Differences
This shows you the differences between two versions of the page.
| Both sides previous revisionPrevious revision | Next revisionBoth sides next revision | ||
| events:2018:isc-io500 [2018/06/29 15:32] – [Agenda] kunkel | events:2018:isc-io500 [2018/06/29 15:32] – [Abstract] kunkel | ||
|---|---|---|---|
| Line 10: | Line 10: | ||
| ===== Abstract ===== | ===== Abstract ===== | ||
| - | Evolving and new storage technologies introduced over the last few years are causing increasing complexity for HPC data management. Hence, analyzing, comparing, or even predicting the performance of different HPC machines and storage systems has become more complicated. To address this challenge, the community has developed a new composite benchmark that has lead to the creation of the competitive IO-500 list. The IO-500 benchmark consists of several data and metadata benchmarks to identify performance boundaries for optimized and suboptimal applications. In addition to offering different ways to compare storage systems, the list collects detailed information about storage system design to help system designers make informed trade-offs when specifying new storage requirements. While the initial list contains only 9 systems, we expect a rapid growth in the second list. | + | Evolving and new storage technologies introduced over the last few years are causing increasing complexity for HPC data management. Hence, analyzing, comparing, or even predicting the performance of different HPC machines and storage systems has become more complicated. To address this challenge, the community has developed a new composite benchmark that has lead to the creation of the competitive |
| The development of the benchmark has been powered by the Virtual Institute for I/O (VI4IO), which provides a platform for I/O researchers and enthusiasts for exchanging information, | The development of the benchmark has been powered by the Virtual Institute for I/O (VI4IO), which provides a platform for I/O researchers and enthusiasts for exchanging information, | ||
