Show simple item record

dc.contributor.authorAlOnazi, Amani
dc.contributor.authorLtaief, Hatem
dc.contributor.authorKeyes, David E.
dc.contributor.authorSaid, I.
dc.contributor.authorThibault, S.
dc.date.accessioned2019-12-16T13:47:40Z
dc.date.available2019-12-16T13:47:40Z
dc.date.issued2019-11-13
dc.identifier.citationAlOnazi, A., Ltaief, H., Keyes, D., Said, I., & Thibault, S. (2019). Asynchronous Task-Based Execution of the Reverse Time Migration for the Oil and Gas Industry. 2019 IEEE International Conference on Cluster Computing (CLUSTER). doi:10.1109/cluster.2019.8891054
dc.identifier.doi10.1109/CLUSTER.2019.8891054
dc.identifier.urihttp://hdl.handle.net/10754/660618
dc.description.abstractWe propose a new framework for deploying Reverse Time Migration (RTM) simulations on distributed-memory systems equipped with multiple GPUs. Our software, TB-RTM, infrastructure engine relies on the StarPU dynamic runtime system to orchestrate the asynchronous scheduling of RTM computational tasks on the underlying resources. Besides dealing with the challenging hardware heterogeneity, TB-RTM supports tasks with different workload characteristics, which stress disparate components of the hardware system. RTM is challenging in that it operates intensively at both ends of the memory hierarchy, with compute kernels running at the highest level of the memory system, possibly in GPU main memory, while I/O kernels are saving solution data to fast storage. We consider how to span the wide performance gap between the two extreme ends of the memory system, i.e., GPU memory and fast storage, on which large-scale RTM simulations routinely execute. To maximize hardware occupancy while maintaining high memory bandwidth throughout the memory subsystem, our framework presents the new-of-core (OOC) feature from StarPU to prefetch data solutions in and out not only from/to the GPU/CPU main memory but also from/to the fast storage system. The OOC technique may trigger opportunities for overlapping expensive data movement with computations. TB-RTM framework addresses this challenging problem of heterogeneity with a systematic approach that is oblivious to the targeted hardware architectures. Our resulting RTM framework can effectively be deployed on massively parallel GPU-based systems, while delivering performance scalability up to 500 GPUs.
dc.description.sponsorshipThis research used resources of the Oak Ridge Leadership Computing Facility at the Oak Ridge National Laboratory, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725. We are grateful to ORNL’s HPC Engineer George Markomanolis and Prof. Rio Yokota of Tokyo Institute of Technology, Japan for their assistance with the runs on Summit and Tsubame 3.0, respectively. We are also grateful to Dr. Rached Abdelkhalak from the Extreme Computing Research Center, KAUST for the fruitful discussions.
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.urlhttps://ieeexplore.ieee.org/document/8891054/
dc.rightsArchived with thanks to IEEE
dc.titleAsynchronous Task-Based Execution of the Reverse Time Migration for the Oil and Gas Industry
dc.typeConference Paper
dc.contributor.departmentComputer Science Program
dc.contributor.departmentExtreme Computing Research Center
dc.contributor.departmentApplied Mathematics and Computational Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentOffice of the President
dc.conference.date2019-09-23 to 2019-09-26
dc.conference.name2019 IEEE International Conference on Cluster Computing, CLUSTER 2019
dc.conference.locationAlbuquerque, NM, USA
dc.eprint.versionPost-print
dc.contributor.institutionNVIDIA, Oil and Gas Department, Paris, France
dc.contributor.institutionUniv. BordeauxTalence, 33400 France
kaust.personAlOnazi, Amani A.
kaust.personLtaief, Hatem
kaust.personKeyes, David E.
refterms.dateFOA2019-12-17T06:06:34Z
kaust.acknowledged.supportUnitExtreme Computing Research Center
dc.date.published-online2019-11-13
dc.date.published-print2019-09


Files in this item

Thumbnail
Name:
2019_tbrtm_cluster.pdf
Size:
1.703Mb
Format:
PDF
Description:
Accepted manuscript

This item appears in the following Collection(s)

Show simple item record