@inproceedings{57cc717618ee4e2ba6e900b0c5461b64,
title = "A system-aware optimized data organization for efficient scientific analytics",
abstract = "Large-scale scientific applications on High End Computing systems produce a large volume of highly complex datasets. Such data imposes a grand challenge to conventional storage systems for the need of efficient I/O solutions during both the simulation runtime and data post-processing phases. With the mounting needs of scientific discovery, the read performance of large-scale simulations has becomes a critical issue for the HPC community. In this study, we propose a system-aware optimized data organization strategy that can organize data blocks of multidimensional scientific data efficiently based on simulation output and the underlying storage systems, thereby enabling efficient scientific analytics. Our experimental results demonstrate a performance speedup up to 72 times for the combustion simulation S3D, compared to the logically contiguous data layout.",
keywords = "Data Layout, I/O",
author = "Yuan Tian and Scott Klasky and Weikuan Yu and Hasan Abbasi and Bin Wang and Norbert Podhorszki",
year = "2012",
doi = "10.1145/2287076.2287095",
language = "English",
isbn = "9781450308052",
series = "HPDC '12 - Proceedings of the 21st ACM Symposium on High-Performance Parallel and Distributed Computing",
pages = "125--126",
booktitle = "HPDC '12 - Proceedings of the 21st ACM Symposium on High-Performance Parallel and Distributed Computing",
note = "21st ACM Symposium on High-Performance Parallel and Distributed Computing, HPDC '12 ; Conference date: 18-06-2012 Through 22-06-2012",
}