|Name:||(RP04) Geological Processing Performance Analysis on Different Hardware Environments|
|Time:||Tuesday, June 20, 2017
08:35 am - 09:45 am
|Breaks:||07:30 am - 10:00 am Welcome Coffee|
|Presenter:||Ekaterina Tyutlyaeva, RSC|
In this research we have used computational-intensive software that implements 2D and 3D seismic migrations to study the mini-application behavior for a set of the computational architectures. In addition to three architecture type comparative analysis, the two CPU generation comparisons have been done. The dynamic behavior of chosen mini-applications is studied using the BSC performance analysis tools to identify their common features. Furthermore, the selected codes are tested and profiled using IPM and MPI Performance Snapshot on the selected computational hardware. In summary, we observe the best performance of mini-applications on Intel Xeon E5-2698 CPU generation 4. The Intel Xeon Phi 7250 peculiar architectural characteristics requires careful source code optimizations to help the compiler to effectively vectorize time-consuming loops and to improve the cache locality in order to achieve higher performance level. The Elbrus-4S CPU is theoretically suitable for such kind of applications, but currently observed performance is an order of magnitude less than on Xeon E5 family, we believe that the frequency and RAM bandwidth increasing, as well as source code optimization work could improve it’s performance.
Ekaterina Tyutlyaeva, ZAO "RSC Technologies"
Alexander Moskovsky, ZAO "RSC Technologies"
Igor Odintsov, ZAO "RSC Technologies"
RP04_Tyutlyaeva.pdf (3790 KB)