TY - GEN
T1 - Accelerating multigrid-based hierarchical scientific data refactoring on GPUs
AU - Chen, Jieyang
AU - Wan, Lipeng
AU - Liang, Xin
AU - Whitney, Ben
AU - Liu, Qing
AU - Pugmire, David
AU - Thompson, Nicholas
AU - Choi, Jong Youl
AU - Wolf, Matthew
AU - Munson, Todd
AU - Foster, Ian
AU - Klasky, Scott
N1 - Funding Information:
ACKNOWLEDGMENT This work was made possible by support from the Department of Energy’s Office of Advanced Scientific Computing Research, including via the CODAR and ADIOS Exascale Computing Project (ECP) projects. This research used resources of the Oak Ridge Leadership Computing Facility, a DOE Office of Science User Facility supported under Contract DE-AC05-00OR22725.
Publisher Copyright:
© 2021 IEEE.
PY - 2021/5
Y1 - 2021/5
N2 - Rapid growth in scientific data and a widening gap between computational speed and I/O bandwidth make it increasingly infeasible to store and share all data produced by scientific simulations. Instead, we need methods for reducing data volumes: ideally, methods that can scale data volumes adaptively so as to enable negotiation of performance and fidelity tradeoffs in different situations. Multigrid-based hierarchical data representations hold promise as a solution to this problem, allowing for flexible conversion between different fidelities so that, for example, data can be created at high fidelity and then transferred or stored at lower fidelity via logically simple and mathematically sound operations. However, the effective use of such representations has been hindered until now by the relatively high costs of creating, accessing, reducing, and otherwise operating on such representations. We describe here highly optimized data refactoring kernels for GPU accelerators that enable efficient creation and manipulation of data in multigrid-based hierarchical forms. We demonstrate that our optimized design can achieve up to 250 TB/s aggregated data refactoring throughput - 83% of theoretical peak - on 1024 nodes of the Summit supercomputer. We showcase our optimized design by applying it to a large-scale scientific visualization workflow and the MGARD lossy compression software.
AB - Rapid growth in scientific data and a widening gap between computational speed and I/O bandwidth make it increasingly infeasible to store and share all data produced by scientific simulations. Instead, we need methods for reducing data volumes: ideally, methods that can scale data volumes adaptively so as to enable negotiation of performance and fidelity tradeoffs in different situations. Multigrid-based hierarchical data representations hold promise as a solution to this problem, allowing for flexible conversion between different fidelities so that, for example, data can be created at high fidelity and then transferred or stored at lower fidelity via logically simple and mathematically sound operations. However, the effective use of such representations has been hindered until now by the relatively high costs of creating, accessing, reducing, and otherwise operating on such representations. We describe here highly optimized data refactoring kernels for GPU accelerators that enable efficient creation and manipulation of data in multigrid-based hierarchical forms. We demonstrate that our optimized design can achieve up to 250 TB/s aggregated data refactoring throughput - 83% of theoretical peak - on 1024 nodes of the Summit supercomputer. We showcase our optimized design by applying it to a large-scale scientific visualization workflow and the MGARD lossy compression software.
KW - Data refactoring
KW - GPU
KW - Multigrid
UR - http://www.scopus.com/inward/record.url?scp=85113528397&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85113528397&partnerID=8YFLogxK
U2 - 10.1109/IPDPS49936.2021.00095
DO - 10.1109/IPDPS49936.2021.00095
M3 - Conference contribution
AN - SCOPUS:85113528397
T3 - Proceedings - 2021 IEEE 35th International Parallel and Distributed Processing Symposium, IPDPS 2021
SP - 859
EP - 868
BT - Proceedings - 2021 IEEE 35th International Parallel and Distributed Processing Symposium, IPDPS 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 35th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2021
Y2 - 17 May 2021 through 21 May 2021
ER -