From Piz Daint to the Stars: Simulation of Stellar Mergers using High-Level Abstractions
arXiv:1908.03121 · doi:10.1145/3295500.3356221
Abstract
We study the simulation of stellar mergers, which requires complex simulations with high computational demands. We have developed Octo-Tiger, a finite volume grid-based hydrodynamics simulation code with Adaptive Mesh Refinement which is unique in conserving both linear and angular momentum to machine precision. To face the challenge of increasingly complex, diverse, and heterogeneous HPC systems, Octo-Tiger relies on high-level programming abstractions. We use HPX with its futurization capabilities to ensure scalability both between nodes and within, and present first results replacing MPI with libfabric achieving up to a 2.8x speedup. We extend Octo-Tiger to heterogeneous GPU-accelerated supercomputers, demonstrating node-level performance and portability. We show scalability up to full system runs on Piz Daint. For the scenario's maximum resolution, the compute-critical parts (hydrodynamics and gravity) achieve 68.1% parallel efficiency at 2048 nodes.
Accepted at SC19
References in corpus (20)
- Athena: A New Code for Astrophysical MHD
- Enzo: An Adaptive Mesh Refinement Code for Astrophysics
- V1309 Scorpii: merger of a contact binary
- Prelude to a double degenerate merger: the onset of mass transfer and its impact on gravitational waves and surface detonations
- A test suite for quantitative comparison of hydrodynamics codes in astrophysics
- Cool and Luminous Transients from Mass-Losing Binary Stars
- A Two-moment Radiation Hydrodynamics Module in Athena Using a Time-explicit Godunov Method
- Pre-explosion spiral mass loss of a binary star merger
- Runaway Coalescence at the Onset of Common Envelope Episodes
- Bound Outflows, Unbound Ejecta, and the Shaping of Bipolar Remnants during Stellar Coalescence
- Petascale turbulence simulation using a highly parallel fast multipole method on GPUs
- Evolution of the progenitor binary of V1309 Scorpii before merger
- Numerical Methods for the Simulation of Dynamical Mass Transfer in Binaries
- Prediction of a red nova outburst in KIC 9832227
- Closing the Performance Gap with Modern C++
- TY Pup: a low-mass-ratio and deep contact binary as a progenitor candidate of luminous red novae
- KIC 9832227: Using Vulcan Data to Negate The 2022 Red Nova Merger Prediction
- A Very Fast And Angular Momentum Conserving Tree Code
- Constructing Synchronously Rotating Double White Dwarf Binaries
- A Numerical Method for Studying Super-Eddington Mass Transfer in Double White Dwarf Binaries
Cited by in corpus (13)
- An asynchronous and task-based implementation of Peridynamics utilizing HPX -- the C++ standard library for parallelism and concurrency
- Stellar Mergers with HPX-Kokkos and SYCL: Methods of using an Asynchronous Many-Task Runtime System with SYCL
- From Merging Frameworks to Merging Stars: Experiences using HPX, Kokkos and SIMD Types
- Preparing for HPC on RISC-V: Examining Vectorization and Distributed Performance of an Astrophyiscs Application with HPX and Kokkos
- Performance Measurements within Asynchronous Task-based Runtime Systems: A Double White Dwarf Merger as an Application
- From Task-Based GPU Work Aggregation to Stellar Mergers: Turning Fine-Grained CPU Tasks into Portable GPU Kernels
- Evaluating HPX and Kokkos on RISC-V using an Astrophysics Application Octo-Tiger
- Simulating Stellar Merger using HPX/Kokkos on A64FX on Supercomputer Fugaku
- Hydrodynamic simulations of WD-WD mergers and the origin of RCB stars
- Fibers are not (P)Threads: The Case for Loose Coupling of Asynchronous Programming Models and MPI Through Continuations
- Asynchronous-Many-Task Systems: Challenges and Opportunities -- Scaling an AMR Astrophysics Code on Exascale machines using Kokkos and HPX
- Visualizing the mass transfer flow in direct-impact accretion
- HPX with Spack and Singularity Containers: Evaluating Overheads for HPX/Kokkos using an astrophysics application