Contribution to a book FZJ-2013-04287

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png
Using GPFS to Manage NVRAM-Based Storage Cache

 ;  ;  ;  ;  ;  ;

2013
Springer New York New York

Supercomputing
28th International Supercomputing Conference, ISC 2013, LeipzigLeipzig, Germany, 16 Jun 2013 - 20 Jun 20132013-06-162013-06-20
New York : Springer New York, Lecture Notes in Computer Science 7905, 435-446 () [10.1007/978-3-642-38750-0_33]

This record in other databases:

Please use a persistent id in citations: doi:

Abstract: I/O performance of large-scale HPC systems grows at a significantly slower rate than compute performance. In this article we investigate architectural options and technologies for a tiered storage system to mitigate this problem. Using GPFS and flash memory cards a prototype is implemented and evaluated. We compare performance numbers obtained by running synthetic benchmarks on a petascale BlueGene/Q system connected to our prototype. Based on these results an assessment of the architecture and technology is performed.


Contributing Institute(s):
  1. Jülich Supercomputing Center (JSC)
Research Program(s):
  1. 411 - Computational Science and Mathematical Methods (POF2-411) (POF2-411)
  2. 41G - Supercomputer Facility (POF2-41G21) (POF2-41G21)

Appears in the scientific report 2013
Click to display QR Code for this record

The record appears in these collections:
Document types > Books > Contribution to a book
Workflow collections > Public records
Institute Collections > JSC
Publications database

 Record created 2013-09-16, last modified 2021-01-29


Restricted:
Download fulltext PDF
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)