检索结果-内蒙古大学图书馆

A Software Implementation of Speculative Memory 18

A Software Implementation of Speculative Memory

18th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)

作者： Fujisawa, Kohei Nunome, Atsushi Shibayama, Kiyoshi Hirata, Hiroaki Kyoto Inst Technol Grad Sch Informat Sci Kyoto Japan Kyoto Inst Technol Fac Informat & Human Sci Kyoto Japan Kyoto Coll Grad Studies Informat Kyoto Japan

ISBN: (纸本)9781509055043

Many techniques for parallelizing a sequentially coded program have been developed and put to practical use, but there are many cases in which program codes cannot be parallelized because it is impossible to assure that their parallel execution does not violate the data dependencies in the program. To parallelize such programs, we have previously proposed speculative memory (SM). With SM, programmers can specify the parallel and speculative execution of threads explicitly in their programs. The SM system manages the memory data that are speculatively read or written by the threads running in parallel. When the system detects inconsistent memory accesses, it recovers the computational state of the program and restarts the execution. If such inconsistencies are not encountered often, we can expect the total execution time of the program to be shorter. In this paper we present a software implementation of SM (SSM). We have developed an SM library by using POSIX threads. In spite of large overheads that are essentially unavoidable in a software implementation, our SSM system can shorten the execution time of a program that compilers cannot parallelize automatically.

关键词： thread-level speculation (TLS) speculative multithreading (SpMT) parallel architecture multithreaded programming

来源：评论

学校读者我要写书评

暂无评论

Multi-threaded Approach to Software High-speed Algorithms for Spectral Analysis of Multi-component Signals 21

Multi-threaded Approach to Software High-speed Algorithms fo...

引用

21st International Conference on Complex Systems - Control and Modeling Problems (CSCMP)

作者： Yakimov, Vladimir Zaberzhinskij, Borislav Mashkov, Andrey Bukanova, Yuliya Samara State Tech Univ Samara Russia

ISBN: (纸本)9781728167008

The article discusses the development of specialized software measuring-computing system, designed to operational spectral analysis of multicomponent signals based on data processing, obtained by simulating the procedure of binary sign-function quantization. The need to create specialized software measuring-computing system that implements the evaluation of the spectral components of multicomponent processes is caused by the fact that existing proprietary software products either have redundant functionality to solve highly specialized tasks or do not provide the necessary flexibility in the provision, support and modification of libraries that meet specific requirements. The software structure consists of the following main software components: a module for visualization of measurement data, a module for implementing the algorithm for spectral analysis of multicomponent signals, and a data processing converter between the user interface and the module for implementing algorithms. The graphical user interface is implemented using the high-tech integrated development environment Intellij IDEA in the Java 8 multi-platform programming language, which allows extending the functionality of the measurement system. The modules of the metrologically significant part of the software that perform the functions of processing, storing and transmitting measurement data and spectral analysis results are implemented in the resource efficient C ++ 17 language. The use of C ++ provided an opportunity to apply a multi-threaded programming approach in order to improve the performance of the procedures for calculating spectral estimates. Using the mechanism of multithreaded algorithm execution, it became possible to parallelize processor calculations and input-output operations and, as a result, reduce the computational costs of obtaining estimates of the time-frequency characteristics of signals by introducing alternation mechanisms for performing various weakly interconnected subtask

关键词： digital signal processing spectral analysis binary sign-function analog-stochastic quantization software measuring-computing system resource-efficient algorithms multithreaded programming

来源：评论

学校读者我要写书评

暂无评论

Going Parallel over the Rainbow

Going Parallel over the Rainbow

引用

International Conference on High Performance Computing & Simulation (HPCS)

作者： Alesii, Giuseppe Univ Aquila Dept Informat Engn Comp Sci & Math I-67010 Coppito Di Laquila AQ Italy

ISBN: (纸本)9781479953134

Some parallel algorithms are proposed to speed up computation of multivariate lattices used to evaluate rainbow options. These novel algorithms have been programmed using multi-threaded syntax in Gauss(tm) of Aptech honing codes for 32 and 128 cores machines. Actual scaling is linear or superlinear in excess of Amdahl theoretical thresholds. Rainbow options have been valued with several multivariate lattices models programmed according to our parallelization algorithms providing results not found in extant literature in terms of granularity and convergence.

关键词： Rainbow Options multivariate binomial lattices multivariate trinomial lattices parallel computation multithreaded programming multicore machines derivatives pricing multivariate binomial/trinomial lattices pthreads OpenMP Aptech Gauss

来源：评论

学校读者我要写书评

暂无评论

PARSNIP: Performant Architecture for Race Safety with No Impact on Precision 17

PARSNIP: Performant Architecture for Race Safety with No Imp...

引用

50th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)

作者： Peng, Yuanfeng Wood, Benjamin P. Devietti, Joseph Univ Penn Philadelphia PA 19104 USA Wellesley Coll Wellesley MA 02181 USA

ISBN: (纸本)9781450349529

Data race detection is a useful dynamic analysis for multithreaded programs that is a key building block in record-and-replay, enforcing strong consistency models, and detecting concurrency bugs. Existing software race detectors are precise but slow, and hardware support for precise data race detection relies on assumptions like type safety that many programs violate in practice. We propose PARSNIP a fully precise hardware-supported data race detector. PARSNIP exploits new insights into the redundancy of race detection metadata to reduce storage overheads. PARSNIP also adopts new race detection metadata encodings that accelerate the common case while preserving soundness and completeness. When bounded hardware resources are exhausted, PARSNIP falls back to a software race detector to preserve correctness. PARSNIP does not assume that target programs are type safe, and is thus suitable for race detection on arbitrary code. Our evaluation of PARSNIP on several PARSEC benchmarks shows that performance overheads range from negligible to 2.6x, with an average overhead of just 1.5x. Moreover, PARSNIP outperforms the state-of-the-art Radish hardware race detector by 4.6x.

关键词： multithreaded programming data race detection hardware support

来源：评论

学校读者我要写书评

暂无评论

A multithreaded concurrent garbage collector parallelizing the new instruction in Java 16

A multithreaded concurrent garbage collector parallelizing t...

引用

16th International Parallel and Distributed Processing Symposium, IPDPS 2002

作者： Lo, C.-T.D. Srisa-An, W. Chang, J.M. Department of Computer Science Illinois Institute of Technology ChicagoIL60616-3793 United States

ISBN: (纸本)0769515738

Parallel, multithreaded Java applications such as Web servers, database servers, and scientific applications are becoming increasingly prevalent. Most of them have high object instantiation rates through the new bytecode that is implemented in a garbage collection subsystem typically. For aforementioned applications, traditional garbage collectors are often the bottleneck that limits program performance and processor utilization on multiprocessor systems. They suffer from long garbage collection pauses (stop-the-world mark-sweep algorithm) or inability of collecting cyclic garbage (reference counting approach). Generational garbage collection, however, is based only on the weak generational hypothesis that most objects die young. In this paper, a new multithreaded concurrent generational garbage collector (MCGC) based on mark-sweep with the assistance of reference counting is proposed. The MCGC can take advantage of multiple CPUs in an SMP system and the merits or light weight processes. Furthermore, the long garbage collection pause can be reduced and the garbage collection efficiency can be enhanced. © 2002 IEEE.

关键词： concurrent garbage collection dynamic memory management Java Virtual Machine multithreaded programming object-oriented programming parallel garbage collector

来源：评论

学校读者我要写书评

暂无评论

High performance computing experiments in enumerative and algebraic combinatorics

High performance computing experiments in enumerative and al...

引用

2017 International Workshop on Parallel and Symbolic Computation, PASCO 2017

作者： Hivert, Florent Univ. Paris Sud 11 Paris France Bureau 33 Bâtiment 650 Université Paris Sud 11 Orsay Cedex91405 France

来源：评论

学校读者我要写书评

暂无评论

RecPlay: A fully integrated practical record/replay system

引用

ACM TRANSACTIONS ON COMPUTER SYSTEMS 1999年第2期17卷 133-152页

作者： Ronsse, M De Bosschere, K Univ Ghent Dept Elect & Informat Sci B-9000 Ghent Belgium

This article presents a practical solution for the cyclic debugging of nondeterministic parallel programs. The solution consists of a combination of record/replay with automatic on-the-fly data race detection. This combination enables us to limit the record phase to the more efficient recording of the synchronization operations, while deferring the time-consuming data race detection to the replay phase. As the record phase is highly efficient, there is no need to switch it off, hereby eliminating the possibility of Heisenbugs because tracing can be left on all the time. This article describes an implementation of the tools needed to support RecPlay.

关键词： binary code modification multithreaded programming race detection

来源：评论

学校读者我要写书评

暂无评论

A Distributed Control and Communication Structure for Multiple Cooperating Robot Agents

引用

IFAC Proceedings Volumes 2000年第28期33卷 279-284页

作者： Gen’ichi Yasuda Department of Mechanical Engineering Faculty of Engineering Nagasaki Institute of Applied Science 536 Aba-machi Nagasaki 851-0193 Japan

This paper describes a distributed control and communication structure for industrial muH i robot systems where several robots and devices have to be controlled simultaneously. A task-level programming and execution system, where task control is performed using Petri ncts, is presented. A commercially available OS, Windows NT, is used to develop and debug application programs and to coordinate cooperating robot agents in real lime. The control software is implemented on a widely used and powerful PC-based architecture using multithreaded programming in order to achieve efficient utilization of CPU time and real-time vision-based control. Workccll tasks demonstrating robotic handling operations, arc successfully implemented using the control system scheme.

关键词： Multirobol systems robot agents: Petri nets distributed cooperative processing: PC multithreaded programming

来源：评论

学校读者我要写书评

暂无评论

Optimizing LZW Text Compression Algorithm via Multithreading programming

Optimizing LZW Text Compression Algorithm via Multithreading...

引用

IEEE Malaysia International Conference on Communications

作者： Ling Sun Tan Sei Ping Lau Chong Eng Tan Faculty of Computer Science and Information Technology University Malaysia Sarawak

ISBN: (纸本)9781424455317;9781424455324

Due to the emerging multimedia technology, multimedia files such as text, image, audio and video files are widely used. These multimedia files take hundreds time more space as compared to early day's media files. Thus, demand for efficient compression algorithm is in great needs. Currently, a lot of general purpose multi-core processor machines and systems are widely available. However, many compression algorithms have not been taking advantage of being optimized for these processors. This paper explores the multithreaded compression algorithm to take advantages offered by multi-core processor.

关键词： Text compression Parallel multithreaded programming Text compression Compression algorithms Parallel Lines Multi-core processors Videotapes Multithreading

来源：评论

学校读者我要写书评

暂无评论

Automated Measurement System for Wireless Transmitters

Automated Measurement System for Wireless Transmitters

引用

2007 8th International Conference on Electronic Measurement & Instruments（ICEMI’2007）

作者： Wang Pinglian Yuan Sumin (Academy of electro-optics,Chinese Academy of Science 100080 China)

In this paper,an automated measurement system for wireless transmitters with different frequencies,modulation types,and bit rates is *** VISA(Virtual Instrument Software Architecture) and COM API(Application programming Interface),the system can operate the spectrum analyzer,vector signal analyzer(VSA89600),oscilloscope according to the user's *** the help of peripheral circuits and multithreaded programming techniques, the automated measurement system can measure from DC to radio frequency signals;perform spectrum and modulation quality analysis of EUT(Equipment under test) automatically;during the measurement process,operating status of EUT can be real time monitored,if the operating status of EUT is abnormal,EUT would be shut down immediately.

关键词： ATE(Automated test equipment) VISA,SCPI COM API multithreaded 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：