TY - JOUR
T1 - Optimization strategies for geophysics models on manycore systems
AU - Serpa, Matheus S.
AU - Cruz, Eduardo H.M.
AU - Diener, Matthias
AU - Krause, Arthur M.
AU - Navaux, Philippe O.A.
AU - Panetta, Jairo
AU - Farrés, Albert
AU - Rosas, Claudia
AU - Hanzich, Mauricio
N1 - Funding Information:
The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This work was supported by the EU H2020 Program and by MCTI/RNP-Brazil under the HPC4E project, grant number 689772. It was also supported by Petro-bras numbero 2016/00133-9.
Funding Information:
The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This work was supported by the EU H2020 Program and by MCTI/RNP-Brazil under the HPC4E project, grant number 689772. It was also supported by Petrobras numbero 2016/00133-9.
Publisher Copyright:
© The Author(s) 2019.
PY - 2019/5/1
Y1 - 2019/5/1
N2 - Many software mechanisms for geophysics exploration in oil and gas industries are based on wave propagation simulation. To perform such simulations, state-of-the-art high-performance computing architectures are employed, generating results faster with more accuracy at each generation. The software must evolve to support the new features of each design to keep performance scaling. Furthermore, it is important to understand the impact of each change applied to the software to improve the performance as most as possible. In this article, we propose several optimization strategies for a wave propagation model for six architectures: Intel Broadwell, Intel Haswell, Intel Knights Landing, Intel Knights Corner, NVIDIA Pascal, and NVIDIA Kepler. We focus on improving the cache memory usage, vectorization, load balancing, portability, and locality in the memory hierarchy. We analyze the hardware impact of the optimizations, providing insights of how each strategy can improve the performance. The results show that NVIDIA Pascal outperforms the other considered architectures by up to 8.5 (Formula presented.).
AB - Many software mechanisms for geophysics exploration in oil and gas industries are based on wave propagation simulation. To perform such simulations, state-of-the-art high-performance computing architectures are employed, generating results faster with more accuracy at each generation. The software must evolve to support the new features of each design to keep performance scaling. Furthermore, it is important to understand the impact of each change applied to the software to improve the performance as most as possible. In this article, we propose several optimization strategies for a wave propagation model for six architectures: Intel Broadwell, Intel Haswell, Intel Knights Landing, Intel Knights Corner, NVIDIA Pascal, and NVIDIA Kepler. We focus on improving the cache memory usage, vectorization, load balancing, portability, and locality in the memory hierarchy. We analyze the hardware impact of the optimizations, providing insights of how each strategy can improve the performance. The results show that NVIDIA Pascal outperforms the other considered architectures by up to 8.5 (Formula presented.).
KW - Geophysics
KW - HPC
KW - manycore systems
KW - memory hierarchy
KW - vectorization
UR - http://www.scopus.com/inward/record.url?scp=85060618774&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85060618774&partnerID=8YFLogxK
U2 - 10.1177/1094342018824150
DO - 10.1177/1094342018824150
M3 - Article
AN - SCOPUS:85060618774
SN - 1094-3420
VL - 33
SP - 473
EP - 486
JO - International Journal of High Performance Computing Applications
JF - International Journal of High Performance Computing Applications
IS - 3
ER -