TY - CHAP AU - El Sayed Mohamed, Salem AU - Graf, Stephan AU - Hennecke, Michael AU - Pleiter, Dirk AU - Schwarz, Georg AU - Schick, Heiko AU - Stephan, Michael TI - Using GPFS to Manage NVRAM-Based Storage Cache VL - 7905 CY - New York PB - Springer New York M1 - FZJ-2013-04287 T2 - Lecture Notes in Computer Science SP - 435-446 PY - 2013 AB - 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. T2 - 28th International Supercomputing Conference CY - 16 Jun 2013 - 20 Jun 2013, Leipzig (Germany) Y2 - 16 Jun 2013 - 20 Jun 2013 M2 - Leipzig, Germany LB - PUB:(DE-HGF)7 DO - DOI:10.1007/978-3-642-38750-0_33 UR - https://juser.fz-juelich.de/record/138002 ER -