Dataset Open Access
Kelling, Jeffrey;
Juckeland, Guido
{ "name": "Profiling of RT-PICLS Code", "url": "https://rodare.hzdr.de/record/16", "keywords": [ "Scorep", "Vampir", "Tracing", "Profiling" ], "datePublished": "2018-04-25", "@type": "Dataset", "creator": [ { "name": "Kelling, Jeffrey", "affiliation": "Helmholtz-Zentrum Dresden-Rossendorf", "@type": "Person" }, { "name": "Juckeland, Guido", "@id": "https://orcid.org/0000-0002-9935-4428", "affiliation": "Helmholtz-Zentrum Dresden-Rossendorf", "@type": "Person" } ], "description": "<p>It was observed, that the RT-PICLS code ran by FWKT on the hypnos cluster was producing an unusual amount of system load, according to Ganglia metrics. Since this may point to an IO-problem in the code, this code was analyzed more closely.</p>\n\n<p>RT-PICLS was run with additionally provided input data on 64 CPU cores (AMD Opteron) in a single node of the hypnos cluster. Score-P 4.0 with IO-tracing support was used for profiling and tracing of the application. A developer version of Vampir 9.2 [3] enabled graphical analysis of the traces.</p>\n\n<p>Different file systems were evaluated for storing the output:</p>\n\n<ul>\n\t<li><strong>bigdata</strong>: the high-performance file system of the cluster based on GPFS.</li>\n\t<li><strong>nfs</strong>: a loop-mounted EXT4 image mounted to the current compute node via NFS.</li>\n\t<li><strong>scr</strong>: the local scratch file-system of the compute node.</li>\n\t<li><strong>tmpfs</strong>: a virtual filesystem, physically located in the main memory of the compute node.</li>\n</ul>\n\n<p>The trace files that were used to compile the referenced report are collected in this upload.</p>", "@id": "https://doi.org/10.14278/rodare.16", "distribution": [ { "contentUrl": "https://rodare.hzdr.de/api/files/bbd4d9ce-0fdb-42a2-84a1-b5ecebf4d2a7/tracefile_rtpicls.zip", "@type": "DataDownload", "fileFormat": "zip" } ], "license": "https://creativecommons.org/licenses/by/4.0/legalcode", "@context": "https://schema.org/", "identifier": "https://doi.org/10.14278/rodare.16", "sameAs": [ "https://www.hzdr.de/publications/Publ-27417" ] }
All versions | This version | |
---|---|---|
Views | 1,307 | 1,307 |
Downloads | 458 | 458 |
Data volume | 3.4 TB | 3.4 TB |
Unique views | 799 | 799 |
Unique downloads | 108 | 108 |
Kelling, Jeffrey, & Juckeland, Guido. (2018). Profiling of RT-PICLS Code [Data set]. Rodare. http://doi.org/10.14278/rodare.16