检索结果-内蒙古大学图书馆

36th IEEE international Parallel and Distributed Processing symposium (IEEE IPDPS)

作者： Castes, Charly Agullo, Emmanuel Aumage, Olivier Saillard, Emmanuelle Inria LaBRI Bordeaux France Ecole Polytech Fed Lausanne Lausanne Switzerland

ISBN: (纸本)9781665497473

The hardware complexity of modern machines makes the design of adequate programming models crucial for jointly ensuring performance, portability, and productivity in high-performance computing (HPC). Sequential task-based programming models paired with advanced runtime systems allow the programmer to write a sequential algorithm independently of the hardware architecture in a productive and portable manner, and let a third party software layer -the runtime system- deal with the burden of scheduling a correct, parallel execution of that algorithm to ensure performance. Many HPC algorithms have successfully been implemented following this paradigm, as a testimony of its effectiveness. Developing algorithms that specifically require fine-grained tasks along this model is still considered prohibitive, however, due to per-task management overhead [1], forcing the programmer to resort to a less abstract, and hence more complex "task+X" model. We thus investigate the possibility to offer a tailored execution model, trading dynamic mapping for efficiency by using a decentralized, conservative in-order execution of the task flow, while preserving the benefits of relying on the sequential taskbased programming model. We propose a formal specification of the execution model as well as a prototype implementation, which we assess on a shared-memory multicore architecture with several synthetic workloads. The results show that under the condition of a proper task mapping supplied by the programmer, the pressure on the runtime system is significantly reduced and the execution of fine-grained task flows is much more efficient.

关键词： Runtime Computational modeling Software algorithms Computer architecture programming Hardware Software

来源：评论

学校读者我要写书评

暂无评论

Data-driven distributionally robust MPC via semi-infinite semidefinite programming with application to financial models 26

Data-driven distributionally robust MPC via semi-infinite se...

引用

26th international symposium on Mathematical Theory of Networks and systems (MTNS)

作者： Das, Souvik Ganguly, Siddhartha Aravind, Ashwin Chatterjee, Debasish Indian Inst Technol Syst & Control Engn Bombay Maharashtra India

This article introduces a novel distributionally robust model predictive control (DRMPC) algorithm for a specific class of controlled dynamical systems where the disturbance multiplies the state and control variables. These classes of systems arise in mathematical finance, where the paradigm of distributionally robust optimization (DRO) fits perfectly, and this serves as the primary motivation for this work. We recast the optimal control problem (OCP) as a semidefinite program with an infinite number of constraints, making the ensuing optimization problem a semi-infinite semidefinite program (SI-SDP). To numerically solve the SI-SDP, we advance the approach established in Das et al. (2022) in the context of convex SIPs (cSIPs) to SI-SDPs and subsequently, solve the DRMPC problem. A numerical example is provided to show the effectiveness of the algorithm. Copyright (c) 2024 The Authors. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0/)

关键词： Model predictive control stochastic control and estimation control issues in finance

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Reactive programming with Modal Types in Haskell 26th

Asynchronous Reactive Programming with Modal Types in Haskel...

引用

26th international symposium on Practical Aspects of Declarative Languages (PADL)

作者： Bahr, Patrick Houlborg, Emil Rordam, Gregers Thomas Skat IT Univ Copenhagen Copenhagen Denmark

ISBN: (纸本)9783031520372;9783031520389

The implementation of asynchronous systems, in particular graphical user interfaces, is traditionally based on an imperative model that uses shared mutable state and callbacks. While efficient, the combination of shared mutable state and callbacks is notoriously difficult to reason about and prone to errors. Functional reactive programming (FRP) provides an elegant alternative and recent theoretical advances in modal FRP suggest that it can be efficient as well. In this paper, we present Async Rattus, an FRP language embedded in Haskell. The distinguishing feature of Async Rattus is a modal type constructor that enables the composition of asynchronous subsystems by keeping track of each subsystem's clock at compile time which in turn enables dynamically changing clocks at runtime. The central component of our implementation is a Haskell compiler plugin that, among other aspects, checks the stricter typing rules of Async Rattus and infers compile-time clocks. This is the first implementation of an asynchronous modal FRP language. By embedding the language in Haskell we can exploit the existing language and library ecosystem as well as rapidly experiment with new language features and library design. We hope that such experimentation with Async Rattus sparks further research in modal FRP and its applications.

关键词： Functional reactive programming Modal types Space leaks

来源：评论

学校读者我要写书评

暂无评论

Solving Vehicle Equipment Specification Problems with Answer Set programming 25th

Solving Vehicle Equipment Specification Problems with Answer...

引用

25th international symposium on Practical Aspects of Declarative Languages (PADL)

作者： Takeuchi, Raito Banbara, Mutsunori Tamura, Naoyuki Schaub, Torsten Nagoya Univ Chikusa Ku Furo Cho Nagoya Aichi 4648601 Japan Kobe Univ Rokko Dai Nada Ku Kobe Hyogo 6578501 Japan Univ Potsdam August Bebel Str D-14482 Potsdam Germany

ISBN: (纸本)9783031248405;9783031248412

We develop an approach to solving mono- and multiobjective vehicle equipment specification problems considering the corporate average fuel economy standard (CAFE problems, in short) in automobile industry. Our approach relies upon Answer Set programming (ASP). The resulting system aspcafe accepts a CAFE instance expressed in the orthogonal variability model format and converts it into ASP facts. In turn, these facts are combined with an ASP encoding for CAFE solving, which can subsequently be solved by any off-the-shelf ASP systems. To show the effectiveness of our approach, we conduct experiments using a benchmark set based on real data provided by a collaborating Japanese automaker.

关键词： Vehicle equipment specification Corporate average fuel economy standard Answer set programming Multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

CIMulator: A Computing in Memory Emulator Framework

引用

IEEE TRANSACTIONS ON CIRCUITS AND systems II-EXPRESS BRIEFS 2022年第10期69卷 4183-4187页

作者： Dervay, Andrew Zhao, Wenfeng SUNY Binghamton Dept Elect & Comp Engn Vestal NY 13850 USA

In this brief, we present CIMulator, an open-source, extensible modeling, simulation, and emulation framework for on-chip digital Computing-In-Memory (CIM) design and assessment. Featuring a synthesizable Register Transfer Level (RTL) model, CIMulator encapsulates the fundamental in-memory bitline logic and the near-memory compute functionalities altogether. In this way, CIMulator ensures cycle-accurate RTL simulation, as well as system-level processor/CIM integration and emulation on COTS (commercially off-the-shelf) FPGA devices with an end-to-end correctness guarantee. In addition, we adopt a CIM intrinsics programming approach and an instruction-level energy model to estimate the application program execution energy. We implement an illustrative CIM system design emulated on a Cyclone-IV FPGA device and assess the functionality and performances of several applications, demonstrating the effectiveness of the proposed methodology. The source code is available at https://***/adervay1/CIMulator.

关键词： Computational modeling Common Information Model (computing) programming Random access memory Emulation Semiconductor device modeling Field programmable gate arrays CIM EDA RTL model emulation FPGA

来源：评论

学校读者我要写书评

暂无评论

ASMETA Tool Set for Rigorous System Design 26th

ASMETA Tool Set for Rigorous System Design

引用

26th international symposium on Formal Methods (FM)

作者： Bombarda, Andrea Bonfanti, Silvia Gargantini, Angelo Riccobene, Elvinia Scandurra, Patrizia Univ Bergamo Bergamo Italy Univ Milan Milan Italy

ISBN: (纸本)9783031711763;9783031711770

This tutorial paper introduces ASMETA, a comprehensive suite of integrated tools around the formal method Abstract State Machines to specify and analyze the executable behavior of discrete event systems. ASMETA supports the entire system development life-cycle, from the specification of the functional requirements to the implementation of the code, in a systematic and incremental way. This tutorial provides an overview of ASMETA through an illustrative case study, the Pill-Box, related to the design of a smart pillbox device. It illustrates the practical use of the range of modeling and V&V techniques available in ASMETA and C++ code generation from models, to increase the quality and reliability of behavioral system models and source code.

关键词： C++ (programming language)

来源：评论

学校读者我要写书评

暂无评论

A Stochastic Bilevel programming Model for an Industrial Symbiosis Network 12th

A Stochastic Bilevel Programming Model for an Industrial S...

引用

12th international symposium on Intelligent Manufacturing and Service systems, IMSS 2023

作者： Daş, G. Sena Yeşilkaya, Murat Altinkaynak, Büşra Birgören, Burak Department of Industrial Engineering Kirikkale University Kirikkale Turkey Niksar Vocational School of Technical Sciences Tokat Gaziosmanpaşa University Tokat Turkey Department of Industrial Engineering Alparslan Turkeş Science and Technology University Adana Turkey

ISBN: (纸本)9789819960613

A stochastic bilevel model for an industrial symbiosis (IS) network in an eco-industrial park (EIP) is presented in this paper. Companies in IS networks produce final products using mostly by-products rather than raw materials. Companies in these networks are known to share a variety of synergies, including wastes and by-products. They mostly negotiate on the price and amount of the by-products. This negotiation is critical as by-products should be available on time at the right amount for smooth production. Moreover, the use of these by-products should provide savings compared to the use of raw materials so that companies could benefit from IS. However, the fluctuations in the final product demand affect both the EIP management (the leader) and companies (followers) in the network. Therefore, we proposed a stochastic bilevel model where the lower-level problem is a two-stage stochastic programming model. Our findings show that the demand uncertainty has an impact on both parties. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Stochastic programming

来源：评论

学校读者我要写书评

暂无评论

Robust X-ray Image Stitching Algorithm Based on Refining Matching Results of Feature Descriptors 20

Robust X-ray Image Stitching Algorithm Based on Refining Mat...

引用

20th IEEE international symposium on Biomedical Imaging (ISBI)

作者： Liang, Yefeng Li, Shibo Li, Xingyu He, Yucheng Hu, Ying Wu, Tailin Tao, Huiren Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen Key Lab Minimally Invas Surg Robot & Sys Shenzhen 518055 Peoples R China Univ Chinese Acad Sci UCAS Beijing 100049 Peoples R China Natl Univ Singapore Coll Design & Engn Singapore 117575 Singapore Shenzhen Univ Clin Med Acad Gen Hosp Dept Orthopaed Shenzhen 518055 Peoples R China

ISBN: (纸本)9781665473583

Panoramic X-ray image provides a convenient way for some orthopedic clinical diagnosis and preoperative planning, while the full body cannot be captured in a single X-ray scan. The classic refining algorithm RANSAC failed to identify the outliers (mismatched points) according to the low signal-to-noise ratio of the matching results of vanilla feature descriptors. The methods based on deep learning based are also difficult to carry out due to the lack of training data pairs clinically. This paper proposes a robust algorithm for X-ray image stitching based on refining the matching results of vanilla feature descriptors. The algorithm transforms the image stitching task into the clique problem in the graph theory owing to the scale consistency of the X-ray images, and the dynamic programming algorithm is used to accelerate the searching process for the maximal clique. 60 clinical X-ray image pairs from different parts of the human body are randomly collected to evaluate our proposed algorithm. The experiment results show the strong robustness throughout different stitching tasks of X-ray images and achieve the best performance among the frequently-used stitching software.

关键词： Image stitching X-ray maximal clique dynamic programming

来源：评论

学校读者我要写书评

暂无评论

LIBRA: Enabling Workload-Aware Multi-Dimensional Network Topology Optimization for Distributed Training of Large AI Models

LIBRA: Enabling Workload-Aware Multi-Dimensional Network Top...

引用

2024 IEEE international symposium on Performance Analysis of systems and Software, ISPASS 2024

作者： Won, William Rashidi, Saeed Srinivasan, Sudarshan Krishna, Tushar Georgia Institute of Technology AtlantaGA United States Hewlett Packard Enterprise Karnataka Bangalore India Intel Karnataka Bangalore India

ISBN: (纸本)9798350376388

As model sizes in machine learning continue to scale, distributed training is necessary to accommodate model weights within each device and to reduce training time. However, this comes with the expense of increased communication overhead due to the exchange of gradients and activations, which become the critical bottleneck of the end-to-end training process. In this work, we motivate the design of multi-dimensional networks within machine learning systems as a cost-efficient mechanism to enhance overall network bandwidth. We also identify that optimal bandwidth allocation is pivotal for multi-dimensional networks to ensure efficient resource utilization. We introduce Libra, a framework specifically focused on optimizing multi-dimensional fabric architectures. Through case studies, we demonstrate the value of Libra, both in architecting optimized fabrics under diverse constraints and in enabling co-optimization opportunities. © 2024 IEEE.

关键词： Quadratic programming

来源：评论

学校读者我要写书评

暂无评论

Teaching Parallel Algorithms Using the Binary-Forking Model

Teaching Parallel Algorithms Using the Binary-Forking Model

引用

1st international Conference on Smart Energy systems and Artificial Intelligence (SESAI)

作者： Blelloch, Guy E. Gu, Yan Sun, Yihan Carnegie Mellon Univ Pittsburgh PA 15213 USA Univ Calif Riverside Riverside CA 92521 USA

ISBN: (纸本)9798350364613;9798350364606

In this paper, we share our experience in teaching parallel algorithms with the binary-forking model. With hardware advances, multicore computers are now ubiquitous. This has created a substantial demand in both research and industry to harness the capabilities of parallel computing. It is thus important to incorporate parallelism in computer science education, especially in the early stages of the curriculum. However, it is commonly believed that understanding and using parallelism requires a deep understanding of computer systems and architecture, which complicates introducing parallelism to young students and non-experts. We propose to use the binary-forking model in teaching parallel algorithms, proposed by our previous research work. This model is meant to capture the performance of algorithms on modern multicore shared-memory machines, which is a simple abstraction to isolate algorithm design ideas with system-level details. The abstraction allows for simple analysis based on the work-span model in theory, and can be directly implemented as parallel programs in practice. In this paper, we briefly overview some basic primitives in this model, and provide a list of algorithms that we believe are well-suited in parallel algorithm courses.

关键词： binary-forking model computer science education fork-join parallel algorithms parallel 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：