检索结果-内蒙古大学图书馆

international symposium on parallel and distributed Processing (IPDPS)

作者： Diogo Nunes Daniel Castro Paolo Romano Instituto Superior T&#x00E9 cnico &#x0026 INESC-ID Lisbon Portugal

GPUs have traditionally focused on streaming applications with regular parallelism. Over the last years, though, GPUs have also been successfully used to accelerate irregular applications in a number of application domains by using fine grained synchronization schemes. Unfortunately, fine-grained synchronization strategies are notoriously complex and error-prone. This has motivated the search for alternative paradigms aimed to simplify concurrent programming and, among these, Transactional Memory (TM) is probably one of the most prominent proposals. This paper introduces CSMV (Client Server Multiversioned), a multi-versioned Software TM (STM) for GPUs that adopts an innovative client-server design. By decoupling the execution of transactions from their commit process, CSMV provides two main benefits: (i) it enables the use of fast on chip memory to access the global metadata used to synchronize transaction (ii) it allows for implementing highly efficient collaborative commit procedures, tailored to take full advantage of the architectural characteristics of GPUs. Via an extensive experimental study, we show that CSMV achieves up to 3 orders of magnitude speed-ups with respect to state of the art STMs for GPUs and that it can accelerate by up to 20× irregular applications running on state of the art STMs for CPUs.

关键词： Concurrent computing distributed processing Memory management Collaboration Programming parallel processing Metadata

来源：评论

学校读者我要写书评

暂无评论

ESSA 2022 Invited Speaker: The Curious Incident of the Data in the Scientific Workflow

ESSA 2022 Invited Speaker: The Curious Incident of the Data ...

引用

IEEE international symposium on parallel and distributed Processing Workshops and Phd Forum (IPDPSW)

作者： Lavanya Ramakrishnan Lawrence Berkeley National Laboratory

ISBN: (数字)9781665497473

ISBN: (纸本)9781665497480

The volume, veracity, and velocity of data generated by the accelerators, colliders, supercomputers, light sources and neutron sources have grown exponentially in the last decade. Data has fundamentally changed the scientific workflow running on high performance computing (HPC) systems. It is necessary that we develop appropriate capabilities and tools to understand, analyze, preserve, share, and make optimal use of data. Intertwined with data are complex human processes, policies and decisions that need to be accounted for when building software tools. In this talk, I will outline our work addressing data lifecycle challenges on HPC systems including effective use of storage hierarchy, managing complex scientific data processing, and enabling search on large-scale scientific data.

关键词： Software tools distributed processing distributed databases Conferences Buildings Supercomputers Neutrons

来源：评论

学校读者我要写书评

暂无评论

Lotus: Characterization of Machine Learning Preprocessing Pipelines via Framework and Hardware Profiling

Lotus: Characterization of Machine Learning Preprocessing Pi...

引用

IEEE international Workshop/symposium on Workload Characterization

作者： Rajveer Bachkaniwala Harshith Lanka Kexin Rong Ada Gavrilovska Georgia Tech

ISBN: (数字)9798350356038

ISBN: (纸本)9798350356045

Preprocessing input data is a crucial step in machine learning pipelines, involving tasks such as loading, decoding, and applying transformations. Prior works have identified preprocessing as a performance bottleneck for ML training jobs and introduced optimizations like CPU and I/O parallelism, accelerator offloading, and on-node/distributed computing as well as caching to mitigate this bottleneck. However, there is a lack of support for characterizing preprocessing pipelines at a finer granularity, especially at the microarchitecture level, which can provide insights to validate and inform the design of existing and future optimization *** enable these insights, we introduce Lotus, a profiling tool for the preprocessing stage of ML pipelines. Firstly, it captures fine-grained preprocessing events (e.g., <10 ms) with minimal time and storage overheads. Secondly, it bridges the gap between high-level Python functions and low-level hardware performance counters by reconstructing a mapping between Python functions and the underlying C++ functions they invoke. This unique combination enables users to better reason about their pipeline’s performance at both the framework and CPU architecture levels. We demonstrate the insights made possible by applying Lotus to representative ML workloads and compare its capabilities, overheads, and ease of use with alternative profilers.

关键词： Training Microarchitecture Instruments Pipelines Data preprocessing Machine learning parallel processing Hardware Timing Optimization

来源：评论

学校读者我要写书评

暂无评论

FlashWalker: An In-Storage Accelerator for Graph Random Walks

FlashWalker: An In-Storage Accelerator for Graph Random Walk...

引用

international symposium on parallel and distributed Processing (IPDPS)

作者： Fuping Niu Jianhui Yue Jiangqiu Shen Xiaofei Liao Haikun Liu 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 Wuhan China Department of Computer Science Michigan Technological University Houghton Michigan USA

Graph random walk is widely used in the graph processing as it is a fundamental component in graph analysis, ranging from vertices ranking to the graph embedding. Different from traditional graph processing workload, random walk features massive processing parallelisms and poor graph data reuse, being limited by low I/O efficiency. Prior designs for random walk mitigate slow I/O operations. However, the state-of-the-art random walk processing systems are bounded by slow disk I/O bandwidth, which is confirmed by our experiments with real-world graphs. To address this issue, we propose FlashWalker, an in-storage accelerator for random walk that moves walk updating close to graph data stored in flash memory, by exploiting significant parallelisms inside SSD. Featuring a heterogeneous and parallel processing system, FlashWalker includes a board-level accelerator, channel-level accelerators, and chip-level accelerators. To address challenges posed by the tight resource constraints for processing large-scale graphs, we propose novel designs: storing a few popular subgraphs in accelerators, the pre-walking for dense walks, two optimizations to search the subgraph mapping table, and a subgraph scheduling algorithm. We implement FlashWalker in RTL, showing small circuit area overhead. Our evaluation shows FlashWalker reduces the execution time of random walk algorithms by up to 660.50×, compared with GraphWalker, which is the state-of-the-art system for random walk algorithms.

关键词： distributed processing Scheduling algorithms Bandwidth parallel processing Distance measurement Flash memories Optimization

来源：评论

学校读者我要写书评

暂无评论

Scheduling Coflows for Minimizing the Makespan in Identical parallel Networks

arXiv

引用

arXiv 2023年

作者： Chen, Chi-Yeh Chen, Jun Department of Computer Science and Information Engineering National Cheng Kung University Taiwan

With the rapid advancement of technology, parallel computing applications have become increasingly popular and are commonly executed in large data centers. These applications involve two phases: computation and communication, which are executed repeatedly to complete the work. However, due to the ever-increasing demand for computing power, large data centers are struggling to meet the massive communication demands. To address this problem, coflow has been proposed as a networking abstraction that captures communication patterns in data-parallel computing frameworks. This paper focuses on the coflow scheduling problem in identical parallel networks, where the primary objective is to minimize the makespan, which is the maximum completion time of coflows. It is considered one of the most significant NP-hard problems in large data centers. In this paper, we consider two problems: flow-level scheduling and coflow-level scheduling. In the flow-level scheduling problem, distinct flows can be transferred through different network cores, whereas in the coflow-level scheduling problem, all flows must be transferred through the same network core. To address the flow-level scheduling problem, this paper proposes two algorithms: (formula presented)-approximation algorithm and a (formula presented)-approximation algorithm, where m represents the number of network cores. For the coflow-level scheduling problem, this paper proposes a (2m)-approximation algorithm. Finally, we conduct simulations on our proposed algorithm and Weaver’s algorithm, as presented in Huang et al. (2020) in the 2020 IEEE international parallel and distributed Processing symposium (IPDPS). We also validate the effectiveness of the proposed algorithms on heterogeneous parallel networks. Copyright © 2023, The Authors. All rights reserved.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Online Scheduling with Redirection for parallel Jobs 34

Online Scheduling with Redirection for Parallel Jobs

引用

34th IEEE international parallel and distributed Processing symposium (IPDPS)

作者： Faure, Adrien Lucarelli, Giorgio Richard, Olivier Trystram, Denis Atos Echirolles France Univ Grenoble Alpes CNRS Grenoble INP INRIALIG Grenoble France Univ Lorraine LCOMS Metz France

ISBN: (纸本)9781728174457

An important component of High Performance computing (HPC) clusters is the job scheduling algorithm, which decides the allocation and the scheduling of the jobs in the system. Such scheduling algorithms need to be scalable to confront the growth both in size and in complexity of the modern clusters. We propose in this paper a new algorithm for scheduling parallel jobs with redirection. Specifically, our algorithm redirects the jobs whose execution affects significantly an important number of other jobs. A redirected job is stopped and restarted from the beginning in a dedicated part of the cluster. We show the effectiveness of our method through an intensive experimental campaign of simulations of production cluster log traces.

关键词： Scheduling parallel jobs Redirection

来源：评论

学校读者我要写书评

暂无评论

Dynamic Computation Offloading for Green Things-Edge-Cloud computing with Local Caching

Dynamic Computation Offloading for Green Things-Edge-Cloud C...

引用

international symposium on parallel and distributed Processing (IPDPS)

作者： Xianzhong Tian Huixiao Meng Yanjun Li Pingting Miao Pengcheng Xu School of Computer Science and Technology Zhejiang University of Technology Hangzhou China

With the increasing popularity of the internet of things (IoT) and 5G, emerging things-edge-cloud computing (TEC) paradigm provides a flexible way for execution of delay-sensitive and computation-intensive applications running on the user equipment (UE). By offloading these workloads to the mobile edge computing (MEC) or mobile cloud computing (MCC) server, the quality of experience, e.g., the execution delay, could be greatly improved. Nevertheless, conventional battery-powered devices face the challenge of battery exhaustion for task offloading. Using renewable energy via energy harvesting (EH) technologies has become a promising way to power these devices. In this paper, we investigate a multi-user green TEC system with EH UEs, each has a task buffer with limited capacity. A joint offloading decision and resource allocation problem is formulated, which addresses the long-term average execution delay, the task dropping and the long-term average energy cost constraint. A low-complexity online algorithm is proposed leveraging Lyapunov optimization framework and matroid theory, which jointly decides the offloading decision, the MEC server CPU frequencies and the transmit power for computation offloading. A unique advantage of this algorithm is that the decisions depend only on the current system state without requiring distribution information of the arrival tasks, wireless channel state, and EH processes. The implementation of the algorithm only requires to solve a deterministic problem in each time slot. Simulation results show that our proposed algorithm makes a best trade-off between minimizing the long-term average generalized delay and satisfying the long-term average energy cost constraint. Impacts of various parameters on the delay and energy cost performance are also discussed.

关键词： Wireless communication Costs Simulation Green products Delays Servers Resource management

来源：评论

学校读者我要写书评

暂无评论

computing Hypergraph Homology in Chapel 34

Computing Hypergraph Homology in Chapel

引用

34th IEEE international parallel and distributed Processing symposium (IPDPS)

作者： Firoz, Jesun Sahariar Jenkins, Louis Joslyn, Cliff Praggastis, Brenda Purvine, Emilie Raugas, Mark Pacific Northwest Natl Lab Seattle WA 98109 USA Univ Rochester Rochester NY USA

ISBN: (纸本)9781728174457

In this paper, we discuss our experience in implementing homology computation, in particular the Betti number calculations in Chapel hypergraph Library (CHGL). Given a dataset represented as a hypergraph, a Betti number for a particular dimension k indicates how many k-dimensional `voids' are present in the dataset. computing the Betti numbers involve various array-centric and linear algebra operations. We demonstrate that implementing these operations in Chapel is both concise and intuitive. In addition, we show that Chapel provides language constructs for implementing parallel and distributed execution of the linear algebra kernels with minimal effort. Syntactically, Chapel provides succinctness of Python, while delivering comparable and better performance than C++-based and Julia-based packages for calculating the Betti numbers respectively.

关键词： Chapel computational topology hypergraphs

来源：评论

学校读者我要写书评

暂无评论

ScaDL 2022 Invited Talk 3: Million-x speedups through convergence of AI and HPC

ScaDL 2022 Invited Talk 3: Million-x speedups through conver...

引用

IEEE international symposium on parallel and distributed Processing Workshops and Phd Forum (IPDPSW)

作者： Anima Anandkumar Caltech and NVIDIA

ISBN: (数字)9781665497473

ISBN: (纸本)9781665497480

Many scientific applications currently rely on the use of brute-force numerical methods performed on highperformance computing (HPC) infrastructure. However, these methods have their limits even with the growing hardware capabilities, e.g. for fine-scale climate prediction and large molecule quantum chemistry. Can artificial intelligence (AI) methods augment or even entirely replace these brute-force calculations to obtain million-x speed-ups? Can we make groundbreaking new discoveries because of such speed-ups? I will present exciting recent advances that build new foundations in AI that are applicable to a wide range of problems such as fluid dynamics and quantum chemistry.

关键词： Artificial intelligence Quantum chemistry distributed processing Conferences Web services US Department of Defense Tensors

来源：评论

学校读者我要写书评

暂无评论

Sequre: a high-performance framework for rapid development of secure bioinformatics pipelines

Sequre: a high-performance framework for rapid development o...

引用

IEEE international symposium on parallel and distributed Processing Workshops and Phd Forum (IPDPSW)

作者： Haris Smajlović Ariya Shajii Bonnie Berger Hyunghoon Cho Ibrahim Numanagić University of Victoria BC Canada MIT Massachusetts USA Broad Institute of MIT and Harvard Massachusetts USA

ISBN: (数字)9781665497473

ISBN: (纸本)9781665497480

Genomic data leaks are irreversible. Leaked DNA cannot be changed, stays disclosed indefinitely, and affects the owner's family members as well. The recent large-scale genomic data collections [1], [2] render the traditional privacy protection mechanisms, like the Health Insurance Portability and Accountability Act (HIPAA), inadequate for protection against the novel security attacks [3]. On the other hand, data access restrictions hinder important clinical research that requires large datasets to operate [4]. These concerns can be naturally addressed by the employment of privacy-enhancing technologies, such as a secure multiparty computation (MPC) [5]–[10]. Secure MPC enables computation on data without disclosing the data itself by dividing the data and computation between multiple computing parties in a distributed manner to prevent individual computing parties from accessing raw data. MPC systems are being increasingly adopted in fields that operate on sensitive datasets [11]–[13], such as computational genomics and biomedical research [14]–[22].

关键词： distributed processing Data privacy Pipelines Employment distributed databases Genomics Insurance

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：