Results 61 to 70 of about 4,462 (194)

TensorFlow Doing HPC

, 2019
TensorFlow is a popular emerging open-source programming framework supporting the execution of distributed applications on heterogeneous hardware. While TensorFlow has been initially designed for developing Machine Learning (ML) applications, in fact ...
Bulatov, Yaroslav, Chien, Steven W. D., Laure, Erwin, Markidis, Stefano, Olshevsky, Vyacheslav, Vetter, Jeffrey S.   +5 more
core   +1 more source

Toward a new linpack‐like benchmark for heterogeneous computing resources

Concurrency and Computation: Practice and Experience, Volume 36, Issue 10, 1 May 2024.
Summary This work describes some first efforts to design a new Linpack‐like benchmark useful to evaluate the performance of Heterogeneous Computing Resources. The benchmark is based on the Schur Complement reformulation of the solution of a linear equation system.
Luisa Carracciuolo, Valeria Mele, Gianluca Sabella   +2 more
wiley   +1 more source

GPU peer-to-peer techniques applied to a cluster interconnect

, 2013
Modern GPUs support special protocols to exchange data directly across the PCI Express bus. While these protocols could be used to reduce GPU data transmission times, basically by avoiding staging to host memory, they require specific hardware features ...
Ammendola, Roberto, Bernaschi, Massimo, Biagioni, Andrea, Bisson, Mauro, Cicero, Francesca Lo, Fatica, Massimiliano, Frezza, Ottorino, Lonardo, Alessandro, Mastrostefano, Enrico, Paolucci, Pier Stanislao, Rossetti, Davide, Simula, Francesco, Tosoratto, Laura, Vicini, Piero   +13 more
core   +1 more source

Scalable Distributed DNN Training using TensorFlow and CUDA-Aware MPI: Characterization, Designs, and Performance Evaluation

, 2018
TensorFlow has been the most widely adopted Machine/Deep Learning framework. However, little exists in the literature that provides a thorough understanding of the capabilities which TensorFlow offers for the distributed training of large ML/DL models ...
Awan, Ammar Ahmad, Bedorf, Jeroen, Chu, Ching-Hsiang, Panda, Dhabaleswar K., Subramoni, Hari   +4 more
core   +1 more source

Detection of Biomarkers through Functionalized Polymers

Small Methods, Volume 8, Issue 1, January 19, 2024.
The incorporation of functional groups into polymer‐based materials such as hydrogels, nanosheets, and nanopores has revolutionized the field of biomarker detection. This comprehensive review explores the latest advancements in materials and techniques employed for polymer functionalization.
Litzy L. García‐Faustino, Stephen M. Morris, Steve J. Elston, Yunuen Montelongo   +3 more
wiley   +1 more source

Optimizing distributed systems with remote direct memory access

大数据, 2018
Fast network devices with RDMA support have been price-compatible with traditional network primitives such as Ethernet,and it’s now widely deployed in modern data centers.RDMA can be used in two ways.Firstly,it can optimize the messaging primitive in ...
Xingda WEI, Rong CHEN, Haibo CHEN
doaj  

Status-Byte-Assisted RDMA Transmission Mechanism for Optimizing Multi-Task Video Streaming in Edge Computing

Applied Sciences
In the context of the rapid development of edge computing, optimizing data transmission and reducing latency is crucial for efficient collaborative processing among edge servers.
Donglei Xiao, Huiyue Yi, Wuxiong Zhang, Wenhui Shen   +3 more
doaj   +1 more source

Rate-adaptive RDMA congestion control for AI clusters

Journal of Cloud Computing: Advances, Systems and Applications
The rapid growth of AI models has imposed increasingly stringent performance demands on data centers. Modern data centers adopt Remote Direct Memory Access (RDMA) to reduce CPU overhead and network latency. RDMA operates over a lossless network, and RDMA
Xin He, Zihao Zhang, Junchang Wang, Zheng Wu, Weibei Fan, Yiping Zuo   +5 more
doaj   +1 more source

Current development status of key technologies for high-performance on-board interconnection buses — analysis of TSN bus application prospects in aerospace

Frontiers in Astronomy and Space Sciences
This paper conducts a comprehensive survey and analysis of interconnection buses for space applications both domestically and internationally in recent years. In response to the future demands of satellites for high-performance computing, high-efficiency
Wenjie Zhao, Wenjie Zhao, Wanying Zhang, Jianing Rao, Jianing Rao, Shuangxue Han, Wenyuan Jia, Jingxing Song, Miao Ma, Zhenxing Dong, Zhenxing Dong, Guodong Yin, Guodong Yin, Yan Zhu, Yan Zhu, Junshe An, Junshe An   +16 more
doaj   +1 more source

Design and implementation of an RDMA-based data transmission system prototype for ETF

Nuclear Engineering and Technology
Data transmission is crucial in nuclear physics experiments. As the size of detectors and measurement data increases, traditional Ethernet protocols have become insufficient for performance requirements.
Yuqiao Zhang, Min Li, Kai Zhou, Kejie You, Yuhong Yu, Zhiyu Sun, Ruishi Mao, Peng Li, Youjin Yuan   +8 more
doaj   +1 more source