检索结果-内蒙古大学图书馆

Design, Automation and Test in Europe Conference and Exhibition

作者： Neethu Bal Mallya Panagiotis Strikos Bhavishya Goel Ahsen Ejaz Ioannis Sourdis Department of Computer Science and Engineering Chalmers University of Technology and University of Gothenburg Gothenburg Sweden

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

As the semiconductor industry struggles to keep Moore's law alive and integrate more functionality on a chip, multi-chiplet chips offer a lower cost alternative to large monolithic chips due to their higher yield. However, chiplet-based chips are naturally Non-Uniform Memory Access (NUMA) systems and therefore suffer from slow remote accesses. NUMA overheads are exacerbated by the limited throughput and higher latency of inter-chiplet communication. This paper offers a comprehensive analysis of chiplet-based systems with different design parameters measuring their performance overheads compared to traditional monolithic multicore designs and their scalability to system and chiplet size. Several design alternatives pertaining to the memory hierarchy, interconnects, and technology aspects are studied. Our analysis shows that although chiplet-based chips can cut (recurring engineering) costs to half, they may give away over a third of the monolithic performance. Part of this performance overhead can be regained with specific design choices.

关键词： Semiconductor device modeling Semiconductor device measurement Costs Multicore processing Chiplets Scalability Moore's Law Throughput Size measurement Performance analysis

来源：评论

学校读者我要写书评

暂无评论

What Happens to a Dataset Transformed by a Projection-based Concept Removal Method?

arXiv

引用

arXiv 2024年

作者： Johansson, Richard Department of Computer Science and Engineering University of Gothenburg Chalmers University of Technology Sweden

We investigate the behavior of methods that use linear projections to remove information about a concept from a language representation, and we consider the question of what happens to a dataset transformed by such a method. A theoretical analysis and experiments on real-world and synthetic data show that these methods inject strong statistical dependencies into the transformed datasets. After applying such a method, the representation space is highly structured: in the transformed space, an instance tends to be located near instances of the opposite label. As a consequence, the original labeling can in some cases be reconstructed by applying an anti-clustering method. © 2024, CC BY-SA.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Fluid and kinetic modeling of runaway electron generation from tritium beta decay and Compton scattering 50

Fluid and kinetic modeling of runaway electron generation fr...

引用

50th EPS Conference on Plasma Physics, EPS 2024

作者： Ekmark, I. Hoppe, M. Fülöp, T. Tinguely, R.A. Sweeney, R. Jansson, P. Antonsson, L. Vallhagen, O. Pusztai, I. Department of Physics Chalmers University of Technology Göteborg Sweden Department of Electrical Engineering KTH Royal Inst. Technology Stockholm Sweden Plasma Science and Fusion Center Massachusetts Inst. Technology CambridgeMA United States Commonwealth Fusion Systems DevensMA United States Department of Computer Science and Engineering Chalmers Univ. Technology Göteborg Sweden

ISBN: (纸本)9798331305239

We derived kinetic sources of energetic electrons generated by tritium beta decay and Compton scattering and compared them to the corresponding fluid RE generation rates [2]. In the SPARC example considered, using kinetic (as opposed to fluid) sources yielded 25 % higher RE current. The reason for this is that energetic electrons generated by the kinetic sources with p c can run away since collisions for these electrons are kinetically resolved. © 2024 50th EPS Conference on Plasma Physics, EPS 2024. All rights reserved.

关键词： Compton scattering

来源：评论

学校读者我要写书评

暂无评论

How Well Do Large Language Models Disambiguate Swedish Words?

arXiv

引用

arXiv 2024年

作者： Johansson, Richard Department of Computer Science and Engineering Chalmers University of Technology University of Gothenburg Sweden

We evaluate a battery of recent large language models on two benchmarks for word sense disambiguation in Swedish. At present, all current models are less accurate than the best supervised disambiguators in cases where a training set is available, but most models outperform graph-based unsupervised systems. Different prompting approaches are compared, with a focus on how to express the set of possible senses in a given context. The best accuracies are achieved when human-written definitions of the senses are included in the prompts. © 2024, CC BY-SA.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A Linear-Time Optimal Broadcasting Algorithm in Stars of Cliques

引用

Journal of Graph Algorithms and Applications 2024年第1期28卷 385-388页

作者： Damaschke, Peter Department of Computer Science and Engineering Chalmers University of Technology and University of Gothenburg GothenburgSE-41296 Sweden

For the telephone broadcast model, an O(n log n)-time algorithm for constructing an optimal broadcasting scheme in a star of cliques with a total of n vertices was recently presented by Ambashankar and Harutyunyan at IWOCA 2024. In the present note we give a considerably shorter and purified algorithm description and correctness proof. Moreover, we improve the time complexity to O(n). © 2024, Brown university. All rights reserved.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

On-demand Memory Compression of Stream Aggregates through Reinforcement Learning 25

On-demand Memory Compression of Stream Aggregates through Re...

引用

Proceedings of the 16th ACM/SPEC International Conference on Performance engineering

作者： Jingyu Liu Vincenzo Gulisano Department of Computer Science and Engineering Chalmers University of Technology Gothenburg Sweden and University of Gothenburg Gothenburg Sweden Department of Computer Science and Engineering Chalmers Universiry of Technology Gothenburg Sweden and University of Gothenburg Gothenburg Sweden

ISBN: (纸本)9798400710735

Stream Aggregates are crucial in digital infrastructures for transforming continuous data streams into actionable insights. However, state-of-the-art Stream Processing Engines lack mechanisms to effectively balance performance with memory consumption - a capability that is especially crucial in environments with fluctuating computational resources and data-intensive *** paper tackles this gap by introducing a novel on-demand adaptive memory compression scheme for stream Aggregates. Our approach uses Reinforcement Learning (RL) to dynamically adapt how a stream Aggregate compresses its state, balancing performance and memory utilization under a given processing latency threshold. We develop a model that incorporates the application- and data-specific nuances of stream Aggregates and create a framework to train RL Agents to adjust memory compression levels in real-time. Additionally, we shed light on a trade-off between the timeliness of an RL Agent training and its resulting behavior, defining several policies to account for this *** extensive evaluation, we show that the proposed RL Agent supports well on-demand memory compression. We also study the effects of our policies - providing guidance on their role in RL applied to stream Aggregates - and show our framework supports lean execution of such RL jobs.

关键词： memory compression

来源：评论

学校读者我要写书评

暂无评论

Dealing with Data: Bringing Order to Chaos

Dealing with Data: Bringing Order to Chaos

引用

Euromicro Conference on Software engineering and Advanced Applications (SEAA)

作者： Helena Holmström Olsson Jan Bosch Computer Science and Media Technology Malmö University Malmö Sweden Computer Science and Engineering Chalmers University of Technology Gothenburg Sweden

ISBN: (数字)9798350380262

ISBN: (纸本)9798350380279

Data is key for rapid and continuous delivery of customer value. By collecting data from products in the field, companies in the embedded systems domain can measure and monitor product performance and they get the opportunity to provide customers with insights and data-driven services. However, while the notion of data-driven development is not new, embedded systems companies are facing a situation in which data volumes are growing exponentially and this is not without its challenges. Suddenly, the cost of collecting, storing and processing data becomes a concern and while there is prominent research on different aspects of data-driven development, there is little guidance for how to reason about business value versus costs of data. In this paper, we present findings from case study research conducted in close collaboration with four companies in the embedded systems domain. The contribution of this paper is a framework that provides a holistic understanding of the multiple dimensions that need to be considered when reasoning about business value versus cost of collecting, storing and processing data.

关键词： Chaos Embedded systems Costs Collaboration Companies Cognition Monitoring Business Software engineering

来源：评论

学校读者我要写书评

暂无评论

On How to Not Prove Faulty Controllers Safe in Differential Dynamic Logic 1

引用

23rd International Conference on Formal engineering Methods, ICFEM 2022

作者： Selvaraj, Yuvaraj Krook, Jonas Ahrendt, Wolfgang Fabian, Martin Department of Electrical Engineering Chalmers University of Technology Göteborg Sweden Department of Computer Science and Engineering Chalmers University of Technology Göteborg Sweden Zenseact Göteborg Sweden

ISBN: (数字)9783031172441

ISBN: (纸本)9783031172434

Cyber-physical systems are often safety-critical and their correctness is crucial, as in the case of automated driving. Using formal mathematical methods is one way to guarantee correctness. Though these methods have shown their usefulness, care must be taken as modeling errors might result in proving a faulty controller safe, which is potentially catastrophic in practice. This paper deals with two such modeling errors in differential dynamic logic. Differential dynamic logic is a formal specification and verification language for hybrid systems, which are mathematical models of cyber-physical systems. The main contribution is to prove conditions that when fulfilled, these two modeling errors cannot cause a faulty controller to be proven safe. The problems are illustrated with a real world example of a safety controller for automated driving, and it is shown that the formulated conditions have the intended effect both for a faulty and a correct controller. It is also shown how the formulated conditions aid in finding a loop invariant candidate to prove properties of hybrid systems with feedback loops. The results are proven using the interactive theorem prover KeYmaera X. © 2022, Springer Nature Switzerland AG.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

The 'Vattn' Case: Analysing Sustainability Impacts in a Software Startup 8

The 'Vattn' Case: Analysing Sustainability Impacts in a Soft...

引用

8th International Conference on Information and Communication Technologies (ICT) for Sustainability, ICT4S 2022

作者： Lieu, Susan Wong, Adelric Penzenstadler, Birgit University of Gothenburg Department of Computer Science and Engineering Gothenburg Sweden University of Chalmers|Gothenburg Department of Computer Science and Engineering Gothenburg Sweden Lappeenranta University of Technology Lappeenranta Finland

ISBN: (纸本)9781665482868

Interest in sustainability research has increased in Software engineering, however most research conducted over-look startups integrating sustainability into the development of their software systems. The goal of this paper is to contribute to filling this knowledge gap by showcasing how startups may adopt sustainability into their software system. This will be achieved using the Sustainability Awareness Framework (SusAF). To demonstrate the use of the SusAF for startups, we conducted a case study with the startup company Vattn, who are developing an online digital water management platform for easier access to clean drinking water. The results show that the SusAF provided the necessary discussion means in order for Vattn to discover the potential sustainability impacts of their software system in the five dimensions of sustainability and across the three orders of effect. Furthermore, the Vattn team were provided with the adequate tool to devise actions to support the identified positive sustainability impacts and mitigate the negative. © 2022 IEEE.

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing engineering and Construction Projects: The Role of Artificial Intelligence in Cost Estimation and Procurement

SSRN

引用

SSRN 2024年

作者： Dzhusupova, Rimma Shteriyanov, Vasil Bosch, Jan Olsson, Helena Holmström Engineering Department McDermott Computer Science and Engineering Chalmers University of Technology Gothenburg Sweden Computer Science and Media Technology Malmö University Malmö Sweden

This study explores an innovative Artificial Intelligence (AI) - based solution for enhancing material procurement and cost estimation in engineering, Procurement and Construction (EPC) projects, particularly within the oil, gas and petrochemical sectors. By integrating deep learning techniques for symbol and text recognition with regression analysis of historical project data, this research aims to automate the traditionally manual and labor-intensive process of estimating material quantities. The proposed solution builds on previous advancements in object detection and machine learning and aims to enhance accuracy, efficiency, and risk management in procurement processes. Significant benefits include time savings, reduction in human error, and cost-effectiveness, thereby facilitating sustainable and competitive EPC project bids. © 2024, The Authors. All rights reserved.

关键词： Cost effectiveness

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：