检索结果-内蒙古大学图书馆

IEEE Conference on Global Communications (GLOBECOM)

作者： Jianguo Xue Ting Wang Puyu Cai MoE Engineering Research Center of Software/Hardware Co-design Technology and Application Shanghai Key Lab. of Trustworthy Computing East China Normal University China Department of Computer Science and Engineering Michigan State University USA

Hadoop Yarn is an open-source cluster manager responsible for resource management and job scheduling. However, data-driven applications are typically organized into workflows that consist of a series of jobs with dependencies. Yarn does not manage users' workflows and only considers the current job rather than the entire workflow when scheduling. In practice, multiple workflows share the same Yarn cluster and are pre-assigned separate Yarn resource queues to avoid mutual interference. However, this coarse-grained resource division can sometimes result in low resource utilization and increased pending time of jobs on the Yarn queue. For instance, one resource queue may have exhausted its quota while still having pending jobs, while other queues may have availab.e resources but cannot begin executing any jobs due to unfulfilled data dependencies. To address this problem, we propose a deep reinforcement learning-based workflow scheduling scheme that takes into account job dependencies, job priorities, and dynamic resource usage. The proposed approach can intelligently identify and utilize free windows of different resource queues. Our simulation results demonstrate that the proposed DRL-based workflow scheduling scheme can significantly reduce the average job latency compared to existing approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Satellite Federated Fine-Tuning for Foundation Models in Space Computing Power Networks

arXiv

引用

arXiv 2025年

作者： Zhu, Yan Zhu, Jingyang Wang, Ting Shi, Yuanming Jiang, Chunxiao Letaief, Khaled Ben MoE Engineering Research-Center of Software/Hardware Co-design Technology and Application The Shanghai Key Lab. of Trustworthy Computing East China Normal University Shanghai200062 China School of Information Science and Technology ShanghaiTech University Shanghai201210 China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

Advancements in artificial intelligence (AI) and low-earth orbit (LEO) satellites have promoted the application of large remote sensing foundation models for various downstream tasks. However, direct downloading of these models for fine-tuning on the ground is impeded by privacy concerns and limited bandwidth. Satellite federated learning (FL) offers a solution by enabling model fine-tuning directly on-board satellites and aggregating model updates without data downloading. Nevertheless, for large foundation models, the computational capacity of satellites is insufficient to support effective on-board fine-tuning in traditional satellite FL frameworks. To address these challenges, we propose a satellite-ground collab.rative federated fine-tuning framework. The key of the framework lies in how to reasonably decompose and allocate model components to alleviate insufficient on-board computation capabilities. During fine-tuning, satellites exchange intermediate results with ground stations or other satellites for forward propagation and back propagation, which brings communication challenges due to the special communication topology of space transmission networks, such as intermittent satellite-ground communication, short duration of satellite-ground communication windows, and unstable inter-orbit inter-satellite links (ISLs). To reduce transmission delays, we further introduce tailored communication strategies that integrate both communication and computing resources. Specifically, we propose a parallel intra-orbit communication strategy, a topology-aware satellite-ground communication strategy, and a latency-minimalization inter-orbit communication strategy to reduce space communication costs. Simulation results demonstrate significant reductions in training time with improvements of approximately 33%. Copyright © 2025, The Authors. All rights reserved.

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

Exhaustive and near-exhaustive memory testing techniques and their BIST implementations

引用

JOURNAL OF ELECTRONIC testing-THEORY AND APPLICATIONS 1997年第3期10卷 215-229页

作者： Das, D Karpovsky, M Research Lab. on Design and Testing of Computer Hardware Boston University Boston

In this work we investigate the problem of detection and location of single and unlinked multiple k-coupling faults in n x 1 random-access memories (RAMs). This fault model covers all crosstalks between any k cells in n x 1 RAMs. The problem of memory testing has been reduced to the problem of the generation of (n, k - 1)-exhaustive backgrounds. We have obtained practical test lengths, for a memory size around 1 M, for detecting up to 6-couplings by exhaustive tests and up to 9-couplings by near-exhaustive tests. The best known test algorithms up to now provide for the detection of 5-couplings only in a 1 M memory, using exhaustive tests. Beyond these parameters, test lengths were impractical. Furthermore, our method for generation of (n, k - 1)-exhaustive backgrounds yields short test lengths giving rise to considerably shorter testing times than the present most efficient tests for large n and for k greater than 3. Our test lengths are 50% shorter than other methods for the case of detecting up to 5-couplings in a 1 Mbit RAM. The systematic nature of both our tests enables us to use a built-in self-test (BIST) scheme, for RAMs, with low hardware overhead. For a 1 Mbit memory, the BIST area overhead for the detection of 5-couplings is less than 1% for SRAM and 6.8% for a DRAM. For the detection of 9-couplings with 99% or higher probability, the BIST area overhead is less than 0.2% for SRAM and 1.5% for DRAM.

关键词： memory testing pattern sensitive faults built-in self-test exhaustive codes near-exhaustive codes

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：