检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wu, Hao Deng, Junxiao Yu, Minchen Yu, Yue Liu, Yaochen Fan, Hao Wu, Song Wang, Wei National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Hong Kong University of Science and Technology Hong Kong The Chinese University of Hong Kong Shenzhen China

Serverless computing has gained significant traction for machine learning inference applications, which are often deployed as serverless workflows consisting of multiple CPU and GPU functions with data dependency. However, existing data-passing solutions for serverless computing primarily reply on host memory for fast data transfer, mandating substantial data movement and resulting in salient I/O overhead. In this paper, we present FaaSTube, a GPU-efficient data passing system for serverless inference. FaaSTube manages intermediate data within a GPU memory pool to facilitate direct data exchange between GPU functions. It enables fine-grained bandwidth sharing over PCIe and NVLink, minimizing data-passing latency for both host-to-GPU and GPU-to-GPU while providing performance isolation between functions. Additionally, FaaSTube implements an elastic GPU memory pool that dynamically scales to accommodate varying data-passing demands. Evaluations on real-world applications show that FaaSTube reduces end-to-end latency by up to 90% and achieves up to 12x higher throughput compared to the state-of-the-art. Copyright © 2024, The Authors. All rights reserved.

关键词： Computer graphics equipment

来源：评论

学校读者我要写书评

暂无评论

Modeling and Analyzing Dynamic Forensics system Based on Intrusion Tolerance

Modeling and Analyzing Dynamic Forensics System Based on Int...

引用

International Conference on Computer and Information technology (CIT)

作者： Lin Chen Zhitang Li Cuixia Gao Yingshu Liu School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Services Computing Technology and System Laboratory Cluster and Grid Computing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

As an important part of computer forensics, network forensics particularly places emphasis on dynamic network information collection and proactive defense. Most forensics systems based on intrusion detection or honeypot rarely emphasize the availability of actual servers. In addition, few of them discussed the occasion of dynamic forensics particularly. The work presented in this paper is based on an idea to assist dynamic forensics with intrusion tolerance and deception technology to enhance the availability of server system and gather more useful evidences on a proper occasion. A mechanism of dynamic forensics based on intrusion forensics is proposed and is modeled with finite state machine. The workflow is described. A semi Markov process based on the embedded Markov chain of the states transition model is built and described. Finally, the forensics capability and server availability are analysis. According to the numerical analysis result, the security performance and forensics capability of the forensics system are enhanced to a certain degree.

关键词： Intrusion detection Computer networks Information analysis Computer science Markov processes grid computing Network servers Protection Digital forensics Law

来源：评论

学校读者我要写书评

暂无评论

Analyzing and Improving MPI Communication Performance in Overcommitted Virtualized systems

Analyzing and Improving MPI Communication Performance in Ove...

引用

International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication systems (MASCOTS)

作者： Zhiyuan Shao Qiang Wang Xuejiao Xie Hai Jin Ligang He Services Computing Technology and System Laboratory Cluster and Grid Computing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Department of Computer Science University of Warwick Coventry UK

Nowadays, it is an important trend in the system domain to use the software-based virtualization technology to build the execution environments (e.g., Clouds) and serve high performance computing (HPC) applications. However, with the extra virtualization layer, the application performance may be negatively affected. Studies revealed that the communication performance of the MPI library, which is widely used by the HPC applications, would suffer a high penalty when a physical host machine becomes overcommitted by virtual processors (VCPU). Unfortunately, the problem has not received enough attention and has not been solved yet in literature. In this paper, we investigate the reasons behind the performance penalty, and propose a solution to improve the communication performance of running MPI applications in the overcommitted virtualized systems. The experimental results show that by our proposal, most HPC applications can gain performance improvement to different extents among the overcommitted systems, depending on their communication patterns and the over committing level.

关键词： Libraries Benchmark testing Virtual machine monitors Kernel Cloud computing Linux Virtual machining

来源：评论

学校读者我要写书评

暂无评论

From General to Specific: Tailoring Large Language Models for Personalized Healthcare

arXiv

引用

arXiv 2024年

作者： Shi, Ruize Huang, Hong Zhou, Wei Yin, Kehan Zhao, Kai Zhao, Yun Huazhong University of Science and Technology Wuhan China Tongji Medical College China Hubei Maternity and Child Health Care Hospital China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

The rapid development of large language models (LLMs) has transformed many industries, including healthcare. However, previous medical LLMs have largely focused on leveraging general medical knowledge to provide responses, without accounting for patient variability and lacking true personalization at the individual level. To address this, we propose a novel method called personalized medical language model (PMLM), which explores and optimizes personalized LLMs through recommendation systems and reinforcement learning (RL). Specifically, by utilizing self-informed and peer-informed personalization, PMLM captures changes in behaviors and preferences to design initial personalized prompts tailored to individual needs. We further refine these initial personalized prompts through RL, ultimately enhancing the precision of LLM guidance. Notably, the personalized prompt are hard prompt, which grants PMLM high adaptability and reusability, allowing it to directly leverage high-quality proprietary LLMs. We evaluate PMLM using real-world obstetrics and gynecology data, and the experimental results demonstrate that PMLM achieves personalized responses, and it provides more refined and individualized services, offering a potential way for personalized medical LLMs. Copyright © 2024, The Authors. All rights reserved.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

Adaptive Disk I/O Scheduling for MapReduce in Virtualized Environment

Adaptive Disk I/O Scheduling for MapReduce in Virtualized En...

引用

International Conference on Parallel Processing (ICPP)

作者： Shadi Ibrahim Hai Jin Lu Lu Bingsheng He Song Wu Cluster and Grid Computing laboratory Services Computing Technology and System laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Computer Engineering Nanyang Technological University Singapore

Virtual machine (VM) interference has long been a challenging problem for performance predictability and system throughput for large-scale virtualized environments in the cloud. Such interferences are contributed by intertwined factors including the application's type, the number of con current VMs, and the VM scheduling algorithms used within the host. Since MapReduce has become an important data processing platform in the cloud, we investigate the impact of disk schedulers in Hadoop. Interestingly, our experimental results report a noticeable variation of the Hadoop performance between different applications when applying different disk pairs' schedulers in both the hypervisor and the virtual machines. Furthermore, a typical Hadoop application consists of different interleaving stages, each requiring different I/O workloads and patterns. As a result, the disk pairs' schedulers are not only sub-optimal for different MapReduce applications, but also sub-optimal for different sub-phases of the whole job. Accordingly, this paper presents a novel approach for adaptively tuning the disk pairs' schedulers in both the hypervisor and the virtual machines during the execution of a single MapReduce job. Our results show that MapReduce performance can be significantly improved; specifically, adaptive tuning of disk pairs' schedulers achieves a 25% performance improvement on a sort benchmark with Hadoop.

关键词： Benchmark testing Throughput Virtual machine monitors Interference Switches Virtual machining Tuning

来源：评论

学校读者我要写书评

暂无评论

LightDAG: A Low-latency DAG-based BFT Consensus through Lightweight Broadcast

LightDAG: A Low-latency DAG-based BFT Consensus through Ligh...

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Xiaohai Dai Guanxiong Wang Jiang Xiao Zhengxuan Guo Rui Hao Xia Xie Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China School of Computer Science and Artificial Intelligence Wuhan University of Technology China School of Computer Science and Technology Hainan University China

ISBN: (数字)9798350387117

ISBN: (纸本)9798350387124

To improve the throughput of Byzantine Fault Tolerance (BFT) consensus protocols, the Directed Acyclic Graph (DAG) topology has been introduced to parallel data processing, leading to the development of DAG-based BFT consensus. However, existing DAG-based works heavily rely on Reliable Broadcast (RBC) protocols for block broadcasting, which introduces significant latency due to the three communication steps involved in each RBC. For instance, DAgrider, a representative DAG-based protocol, exhibits the best latency of 12 steps, considerably higher than non-DAG protocols like PBFT, which only requires 3 steps. To tackle this issue, we propose LightDAG, which replaces RBC with lightweight broadcasting protocols such as Consistent Broadcast (CBC) and Plain Broadcast (PBC). Since CBC and PBC can be implemented in two and one communication steps, respectively, LightDAG achieves low *** our proposal, we present two variants of LightDAG, namely LightDAG1 and LightDAG2, each providing a trade-off between the best latency and the expected worst latency. In LightDAG1, every block is broadcast using CBC, which exhibits a best latency of 5 steps and an expected worst latency of 14 steps. Since CBC cannot guarantee the totality property, we design a block retrieval mechanism in LightDAG1 to assist replicas in retrieving missing blocks. LightDAG2 utilizes a combination of PBC and CBC for block broadcasting, resulting in the best latency of 4 steps and an expected worst latency of 12(t+1) steps, where t represents the number of actual Byzantine replicas. Since a Byzantine replica may equivocate through PBC, LightDAG2 prohibits blocks from directly referencing contradictory blocks. To ensure liveness, we propose a mechanism to identify and exclude Byzantine replicas if they engage in equivocation attacks. Extensive experiments have been conducted to evaluate LightDAG, and the results demonstrate its feasibility and efficiency.

关键词： Fault tolerance Distributed processing Directed acyclic graph Fault tolerant systems Broadcasting Throughput Data processing

来源：评论

学校读者我要写书评

暂无评论

SHelp: Automatic Self-Healing for Multiple Application Instances in a Virtual Machine Environment

SHelp: Automatic Self-Healing for Multiple Application Insta...

引用

IEEE International Conference on cluster computing

作者： Gang Chen Hai Jin Deqing Zou Bing Bing Zhou Weizhong Qiang Gang Hu Cluster and Grid Computing Laboratory Services Computing Technology and System Laboratory Huazhong University of Science and Technology Wuhan China Centre of Distributed and High Performance Computing School of Information Technologies University of Sydney NSW Australia

When multiple instances of an application running on multiple virtual machines, an interesting problem is how to utilize the fault handling result from one application instance to heal the same fault occurred on other sibling instances, and hence to ensure high service availability in a cloud computing environment. This paper presents SHelp, a lightweight runtime system that can survive software failures in the framework of virtual machines. It applies weighted rescue points and error virtualization techniques to effectively make applications by-pass the faulty path. A two-level storage hierarchy is adopted in the rescue point database for applications running on different virtual machines to share error handling information to reduce the redundancy and to more effectively and quickly recover from future faults caused by the same bugs. A Linux prototype is implemented and evaluated using four web server applications that contain various types of bugs. Our experimental results show that SHelp can make server applications to recover from these bugs in just a few seconds with modest performance overhead.

关键词： Virtual machining Databases Servers Buffer overflow Computer bugs Software Computer architecture

来源：评论

学校读者我要写书评

暂无评论

SMOG: Accelerating Subgraph Matching on GPUs

SMOG: Accelerating Subgraph Matching on GPUs

引用

IEEE Conference on High Performance Extreme computing (HPEC)

作者： Zhibin Wang Ziheng Meng Xue Li Xi Lin Long Zheng Chen Tian Sheng Zhong State Key Laboratory for Novel Software Technology Nanjing University Alibaba Group“ National Engineering Research Center for Big Data Technology and System/ Services Computing Technology and System Lab/Cluster and Grid Computing Laboratory Huazhong University of Science and Technology Zhejiang Lab

Subgraph matching is a crucial problem in graph theory with diverse applications in fields, such as bioinformatics, social networks and recommendation systems. Accelerating subgraph matching can be greatly facilitated by GPUs, which offer exceptional parallelism and high memory bandwidth. By leveraging the power of multiple GPU cards, subgraph matching can be scaled to achieve unprecedented levels of performance. In this paper, we propose SMOG, an abbreviation for. Subgraph Matching On Multi-Card GPUs. It is a general, high-performance and scalable sub graph matching system that utilizes multi-card GPUs. To address the issue of duplication resulting from subgraph automorphism, SMOG introduces a two-step approach. Firstly, it analyzes the symmetry within the subgraph. Then, it adaptively adjusts the graph preprocessing and generates subgraph-aware GPU codes tailored to the given subgraph. Furthermore, SMOG leverages multi-level parallelism by designing the specific strategy for each level, enabling it to scale from 1 to 1,024 GPU cards, resulting in an extraordinary $553\times$ speedup. We evaluate SMOG on various subgraph queries and datasets. The experimental results demonstrate that SMOG outperforms the triangle-specific system TRUST with an average speedup of $2.94\times$ . And it performs significantly better than the subgraph matching system RPS by $203.55\times$ and the graph processing system Gunrock by 35, $455.52\times$ on average.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FusionANNS: An Efficient CPU/GPU Cooperative Processing Architecture for Billion-scale Approximate Nearest Neighbor Search

arXiv

引用

arXiv 2024年

作者： Tian, Bing Liu, Haikun Tang, Yuhang Xiao, Shihai Duan, Zhuohui Liao, Xiaofei Zhang, Xuecang Zhu, Junhua Zhang, Yu National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Huawei Technologies Co. Ltd China

Approximate nearest neighbor search (ANNS) has emerged as a crucial component of database and AI infrastructure Ever-increasing vector datasets pose significant challenges in terms of performance, cost, and accuracy for ANNS services None of modern ANNS systems can address these issues simultaneously. We present FusionANNS, a high-throughput, low-latency cost-efficient, and high-accuracy ANNS system for billion scale datasets using SSDs and only one entry-level GPU The key idea of FusionANNS lies in CPU/GPU collabo rative filtering and re-ranking mechanisms, which signifi cantly reduce I/O operations across CPUs, GPU, and SSDs to break through the I/O performance bottleneck. Specifically we propose three novel designs: (1) multi-tiered indexing to avoid data swapping between CPUs and GPU, (2) heuristic re-ranking to eliminate unnecessary I/Os and computations while guaranteeing high accuracy, and (3) redundant-aware I/O deduplication to further improve I/O efficiency. We imple ment FusionANNS and compare it with the state-of-the-art SSD-based ANNS system–SPANN and GPU-accelerated in memory ANNS system–RUMMY. Experimental results show that FusionANNS achieves 1) 9.4-13.1× higher query per second (QPS) and 5.7-8.8× higher cost efficiency compared with SPANN;2) and 2-4.9× higher QPS and 2.3-6.8× higher cost efficiency compared with RUMMY, while guaranteeing low latency and high accuracy. Copyright © 2024, The Authors. All rights reserved.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

HI-Net: Hyperdense inception 3D UNet for brain tumor segmentation

arXiv

引用

arXiv 2020年

作者： Qamar, Saqib Ahmad, Parvez Shen, Linlin Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

The brain tumor segmentation task aims to classify tissue into the whole tumor (WT), tumor core (TC) and enhancing tumor (ET) classes using multimodel MRI images. Quantitative analysis of brain tumors is critical for clinical decision making. While manual segmentation is tedious, time-consuming, and subjective, this task is at the same time very challenging to automatic segmentation methods. Thanks to the powerful learning ability, convolutional neural networks (CNNs), mainly fully convolutional networks, have shown promising brain tumor segmentation. This paper further boosts the performance of brain tumor segmentation by proposing hyperdense inception 3D UNet (HI-Net), which captures multi-scale information by stacking factorization of 3D weighted convolutional layers in the residual inception block. We use hyper dense connections among factorized convolutional layers to extract more contexual information, with the help of features reusability. We use a dice loss function to cope with class imbalances. We validate the proposed architecture on the multi-modal brain tumor segmentation challenges (BRATS) 2020 testing dataset. Preliminary results on the BRATS 2020 testing set show that achieved by our proposed approach, the dice (DSC) scores of ET, WT, and TC are 0.79457, 0.87494, and 0.83712, respectively. © 2020, CC BY.

关键词： Convolution

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：