检索结果-内蒙古大学图书馆

New fast divide-and-conquer algorithms for the symmetric tridiagonal eigenvalue problem

NUMERICAL LINEAR ALGEBRA WITH APPLICATIONS 2016年第4期23卷 656-673页

作者： Li, Shengguo Liao, Xiangke Liu, Jie Jiang, Hao Natl Univ Def Technol Coll Comp Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha 410073 Hunan Peoples R China Natl Univ Def Technol State Key Lab High Performance Comp Changsha 410073 Hunan Peoples R China

In this paper, two accelerated divide-and-conquer (ADC) algorithms are proposed for the symmetric tridiagonal eigenvalue problem, which cost O(N(2)r) flops in the worst case, where N is the dimension of the matrix and r is a modest number depending on the distribution of eigenvalues. Both of these algorithms use hierarchically semiseparable (HSS) matrices to approximate some intermediate eigenvector matrices, which are Cauchy-like matrices and are off-diagonally low-rank. The difference of these two versions lies in using different HSS construction algorithms, one (denoted by ADC1) uses a structured low-rank approximation method and the other (ADC2) uses a randomized HSS construction algorithm. For the ADC2 algorithm, a method is proposed to estimate the off-diagonal rank. Numerous experiments have been carried out to show their stability and efficiency. These algorithms are implemented in parallel in a shared memory environment, and some parallel implementation details are included. Comparing the ADCs with highly optimized multi-threaded libraries such as Intel MKL, we find that ADCs could be more than six times faster for some large matrices with few deflations. Copyright (C) 2016 John Wiley & Sons, Ltd.

关键词： HSS matrices cauchy-like matrices eigenvalue problems Schur complements divide-and-conquer algorithm

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis and Optimization of Full Garbage Collection in Memory-hungry Environments 16

Performance Analysis and Optimization of Full Garbage Collec...

引用

12th ACM SIGPLAN/SIGOPS International Conference on Virtual Execution Environments

作者： Yu, Yang Lei, Tianyang Zhang, Weihua Chen, Haibo Zang, Binyu Fudan Univ Sch Comp Sci Shanghai Peoples R China Fudan Univ Shanghai Key Lab Data Sci Shanghai Peoples R China Shanghai Jiao Tong Univ Inst Parallel & Distributed Syst Shanghai 200030 Peoples R China Fudan Univ Parallel Proc Inst Shanghai Peoples R China

ISBN: (纸本)9781450339476

Garbage collection (GC), especially full GC, would nontrivially impact overall application performance, especially for those memory-hungry ones handling large data sets. This paper presents an in-depth performance analysis on the full GC performance of parallel Scavenge (PS), a state-of-the-art and the default garbage collector in the HotSpot JVM, using traditional and big-data applications running atop JVM on CPU (e. g., Intel Xeon) and many-integrated cores (e. g., Intel Xeon Phi). The analysis uncovers that unnecessary memory accesses and calculations during reference updating in the compaction phase are the main causes of lengthy full GC. To this end, this paper describes an incremental query model for reference calculation, which is further embodied with three schemes (namely optimistic, sort-based and region-based) for different query patterns. Performance evaluation shows that the incremental query model leads to averagely 1.9X (up to 2.9X) in full GC and 19.3% (up to 57.2%) improvement in application throughput, as well as 31.2% reduction in pause time over the vanilla PS collector on CPU, and the numbers are 2.1X (up to 3.4X), 11.1% (up to 41.2%) and 34.9% for Xeon Phi accordingly.

关键词： incremental query hotspot jvm full garbage collection compaction

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Multimedia Retrieval Workloads Running on Multicores

引用

IEEE TRANSACTIONS ON parallel AND distributed SYSTEMS 2016年第11期27卷 3323-3337页

作者： Lu, Yunping Wang, Xin Zhang, Weihua Chen, Haibo Peng, Lu Zhao, Wenyun Fudan Univ Shanghai Key Lab Data Sci Shanghai Peoples R China Fudan Univ Sch Comp Sci Shanghai Peoples R China Fudan Univ Parallel Proc Inst Shanghai Peoples R China Fudan Univ Software Sch Shanghai Peoples R China Shanghai Jiao Tong Univ Inst Parallel & Distributed Syst Shanghai Peoples R China Louisiana State Univ Div Elect & Comp Engn Baton Rouge LA 70803 USA

Multimedia data has become a major data type in the Big Data era. The explosive volume of such data and the increasing real-time requirement to retrieve useful information from it have put significant pressure in processing such data in a timely fashion. However, while prior efforts have done in-depth analysis on architectural characteristics of traditional multimedia processing and text-based retrieval algorithms, there has been no systematic study towards the emerging multimedia retrieval applications. This may impede the architecture design and system evaluation of these applications. In this paper, we make the first attempt to construct a multimedia retrieval benchmark suite (MMRBench for short) that can be used to evaluate architectures and system designs for multimedia retrieval applications. MMRBench covers modern multimedia retrieval algorithms with different versions (sequential, parallel and distributed). MMRBench also provides a series of flexible interfaces as well as certain automation tools. With such a flexible design, the algorithms in MMRBench can be used both in individual kernel-level evaluation and in integration to form a complete multimedia data retrieval infrastructure for full system evaluation. Furthermore, we use performance counters to analyze a set of architecture characteristics of multimedia retrieval algorithms in MMRBench, including the characteristics of core level, chip level and inter-chip level. The study shows that micro-architecture design in current processor is inefficient (both in performance and power) for these multimedia retrieval workloads, especially in core resources and memory systems. We then derive some insights into the architecture design and system evaluation for such multimedia retrieval algorithms.

关键词： Multimedia retrieval benchmarks architectural characteristics

来源：评论

学校读者我要写书评

暂无评论

Enabling Tissue-scale Cardiac Simulations using Heterogeneous Computing on Tianhe-2 22

Enabling Tissue-scale Cardiac Simulations using Heterogeneou...

引用

22nd IEEE International Conference on parallel and distributed Systems (ICPADS)

作者： Langguth, Johannes Lan, Qiang Gaur, Namit Cai, Xing Wen, Mei Zhang, Chun-yuan Simula Res Lab N-1325 Lysaker Norway Univ Oslo Dept Informat N-0316 Oslo Norway Natl Univ Def Technol Coll Comp Changsha 410000 Hunan Peoples R China Natl Key Lab Parallel & Distributed Proc Changsha 410000 Hunan Peoples R China

ISBN: (纸本)9781509044573

We develop a simulator for 3D tissue of the human cardiac ventricle with a physiologically realistic cell model and deploy it on the supercomputer Tianhe-2. In order to attain the full performance of the heterogeneous CPU-Xeon Phi design, we use carefully optimized codes for both devices and combine them to obtain suitable load balancing. Using a large number of nodes, we are able to perform tissue-scale simulations of the electrical activity and calcium handling in millions of cells, at a level of detail that tracks the states of trillions of ryanodine receptors. We can thus simulate arrythmogenic spiral waves and other complex arrhythmogenic patterns which arise from calcium handling deficiencies in human cardiac ventricle tissue. Due to extensive code tuning and parallelization via OpenMP, MPI, and SCIF/COI, large scale simulations of 10 heartbeats can be performed in a matter of hours. Test results indicate excellent scalability, thus paving the way for detailed whole-heart simulations in future generations of leadership class supercomputers.

关键词： Calcium Handling Multiscale Cardiac Tissue Simulation Supercomputing Xeon Phi

来源：评论

学校读者我要写书评

暂无评论

parallelizing image feature extraction algorithms on multi-core platforms

引用

JOURNAL OF parallel AND distributed COMPUTING 2016年 92卷 1-14页

作者： Lu, Yunping Li, Yi Song, Bo Zhang, Weihua Chen, Haibo Peng, Lu Fudan Univ Software Sch Shanghai 200433 Peoples R China Fudan Univ Shanghai Key Lab Data Sci Shanghai 200433 Peoples R China Fudan Univ Parallel Proc Inst Shanghai 200433 Peoples R China Fudan Univ Sch Comp Sci Shanghai 200433 Peoples R China Shanghai Jiao Tong Univ Inst Parallel & Distributed Syst Shanghai 200030 Peoples R China Louisiana State Univ Div Elect & Comp Engn Baton Rouge LA 70803 USA

Currently, multimedia data has become one of the most important data types processed and transferred over the Internet. To extract useful information from a huge amount of such data, SIFT and SURF, as two most popular image feature extraction algorithms, have been widely used in many applications running on multi-core platforms. However, limited parallelism in existing designs makes it hard or impossible to apply them in many applications with real-time requirements. Therefore, it has become one of the major challenges to improve the processing speed of image feature extraction algorithms. In this paper, we first analyze the parallelism constraints in the algorithms, such as imbalanced workloads and indeterminate time distributions. Based on such analyses, we present an adaptive pipeline parallel scheme (AD-PIPE) to adjust the thread number in different stages according to their workloads dynamically, which achieves a balanced partition for constant input workloads. Furthermore, we also implement a power efficient version (AE-PIPE) for AD-PIPE through scheduling threads based on variable input workloads. Experimental results show that AD-PIPE achieves a speedup of 16.88X and 2033X respectively over SIFT and SURF on a 16-core machine. Moreover, AE-PIPE achieves up to 52.94% and 58.82% power saving with only 3% performance loss. (C) 2016 Elsevier Inc. All rights reserved.

关键词： Image feature extraction SIFT SURF Adaptive pipeline Multi-core

来源：评论

学校读者我要写书评

暂无评论

An improved divide-and-conquer algorithm for the banded matrices with narrow bandwidths

引用

COMPUTERS & MATHEMATICS WITH APPLICATIONS 2016年第10期71卷 1933-1943页

作者： Liao, Xiangke Li, Shengguo Cheng, Lizhi Gu, Ming Natl Univ Def Technol Coll Comp Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha 410073 Hunan Peoples R China Natl Univ Def Technol State Key Lab High Performance Comp Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Coll Sci Changsha 410073 Hunan Peoples R China Univ Calif Berkeley Dept Math Berkeley CA 94720 USA

In this paper we propose a novel divide-and-conquer (DC) algorithm to compute the SVD of banded matrices, and further accelerate it by using rank-structured matrix techniques, especially the hierarchically semiseparable (HSS) matrix. The DC algorithm for the symmetric banded eigenvalue problem can also be accelerated similarly. For matrices with few deflations, the banded DC algorithms require more flops than the classical DC algorithm, and thus they are suitable for narrowly banded matrices. While, if there exist many deflations, the banded DC algorithms can be faster than the classical ones for matrices with relatively large bandwidths. Numerous experiments have been done to test the proposed algorithms. Some of the tested matrices are from construction and some are from real applications. Comparing with the DC algorithm in Intel MKL, our proposed algorithms can be hundreds times faster for matrices with narrow bandwidths or many deflations. (C) 2016 Elsevier Ltd. All rights reserved.

关键词： Divide and conquer algorithm Banded matrices SVD HSS matrices Eigenvalue problem

来源：评论

学校读者我要写书评

暂无评论

An efficient scheme for probabilistic skyline queries over distributed uncertain data

引用

TELECOMMUNICATION SYSTEMS 2015年第2期60卷 225-237页

作者： Li, Xiaoyong Wang, Yijie Yu, Jie Natl Univ Def Technol Natl Key Lab Parallel & Distributed Proc Coll Comp Acad Ocean Sci & Engn Changsha Hunan Peoples R China

Uncertain data has already widely existed in many practical applications, such as sensor networks, RFID networks, location-based services and mobile object management, etc. The skyline queries over uncertain data as an important aspect of uncertain data management, has received extensive attention from the database research community currently, due to its importance in many application including multi-criteria decision making, preference answering, market analysis, etc. However, in most uncertainty applications, the uncertain data are usually collected from vast number of independent data sources among geographically scattered sites, which makes the central assembly of data at one location for storage and query is infeasible and inefficient. Taking account of the network delay and limited bandwidth associated with sharing and communicating large amounts of distributed data over an internet, an important and challenging problem in the scenario is to retrieve all the global skyline tuples from all the distributed local sites with minimum communication cost. In this paper, we propose GFS, which is an efficient scheme for probabilistic skyline over distributed uncertain data. GFS firstly prunes the unqualified tuples with the global grid information and further iteratively prune the unqualified tuples with an improved feedback mechanism. Extensive experiments confirm that the effectiveness and the efficiency of the GFS scheme.

关键词： Uncertain data Probabilistic skyline distributed skyline Grid filtration

来源：评论

学校读者我要写书评

暂无评论

An Efficient Searchable Encryption Against keyword Guessing Attacks for Sharable Electronic Medical Records in Cloud-based System

引用

JOURNAL OF MEDICAL SYSTEMS 2016年第12期40卷 258-258页

作者： Wu, Yilun Lu, Xicheng Su, Jinshu Chen, Peixin Natl Univ Def Technol Coll Comp Changsha Hunan Peoples R China Natl Univ Def Technol Natl Key Lab Parallel & Distributed Proc Changsha Hunan Peoples R China

Preserving the privacy of electronic medical records (EMRs) is extremely important especially when medical systems adopt cloud services to store patients' electronic medical records. Considering both the privacy and the utilization of EMRs, some medical systems apply searchable encryption to encrypt EMRs and enable authorized users to search over these encrypted records. Since individuals would like to share their EMRs with multiple persons, how to design an efficient searchable encryption for sharable EMRs is still a very challenge work. In this paper, we propose a cost-efficient secure channel free searchable encryption (SCF-PEKS) scheme for sharable EMRs. Comparing with existing SCF-PEKS solutions, our scheme reduces the storage overhead and achieves better computation performance. Moreover, our scheme can guard against keyword guessing attack, which is neglected by most of the existing schemes. Finally, we implement both our scheme and a latest medical-based scheme to evaluate the performance. The evaluation results show that our scheme performs much better performance than the latest one for sharable EMRs.

关键词： Electronic medical record Searchable encryption Cloud storage Secure channels Privacy Security

来源：评论

学校读者我要写书评

暂无评论

Enhanced performance of 17.7 GHz SAW devices based on AlN/diamond/Si layered structure with embedded nanotransducer

引用

APPLIED PHYSICS LETTERS 2017年第25期111卷 253502-253502页

作者： Wang, Lei Chen, Shuming Zhang, Jinying Xiao, Dingbang Han, Kaifeng Ning, Xi Liu, Jingtian Chen, Zhe Zhou, Jian Natl Univ Def Technol Coll Comp Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Natl Lab Parallel & Distributed Proc Changsha 410073 Hunan Peoples R China Chinese Acad Sci Inst Semicond Beijing 100083 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100049 Peoples R China State Key Lab Transducer Technol Shanghai 200050 Peoples R China Natl Univ Def Technol Coll Mechatron Engn & Automat Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Inst Marine Sci & Engn Changsha 410073 Hunan Peoples R China

Surface acoustic wave (SAW) devices using embedded interdigital transducers (IDTs) on an AlN/diamond/Si layered substrate are fabricated, and their performances are investigated. The Sezawa mode is the dominant resonance with the highest resonant frequency up to 17.7 GHz, a signal amplitude of 20 dB, and an electromechanical coupling coefficient of 0.92%. Comparing these SAW devices with those having the conventional IDTs on the same layered structure, the output SAW power and resonant frequency of devices are improved by 10.7% and 1.1%, respectively, for the embedded IDT devices. This is because the different field distribution leads to the different Bragg reflection and phase velocity for the two types of IDTs. The radiation frequency characteristics indicate that the advantages of the embedded IDTs would be useful for high frequency, high power applications such as monolithic integrated millimeter-wave integrated circuit and high speed communications. Published by AIP Publishing.

关键词： Aluminum nitride

来源：评论

学校读者我要写书评

暂无评论

Requirement Acquisition from Social Q&A Sites 2nd

Requirement Acquisition from Social Q&A Sites

引用

2nd Asia-Pacific Requirements Engineering Symposium (APRES)

作者： Xiao, Ming Yin, Gang Wang, Tao Yang, Cheng Chen, Mengwen Natl Univ Def Technol Coll Comp Sci Natl Key Lab Parallel & Distributed Proc Changsha Hunan Peoples R China

ISBN: (纸本)9783662486344;9783662486337

Social Q&A sites have changed the way of knowledge sharing in software communities. Comparing to the traditional mail-list, bug/change repositories, software forums and software marketplaces, users and developers are more active in social Q&A sites, and social Q&A sites are more open and free. The feedbacks from users have much potential valuable information, such as feature requests, bugs or sentiment, but there also exists lots of noise especially for social Q&A sites. How to mine the useful information from the feedbacks in social Q&A sites has become a problem. This paper focuses on the feature requirements in requirement acquisition, which can be used to assist software development. We propose an effective approach, which combines Support Vector Machine (SVM) with requirement dictionary to find the questions about feature requests from the posts in social Q&A sites. We evaluate the approach on available dataset, and compare it to the other different approaches. The results show that the automatically requirement acquisition through improved SVM approach is useful and can significantly decreases the manual effort.

关键词： Requirement acquisition Feature requests Q&A sites

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：