A5039454582- Advanced Data Storage Technologies
- Distributed and Parallel Computing Systems
- Parallel Computing and Optimization Techniques
- Cloud Computing and Resource Management
- Scientific Computing and Data Management
- Computational Fluid Dynamics and Aerodynamics
- Software System Performance and Reliability
- Astrophysics and Star Formation Studies
- Matrix Theory and Algorithms
- Gamma-ray bursts and supernovae
- Galaxies: Formation, Evolution, Phenomena
- Biomedical and Engineering Education
- Meteorological Phenomena and Simulations
- Energy Harvesting in Wireless Networks
- Particle accelerators and beam dynamics
- Magnetic confinement fusion research
- Gas Dynamics and Kinetic Theory
- Simulation Techniques and Applications
- Advanced Numerical Methods in Computational Mathematics
- Lattice Boltzmann Simulation Studies
- Engineering Applied Research
- Electromagnetic Scattering and Analysis
- Educational Games and Gamification
- Nuclear reactor physics and engineering
- Radiation Effects in Electronics
Lawrence Berkeley National Laboratory
2015-2024
National Energy Research Scientific Computing Center
2013-2024
Oak Ridge National Laboratory
2022
University of Chicago
2009-2015
Argonne National Laboratory
2012
Albert Ellis Institute
2010
The FLASH code has evolved into a modular and extensible scientific simulation software system over the decade of its existence. During this time it been cumulatively used by thousand researchers to investigate problems in astrophysics, cosmology, some areas basic physics, such as turbulence. Recently, many new capabilities have added enable simulate high-energy density physics. Enhancements these continue, along with enhancements enabling simulations fluid-structure interactions. started...
Flash-X is a highly composable multiphysics software system that can be used to simulate physical phenomena in several scientific domains. It derives some of its solvers from FLASH, which was first released 2000. has new framework relies on abstractions and asynchronous communications for performance portability across range increasingly heterogeneous hardware platforms. meant primarily solving Eulerian formulations applications with compressible and/or incompressible reactive flows. also...
The FLASH code is a computational science tool for simulating and studying thermonuclear reactions. program periodically outputs large checkpoint files (to resume calculation from particular point in time) smaller plot (for visualization analysis). Initial experiments on BlueGene/P spent excessive time input/output (I/O), making it difficult to do actual science. Our investigation of I/O revealed several locations the software stack where we could make improvements. Fixing data corruption...
In many astrophysical simulations, both Eulerian and Lagrangian quantities are of interest. For example, in a galaxy cluster merger simulation, the intracluster gas can have discretization, while dark matter be modeled using particles. FLASH, component-based scientific simulation code, superimposes framework atop an adaptive mesh refinement to enable such simulations. The discretization field variables is Eulerian, entities occur different forms including tracer particles, massive charged...
Advances in modeling and algorithms, combined with growth computing resources, have enabled simulations of multiphysics–multiscale phenomena that can greatly enhance our scientific understanding. However, on currently available high-performance (HPC) maximizing the outcome requires many trade-offs. In this paper we describe experiences running explosion phase Type Ia supernovae largest platforms. The use FLASH, a modular, adaptive mesh, parallel simulation code wide user base. multiple...
Summary Disaggregated memory is a promising approach that addresses the limitations of traditional architectures by enabling to be decoupled from compute nodes and shared across data center. Cloud platforms have deployed such systems improve overall system utilization, but performance can vary workloads. High‐performance computing (HPC) crucial in scientific engineering applications, where HPC machines also face issue underutilized memory. As result, improving utilization while understanding...
The SPEChpc 2021 suites are application-based benchmarks de- signed to measure performance of modern HPC systems. bench- marks support MPI, MPI+OpenMP, MPI+OpenMP target offload, MPI+OpenACC and portable across all major platforms.
Summary This article studies mini‐applications—Minisweep, GenASiS , GPP, and FF—that use computational methods commonly encountered in HPC. We have ported these applications to develop OpenACC OpenMP versions, evaluated their performance on Titan (Cray XK7 with K20x GPUs), Cori XC40 Intel KNL), Summit (IBM AC922 Volta Cori‐GPU CS‐Storm 500NX Skylake GPUs). Our goals are for new ports be useful both application compiler developers, document describe the lessons learned methodology create...
SUMMARY FLASH is a multiphysics multiscale adaptive mesh refinement (AMR) code originally designed for simulation of reactive flows often found in Astrophysics. With its wide user base and flexible applications configuration capability, has dual task maintaining scalability portability all solvers. The fully explicit solvers the tied very closely to that underlying mesh. Others such as Poisson solver based on multigrid method have more complex scaling behavior. Multigrid methods suffer from...
This paper presents optimizations in a high-performance conjugate gradient benchmark (HPCG) for multi-core Intel ® Xeon processors and many-core Phi™ coprocessors. Without careful optimization, the HPCG under-utilizes compute resources available modern due to its low arithmetic intensity challenges parallelizing Gauss–Seidel smoother (GS). Our optimized implementation fuses GS with sparse matrix vector multiplication (SpMV) address intensity, overcoming performance otherwise bound by memory...
Nyx is a highly parallel, adaptive mesh, finite-volume N-body compressible hydrodynamics solver for cosmological simulations.It has been used to simulate different scenarios with recent focus on the intergalactic medium and Lyman alpha forest.Together, Nyx, astrophysical simulation code, Castro (Almgren et al., 2010), low Mach number code MAESTROeX (Fan 2019), make up AMReX-Astrophysics Suite of open-source, performance-portable codes.
SUMMARY When developing a complex, multi‐authored code, daily testing on multiple platforms and under variety of conditions is essential. It therefore necessary to have regression test suite that easily administered configured, as well way view interpret the results. We describe methodology for verification FLASH, highly capable multiphysics scientific application code with wide user base. The uses combination unit tests an in‐house software optimized operation limited resources. Although...
In recent years there has been increasing use of HPC facilities for HEP experiments. This initially focussed on less I/O intensive workloads such as generator-level or detector simulation. We now demonstrate the efficient running I/O-heavy analysis at NERSC, ATLAS and ALICE LHC collaborations well astronomical image DESI BOSS.
When acquiring a supercomputer it is desirable to specify its performance using single number. For many procurements, this usually stated as increase over current generation platform, for example machine A provides 10 times greater than B. The determination of such number not necessarily simple process; there no universal agreement on how calculation performed and each facility uses their own method. In the future, landscape will be further complicated because systems contain heterogeneous...