检索结果-内蒙古大学图书馆

Towards a compilation paradigm for computational applications on the information power grid

MATHEMATICS AND COMPUTERS IN SIMULATION 2000年第4-5期54卷 307-320页

作者： Eigenmann, R Voss, MJ Purdue Univ Sch Elect & Comp Engn W Lafayette IN 47907 USA

The Information Power Grid (IPG) refers to the world-wide infrastructure of computers and their interconnections. We are only at the very beginning of exploring applications and system software that can exploit these resources effectively and, at the same time, provide adequate interfaces to the programmer and end-user. In this paper, we discuss compiler technology that serves this purpose. The core consists of methods and services that enable an application to adapt flexibly to the dynamically changing nature of the IPG. We present several applications that demonstrate performance opportunities in such scenarios. We:then present and evaluate new compiler techniques and services that allow an application to be dynamically re-optimized as the execution environments change. One very important property of such system support is that the overheads of dynamic re-optimizations are kept small. We will show that this is the case for the presented techniques. The resulting applications can run close to the best performance that could be obtained with prior knowledge of the runtime situations. (C) 2000 IMACS. Published by Elsevier Science B.V. All rights reserved.

关键词： information power grid adaptive program optimization computational applications

来源：评论

学校读者我要写书评

暂无评论

Analysis on the Levi-Civita field and computational applications

引用

APPLIED MATHEMATICS AND COMPUTATION 2015年 255卷 44-57页

作者： Shamseddine, Khodr Univ Manitoba Dept Phys & Astron Winnipeg MB R3T 2N2 Canada

In this paper, we present an overview of some of our research on the Levi-Civita fields R and C. R (resp. C) is the smallest non-Archimedean field extension of the real (resp. complex) numbers that is Cauchy-complete and real closed (resp. algebraically closed);in fact, R is small enough to allow for the calculus on the field to be implemented on a computer and used in applications such as the fast and accurate computation of the derivatives of real functions as "differential quotients'' up to very high orders. We summarize the convergence and analytical properties of power series, showing that they have the same smoothness behavior as real and complex power series;we present a Lebesgue-like measure and integration theory on the Levi-Civita field R;we discuss solutions to one-dimensional and multi-dimensional optimization problems based on continuity and differentiability concepts that are stronger than the topological ones;and we give a brief summary of the results of our ongoing work on developing a non-Archimedean operator theory on a Banach space over C. (C) 2014 Elsevier Inc. All rights reserved.

关键词： Non-Archimedean analysis Levi-Civita fields Power series Measure theory and integration Optimization computational applications

来源：评论

学校读者我要写书评

暂无评论

Supporting Opportunistic Data Operations for Data-Intensive computational applications

Supporting Opportunistic Data Operations for Data-Intensive ...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Nguyen, Minh-Tri Nguyen, Anh-Dung Rantaharju, Jarno Puro, Touko Rheinhardt, Matthias Korpi-Lagg, Maarit Truong, Hong-Linh Aalto University Department of Computer Science Finland

ISBN: (纸本)9798350362480

A long running data-intensive computational application acquires costly computing resources. With the emerging new architectures, like computing systems with multiple nodes of many-core CPUs and accelerators, while domain-specific tools and libraries employed in such an application leverage high parallelism on accelerators for intensive computations, the remaining resources can potentially be utilized for other application-related data operations. Such data operations, called opportunistic data operations in this work, must usually be carried out for post-processing or follow-up analytics based on results produced during the runtime of the application. These operations are not easily backfilled or preempted under the guidance of the domain scientist or by common task scheduling systems due to their complex *** this paper, we introduce a framework for domain scientists to identify and execute opportunistic data operation tasks. With a minimal specification or modification of the main application, the scientists can specify, monitor, and execute opportunistic tasks independently from the main application and the framework will detect underutilized resources to execute these tasks, thereby, optimizing utilization efficiency within the allocated resources. We present experiments to demonstrate the applicability of our framework on a magnetic field modeling running on the LUMI computing system. © 2024 IEEE.

关键词： computational applications data operations opportunistic tasks performance optimization

来源：评论

学校读者我要写书评

暂无评论

DfAnalyzer: Runtime dataflow analysis tool for computational Science and Engineering applications

引用

SOFTWAREX 2020年 12卷

作者： Silva, Vitor Campos, Vinicius Guedes, Thaylon Camata, Jose de Oliveira, Daniel Coutinho, Alvaro L. G. A. Valduriez, Patrick Mattoso, Marta Univ Fed Rio de Janeiro COPPE Rio De Janeiro Brazil Fluminense Fed Univ Niteroi RJ Brazil Univ Fed Juiz de Fora Juiz De Fora Brazil Univ Montpellier LIRMM CNRS INRIA Montpellier France Snap Inc Santa Monica CA USA

DfAnalyzer is a tool for monitoring, debugging, and analyzing dataflows generated by computational Science and Engineering (CSE) applications. It collects strategic raw data, registering provenance data, and enabling query processing, all asynchronously and at runtime. DfAnalyzer provides lightweight dataflow components to be invoked by CSE applications using High-Performance Computing (HPC), in the same way computational scientists plug HPC (e.g., PETSc) and visualization (e.g., ParaView) libraries. We show DfAnalyzer's main functionalities and how to analyze dataflows in CSE applications at runtime. The performance evaluation of CSE executions for a complex multiphysics application shows that DfAnalyzer has negligible time overhead on the total elapsed time. (C) 2020 The Authors. Published by Elsevier B.V.

关键词： computational Science and Engineering (CSE) Dataflow Provenance computational applications Data analysis

来源：评论

学校读者我要写书评

暂无评论

On the Hahn and Levi-Civita fields: topology, analysis, and applications

On the Hahn and Levi-Civita fields: topology, analysis, and ...

引用

作者： Flynn-Primrose, Darren M. University of Manitoba

学位级别：博士

In this thesis, we present a number of developments regarding the Hahn and Levi-Civita fields. After reviewing the algebraic and order structures of the Hahn field, we introduce different vector topologies that are induced by families of semi-norms and all of which are weaker than the order or valuation topology. We compare those vector topologies and we identify the weakest one whose properties are similar to those of the weak topology on the Levi-Civita field (Shamseddine, 2010). In particular, we state and prove a convergence criterion for power series that is similar to that for power series on the Levi-Civita field in its weak topology (Shamseddine, 2013). We also state three conjectures regarding so-called simple regions and prove a version of Weierstrass' Preparation Theorem in their support. Moreover we show how these conjectures can be used to extend the 2-dimensional integration theory to higher dimensions (Flynn, 2014). We prove a version of Leibniz' Rule for integration on the Hahn field and show how it determines the necessary boundary conditions for Green's Functions derived from the non-Archimedian delta function (Flynn, 2014), we also include corrected and extended examples of the use of Green's Functions for solving linear ordinary differential equations. Finally we investigate some of the computational applications of the Levi-Civita field. We replicate the results of (Shamseddine, 2015) regarding the computation of derivatives of real-valued functions representable on a computer and we show how a similar method can be employed to compute real numerical sequences using their generating functions. We discuss a number of methods of numerical integration that are viable on the Levi-Civita field and we compare their performance to conventional methods as well as to commercial mathematical software.

关键词： Mathematical physics Non-Archimedean Ultrametric Analysis computational applications Hahn field Levi-Civita field Delta function Differential equations Numerical methods

来源：评论

学校读者我要写书评

暂无评论

computational STUDY ON THE RUPTURE RISK IN REAL CEREBRAL ANEURYSMS WITH GEOMETRICAL AND FLUID-MECHANICAL PARAMETERS USING FSI SIMULATIONS AND MACHINE LEARNING ALGORITHMS

引用

JOURNAL OF MECHANICS IN MEDICINE AND BIOLOGY 2019年第3期19卷 1137-1145页

作者： Aranda, Alfredo Valencia, Alvaro Univ Chile Dept Mech Engn Beauchef 851 Santiago 8370456 Chile

Fluid-mechanical and morphological parameters are recognized as major factors in the rupture risk of human aneurysms. On the other hand, it is well known that a lot of machine learning tools are available to study a variety of problems in many fields. In this work, fluid-structure interaction (FSI) simulations were carried out to examine a database of 60 real saccular cerebral aneurysms (30 ruptured and 30 unruptured) using reconstructions by angiography images. With the results of the simulations and geometric analyses, we studied the analysis of variance (ANOVA) statistic test in many variables and we obtained that aspect ratio (AR), bottleneck factor (BNF), maximum height of the aneurysms (MH), relative residence time (RRT), Womersley number (WN) and Von-Mises strain (VMS) are statically significant and good predictors for the models. In consequence, these ones were used in five machine learning algorithms to determine the rupture risk predictions of the aneurysms, where the adaptative boosting (AdaBoost) was calculated with the highest area under the curve (AUC) in the receiver operating characteristic (ROC) curve (AUC 0.944).

关键词： Machine learning FSI simulations cerebral aneurysm simulations statistic predictions statistical significance computational applications

来源：评论

学校读者我要写书评

暂无评论

Can bio-inspired optimization algorithms be used to further improve the collective computing performance? Comment on review article "Does being multi-headed make you better at solving problems? A survey of Physarum-based models and computations" by Chao Gao et al.

引用

PHYSICS OF LIFE REVIEWS 2019年 29卷 48-50页

作者： Xia, Chengyi Huang, Jiechen Tianjin Univ Technol Tianjin Key Lab Intelligence Comp & Novel Softwar Tianjin 300384 Peoples R China Tianjin Univ Technol Minist Educ Key Lab Comp Vis & Syst Tianjin 300384 Peoples R China

来源：评论

学校读者我要写书评

暂无评论

Blockchain Adherence to System Reliability and Security 5

Blockchain Adherence to System Reliability and Security

引用

5th International Conference on Inventive Computation Technologies (ICICT)

作者： Raimundo Mendes, Nilton Paulo de Almeida, Jorge Rady, Jr. Univ Sao Paulo USP Elect Engn Polytech Sch Sao Paulo Brazil

ISBN: (数字)9781665408370

ISBN: (纸本)9781665408387;9781665408370

Currently, the massive use of remote equipment and applications at different levels of modern society is an unprecedented reality. This trend is due to an increasing decentralization and popularization of computing and communication devices for personal use. Due to the demands imposed by environmental and professional factors, work on the virtual model, in which employees are somehow connected and interacting in a network and in a data cloud, has dazzlingly benefited from this infrastructure. The financial market is one of the sectors that favored this context, mainly providing its operations in the hands of its clients. And in this trend, electronic coins also germinated, incorporating a cryptographic procedure with key validation in linked blocks, the so-called Blockchain. But, on the one hand, the systems technology tools allow the benefit of the prompt interaction between people and institutions;on the other hand, they hide the possibility of the improper use of information. Two pillars of the configuration of current solutions are based on the Security and Reliability of Systems: either by characterizing it by the probability of its operation or failure in a safe way or by determining its functioning according to its specification. As it is an essential subject of scientific research, this paper proposes and aims to verify the adherence of Blockchain to the Reliability and Security of Systems using the Markov Model, with the specific outline of the attack strategy, the states of possible attacks, and the observation of this interaction. Due to the evidence of the data presented and its consistent result, the method proved reliable. When addressing security, he crossed the probabilities of an attack versus an honest node finding the next block. The security sensitivity is perceived as a function of a brief period between each attack attempt.

关键词： Blockchain computational applications Critical Security Information Systems Reliability

来源：评论

学校读者我要写书评

暂无评论

A Data Management System for Ab-Initio Nuclear Physics applications 11

A Data Management System for Ab-Initio Nuclear Physics Appli...

引用

High Performance Computing Symposium

作者： Fang Liu Ritu Mundhe Masha Sosonkina Chase Cockrell Miles Aronnax Pieter Maris James P. Vary Ames Laboratory Iowa State University Iowa State University

ISBN: (纸本)9781617828409

Reproducible Research lies at the very core of the scientific method: an experiment is reproducible if it can be replicated by researchers independent from those that conducted it in the first place. Provenance is an emerging concept in computational sciences. In this work, provenance is introduced to another scientific domain - ab initio nuclear physics calculations. Through a data management system, the provenance information is consistently recorded for post-processing, validation, and education purposes. Due to the large volume of data generated in each large scale simulation, the proposed data management system needs to address the high performance computing needs as compared with a traditional database management system.

关键词： Data management system computational applications Reproducible research

来源：评论

学校读者我要写书评

暂无评论

A Parallel Algorithm for a Physiological Non-linear Model of the Cochlea

引用

Procedia Computer Science 2013年 18卷 682-691页

作者： Doron Sabo Shlomo Weiss Miriam Furst School of Electrical Engineering Tel Aviv University Tel Aviv 69978 Israel

We present a parallel algorithm that solves a time-domain non-linear mathematical model of the cochlea. The previously known serial solution of the cochlear model is recursive in the longitudinal dimension and iterative in the time dimension. These two characteristics of the serial solution limit parallelism and prevent efficient computations on a massively parallel processor. We introduce a novel parallel algorithm that successfully overcomes the challenges posed by the cochlear model. We present performance results of a parallel implementation of the algorithm that shortens the computation time by a typical factor of 160 – 180, which makes the proposed algorithm of practical value for applications such as clinical audiological diagnosis.

关键词： computational Methods Complex Systems computational applications Parallel and Distributed Computing Advanced Computing Architectures GPU

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：