Filters








21 Hits in 7.5 sec

Zenoh-based Dataflow Framework for Autonomous Vehicles

Gabriele Baldoni, Julien Loudet, Luca Cominardi, Angelo Corsaro, Yong He
2021 Zenodo  
For that purpose, we first show how we used Zenoh to enhance ERDOS, a dataflow framework for Autonomous Vehicles. We then motivate and draft our own dataflow framework based on Zenoh: Zenoh Flow.  ...  To cope with these requirements, frameworks based on dataflow programming are emerging.  ...  However powerful, the Cloud-computing is not a "one size fits all" solution: for instance, latency-sensitive applications or applications in remote locations with poor connectivity cannot rely on it.  ... 
doi:10.5281/zenodo.5734287 fatcat:4thjxj7ysfeuhjx72zeytfzoqi

AutoSys: The Design and Operation of Learning-Augmented Systems

Chieh-Jan Mike Liang, Hui Xue, Mao Yang, Lidong Zhou, Lifei Zhu, Zhao Lucis Li, Zibo Wang, Qi Chen, Quanlu Zhang, Chuanjie Liu, Wenjun Dai
2020 USENIX Annual Technical Conference  
Furthermore, this paper demonstrates the benefits of adopting AutoSys with measurements from one production system, Web Search.  ...  AutoSys is a framework that unifies the development process, and it addresses common design considerations including ad-hoc and nondeterministic jobs, learning-induced system failures, and programming  ...  Ana Klimovic, for their extensive comments and suggestions.  ... 
dblp:conf/usenix/LiangXYZZLWCZLD20 fatcat:yjykcwwaynfmtegyeuesppnile

D1.1 - State of the Art Analysis

Danilo Ardagna
2021 Zenodo  
It examines the standardisation and opensource landscape, where many of the emerging standards are mainly focused on the network layer, also highlighting opportunities for open-source community involvement  ...  Then, the deliverable provides a background on AI applications design, also considering some advanced design trends (e.g., Network Architecture Search, Federated Learning, Deep Neural Networks partitioning  ...  on a CPU or a GPU.  ... 
doi:10.5281/zenodo.6372377 fatcat:f6ldfuwivbcltew4smiiwphfty

Efficient local locking for massively multithreaded in-memory hash-based operators

Bashar Romanous, Skyler Windh, Ildar Absalyamov, Prerna Budhkar, Robert Halstead, Walid Najjar, Vassilis Tsotras
2021 The VLDB journal  
AbstractThe join and group-by aggregation are two memory intensive operators that are affecting the performance of relational databases. Hashing is a common approach used to implement both operators.  ...  Throughput results for our hash-join operator accelerator show a speedup between 2$$\times $$ × and 3.4$$\times $$ × over the best multi-core approaches with comparable memory bandwidths on uniform and  ...  Different FPGA architectures are optimized for various use cases: HPC computations, database workloads, or packet processing.  ... 
doi:10.1007/s00778-020-00642-5 fatcat:cectiabfwrdfzj7s7e5kqrhwmu

D5.1 Operator Cost Estimation and Workflow Optimisation Technology V1

Project Consortium Members
2020 Zenodo  
Big Data processing workflows typically span a multitude of execution and storage platforms.  ...  or more (potentially distributed) Big Data platforms or within other clusters (i.e., GPUs) of a supercomputer.  ...  [NL16] develops a GPU performance model for stream workload partitioning in multi-GPU platforms. [CXT+15] proposes G-Storm, which enables Apache Storm to utilize GPUs.  ... 
doi:10.5281/zenodo.4034108 fatcat:t22h4qqgjfbsporpl4zkf5c2qm

Artificial Intelligence (AI) and Machine Learning for Multimedia and Edge Information Processing

Jasmine Kah Phooi Seng, Kenneth Li-minn Ang, Eno Peter, Anthony Mmonyi
2022 Electronics  
The motivation of this paper was to survey these new paradigms for multimedia and edge information processing from several technological perspectives including: (1) multimedia analytics on the edge empowered  ...  Compared to cloud information processing approaches where the data are collected and sent to a centralized server for information processing, the edge information processing paradigm distributes the tasks  ...  The EO has a controlling role of the edge server making use of the three database modules (movement data, contextual database and trajectory and edge database).  ... 
doi:10.3390/electronics11142239 fatcat:wf5wt7whbrbkdggygptum56244

The Mondrian Data Engine

Mario Drumond, Alexandros Daglis, Nooshin Mirzadeh, Dmitrii Ustiugov, Javier Picorel, Babak Falsafi, Boris Grot, Dionisios Pnevmatikatos
2017 Proceedings of the 44th Annual International Symposium on Computer Architecture  
Modern data analytics operators are optimized for CPU execution and hence rely on large caches and employ random memory accesses.  ...  NMP architectures are especially fitting for data analytics, as they provide immense bandwidth to memory-resident data and dramatically reduce data movement, the main source of energy consumption.  ...  ACKNOWLEDGEMENTS The authors thank the anonymous reviewers and Arash Pourhabibi for their precious comments and feedback.  ... 
doi:10.1145/3079856.3080233 fatcat:lctwfx5ilbdazdhjvjtbvgo3fq

The Mondrian Data Engine

Mario Drumond, Alexandros Daglis, Nooshin Mirzadeh, Dmitrii Ustiugov, Javier Picorel, Babak Falsafi, Boris Grot, Dionisios Pnevmatikatos
2017 SIGARCH Computer Architecture News  
Modern data analytics operators are optimized for CPU execution and hence rely on large caches and employ random memory accesses.  ...  NMP architectures are especially fitting for data analytics, as they provide immense bandwidth to memory-resident data and dramatically reduce data movement, the main source of energy consumption.  ...  ACKNOWLEDGEMENTS The authors thank the anonymous reviewers and Arash Pourhabibi for their precious comments and feedback.  ... 
doi:10.1145/3140659.3080233 fatcat:zjfvuprhmnahhmqfnj6ems7fli

Elaborated report of cross-discipline principles-rules-constraints, and interfaces definition for cross-disciplinary and multi-simulation perspectives in VR

Jeg Dudley, Helmut Kinzler, Arun Selvaraj, Spiros Nikolopoulos, Martin Brösamle
2021 Zenodo  
Various PrismArch-specific requirements are then described in detail, and solutions are proposed for how they could be integrated into the chosen software ontology.  ...  Deliverable D1.2 builds upon the cross-disciplinary perspectives of the AEC industry discussed in D1.1, by providing a more detailed description of the specific software framework ('ontology') and functionalities  ...  However we also believe that the earlier options would be very complex to achieve, with increasingly simplicity for latter options.  ... 
doi:10.5281/zenodo.5667710 fatcat:owl3htuarfgrvoicuerz5tduqi

Just-in-time Analytics Over Heterogeneous Data and Hardware

Manolis Karpathiotakis
2017
From a database-oriented perspective, the Kleisli functional 9 Chapter 2.  ...  Finally, to mimic the storage that better fits the current workload, we materialize in-memory caches and treat them as an extra input.  ...  However, research on CPU-based database engines has shown that different workloads benefit from different storage layouts [33, 86] .  ... 
doi:10.5075/epfl-thesis-8077 fatcat:y4a3i5zgcfewjbaarrkejthcgi

Data processing on heterogeneous hardware [article]

Max Heimel, Technische Universität Berlin, Technische Universität Berlin, Volker Markl
2018
For this, we propose an alternative system design, based on a single set of hardware-oblivious operators which are compiled down to the actual hardware at runtime.  ...  We also present Ocelot, a prototypical hardware-oblivious database engine to demonstrate the feasibility of this concept. [...]  ...  Introduction: GPU-Assisted Query Optimization From the perspective of a database performance engineer, graphics cards could be considered to be a godsend: Their architectural focus on delivering massively  ... 
doi:10.14279/depositonce-7255 fatcat:ymjwoicorzaylpwzkjktvmhjge

Comparative Analysis of Different Machine Learning Classifiers for the Prediction of Chronic Diseases [chapter]

Rajesh Singh, Anita Gehlot, Dharam Buddhi
2022 Comparative Analysis of Different Machine Learning Classifiers for the Prediction of Chronic Diseases  
Precise diagnosis of these diseases on time is very significant for maintaining a healthy life.  ...  Chronic Diseases are the most dangerous diseases for humans and have significant effects on human life. Chronic Diseases like heart disease & Diabetes are the main causes of death.  ...  This work implements k-mean segmentation for segmenting the pre-processed image. The region-based segmentation will segment the data dependent on the taken-out features using GLCM algorithm.  ... 
doi:10.13052/rp-9788770227667 fatcat:da47mjbbyzfwnbpde7rgbrlppe

Efficient query processing in distributed search engines

Simon Jonassen
2012 SIGIR Forum  
Second, we look at skipping and pruning optimizations designed for a monolithic index.  ...  This approach assumes one disk access per posting list and traditional term-at-a-time processing.  ...  Rocha-Junior for the useful advices and comments on the paper. Acknowledgments. This work was done while the second author was an intern at Yahoo!  ... 
doi:10.1145/2492189.2492201 fatcat:uwasxhngrfgntemkhawyv3te64

Resource-efficient processing of large data volumes

Stefan Noll, Technische Universität Dortmund
2021
In this thesis, we develop solutions that improve resource efficiency at multiple system levels by focusing on three scenarios that are relevant—but not limited—to database management systems.  ...  Third, after optimizing resource usage within a multicore processor, we optimize resource usage across multiple computer systems by addressing the problem of resource contention for bulk loading, i.e.,  ...  Database systems typically choose a row-oriented storage layout for OLTP workloads.  ... 
doi:10.17877/de290r-21938 fatcat:5rzmwtrgovbxvd6yaaw2ielbii

CLOUD COMPUTING 2012 Editors CLOUD COMPUTING 2012 Committee CLOUD COMPUTING Advisory Chairs CLOUD COMPUTING 2012 Technical Program Committee

Wolf Zimmermann, Yong Lee, Yuri Demchenko, Yong Lee, Jorge Ejarque, Supercomputing Barcelona, Spain Center, Ibm Liu, Watson, Research, Javier Diaz, Ivan Rodero (+101 others)
2012 unpublished
We are grateful to the members of the CLOUD COMPUTING 2012 organizing committee for their help in handling the logistics and for their work to make this professional meeting a success.  ...  We hope that CLOUD COMPUTING 2012 was a successful international forum for the exchange of ideas and results between academia and industry and for the promotion of progress in the area of cloud computing  ...  We thank the company Centrum for providing material for our experiment and insights on private clouds from the business perspective.  ... 
fatcat:on2nztutnvczjdrrrqbxebu64y
« Previous Showing results 1 — 15 out of 21 results