculated half the frame size, thus, it can not only eliminate (De-)Interleaver delay but also save the storage space. For verifying the proposed parallel phase turbo decoder, we have used FPGA to emulate the hardware architectures, and designed this turbo decoder chip with TSMC 0.18μm 1P6M CMOS process. the gate count of this decoder chip is 128284. the chip size including I/O pad is 1.91x1.91mm2. the simulation result shows that, compared to traditional sliding window method, for different code size, parallel phase turbo decoding method has 51.23%~58.13% decoding time saved, with 8 iteration times at 100MHz working frequency. © 2012 Springer-Verlag.

关键词： Iterative decoding

来源：评论

学校读者我要写书评

暂无评论

Advances in Natural Language processing - 8th international conference on NLP, JapTAL 2012, Proceedings

Advances in Natural Language Processing - 8th International ...

引用

8th international conference on Natural Language processing, JapTAL 2012

ISBN: (纸本)9783642339820

the proceedings contain 32 papers. the topics discussed include: the impact of crowdsourcing post-editing with the collaborative translation framework;translation of quantifiers in Japanese-Chinese machine translation;toward practical use of machine translation;phrase-level pattern-based machine translation based on analogical mapping method;parallel texts extraction from multimodal comparable corpora;a reliable communication system to maximize the communication quality;exploiting a web-based encyclopedia as a knowledge base for the extraction of multilingual terminology;segmenting long sentence pairs to improve word alignment in English-Hindi parallel corpora;shallow syntactic preprocessing for statistical machine translation;linguistic rules based approach for automatic restoration of accents on French texts;word clustering for Persian statistical parsing;and building a lexically and semantically-rich resource for paraphrase processing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A note on developing optimal and scalable parallel two-list algorithms

A note on developing optimal and scalable parallel two-list ...

引用

12th international conference on algorithms and architectures for parallel processing, ICA3PP 2012

作者： Chedid, Fouad B. College of Arts and Applied Sciences Dhofar University Oman Department of Computer Science Notre Dame University - Louaize Lebanon

ISBN: (纸本)9783642330643

We show that developing an optimal parallelization of the two-list algorithm is much easier than we once thought. All it takes is to observe that the steps of the search phase of the two-list algorithm are closely related to the steps of a merge procedure for merging two sorted lists, and we already know how to parallelize merge efficiently. Armed with this observation, we present an optimal and scalable parallel two-list algorithm that is easy to understand and analyze, while it achieves the best known range of processor-time tradeoffs for this problem. In particular, our algorithm based on a CREW PRAM model takes time O(2n/2 - α) using 2α processors, for 0 ≤ α ≤ n/2 - 2logn + 2. © 2012 Springer-Verlag.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

A parallel Corpus of Music and Lyrics Annotated with Emotions 8

A Parallel Corpus of Music and Lyrics Annotated with Emotion...

引用

8th international conference on Language Resources and Evaluation (LREC)

作者： Strapparava, Carlo Mihalcea, Rada Battocchi, Alberto FBK Irst Trento Italy Univ North Texas Denton TX USA Univ Trento DISI Trento Italy

ISBN: (纸本)9782951740877

In this paper, we introduce a novel parallel corpus of music and lyrics, annotated with emotions at line level. We first describe the corpus, consisting of 100 popular songs, each of them including a music component, provided in the MIDI format, as well as a lyrics component, made available as raw text. We then describe our work on enhancing this corpus with emotion annotations using crowdsourcing. We also present some initial experiments on emotion classification using the music and the lyrics representations of the songs, which lead to encouraging results, thus demonstrating the promise of using joint music-lyric models for song processing.

关键词： emotion recognition multimodal processing music analysis

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：