Full text loading...
-
Optimizing Performance of a TTI RTM Finite Difference Kernel for x86 Instruction Set Architectures
- Publisher: European Association of Geoscientists & Engineers
- Source: Conference Proceedings, Third EAGE Workshop on High Performance Computing for Upstream, Oct 2017, Volume 2017, p.1 - 5
Abstract
Summary
We examine the performance of a 3D finite difference seismic reverse time migration (RTM) kernel on systems with Intel® Xeon® processors and Intel® Xeon Phi™ x200 processors. Using an identical tuned RTM TTI source code, an system with one Intel Xeon Phi 7250 processor outperforms a system with two-socket Intel Xeon 2697v4 processors by a factor of 1.5.
© EAGE Publications BV