A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2015; you can also visit the original URL.
The file type is
With exascale computing on the horizon, reducing performance variability in data management tasks (storage, visualization, analysis, etc.) is becoming a key challenge in sustaining high performance. ... In this paper, we present Damaris, a system that leverages dedicated cores in multicore nodes to offload data management tasks, including I/O, data compression, scheduling of data movements, in situ analysis ... Applications (Urbana-Champaign, USA) and Argonne National Laboratory, within the Joint Inria-UIUC-ANL-BSC-JSC Laboratory for Extreme-Scale Computing (JLESC), formerly Joint Laboratory for Petascale Computing ...doi:10.1145/2987371 fatcat:rc4h6ec6hrehzo7mc5bwkg7uli
data processing and I/O in order to hide this variability. ... With exascale computing on the horizon, the performance variability of I/O systems represents a key challenge in sustaining high performance. ... Laboratory for Petascale Computing. ...doi:10.1109/cluster.2012.26 dblp:conf/cluster/DorierACSO12 fatcat:m5n3qnb4irai5l24ldjzvxtdgi
DEVELOPMENT DIRECTIONS As mentioned in the introduction, improving I/O at the simulation level partially addresses the "Big Data" challenge raised by post-petascale machines. ... We also present current work and future directions leveraging Damaris for in-situ data analysis, thus addressing several aspects of this "Big Data" challenge. II. ...doi:10.1109/ipdpsw.2013.101 dblp:conf/ipps/Dorier13 fatcat:zuyqjkg425duvdfypoyndsn3ku
With I/O management acquiring a crucial role in supporting scientific simulations, various I/O management approaches have been proposed to achieve high performance and scalability. ... To the best of our knowledge, our work provides the first in-depth look into the energy-performance tradeoffs of I/O management approaches . ... The Damaris Middleware Damaris  is a middleware for efficient data management in large-scale HPC simulations. ...doi:10.1016/j.future.2016.03.002 fatcat:qgzcoxpja5hkffbuxwzadr3sxa
However, as we look forward, we still foresee two major concerns: the lack of suitable programming tools and the growing gap between processor performance and data bandwidth (i.e., memory, storage, networks ... We use a three-stage approach in which we (1) discuss various exascale landmark studies, (2) use data-driven techniques to analyze the large collection of related literature, and (3) discuss eight research ... situ, analysis, post, processing, data, simulation, interactions, image, disk, extract, savings, rendering, explore, tools, damaris, scientists, raw, parallel, traditional, P model, prediction, climate ...doi:10.1145/3372390 fatcat:jhtwt7pxd5c5darhz75hiqgsnq
A performance model that provides an a priori answer for the cost of using an in situ approach for a given task would assist in managing the trade-offs between simulation and visualization resources. ... Performance analysis tools such as Vampir and Scalasca have handled execution traces (performance data) in an in situ manner for large scale simulation runs. ... Experiments show the methods perform better than others for the problem. We study the problem of learning similarity functions over very large corpora using neural network embedding models. ...doi:10.4230/dagrep.8.7 fatcat:3ijkweopore5demqz5y4ja6a3e