检索结果-内蒙古大学图书馆

28th ACM SIGPLAN Annual Symposium on Principles and Practice of parallel Programming, PPoPP 2023

作者： Chadha, Mohak Krueger, Nils John, Jophin Jindal, Anshul Gerndt, Michael Benedict, Shajulin Computer Architecture and Parallel Systems Technische Universität München Germany Department of Computer Science and Engg. Indian and Institute of Information Technology Kottayam Kerala India

ISBN: (纸本)9798400700156

Containerization approaches based on namespaces offered by the Linux kernel have seen an increasing popularity in the HPC community both as a means to isolate applications and as a format to package and distribute them. However, their adoption and usage in HPC systems faces several challenges. These include difficulties in unprivileged running and building of scientific application container images directly on HPC resources, increasing heterogeneity of HPC architectures, and access to specialized networking libraries available only on HPC systems. These challenges of container-based HPC application development closely align with the several advantages that a new universal intermediate binary format called WebAssembly (Wasm) has to offer. These include a lightweight userspace isolation mechanism and portability across operating systems and processor architectures. In this paper, we explore the usage of Wasm as a distribution format for MPI-based HPC applications. To this end, we present MPIWasm, a novel Wasm embedder for MPI-based HPC applications that enables high-performance execution of Wasm code, has low-overhead for MPI calls, and supports high-performance networking interconnects present on HPC systems. We evaluate the performance and overhead of MPIWasm on a production HPC system and AWS Graviton2 nodes using standardized HPC benchmarks. Results from our experiments demonstrate that MPIWasm delivers competitive native application performance across all scenarios. Moreover, we observe that Wasm binaries are 139.5x smaller on average as compared to the statically-linked binaries for the different standardized benchmarks. © 2023 ACM.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Proximity-based service discovery for distributed digital twin systems

引用

Discover Internet of Things 2025年第1期5卷 1-24页

作者： Rothermel, Kurt Herzog, Otthein Zhiqiang, Siegfried Wu Institute Of Parallel and Distributed Systems University of Stuttgart Universitaetsstr. 38 Stuttgart70569 Germany College of Architecture and Urban Planning Tongji University 1239 Siping Road Shanghai200092 China Department of Mathematics and Computer Science University of Bremen Bibliothekstrasse 5 Bremen23884 Germany

Over the past decade, there has been a significant increase in interest in digital twin (DT) technology in a variety of domains. While research on DTs of single assets was initially prevalent, there has been a notable shift towards distributed systems of DTs, which connect to each other to collaborate. Typically, collaboration is enabled by DTs providing services that can be consumed by other DTs. In service-oriented systems, a service is typically identified by type information. However, this is not sufficient in distributed DT systems, where DTs associated with different physical entities may provide the same type of service. Consequently, selecting the appropriate service depends not only on the service type, but also on the associated physical entity. However, requiring DTs to know the mapping of services to their physical environment is not feasible for large dynamic systems. This paper presents a novel proximity-based service discovery method that allows DTs to select services based on service type and their proximity to other objects. That is, service specifications are fully abstracted from the mapping of services to physical objects, relieving DTs from maintaining information about this mapping. Furthermore, service discovery is robust to changes in the physical environment and service population. The proposed service discovery method has been implemented on top of a spatial DBMS. We argue that this implementation is optimal in terms of network utilization and latency, and perform comprehensive evaluations to show the performance of discovery queries as a function of their complexity. © The Author(s) 2025.

关键词： Location based services

来源：评论

学校读者我要写书评

暂无评论

LoRa-Powered Energy-Effcient Object Detection Mechanism in Edge Computing Nodes 6

LoRa-Powered Energy-Effcient Object Detection Mechanism in E...

引用

6th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2022

作者： Jindal, Anshul Jose, Jiby Mariya Benedict, Shajulin Gerndt, Michael Technical University Munich Computer Architecture and Parallel Systems Germany Indian Institute of Information Technology Kottayam Department of Computer Science and Engg. India

ISBN: (数字)9781665469418

ISBN: (纸本)9781665469418

The ongoing accomplishments in the decades-long realization of computer vision have infused new dimensions in various research areas such as smart mobility, smart healthcare, education, finance, and so forth. Research works relating to automated object detection, deep learning-assisted data pipelines, and energy-efficient end-to-end solutions have enabled newer perceptions among researchers, albeit the existence of challenges. This paper proposes an object detection system using energy-efficient Long Range (LoRA) communication media on edge nodes such as Raspberry Pi, Coral DevBoard, and Nvidia Jetson Nano. The proposed approach utilized energy-efficient methods to collaboratively offload object detection-related tasks such as capturing images, training images, and inferring objects across a compendium of computing nodes using LoRA. In addition, this research study has attempted to reveal the inference capabilities of images on three different edge nodes. The proposed work has achieved a power difference of at least 1.2 watts during the inference period of the deep learning models without challenging the prediction accuracy with respect to the base model. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Bfloat16, Posit, and Takum Arithmetics in Sparse Linear Solvers

arXiv

引用

arXiv 2024年

作者： Hunhold, Laslo Quinlan, James Parallel and Distributed Systems Group University of Cologne Cologne Germany Department of Computer Science University of Southern Maine Portland ME United States

Solving sparse linear systems lies at the core of numerous computational applications. Consequently, understanding the performance of recently proposed alternatives to the established IEEE 754 floating-point numbers, such as bfloat16 and the tapered-precision posit and takum machine number formats, is of significant interest. This paper examines these formats in the context of widely used solvers, namely LU, QR, and GMRES, with incomplete LU preconditioning and mixed precision iterative refinement (MPIR). This contrasts with the prevailing emphasis on designing specialized algorithms tailored to new arithmetic formats. This paper presents an extensive and unprecedented evaluation based on the SuiteSparse Matrix Collection—a dataset of real-world matrices with diverse sizes and condition numbers. A key contribution is the faithful reproduction of SuiteSparse’s UMFPACK multifrontal LU factorization and SPQR multifrontal QR factorization for machine number formats beyond single and double-precision IEEE 754. Tapered-precision posit and takum formats show better accuracy in direct solvers and reduced iteration counts in indirect solvers. Takum arithmetic, in particular, exhibits exceptional stability, even at low precision. © 2024, CC BY.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Exploring the Use of WebAssembly in HPC

arXiv

引用

arXiv 2023年

作者： Chadha, Mohak Krueger, Nils John, Jophin Jindal, Anshul Gerndt, Michael Benedict, Shajulin Chair of Computer Architecture and Parallel Systems Technische Universität München Germany Department of Computer Science and Engg. Indian Institute of Information Technology Kerala Kottayam India

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Efficient Evolution of Variable Ordering for Binary Decision Diagram Optimization

引用

IEEE Transactions on Evolutionary Computation 2025年

作者： Krauss, Rune Drechsler, Rolf German Research Center for Artificial Intelligence Cyber-Physical Systems Department Bremen28359 Germany University of Bremen Group of Computer Architecture Institute of Computer Science Bremen28359 Germany

The hardware complexity related to the number of transistors in electronic devices used by today's society has grown considerably in the last decades because of technological progress. In order to guarantee the correct behavior of such devices and meet time-to-market constraints, there is a need to continuously develop more efficient data structures and algorithms in formal verification. The performance of verification algorithms depends in particular on the compactness of data structures. A reduced ordered binary decision diagram (BDD) is basically a suitable data structure to verify digital circuits, as it represents Boolean functions canonically respecting a variable ordering and allows direct manipulation of them. However, one of the main challenges with BDDs is to find a variable ordering so that the BDD size of a function is compact and does not become impractical due to a dramatically increasing number of BDD nodes. To address the aforementioned issue, this article presents a novel evolution strategy having an efficient evaluation of variable ordering in a divide-and-conquer manner for BDD optimization. Experiments on benchmarks of multilevel circuits show that using this strategy results in considerably smaller BDDs being found significantly faster compared to state-of-the-art optimization techniques. © 1997-2012 IEEE.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Telemetry for Quantum systems in HPC Centers

Telemetry for Quantum Systems in HPC Centers

引用

ISC High Performance 2025 Research Paper Proceedings (40th International Conference)

作者： Hossam Ahmed Burak Mete Helmut Heller Matthew Tovey Xiaolong Deng Asim Zulfiqar Muhammad Nufail Farooqi Mahmoud Abuzayed Martin Schulz Laura Schulz QCT Department Leibniz Supercomputing Centre of the Bavarian Academy of Science and Humanities (LRZ) Garching b. München Germany Chair for Computer Architecture and Parallel Systems (CAPS) Technical University of Munich (TUM) Garching b. München Germany

ISBN: (数字)9783982633619

Quantum systems have traditionally operated within highly controlled laboratory environments to minimize internal noise and maximize stability. However, when these systems are integrated into High Performance Computing (HPC) environments and setup for continuous operation, they encounter significantly higher levels of external noise and instability coupled with higher demands. This paper introduces a comprehensive framework to counter the challenges of maintaining the stability of operational quantum computers in such noisy HPC settings. We propose a novel system architecture that monitors and manages the environmental conditions of quantum computing systems using a broad set of sensors, enhancing their robustness and reliability. Our architecture is open and can be extended to other setups. It can serve as a blueprint for other sites as it spans quantum technologies and offers broad coverage. Ultimately, this data will be essential to facilitate advancements in machine learning to drive real-time error mitigation.

关键词： computers Quantum system Trapped ions Quantum computing Working environment noise systems architecture Machine learning Stability analysis Telemetry Monitoring

来源：评论

学校读者我要写书评

暂无评论

A preliminary study about gender gap perception in informatics studies in Spain 12

A preliminary study about gender gap perception in informati...

引用

12th International Conference on Virtual Campus, JICV 2022

作者： Garcia-Holgado, Alicia Gonzalez-Gonzalez, Carina S. Fernandez, Inmaculada Garcia Lopez, Lourdes Moreno Barrenechea, Edurne Rueda, Silvia Navarro, Angeles G. Martinez, Paloma Masia, Belen Navarro, Elena Fornes, Alicia Grial Research Group Universidad DeSalamanca Computer Science and Automation Department Salamanca Spain University of la Laguna Computer Engineering Department San Cristobal de La Laguna Spain Universidad de Málaga Computer Architecture Department Málaga Spain Universidad Carlos Iii de Madrid Computer Science and Engineering Department Madrid Spain Universidad Pública de Navarra Departamento de Estadística Informática y Matemáticas Pamplona Spain Universitat de València Departament of Computer Science Valencia Spain Universidad de Zaragoza Computer Science Department Zaragoza Spain Universidad de Castilla la Mancha Departament of Computing Systems Albacete Spain Computer Vision Center Universitat Autónoma de Barcelona Barcelona Spain

ISBN: (数字)9781665451062

ISBN: (纸本)9781665451062

The gender gap in STEM is an issue that affects regions and countries worldwide. Furthermore, the percentage of women in these areas depends on a range of different factors. In particular, the gender gap is critical in technology in general and, more specifically, in informatics. This problem affects not only the business sector but also society. Informatics is part of our lives;however, 50% of the world population is not represented in the teams that are developing solutions for solving society's problems. In Spain, the number of women with informatics degrees is around 15%. This work describes a case study developed by the committee of Women in Informatics at the Scientific Society of Spanish Informatics (SCIE) to analyse the perception of informatics scientists on the gender gap in informatics. © 2022 IEEE.

关键词： computers

来源：评论

学校读者我要写书评

暂无评论

Strong consistency is not hard to get: Twophase locking and twophase commit on thousands of cores 46th

Strong consistency is not hard to get: Twophase locking and ...

引用

46th International Conference on Very Large Data Bases, VLDB 2020

作者： Barthels, Claude Müller, Ingo Taranov, Konstantin Alonso, Gustavo Hoefler, Torsten Systems Group Department of Computer Science ETH Zurich Switzerland Scalable Parallel Computing Lab Department of Computer Science ETH Zurich Switzerland

Concurrency control is a cornerstone of distributed database engines and storage systems. In pursuit of scalability, a common assumption is that Two-Phase Locking (2PL) and Two-Phase Commit (2PC) are not viable solutions due to their communication overhead. Recent results, however, have hinted that 2PL and 2PC might not have such a bad performance. Nevertheless, there has been no attempt to actually measure how a state-of-the-art implementation of 2PL and 2PC would perform on modern hardware. The goal of this paper is to establish a baseline for concurrency control mechanisms on thousands of cores connected through a lowlatency network. We develop a distributed lock table supporting all the standard locking modes used in database engines. We focus on strong consistency in the form of strict serializability implemented through strict 2PL, but also explore read-committed and repeatableread, two common isolation levels used in many *** do not leverage any known optimizations in the locking or commit parts of the protocols. The surprising result is that, for TPC-C, 2PL and 2PC can be made to scale to thousands of cores and hundreds of machines, reaching a throughput of over 21 million transactions per second with 9.5 million New Order operations per second. Since most existing relational database engines use some form of locking for implementing concurrency control, our findings provide a path for such systems to scale without having to significantly redesign transaction management. To achieve these results, our implementation relies on Remote Direct Memory Access (RDMA). Today, this technology is commonly available on both Infiniband as well as Ethernet networks, making the results valid across a wide range of systems and platforms, including database appliances, data centers, and cloud environments. © VLDB Endowment.

关键词： Concurrency control

来源：评论

学校读者我要写书评

暂无评论

PROV-IO+: A Cross-Platform Provenance Framework for Scientific Data on HPC systems

arXiv

引用

arXiv 2023年

作者： Han, Runzhou Zheng, Mai Byna, Suren Tang, Houjun Dong, Bin Dai, Dong Chen, Yong Kim, Dongkyun Hassoun, Joseph Thorsley, David Wolf, Matthew Department of Electrical and Computer Engineering Iowa State University United States Department of Computer Science and Engineering The Ohio State University United States Scientific Data Management Group Lawrence Berkeley National Laboratory United States Computer Science Department University of North Carolina Charlotte United States Systems Architecture Lab Samsung United States Samsung Advanced Institute of Technology Samsung Korea Republic of

Data provenance, or data lineage, describes the life cycle of data. In scientific workflows on HPC systems, scientists often seek diverse provenance (e.g., origins of data products, usage patterns of datasets). Unfortunately, existing provenance solutions cannot address the challenges due to their incompatible provenance models and/or system implementations. In this paper, we analyze four representative scientific workflows in collaboration with the domain scientists to identify concrete provenance needs. Based on the first-hand analysis, we propose a provenance framework called PROV-IO+, which includes an I/O-centric provenance model for describing scientific data and the associated I/O operations and environments precisely. Moreover, we build a prototype of PROV-IO+ to enable end-to-end provenance support on real HPC systems with little manual effort. The PROV-IO+ framework can support both containerized and non-containerized workflows on different HPC platforms with flexibility in selecting various classes of provenance. Our experiments with realistic workflows show that PROV-IO+ can address the provenance needs of the domain scientists effectively with reasonable performance (e.g., less than 3.5% tracking overhead for most experiments). Moreover, PROV-IO+ outperforms a state-of-the-art system (i.e., ProvLake) in our experiments. © 2023, CC BY-NC-SA.

关键词： Life cycle

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

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

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：