LANL SDAV Visualization Update [Slides]
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Xeon Phi (MIC) on Stampede: •To demonstrate the portability of our algorithms, the same code was compiled to the Thrust OpenMP backend (including our own OpenMP implementation of scan) and run on a 2563 particle data set on an Intel Xeon Phi SE10P (MIC) Coprocessor on a single node of Stampede at TACC • PISTON version scales to more cores than running the existing serial algorithms with multiple MPI processes. Titan: • This test problem has ~90 million particles per process. • Due to memory constraints on the GPUs, we utilize a hybrid approach, in which the halos are computed on the CPU but the centers on the GPU. • The PISTON MBP center finding algorithm requires much less memory than the halo finding algorithm but provides the large majority of the speed-up, since MBP center finding takes much longer than FOF halo finding with the original CPU code. In-situ Integration in HACC: • Successfully ran 500 time-step, 5123 particle simulation on Moonlight using our GPU halo and center finders integrated with HACC in-situ • Completed prototype integration with CosmoTools
- Research Organization:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA); USDOE Office of Science (SC)
- DOE Contract Number:
- AC52-06NA25396
- OSTI ID:
- 1134773
- Report Number(s):
- LA-UR--14-24408
- Country of Publication:
- United States
- Language:
- English
Similar Records
Optimizing legacy molecular dynamics software with directive-based offload
Accelerating gravitational microlensing simulations using the Xeon Phi coprocessor