检索结果-内蒙古大学图书馆

8th International Workshop on Languages and Compilers for Parallel Computing, LCPC 1995

作者： Moreira, José E. Schouten, Dale Polychronopoulos, Constantine IBM T. J. Watson Research Center Yorktown HeightsNY10598-0218 United States Center for Supercomputing Research and Development Coordinated Science Laboratory University of Illinois at Urbana-Champaign 1308 W. Main St UrbanaIL61801-2307 United States

ISBN: (纸本)9783540607656

Task granularity and functional parallelism are fundamental issues in the optimization of parallel programs. Appropriate granularity for exploitation of parallelism is affected by characteristics of both the program and the execution environment. In this paper we demonstrate the efficacy of dynamic granularity control. The scheme we propose uses dynamic runtime information to select the task size of exploited parallelism at various stages of the execution of a program. We also demonstrate that functional parallelism can be an important factor in improving the performance of parallel programs, both in the presence and absence of loop-level parallelism. Functional parallelism can increase the amount of large-grain parallelism as well as provide finer-grain parallelism that leads to better load balance. Analytical models and benchmark results quantify the impact of granularity control and functional parallelism. The underlying implementation for this research is a low-overhead threads model based on user-level scheduling. © Springer-Veriag Berlin Heidelberg 1996.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Polaris: Improving the effectiveness of parallelizing compilers 7th

Polaris: Improving the effectiveness of parallelizing compil...

引用

7th International Workshop on Languages and Compilers for Parallel Computing, 1994

作者： Blume, William Eigenmann, Rudolf Faigin, Keith Grout, John Hoeflinger, Jay Padua, David Petersen, Paul Pottenger, William Rauchwerger, Lawrence Tu, Peng Weatherford, Stephen Center for Supercomputing Research and Development Coordinated Science Laboratory University of Illinois United States

ISBN: (纸本)354058868X

It is the goal of the Polaris project to develop a new parallelizing compiler that will overcome limitations of current compilers. While current parallelizing compilers may succeed on small kernels, they often fail to extract any meaningful parallelism from large applications. After a study of application, codes, it was concluded that by adding a few new techniques to current compilers, automatic parallelization becomes possible. The techniques needed are interprocedural analysis, scalar and array privatization, symbolic dependence analysis, and advanced induction and reduction recognition and elimination, along with run-time techniques to allow data dependent behavior. © Springer-Verlag Berlin Heidelberg 1995.

关键词： Privatization

来源：评论

学校读者我要写书评

暂无评论

Autoscheduling in a distributed shared-memory environment 7th

Autoscheduling in a distributed shared-memory environment

引用

7th International Workshop on Languages and Compilers for Parallel Computing, 1994

作者： Moreira, José E. Polychronopoulos, Constantine D. Center for Supercomputing Research and Development and Coordinated Science Laboratory University of Illinois at Urbana-Champaign 1308 W. Main St. UrbanaIL61801-2307 United States

ISBN: (纸本)354058868X

The ease of programming and compiling for the shared memory multiprocessor model, coupled with the scalability and cost advantages of distributed memory computers, give an obvious appeal to distributed shared memory architectures. In this paper we discuss the design and implementation issues of a dynamic data management and scheduling environment for distributed shared memory architectures. In contrast to the predominantly static approaches used on distributed and message passing machines, we advocate the advantages of dynamic resource allocation, especially in the case of multi-user environments. We propose hybrid data and work distribution techniques that adjust to variations in the physical partition and achieve better load balance than purely static schemes. We present the architecture of our execution environment and discuss implementation details of some of the critical components. Preliminary results using benchmarks of representative execution profiles support our main thesis: With minimal control, the load balancing and resource utilization advantages offered by dynamic methods often outweigh the disadvantage of increased memory latency stemming from slightly compromised data locality, and perhaps additional run-time overhead. © Springer-Verlag Berlin Heidelberg 1995.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

Acquisition time performance of a novel serial search acquisition scheme for chip-asynchronous DS/SS systems

Acquisition time performance of a novel serial search acquis...

引用

MILCOM, Military Communications Conference

作者： R.A. Korkosz D.V. Sarwate Electronic Systems Laboratory GE Corporate Research and Development Center Schenectady NY USA Coordinated Science Laboratory University of Illinois Urbana-Champaign Urbana-Champaign IL USA

We study the mean acquisition time performance of a novel serial search acquisition scheme for chip-asynchronous direct-sequence spread-spectrum systems. The sequences arising under the out-of-phase hypothesis are modeled as random sequences, and an appropriate likelihood ratio is used in a sequential probability ratio test (SPRT) to test for the true phase of the received sequence. A different (and commonly used) likelihood ratio is obtained for the SPRT if the out-of-phase sequences are modeled as zero sequences, and we use the performance under this model as a benchmark for comparison. An appropriate verification stage for the serial search scheme is designed based on fixed sample size (FSS) tests which employ the same likelihood ratio as used in the testing stage. A general expression for the mean acquisition time Er[T/sub acq/] is derived, and the results indicate that the test statistic based on the random sequence model offers considerable savings in E[T/sub acq/] for moderate to large values of chip SNR.

关键词： Random sequences Sequential analysis System testing Spread spectrum communication Laboratories Benchmark testing Frequency selective surfaces Genetic expression Statistical analysis Correlators

来源：评论

学校读者我要写书评

暂无评论

MPSA abstracts

引用

Journal of Protein Chemistry 1994年第5期13卷 515-543页

作者： Aminlari, Mahmoud Asquith, Thomas Sarlo, Katherine Bailey, Jerome M. Tu, Oanh Issai, Gilbert Ha, Alice Shively, John E. Bell, Alexander W. Baur, Nicole C. Bergeron, John J. M. Ou, Wei -Jia Thomas, David Y. Cianflone, Katherine Baldo, Allain Hincke, Maxwell T. Momparler, Richard L. Laliberté, Josée Thomson, David M. P. Sutherland, M. Besada, Vladimir Gonzalez, Javier Padron, Gabriel Garay, Hilda Reyes, Osvaldo Takao, Toshifumi Shimonishi, Yasutsugu Bischoff, Rainer Roecklin, Dominique Bouchon, Bernadette Klarskov, Klaus Van Dorsselaer, Alain Brake, Patricia G. Pacitti, Anne Higgins, Terry Stevis, Panos Malinowski, John McElhiney, Sue Huang, Janes Vestal, Christine Buckel, Scott D. Stevenson, Tracy Loo, Joseph A. Caffrey, Martin Wang, Jin Wallace, Carmichael J. A. Clark-Lewis, Ian Carraway, C. A. Carothers Huang, J. Li, Y. Juang, S. -H. Gallo, A. Mayer, B. J. Carraway, K. L. Coleman, Patrick L. Sarpong, Daniel Deerfield, David W. Holland-Minkley, Amanda Hempel, John D. Nicholas, Hugh B. Denslow, Nancy D. Folmar, Leroy C. Sullivan, Craig V. Dixon, James D. Mark, Jonathan P. Elicone, Christopher P. Maleknia, Simin D. McGuinness, Brian F. Regnier, Fred E. Afeyan, Noubar B. Dolence, Julia M. Poulter, C. Dale Egorov, Tsezi Musolyamov, Alexander Popineau, Yves Andersen, Jens Roepstorff, Peter Falkenstein, Roberto J. Biscoglio de Jiménez Bonino, Mirtha J. Peña, Clara Gauggel, D. L. Asquith, T. N. Isfort, R. J. Miller, N. S. Cody, D. B. Giblin, Michael F. Wong, Tuck C. Quinn, Thomas P. Grant, Gregory A. Crankshaw, Mark W. Griffith, Scott Schroeder, Steve Quinn, Thomas Guinet, F. Petillot, Y. Chapsal, J. M. Dubayle, J. Greco, F. Barge, O. Forest, E. Valentin, C. Hahn, Frederick M Baker, Jonathan A. Haniu, Mitsuru Kenney, William C. Rohde, Michael F. Harman, James G. Lee, Eun Ju Glasgow, Joel Lew, Sew Fen Belduz, Ali O. Harris, Reed J. Molony, Michael S. Keyt, Lene H. Wu, Shiaw -Lin Hawke, David H. Tso, Jaqueline Early, Sherrell Miller, Chad G. Hayman, G. Thomas Miernyk, Jan A. Hellman, Ulf Wernstedt, Christer Góñez, Jorge H Department of Biochemistry School of Veterinary Medicine Shiraz University Shiraz Iran Corporate Professional & Regulatory Services/Human Safety Dept. The Procter & Gamble Co. Cincinnati Division of Immunology Beckman Research Institute of the City of Hope Duarte Protein Analytic Facility Sheldon Biotechnology Centre USA McGill University Montreal Department of Anatomy USA Biotechnology Research Institute NRC Canada Division of Cardiology Royal Victoria Hospital USA Department of Anatomy University of Ottawa Faculty of Health Science Ottawa Centre de Recherche Pediatrique Hôpital Ste-Justine Université de Montréal Montreal Department of Immunology Montreal General Hospital USA Center for Genetic Engineering & Biotechnology Cuba Institute for Protein Research Osaka University Osaka Japan Protein Analytical Group TRANSGENE S.A. Strasbourg Cedex France Vakgroep Biochemie Fysiologie en Microbiologie Gent Belgium Laborat. de Spectrométrie de Masse Bioorganique URA 31 CNRS Université Louis Pasteur Strasbourg Cedex France Sterling winthrop Inc. Collegeville Lexin Pharmaceutical Corporation Horsham PerSeptive Biosystems Houston Parke-Davis Pharmaceutical Research Division of Warner Lambert Company Ann Arbor Dept. of Chemistry The Ohio State University Columbus USA Dept. of Biochemistry Dalhousie University Halifax Canada Biomedical Research Center University of British Columbia Vancouver Canada Dept. of Biochem. & Molec. Biol. Univ. of Miami Sch. of Medicine Miami The Rockefeller Institute New York Dept. of Cell Biol. & Anat. Univ. of Miami Sch. of Medicine Miami Biosciences Laboratory 3M Co. St. Paul Pittsburgh Supercomputing Center Pittsburgh Department of Molecular Genetics/Biochemistry University of Pittsburgh Pittsburgh Dept. Biochem. and Mol. Biol. University of Florida Gainesville U.S. Environmental Protection Agency Gulf Breeze Dept. Zoology North Carolina State University Raleigh PerSeptive Biosystems Inc. Cambridge Department of Chemistry Univ

来源：评论

学校读者我要写书评

暂无评论

Dense and iterative concurrent linear algebra in the Multicomputers Toolbox

Dense and iterative concurrent linear algebra in the Multico...

引用

1993 Scalable Parallel Libraries Conference, SPLC 1993

作者： Bangalore, P.V. Skjellum, A. Baldwin, C. Smith, S.G. Computer Science Department NSF Engineering Research Center Mississippi State University MS39762 United States Center for Supercomputing Research and Development University of Illinois UrbanaIL61801 United States Center for Computational Sciences and Engineering Lawrence Livermore National Laboratory LivermoreCA94551 United States

ISBN: (纸本)0818649801

The Multicomputer Toolbox includes sparse, dense, and iterative scalable linear algebra libraries. Dense direct, and iterative linear algebra libraries are covered in this paper, as well as the distributed data structures used to implement these algorithms;concurrent BLAS are covered elsewhere. We discuss uniform calling interfaces and functionality for linear algebra libraries. We include a detailed explanation of how the level-3 dense LU factorization works, including features that support data distribution independence with a blocked algorithm. We illustrate the data motion for this algorithm, and for a representative iterative algorithm, PCGS. We conclude that data distribution independent libraries are feasible and highly desirable. Much work remains to be done in performance tuning of these algorithms, though good portability and application-relevance have already been achieved. © 1994 IEEE.

关键词： Libraries

来源：评论

学校读者我要写书评

暂无评论

THE CALLING(SM) NETWORK - A GLOBAL WIRELESS COMMUNICATION-SYSTEM

引用

INTERNATIONAL JOURNAL OF SATELLITE COMMUNICATIONS 1994年第1期12卷 45-61页

作者： TUCK, EF PATTERSON, DP STUART, JR LAWRENCE, MH Calling Communications Corporation. 1900 West Garvey Ave South. Suite 200 West Covina CA 91790 USA. Chairman of Calling Communications Corporation. He is also the Managing Director of Kinship Venture Management Inc. the general partner of Kinship Partners 11 and a General Partner of Boundary the general partner of The Boundary Fund. As a venture capitalist he has founded or participated in founding several telecommunications companies including Calling Communications Corporation Magellan Systems Corporation manufactures of Global Positioning System receivers Applied Digital Access manufacturer of DS-3 test access and network performance monitoring equipment Endgate Technology Corporation specialists in satellite phased array antennas and Poynting Systems Corporation. now a division of Reliance Corporation manufacturers of fibre optic transport equipment. He was a founder of Kebby Microwave Corporation where he invented the first solid-state. frequency-modulated commercial microwave link system. The company was acquired by ITT Corporation where he rose to the position of V.P. and Technical Director of ITT North America Telecommunications Inc. Subsequently he was V.P. of Marketing and Engineering at American Telecommunications Inc. (ATC). He was founding Director of American Telecom Inc. a joint venture between ATC and Fujitsu and has served on more than 20 boards of directors including those of three public companies. He has authored articles on microwave engineering and telephone signalling and was a contributor to Reference Data For Radio Engineers. He is a graduate of the University of Missouri at Rolla where he was later awarded an honorary Professional degree and serves on its Academy of Electrical Engineering. Mr Tuck is a Senior Member of the IEEE a Fellow of the Institution of Engineers (Australia) a Professional Member of the AIAA and a registered professional engineer in three states. More than 25 years of experience in the telecommunications industry where he has been responsibl

There is a very large demand for basic telephone service in developing nations, and remote parts of industrialized nations, which cannot be met by conventional wireline and cellular systems. This is the world's largest unserved market. We describe a system which uses recent advances in active phased arrays, fast-packet switching technology, adaptive routeing, and light spacecraft technology, in part based on the work of the Jet Propulsion laboratory and on recently-declassified work done on the Strategic Defense Initiative, to make it possible to address this market with a global telephone network based on a large low-Earth-orbit constellation of identical satellites. A telephone utility can use such a network to provide the same modern basic and enhanced telephone services offered by telephone utilities in the urban centres of fully-industrialized nations. Economies of scale permit capital and operating costs per subscriber low enough to provide a service to all subscribers, regardless of location, at prices comparable to the same services in urban areas of industrialized nations, while generating operating profits great enough to attract the capital needed for its construction. The bandwidth needed to support the capacity needed to gain these economies of scale requires that the system use K(alpha)-band frequencies. This choice of frequencies places unusual constraints on the network design, and in particular forces the use of a large number of satellites. Global demand for basic and enhanced telephone service is great enough to support at least three networks of the size described herein. The volume of advanced components, and services such as launch services, required to construct and replace these networks is sufficient to propel certain industries to market leadership positions in the early 21st Century.

关键词： LOW EARTH ORBIT SATELLITE COMMUNICATIONS FAST PACKET SWITCHING EARTH FIXED CELLS ADAPTIVE ROUTEING LIGHT SPACECRAFT K(A) BAND PHASED-ARRAY ANTENNAS

来源：评论

学校读者我要写书评

暂无评论

Dense and iterative concurrent linear algebra in the Multicomputers Toolbox

Dense and iterative concurrent linear algebra in the Multico...

引用

Scalable Parallel Libraries Conference

作者： P.V. Bangalore A. Skjellum C. Baldwin S.G. Smith Computer Science Department & NSF Engineering Research Center Mississippi State University MS USA Center for Supercomputing Research & Development University of Illinois Urbana IL USA Center for Computational Sciences & Engineering Lawrence Livemore National Laboratory Livermore CA USA

The Multicomputer Toolbox includes sparse, dense, and iterative scalable linear algebra libraries. Dense direct, and iterative linear algebra libraries are covered in this paper, as well as the distributed data structures used to implement these algorithms; concurrent BLAS are covered elsewhere. We discuss uniform calling interfaces and functionality for linear algebra libraries. We include a detailed explanation of how the level-3 dense LU factorization works, including features that support data distribution independence with a blocked algorithm. We illustrate the data motion for this algorithm, and for a representative iterative algorithm, PCGS. We conclude that data distribution independent libraries are feasible and highly desirable. Much work remains to be done in performance tuning of these algorithms, though good portability and application-relevance have already been achieved.< >

关键词： Linear algebra Libraries Iterative algorithms Data structures Data engineering Vectors Linear systems Jacobian matrices Computer science Message passing

来源：评论

学校读者我要写书评

暂无评论

Languages and compilers for parallel computing: 5th international workshop New Haven, Connecticut, USA august 3-5, 1992 proceedings

Languages and compilers for parallel computing: 5th internat...

引用

IFIP WG 5.7 International Conference on Advances in Production Management Systems, APMS 2017

作者： Banerjee, Utpal Gelernter, David Nicolau, Alex Padua, David Intel Corporation 2200 Mission College Blvd. P. O. Box 58119 RN6-18 Santa ClaraCA95052 United States Dept. of Computer Science Yale University 51 Prospect St. New HavenCT06520 United States Dept. of Information & Computer Science University of California 444 Computer Science Bldg. IrvineCA92717 United States Center for Supercomputing Research and Development 465 Computer and Systems Research Laboratory 1308 West Main St. UrbanaIL61801 United States

来源：评论

学校读者我要写书评

暂无评论

A new approach for solving symmetric eigenvalue problems

引用

Computing Systems in Engineering 1992年第6期3卷 671-679页

作者： Carey, C. Chen, H.-C. Golub, G. Sameh, A. Department of Computer Science Stanford University Stanford CA 94305 United States Center for Supercomputing Research and Development University of Illinois at Urbana-Champaign 305 Talbot Laboratory Urbana IL 61801-2932 104 South Wright St United States Department of Computer Science University of Minnesota Minneapolis MN 55455 4-192 EE/Sci. Bldg. 200 Union St SE United States

In this paper, we present a new approach for the solution to a series of slightly perturbed symmetric eigenvalue problems (A + BSiBT)x = λx, 0 ≤ i ≤ m, where A = AT ε{lunate} Rn × n, B ε{lunate} Rn × p,...

In this paper, we present a new approach for the solution to a series of slightly perturbed symmetric eigenvalue problems (A + BS_iB^T)x = λx, 0 ≤ i ≤ m, where A = A^T ε{lunate} R^{n × n}, B ε{lunate} R^{n × p}, and S_i = S^T_i ε{lunate} R^{p × p}, p ≪ n. The matrix B is assumed to have full column rank. The main idea of our approach lies in a specific choice of starting vectors used in the block Lanczos algorithm so that the effect of the perturbations is confined to lie in the first diagonal block of the block tridiagonal matrix that is produced by the block Lanczos algorithm. Subsequently, for the perturbed eigenvalue problems under our consideration, the block Lanczos scheme needs to be applied to the original (unperturbed) matrix only once and then the first diagonal block updated for each perturbation so that for low-rank perturbations, the algorithm presented in this paper results in significant savings. Numerical examples based on finite element vibration analysis illustrate the advantages of this approach. © 1993.

关键词：

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：