检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Hu, Gansen Wang, Zhaoguo Wei, Jinglin Huang, Wei Chen, Haibo Institute of Parallel and Distributed Systems SEIEE Shanghai Jiao Tong University China

Large language models (LLMs) demonstrate remarkable capabilities but face deployment challenges due to their massive parameter counts. While existing compression techniques like pruning can reduce model size, it leads to significant accuracy degradation under high compression ratios. We present a novel perspective inspired by constant folding in compiler optimization. Our approach enables parameter reduction by treating activation functions in LLMs as linear functions. However, recent LLMs use complex non-linear activations like GELU that prevent direct application of this technique. We propose TARDIS, which enables optimization of LLMs with non-linear activations by partially approximating them with linear functions in frequently occurring input ranges. For outlier inputs, TARDIS employs an online predictor to dynamically fall back to original computations. Our experiments demonstrate that TARDIS achieves 80% parameter reduction in feed-forward networks, while significantly outperforming state-of-the-art pruning methods Wanda and RIA with up to 65% higher accuracy. In practical deployments for a 7B model, TARDIS achieves 1.6× end-to-end inference speedup when integrated with the vLLM serving system, and 1.4× speedup with the widely adopted HuggingFace implementation, while incurring only a 10.9% accuracy trade-off. © 2025, CC BY.

关键词： Program compilers

来源：评论

学校读者我要写书评

暂无评论

Harmonizing Security and Performance in Microkernel File Servers

引用

Journal of Computer Science and Technology 2025年第2期40卷 464-481页

作者： Li, Wen-Tai Wang, Zi-Xuan Gu, Jin-Yu Xia, Yu-Bin Zang, Bin-Yu Institute of Parallel and Distributed Systems School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai200240 China

Microkernel OSes separate OS functionalities, including file systems and device drivers, into different user-level services, which mitigates the problem of lacking isolation in monolithic OSes. Nevertheless, from the perspective of applications, compromised services may still threaten applications’ security. Specifically, attackers can utilize vulnerabilities in file systems and disk drivers to leak or manipulate applications’ file content. The key problem is that de-privileging OS services from the kernel level to the user level does not mean the reduction of applications’ trusted computing base (TCB), and applications still need to trust all the required system services. This paper shows a case for providing the file service to applications with minimum TCB on microkernel OSes. Observing that file services actually do not need to access concrete file content, we propose a mechanism named Mirage, which deprives their privilege of accessing file content while preserving their management capability. Mirage efficiently protects the confidentiality and integrity of application files from untrusted services. The evaluation demonstrates that Mirage outperforms an encryption-based mechanism by up to 128% for IO-intensive workloads. © Institute of Computing Technology, Chinese Academy of Sciences 2025.

关键词： Carrier sense multiple access

来源：评论

学校读者我要写书评

暂无评论

A Counterfactual Ultrasound Anti-Interference Self-Supervised Network for B-mode Ultrasound Tongue Extraction

A Counterfactual Ultrasound Anti-Interference Self-Supervise...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Jia, Yan Cheng, Yuqing Xu, Kele Dou, Yong Qiao, Peng He, Zhouyu National Key Laboratory of Parallel and Distributed Computing College of Computer Science and Technology National University of Defense Technology Changsha China College of Systems Engineering National University of Defense Technology Changsha China

ISBN: (纸本)9798350368741

B-mode ultrasound tongue imaging is a non-invasive and real-time method for visualizing vocal tract deformation. However, accurately extracting the tongue's surface contour remains a significant challenge due to the low signal-to-noise ratio (SNR) and prevalent speckle noise in ultrasound images. Traditional supervised learning models often require large labeled datasets, which are labor-intensive to produce and susceptible to noise interference. To address these limitations, we present a novel Counterfactual Ultrasound Anti-Interference Self-Supervised Network (CUAI-SSN), which integrates self-supervised learning (SSL) with counterfactual data augmentation, progressively disentangles confounding factors, ensuring that the model generalizes well across varied ultrasound conditions. Our approach leverages causal reasoning to decouple noise from relevant features, enabling the model to learn robust representations that focus on essential tongue structures. By generating counterfactual image-label pairs, our method introduces alternative, noise-independent scenarios that enhance model training. Furthermore, we introduce attention mechanisms to enhance the network's ability to capture fine-grained details even in noisy conditions. Extensive experiments on real ultrasound tongue images demonstrate that CUAI-SSN outperforms existing methods, setting a new benchmark for automated contour extraction in ultrasound tongue imaging. Our code is publicly available at https://***/inexhaustible419/CounterfactualultrasoundAI. © 2025 IEEE.

关键词： contour extraction counterfactual inference self-supervised learning speech production ultrasound image

来源：评论

学校读者我要写书评

暂无评论

HeteroLLM: Accelerating Large Language Model Inference on Mobile SoCs platform with Heterogeneous AI Accelerators

arXiv

引用

arXiv 2025年

作者： Chen, Le Feng, Dahu Feng, Erhu Zhao, Rong Wang, Yingrui Xia, Yubin Chen, Haibo Xu, Pinjie Institute of Parallel and Distributed Systems Shanghai Jiao Tong University China Tsinghua University China SenseTime Research

With the rapid advancement of artificial intelligence technologies such as ChatGPT, AI agents and video generation, contemporary mobile systems have begun integrating these AI capabilities on local devices to enhance privacy and reduce response latency. To meet the computational demands of AI tasks, current mobile SoCs are equipped with diverse AI accelerators, including GPUs and Neural Processing Units (NPUs). However, there has not been a comprehensive characterization of these heterogeneous processors, and existing designs typically only leverage a single AI accelerator for LLM inference, leading to suboptimal use of computational resources and memory bandwidth. In this paper, we first summarize key performance characteristics of mobile SoC, including heterogeneous processors, unified memory, synchronization, etc. Drawing on these observations, we propose different tensor partition strategies to fulfill the distinct requirements of the prefill and decoding phases. We further design a fast synchronization mechanism that leverages the unified memory address provided by mobile SoCs. By employing these techniques, we present HeteroLLM, the fastest LLM inference engine in mobile devices which supports both layer-level and tensor-level heterogeneous execution. Evaluation results show that HeteroLLM achieves 9.99× and 4.36× performance improvement over other mobile-side LLM inference engines: MLC and MNN. © 2025, CC BY.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

YFLM: An Improved Levenberg-Marquardt Algorithm for Global Bundle Adjustment 41st

YFLM: An Improved Levenberg-Marquardt Algorithm for Global ...

引用

41st Computer Graphics International Conference, CGI 2024

作者： Peng, Jiaxin Li, Tao Jiang, Qin Liu, Jie Wang, Ruibo Laboratory of Software Engineering for Complex Systems School of Computer Science National University of Defense Technology Hunan Changsha410073 China Parallel and Distributed Processing Laboratory School of Computer Science National University of Defense Technology Hunan Changsha410073 China

ISBN: (纸本)9783031820205

The conventional Levenberg-Marquardt (LM) algorithm is a state-of-the-art trust-region optimization method for solving bundle adjustment problems in the Structure-from-Motion community, which not only takes advantage of the fast convergence of the Gauss-Newton method, but also the stability of the gradient descent method when approaching optimal solutions. However, the damping ratio of LM is simply provided by trial-and-error, which causes slow convergence rate for large-scale problems. This paper proposes the Yamashita-Fukushima LM (YFLM) algorithm to reduce the time complexity for global bundle adjustment, where the damping factor is determined by Yamashita and Fukushima’s method. YFLM dynamically calculates a more reasonable and optimal damping ratio according to the newest reprojection error. The experimental results show that the YFLM algorithm outperforms the conventional LM algorithm for most public bundle adjustment datasets. Besides this, the convergence of the YFLM algorithm is also evaluated with different σ∈(0,2]. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Damping

来源：评论

学校读者我要写书评

暂无评论

Liquid-State Drive: A Case for DNA Block Device for Enormous Data 23

Liquid-State Drive: A Case for DNA Block Device for Enormous...

引用

23rd USENIX Conference on File and Storage Technologies, FAST 2025

作者： Zhou, Jiahao Dong, Mingkai Wang, Fei Zeng, Jingyao Zhao, Lei Fan, Chunhai Chen, Haibo Institute of Parallel and Distributed Systems SEIEE Shanghai Jiao Tong University China School of Chemistry and Chemical Engineering New Cornerstone Science Laboratory Frontiers Science Center for Transformative Molecules National Center for Translational Medicine Shanghai Jiao Tong University China

ISBN: (纸本)9781939133458

The rapid development of DNA synthesis and sequencing technologies is making the ultra-high-density storage medium DNA to meet the rising demand for enormous data storage. The block storage interface, which is massively employed in storage systems, is the critical abstraction to integrate DNA storage into silicon-based computer systems. In this paper, we explore building block devices on DNA and identify the challenges of petabyte-scale metadata management and high DNA access costs. We propose a holistic DNA block device design called LIQUID-STATE DRIVE to provide low-cost block access to exabyte-scale data with the help of small yet fast SSDs. We adopt the dual-layer translation table to leverage SSDs to decrease the metadata updating cost. We introduce symbiotic metadata and delayed invalidation to reduce the cost of garbage collection and block updating. Our evaluation demonstrates that in microbenchmarks and real-world traces, the write cost reduces up to seven orders of magnitude and 2, 927×, and the read cost reduces up to 6, 206× and 7×, respectively. We expect our exploration and experience in building DNA block devices to be useful in expediting the advancement of DNA storage and bridging the gap between information technology and biotechnology. © 2025 FAST. All Rights Reserved.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Using dynamically layered definite releases for verifying the RefFS file system 24

Using dynamically layered definite releases for verifying th...

引用

Proceedings of the 18th USENIX Conference on Operating systems Design and Implementation

作者： Mo Zou Dong Du Mingkai Dong Haibo Chen Institute of Parallel and Distributed Systems SEIEE Shanghai Jiao Tong University and Engineering Research Center for Domain-specific Operating Systems Ministry of Education China Institute of Parallel and Distributed Systems SEIEE Shanghai Jiao Tong University and Engineering Research Center for Domain-specific Operating Systems Ministry of Education China and Huawei Technologies Co. Ltd

ISBN: (纸本)9781939133403

RefFS is the first concurrent file system that guarantees both liveness and safety, backed by a machine-checkable proof. Unlike earlier concurrent file systems, RefFS provably avoids termination bugs such as livelocks and deadlocks, through the dynamically layered definite releases specification. This specification enables handling of general blocking scenarios (including ad-hoc synchronization), facilitates modular reasoning for nested blocking, and eliminates the possibility of circular *** methodology underlying the aforementioned specification is integrated into a framework called MoLi (Modular Liveness Verification). This framework helps developers verify concurrent file *** further validate the correctness of the locking scheme for the Linux Virtual File System (VFS). Remarkably, even without conducting code proofs, we uncovered a critical flaw in a recent version of the locking scheme, which may lead to deadlocks of the entire OS (confirmed by Linux maintainers). RefFS achieves better overall performance than AtomFS, a state-of-the-art, verified concurrent file system without the liveness guarantee.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast and scalable in-network lock management using lock fission 24

Fast and scalable in-network lock management using lock fiss...

引用

Proceedings of the 18th USENIX Conference on Operating systems Design and Implementation

作者： Hanze Zhang Ke Cheng Rong Chen Haibo Chen Institute of Parallel and Distributed Systems SEIEE Shanghai Jiao Tong University and Shanghai AI Laboratory and MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Institute of Parallel and Distributed Systems SEIEE Shanghai Jiao Tong University and Engineering Research Center for Domain-specific Operating Systems Ministry of Education China Institute of Parallel and Distributed Systems SEIEE Shanghai Jiao Tong University and Shanghai AI Laboratory and Engineering Research Center for Domain-specific Operating Systems Ministry of Education China Institute of Parallel and Distributed Systems SEIEE Shanghai Jiao Tong University and Engineering Research Center for Domain-specific Operating Systems Ministry of Education China and Key Laboratory of System Software (Chinese Academy of Sciences)

ISBN: (纸本)9781939133403

distributed lock services are extensively utilized in distributed systems to serialize concurrent accesses to shared resources. The need for fast and scalable lock services has become more pronounced with decreasing task execution times and expanding dataset scales. However, traditional lock managers, reliant on server CPUs to handle lock requests, experience significant queuing delays in lock grant latency. Advanced network hardware (e.g. programmable switches) presents an avenue to manage locks without queuing delays due to their high packet processing power. Nevertheless, their constrained memory capacity restricts the manageable lock scale, thereby limiting their effect in large-scale *** paper presents FISSLOCK, a fast and scalable distributed lock service that exploits the programmable switch to improve (tail) latency and peak throughput for millions of locks. The key idea behind FISSLOCK is the concept of lock fission, which decouples lock management into grant decision and participant maintenance. FISSLOCK leverages the programmable switch to decide lock grants synchronously and relies on servers to maintain participants (i.e., holders and waiters) asynchronously. By using the programmable switch for routing, FISSLOCK enables on-demand fine-grained lock migration, thereby reducing the lock grant and release delays. FISSLOCK carefully designs and implements grant decision procedure on the programmable switch, supporting over one million locks. Evaluation using various benchmarks and a real-world application shows the efficiency of FISSLOCK. Compared to the state-of-the-art switch-based approach (NetLock), FISSLOCK cuts up to 79.1% (from 43.0%) of median lock grant time in the microbenchmark and improves transaction throughput for TATP and TPC-C by 1.76× and 2.28×, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Smarter Maritime Security: Apriori Algorithm Optimization in Serverless Environments

引用

Procedia Computer Science 2025年 257卷 452-459页

作者： Mahtab Shahin Saeed Rahimpour Tara Ghasempouri Sanja Bauk Thomas Fahringer Dirk Draheim Estonian Maritime Academy Tallinn University of Technology Tallinn Estonia Department of Computer Systems Tallinn University of Technology Tallinn Estonia Distributed and Parallel Systems Group University of Innsbruck Tirol Austria Information Systems Group Tallinn University of Technology Tallinn Estonia

This paper presents an optimized implementation of the Apriori algorithm tailored for large-scale data mining in cloud-native, serverless environments, utilizing real-world fuel datasets. Our approach achieves a 28% reduction in execution time and a 22% decrease in memory consumption compared to traditional distributed Apriori methods. The study leverages high-dimensional fuel datasets, spanning from 2020 to 2050, to evaluate scalability and efficiency in processing energy-related data. By employing advanced synchronization and deferred partitioning strategies, communication overhead is significantly reduced, improving performance while effectively balancing computational loads across distributed nodes. Security measures, including AES-256 encryption and role-based access control (RBAC), are incorporated to safeguard data confidentiality and ensure compliance with regulatory frameworks. The proposed solution scales efficiently for datasets up to 1 million records, demonstrating applicability across domains such as transportation and logistics. Future work will explore adaptive partitioning techniques, hybrid cloud architectures, and AI-driven predictive analytics to further enhance scalability and operational efficiency in serverless multi-cloud systems.

关键词： Cloud-Native Architectures Serverless Computing Data Mining Apriori Algorithm distributed Computing Big Data Maritime

来源：评论

学校读者我要写书评

暂无评论

SmartKV: A cost-effective and low-latency geo-distributed key-value store for the computing continuum

引用

Future Generation Computer systems 2025年 171卷

作者： Aznar Poveda, Juan Ebner, Maximilian Franz Fahringer, Thomas Najafabadi Samani, Zahra Etheredge, Marlon Pedratscher, Stefan Saurabh, Nishant Distributed and Parallel Systems Group University of Innsbruck Technikerstraße 21a Innsbruck6020 Austria Department of Information and Computing Sciences Utrecht University Princetonplein 5 Utrecht3584 Netherlands

Many data-intensive and distributed applications rely on low-latency and scalable key–value storage systems across the Computing Continuum. Key–value storage systems typically use consistent hashing or hash slot-sharding mechanisms to distribute data across storage nodes, which ensures load balancing but often leads to sub-optimal response times and monetary costs, particularly in geo-distributed systems where nodes might have different unit prices and be widely dispersed. In this paper, we propose SmartKV, a cost-efficient geo-distributed key–value store that optimizes data placement dynamically, abstracting the intricacies of data organization, transfer, access, and processing. SmartKV integrates a decentralized data placement algorithm that optimizes the replication factor and selects suitable locations for key–value pairs and replicas, balancing cost and access latency while keeping optimization overhead low. We employ a realistic cost model based on public and private Cloud and Edge providers that consider data transfer, request, and storage costs. In addition to conventional key–value pairs, SmartKV supports active key–value pairs, which enable the definition of custom data types and the execution of user-defined functions directly on the storage side. This contributes to reducing data transfer costs and round-trip times. We thoroughly evaluate SmartKV across different regions of the Chameleon testbed using several realistic workloads. Results show that the utilized decentralized data placement strategy allows SmartKV to reduce round trip times between 9 and 84% while reducing costs up to 4.84× under different client workloads and consistency models compared to state-of-the-art data placement strategies. © 2025 The Authors

关键词： Cloud storage

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：