A buffering approach to manage I/O in a normalized cross-correlation earthquake detection code for large seismic datasets

Dawei Mu, Pietro Cicotti, Yifeng Cui, En-Jui Lee, Po Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Continued advances in high-performance computing architectures constantly move the computational performance forward widening performance gap with I/O. As a result, I/O plays an increasingly critical role in modern data-intensive scientific applications. We have developed a high-performance GPU-based software called cuNCC, which is designed to calculate seismic waveform similarity for subjects like hypocenter estimates and small earthquake detection. GPU's acceleration greatly reduced the compute time and we are currently investigating I/O optimizations, to tackle this new performance bottleneck. In order to find an optimal I/O solution for our cuNCC code, we had performed a series of I/O benchmark tests and implemented buffering in CPU memory to manage the output transfers. With this preliminary work, we were able to establish that buffering improves the I/O bandwidth achieved, but is only beneficial when I/O bandwidth is limited, since the cost of the additional memory copy may exceed improvement in I/O. However, in realistic environment where I/O bandwidth per node is limited, and small I/O transfers are penalized, this technique will improve overall performance. In addition, by using a large memory system, the point at which computing has to stop to wait for I/O is delayed, enablingfast computations on larger data sets.

Original languageEnglish
Title of host publicationPEARC 2017 - Practice and Experience in Advanced Research Computing 2017
Subtitle of host publicationSustainability, Success and Impact
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450352727
DOIs
Publication statusPublished - 2017 Jul 9
Event2017 Practice and Experience in Advanced Research Computing, PEARC 2017 - New Orleans, United States
Duration: 2017 Jul 92017 Jul 13

Publication series

NameACM International Conference Proceeding Series
VolumePart F128771

Other

Other2017 Practice and Experience in Advanced Research Computing, PEARC 2017
CountryUnited States
CityNew Orleans
Period17-07-0917-07-13

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'A buffering approach to manage I/O in a normalized cross-correlation earthquake detection code for large seismic datasets'. Together they form a unique fingerprint.

  • Cite this

    Mu, D., Cicotti, P., Cui, Y., Lee, E-J., & Chen, P. (2017). A buffering approach to manage I/O in a normalized cross-correlation earthquake detection code for large seismic datasets. In PEARC 2017 - Practice and Experience in Advanced Research Computing 2017: Sustainability, Success and Impact [a1] (ACM International Conference Proceeding Series; Vol. Part F128771). Association for Computing Machinery. https://doi.org/10.1145/3093338.3093382