检索结果-内蒙古大学图书馆

11th IEEE International Conference on Communication systems and Network Technologies, CSNT 2022

作者： Shukla, Surendra Kumar Shukla, Mukul Dwivedi, Upendra Pant, Bhaskar Graphic Era Deemed to Be University Department of Cse Dehradun India Sgsits Department of It Indore India G.L. Bajaj Institute of Technology and Management Department of Cse Greater Noida India

ISBN: (纸本)9781665480383

Multi-core processors are the engine of state-of-the-art computing devices. These processors outperform in the presence of parallelism in the applications. parallelism improves the throughput of the applications, however, imposes the synchronization and communication overhead. The communication is eased by introducing the Last level cache (LLC). LLC is fast and proved to be an effective mechanism for intercore communication. However, intercore communication adversely affects the LLC due to the interference among the applications for the common space. In this research article, interference, a well-known problem of Multicore systems has been analyzed in the perspective of LLC size. The analysis resulted that, increasing the LLC size mitigates the interference only to a certain extent only. Further, increase in LLC neither increases the performance nor diminishes the interference. The analysis has been performed employing Mi-bench benchmark suite under gem5 simulator. The results are promising and could be employed for designing the modern power constraint devices. © 2022 IEEE.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Empirical Evaluation of the Asymptotic Behavior of the Analysis Complexity of Hard Random 3-CNF Formulas 4

Empirical Evaluation of the Asymptotic Behavior of the Analy...

引用

4th International Conference on Machine Learning and Intelligent systems, MLIS 2022

作者： Uvarov, Sergey I. Institute of Control Science Ras Moscow Russia

ISBN: (纸本)9781643683560

This paper continued the study of the complexity behavior of the satisfiability analysis of hard random formulas given in the conjunctive normal form (CNF). In the 3-CNF formula, each clause contains three literals of logical variables. The number of logical variables in the formula is N. In this paper, the SAT solver is improved by introducing equality reduction and pure literal identification procedures. The solver improvement reduced the exponent (with base 2) from N/20.86 to N/21.41 with an R=4.6 ratio of the number of clauses to the number of variables. The results show that the efficiency of the pure literals identification procedure decreases as R increases. An important part of the study is an empirical estimation of the algorithmic complexity of the SAT problem with large number of variables. The proposed method gives a convenient lower bound on the complexity of analysis for random 3-CNF formulas. We estimated the algorithmic complexity for the range N=256÷8192. The exponential dependence of complexity on N for random 3-CNF formulas at a fixed value of R is demonstrated in this range. © 2022 The authors and IOS Press.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

On the Localization of Sound Sources with Moving Microphones 21

On the Localization of Sound Sources with Moving Microphones

引用

21. ITG/GMA-Fachtagung Sensoren und Messsysteme - 21st ITG/GMA Conference on Sensors and Measuring systems

作者： Rittenschober, Thomas Seven Bel GmbH Linz Austria

ISBN: (纸本)9783800758364

This contribution describes a novel method for visualizing sound sources using a rotating linear array of a few digital microphones. The rotating array scans the incident sound field on a circular area. While the reduced hardware complexity allows for the design of a lightweight, handheld sound imaging device, the algorithmic portion ofthe measurement system requires special attention. In fact, established methods of sound imaging like beamforming and nearfield holography cannot be applied to signals stemming from moving sensors. The proposed method of computing an acoustic image using the described measurement setup is based on compensating the moving microphone signals for Doppler distortions and evaluating the coherence ofthe resulting signals with a non-moving reference microphone for each point in the acoustic image. The method is evaluated in the context of leakage detection in automotive structures. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Uncertainty and the Social Planner's Problem: Why Sample Complexity Matters 22

Uncertainty and the Social Planner's Problem: Why Sample Com...

引用

5th ACM Conference on Fairness, Accountability, and Transparency, FAccT 2022

作者： Cousins, Cyrus Department of Computer Science Brown University ProvidenceRI United States

ISBN: (纸本)9781450393522

Welfare measures overall utility across a population, whereas malfare measures overall disutility, and the social planner's problem can be cast either as maximizing the former or minimizing the latter. We show novel bounds on the expectations and tail probabilities of estimators of welfare, malfare, and regret of per-group (dis)utility values, where estimates are made from a finite sample drawn from each group. In particular, we consider estimating these quantities for individual functions (e.g., allocations or classifiers) with standard probabilistic bounds, and optimizing and bounding generalization error over hypothesis classes (i.e., we quantify overfitting) using Rademacher averages. We then study algorithmic fairness through the lens of sample complexity, finding that because marginalized or minority groups are often understudied, and fewer data are therefore available, the social planner is more likely to overfit to these groups, thus even models that seem fair in training can be systematically biased against such groups. We argue that this effect can be mitigated by ensuring sufficient sample sizes for each group, and our sample complexity analysis characterizes these sample sizes. Motivated by these conclusions, we present progressive sampling algorithms to efficiently optimize various fairness objectives. © 2022 ACM.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Bipartite Temporal Graphs and the Parameterized Complexity of Multistage 2-Coloring 1

Bipartite Temporal Graphs and the Parameterized Complexity o...

引用

1st Symposium on Algorithmic Foundations of Dynamic Networks, SAND 2022

作者： Fluschnik, Till Kunz, Pascal

ISBN: (纸本)9783959772242

We consider the algorithmic complexity of recognizing bipartite temporal graphs. Rather than defining these graphs solely by their underlying graph or individual layers, we define a bipartite temporal graph as one in which every layer can be 2-colored in a way that results in few changes between any two consecutive layers. This approach follows the framework of multistage problems that has received a growing amount of attention in recent years. We investigate the complexity of recognizing these graphs. We show that this problem is NP-hard even if there are only two layers or if only one change is allowed between consecutive layers. We consider the parameterized complexity of the problem with respect to several structural graph parameters, which we transfer from the static to the temporal setting in three different ways. Finally, we consider a version of the problem in which we only restrict the total number of changes throughout the lifetime of the graph. We show that this variant is fixed-parameter tractable with respect to the number of changes. © Till Fluschnik and Pascal Kunz;licensed under Creative Commons License CC-BY 4.0

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Prompt, Divide, and Conquer: Bypassing Large Language Model Safety Filters via Segmented and Distributed Prompt processing

arXiv

引用

arXiv 2025年

作者： Wahréus, Johan Hussain, Ahmed Papadimitratos, Panos Group KTH Royal Institute of Technology Stockholm Sweden

Large Language Models (LLMs) have transformed task automation and content generation across various domains while incorporating safety filters to prevent misuse. We introduce a novel jailbreaking framework that employs distributed prompt processing combined with iterative refinements to bypass these safety measures, particularly in generating malicious code. Our architecture consists of four key modules: prompt segmentation, parallel processing, response aggregation, and LLM-based jury evaluation. Tested on 500 malicious prompts across 10 cybersecurity categories, the framework achieves a 73.2% Success Rate (SR) in generating malicious code. Notably, our comparative analysis reveals that traditional single-LLM judge evaluation overestimates SRs (93.8%) compared to our LLM jury system (73.2%), with manual verification confirming that single-judge assessments often accept incomplete implementations. Moreover, we demonstrate that our distributed architecture improves SRs by 12% over the non-distributed approach in an ablation study, highlighting both the effectiveness of distributed prompt processing and the importance of robust evaluation methodologies in assessing jailbreak attempts. © 2025, CC BY.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

The Dimension Spectrum Conjecture for Planar Lines 49

The Dimension Spectrum Conjecture for Planar Lines

引用

49th EATCS International Conference on Automata, Languages, and Programming, ICALP 2022

作者： Stull, D.M. Department of Computer Science Northwestern University Evanston IL United States

ISBN: (纸本)9783959772358

Let La,b be a line in the Euclidean plane with slope a and intercept b. The dimension spectrum sp(La,b) is the set of all effective dimensions of individual points on La,b. Jack Lutz, in the early 2000s posed the dimension spectrum conjecture. This conjecture states that, for every line La,b, the spectrum of La,b contains a unit interval. In this paper we prove that the dimension spectrum conjecture is true. Specifically, let (a, b) be a slope-intercept pair, and let d = min{dim(a, b), 1}. For every s ∈ [0, 1], we construct a point x such that dim(x, ax + b) = d + s. Thus, we show that sp(La,b) contains the interval [d, 1 + d]. © D. M. Stull;licensed under Creative Commons License CC-BY 4.0

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Work Stealing Algorithms 15th

Evaluation of Work Stealing Algorithms

引用

15th Colombian Congress on Advances in Computing, CCC 2021

作者： Numpaque, Juan Sebatían Cardozo, Nicolás Systems and Computing Engineering Department Universidad de los Andes Bogotá Colombia

ISBN: (纸本)9783031199509

Work stealing is a common model in parallel computing used to schedule the execution of tasks. In this model, tasks are assigned dynamically to different processors as they are generated by a computation. However, to improve execution time, idle processors can steal tasks from other processors. Different underlying techniques have been proposed for work stealing, with FIFO and LIFO among the most used techniques. In this work we propose an alternative to these techniques, based on task priority, as a means to avoid fairness problems in the way that tasks are stolen across processors. To evaluate our technique we use a benchmark of different computation topologies variating the amount of tasks, the dependance between tasks, and the number of processors used. Our results show different performances for the three evaluated techniques. In cases managing smaller computations with fewer processors, both FIFO and LIFO perform better. When we increase the size of the computations and the number of processors used, our proposed priority-based technique performs better. With respect to the fairness of the algorithms, they are all unbalanced and no significant conclusion can be reached. © 2022, Springer Nature Switzerland AG.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Multi-dimensional State Space Collapse in Non-complete Resource Pooling Scenarios

引用

Performance Evaluation Review 2024年第1期52卷 3-4页

作者： Cardinaels, Ellen Borst, Sem Van Leeuwaarden, Johan S.H. Eindhoven University of Technology Eindhoven Netherlands Tilburg University Tilburg Netherlands

We establish an explicit multi-dimensional state space collapse (SSC) for parallel-processing systems with arbitrary compatibility constraints between servers and job types. This breaks major new ground beyond the SSC results and queue length asymptotics in the literature which are largely restricted to complete resource pooling (CRP) scenarios where the steady-state queue length vector concentrates around a line in heavy traffic. The multi-dimensional SSC that we establish reveals heavy-traffic behavior which is also far more tractable than the pre-limit queue length distribution, yet exhibits a fundamentally more intricate structure than in the one-dimensional case. © 2024 Owner/Author.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Assignment of idle processors to spatial redistributed domains on coarse levels in multigrid reduction in time 2022

Assignment of idle processors to spatial redistributed domai...

引用

5th International Conference on High Performance Computing in Asia-Pacific Region, HPC Asia 2022

作者： Yoda, Ryo Bolten, Matthias Nakajima, Kengo Fujii, Akihiro The University of Tokyo Japan University of Wuppertal Germany Kogakuin University Japan

ISBN: (纸本)9781450384988

parallel-in-time approaches for time-dependent PDEs have attracted a great deal of attention in the context of massively parallel environments. One such approach, multigrid reduction in time (MGRIT), extracts temporal parallelism by applying the reduction-based multigrid method for the temporal domain. To make efficient use of this parallelism, some processors need to be idle on a temporal coarse level of MGRIT. This paper proposes an optimization of the implementation that uses idle processors by assigning the spatial redistributed domain on coarse levels. It accelerates coarse-level spatial solvers and promotes early switching to parallelization-in-time by reducing its overhead. Although the spatial redistribution is contrary to the motivation of parallel-in-time approaches, it is expected to be effective when we need to balance spatial and temporal parallelism. This is because parallelization-in-time is already usually switched on when parallelization-in-space starts to saturate, so one can still benefit from additional parallelism. Numerical experiments demonstrate an improvement in runtime, at most, about 16.6% compared with pure MGRIT, which assigns best spatial and temporal parallelism at specific parallelism. © 2022 ACM.

关键词： parallel processing systems

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：