Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Experiences with Porting the FLASH Code to Ookami, an HPE Apollo 80 A64FX Platform

Conference · · International Conference on High Performance Computing in Asia-Pacific Region Workshops
 [1];  [2];  [2];  [2];  [3];  [2]
  1. Stony Brook Univ., NY (United States); Stony Brook University
  2. Stony Brook Univ., NY (United States)
  3. The Ohio State Univ., Columbus, OH (United States)
+ Show Author Affiliations

We present initial experiences with running the community simulation code FLASH, developed at the University of Chicago for multi-scale multi-physics applications, on Ookami, a technology testbed featuring the A64FX processor developed by Fujitsu. Our effort focused largely on running FLASH “right out of the box” to see which combinations of compilers and software implementations (e.g. MPI) allowed the code to run with minimal modification. FLASH was one application in a larger effort to deploy Ookami; it served as a test for different versions of newly installed software, and as a cornerstone for the FAQ page of the Ookami website. Here, we report on our results with different compilers and other software, along with our initial scaling results and attempts to utilize the A64FX’s SVE instructions and NUMA architecture. We found that FLASH readily ran with different compilers and MPI implementations, and showed the expected good scaling with no turning. However, more work must be done to fully take advantage of the A64FX’s architectural features and produce a significant speedup for FLASH on Ookami.

Research Organization:
Stony Brook Univ., NY (United States)
Sponsoring Organization:
USDOE
DOE Contract Number:
FG02-87ER40317
OSTI ID:
1907875
Journal Information:
International Conference on High Performance Computing in Asia-Pacific Region Workshops, Journal Name: International Conference on High Performance Computing in Asia-Pacific Region Workshops
Country of Publication:
United States
Language:
English

References (11)

Flame capturing with an advection–reaction–diffusion model journal October 2006
Deflagrations in hybrid CONe white dwarfs: a route to explain the faint Type Iax supernova 2008ha journal May 2015
PARAMESH: A parallel adaptive mesh refinement community toolkit journal April 2000
Evolution of FLASH, a multi-physics scientific simulation code for high-performance computing journal October 2013
Propagation of Turbulent Flames in Supernovae journal August 1995
FLASH: An Adaptive Mesh Hydrodynamics Code for Modeling Astrophysical Thermonuclear Flashes journal November 2000
The conductive propagation of nuclear flames. I - Degenerate C + O and O + NE + MG white dwarfs journal September 1992
Terascale turbulence computation using the FLASH3 application framework on the IBM Blue Gene/L system journal January 2008
Invited Talk 1 conference May 2019
TYPE Iax SUPERNOVAE: A NEW CLASS OF STELLAR EXPLOSION journal March 2013
Power-Law Wrinkling Turbulence-Flame Interaction Model for Astrophysical Flames journal March 2014

Similar Records

On Using Linux Kernel Huge Pages with FLASH, an Astrophysical Simulation Code
Journal Article · 2022 · Proceedings - IEEE International Conference on Cluster Computing · OSTI ID:1907872
Performance of an Astrophysical Radiation Hydrodynamics Code under Scalable Vector Extension Optimization
Journal Article · 2022 · Proceedings - IEEE International Conference on Cluster Computing · OSTI ID:1907870
Studying CPU and memory utilization of applications on Fujitsu A64FX and Nvidia Grace Superchip
Conference · 2024 · OSTI ID:2496226

Related Subjects

79 ASTRONOMY AND ASTROPHYSICS
97 MATHEMATICS AND COMPUTING
A64FX
astrophysics
high-performance computing
porting software