Filters








6,932 Hits in 10.4 sec

Increasing Parallelism in the ROOT I/O Subsystem

G Amadio, B P Bockelman, P Canal, D Piparo, E Tejedor, Z Zhang
2018 Journal of Physics, Conference Series  
need of increasing the implicit parallelism expressed within the ROOT I/O.  ...  In this contribution we highlight the improvements of the ROOT I/O subsystem which targeted a satisfactory scaling behaviour in a multithreaded context.  ...  The Meaning of ROOT I/O One of the key innovations of ROOT is its columnar data format.  ... 
doi:10.1088/1742-6596/1085/3/032014 fatcat:f6ulnihgbvfipjj6jnl7usms7q

Increasing Parallelism in the ROOT I/O Subsystem [article]

Guilherme Amadio, Brian Bockelman, Philippe Canal, Danilo Piparo, Enric Tejedor, Zhe Zhang
2018 arXiv   pre-print
need of increasing the implicit parallelism expressed within the ROOT I/O.  ...  In this contribution we highlight the improvements of the ROOT I/O subsystem which targeted a satisfactory scaling behaviour in a multithreaded context.  ...  Figure 7 . 7 Concurrency optimisations in ROOT I/O.  ... 
arXiv:1804.03326v1 fatcat:bnqyvqlsqva2hkj4eq7kclmwqu

The JUGENE I/O Subsystem, its Architecture, Guidelines and Tools for Using it Efficiently

Huub Stoffers
2012 Zenodo  
The I/O subsystem of JUGENE at the Forschungszentrum Jülich is not necessarily very similar to the I/O subsystems of IBM Blue Gene/P installations elsewhere.  ...  Splitting a parallel program of multiple tasks into a number of equally sized I/O groups, in which a few tasks do I/O on behalf improves performance only moderately when group membership is determined  ...  Acknowledgements This work was financially supported by the PRACE project funded in part by the EUs 7th Framework Programme (FP7/2007-2013) under grant agreement no. RI-211528 and FP7-261557.  ... 
doi:10.5281/zenodo.6242104 fatcat:i5imascibfd2fcrgjaq2jd44ai

Optimizing the Block I/O Subsystem for Fast Storage Devices

Young Jin Yu, Dong In Shin, Woong Shin, Nae Young Song, Jae Woo Choi, Hyeong Seog Kim, Hyeonsang Eom, Heon Young Yeom
2014 ACM Transactions on Computer Systems  
in throughput under multi-threaded workload, compared to the Linux block I/O subsystem.  ...  In this paper, we propose six types of block I/O subsystem that exploit the performance feature of an SSD with ultra low latency.  ...  the I/O path in the I/O subsystem.  ... 
doi:10.1145/2619092 fatcat:4qkksnb2onbohfz7aiha2p6mau

Optimizing I/O server placement for parallel I/O on switch-based irregular networks

Yih-Fang Lin, Chien-Min Wang, Jan-Jan Wu
2006 Journal of Supercomputing  
In particular, the load-balancebased algorithm is superior to the other algorithms in most cases, with improvement ratio of 10 to 95% in terms of parallel I/O throughput.  ...  In this paper, we study I/O server placement for optimizing parallel I/O performance on switch-based clusters, which typically adopt irregular network topologies to allow construction of scalable systems  ...  Acknowledgments This work is supported in part by the National Science Concile of Taiwan under grant number NSC-93-2213-E-001-027.  ... 
doi:10.1007/s11227-006-8293-2 fatcat:ilqx72sojzal7c4wejdwgweoda

Optimizing I/O Server Placement for Parallel I/O on Switch-Based Irregular Networks [chapter]

Yih-Fang Lin, Chien-Min Wang, Jan-Jan Wu
2004 Lecture Notes in Computer Science  
In particular, the load-balancebased algorithm is superior to the other algorithms in most cases, with improvement ratio of 10 to 95% in terms of parallel I/O throughput.  ...  In this paper, we study I/O server placement for optimizing parallel I/O performance on switch-based clusters, which typically adopt irregular network topologies to allow construction of scalable systems  ...  Acknowledgments This work is supported in part by the National Science Concile of Taiwan under grant number NSC-93-2213-E-001-027.  ... 
doi:10.1007/978-3-540-30566-8_113 fatcat:2uc4jgsbqbdzfpagw7jfhjeeja

Parallel I/O aware query optimization

Pedram Ghodsnia, Ivan T. Bowman, Anisoara Nica
2014 Proceedings of the 2014 ACM SIGMOD international conference on Management of data - SIGMOD '14  
We characterize the benefit of exploiting I/O parallelism in database scan operators in SAP SQL Anywhere and propose a novel general I/O cost model that considers the impact of device I/O queue depth in  ...  In this paper, at first, we show why the query optimizer needs to be aware of the benefit of the I/O parallelism in solid state drives.  ...  In other words, increasing the I/O queue depth of the modern SSDs will result in a significant increase in I/O throughput of the random I/O.  ... 
doi:10.1145/2588555.2595635 dblp:conf/sigmod/GhodsniaBN14 fatcat:3guxfut5mjdqflhunfwtye7xmy

Scaling parallel I/O performance through I/O delegate and caching system

Arifa Nisar, Wei-keng Liao, Alok Choudhary
2008 2008 SC - International Conference for High Performance Computing, Networking, Storage and Analysis  
As a side effect of high degree of parallelism, I/O contention at servers doesn't allow overall performance to scale with increasing number of processors.  ...  To bridge the gap between parallel computational and I/O performance, we propose a portable MPI-IO layer where certain tasks, such as file caching, consistency control, and collective I/O optimization  ...  So, by keeping these trends and guidelines in mind, we designed a I/O subsystem that optimizes these requests, such that overall I/O performance is improved.  ... 
doi:10.1109/sc.2008.5214358 dblp:conf/sc/NisarLC08 fatcat:i6zjcsdk4zai3lup6cav56wlji

Evolution of the ROOT Tree I/O [article]

Jakob Blomer and Philippe Canal and Axel Naumann and Danilo Piparo
2020 arXiv   pre-print
In this contribution, we present the status and plans of the future ROOT 7 event I/O.  ...  On the performance side, we show first benchmarks using ROOT's new experimental I/O subsystem that combines the best of TTrees with recent advances in columnar data formats.  ...  Breaking backwards compatibility allows us to use contemporary nomenclature and to design the ROOT event I/O from the ground up for next-generation devices and the increased data rates expected from HL-LHC  ... 
arXiv:2003.07669v1 fatcat:gvqgylfmvbfkxhguinahcqnlk4

Adaptable I/O System based I/O Reduction for Improving the Performance of HDFS

Jung Kyu Park, Jaeho Kim, Sungmin Koo, Seungjae Baek
2016 JSTS Journal of Semiconductor Technology and Science  
In this paper, we propose a new HDFS-AIO framework to enhance HDFS with Adaptive I/O System (ADIOS), which supports many different I/O methods and enables applications to select optimal I/O routines for  ...  We also examine the performance of HDFS-AIO using various I/O techniques. There have been many studies that use ADIOS, however our research is expected to help in expanding the function of HDFS.  ...  To address this, Adaptive I/O System (ADIOS) has been designed [4] . ADIOS, as middleware, supports many different I/O methods, data formats, and parallel file systems.  ... 
doi:10.5573/jsts.2016.16.6.880 fatcat:inx5rxz5ardcvnxyxpn65xzplq

Introduction to Multiprocessor I/O Architecture [chapter]

David Kotz
1996 The Kluwer International Series in Engineering and Computer Science  
In this paper we p r o vide an introduction to I/O architectural issues in multiprocessors, with a focus on disk subsystems.  ...  T h us, it is imperative that a parallel I/O architecture is provided to support the parallel computational architecture.  ...  DISK I/O In this section we discuss some of the architectural issues in parallel disk subsystems, and speci c ways in which our example architectures deal with those issues.  ... 
doi:10.1007/978-1-4613-1401-1_4 fatcat:zdvyvbg7xrdr3jzuhis5a6vrjy

Tools for Analyzing Parallel I/O [article]

Julian M. Kunkel, Eugen Betke, Matt Bryson, Philip Carns, Rosemary Francis, Wolfgang Frings, Roland Laifer, Sandra Mendez
2018 arXiv   pre-print
Parallel application I/O performance often does not meet user expectations.  ...  We also describe best practices, identify issues in measurement and analysis, and provide practical approaches to translate parallel I/O analysis into actionable outcomes for users, facility operators,  ...  Acknowledgments PIOM-MP is a work partially supported by the MICINN/MINECO Spain under contracts TIN2014-53172-P and TIN2017-84875-P. This material is based in part on work supported by the U.S.  ... 
arXiv:1807.04985v3 fatcat:my7aswjrhjfi3fvx6m6y76jbya

ROOT I/O: The Fast and Furious

Philippe Canal, Brian Bockelman, Rene Brun
2011 Journal of Physics, Conference Series  
The increases of data size and in the geographical distribution of analysis intensify the demand on the I/O subsystem.  ...  Over the last year, we greatly improved the I/O throughput, in some case by several factors, when reading ROOT files.  ...  This removes the backward seeks when prefetching in files written with ROOT v5.26, increases the average read size, and results in a dramatic increase in the I/O speed from disk.  ... 
doi:10.1088/1742-6596/331/4/042005 fatcat:625oedzp6ncudnh5iw6km3iot4

Tools for Analyzing Parallel I/O [chapter]

Julian Martin Kunkel, Eugen Betke, Matt Bryson, Philip Carns, Rosemary Francis, Wolfgang Frings, Roland Laifer, Sandra Mendez
2018 Lecture Notes in Computer Science  
Parallel application I/O performance often does not meet user expectations.  ...  We also describe best practices, identify issues in measurement and analysis, and provide practical approaches to translate parallel I/O analysis into actionable outcomes for users, facility operators,  ...  Acknowledgments PIOM-MP is a work partially supported by the MICINN/MINECO Spain under contracts TIN2014-53172-P and TIN2017-84875-P. This material is based in part on work supported by the U.S.  ... 
doi:10.1007/978-3-030-02465-9_4 fatcat:heg3otk57jd3dlfkmukjh5kpfq

Evolution of the ROOT Tree I/O

Jakob Blomer, Philippe Canal, Axel Naumann, Danilo Piparo, C. Doglioni, D. Kim, G.A. Stewart, L. Silvestris, P. Jackson, W. Kamleh
2020 EPJ Web of Conferences  
In this contribution, we present the status and plans of the future ROOT 7 event I/O.  ...  On the performance side, we show first benchmarks using ROOT's new experimental I/O subsystem that combines the best of TTrees with recent advances in columnar data formats.  ...  It is foreseen to further refine the I/O scheduler to the device at hand, for instance by using parallel, asynchronous I/O for file system reading.  ... 
doi:10.1051/epjconf/202024502030 fatcat:fpb3lv62rfcwzmhjol35ww75uy
« Previous Showing results 1 — 15 out of 6,932 results