Stellar Mergers with HPX-Kokkos and SYCL: Methods of using an Asynchronous Many-Task Runtime System with SYCL
Gregor Daiß, Patrick Diehl, Hartmut Kaiser, Dirk Pflüger
Abstract
Ranging from NVIDIA GPUs to AMD GPUs and Intel GPUs: Given the heterogeneity of available accelerator cards within current supercomputers, portability is a key aspect for modern HPC applications. In Octo-Tiger, an astrophysics application simulating binary star systems and stellar mergers, we rely on Kokkos and its various execution spaces for portable compute kernels. In turn, we use HPX, a distributed task-based runtime system, to coordinate kernel launches, CPU tasks, and communication. This combination allows us to have a fine interleaving between portable CPU/GPU computations and communication, enabling scalability on various supercomputers.
Topics & Concepts
Computer scienceSoftware portabilityScalabilityKernel (algebra)Asynchronous communicationParallel computingTask (project management)Runtime systemInterleavingOperating systemComputer networkEconomicsMathematicsCombinatoricsManagementParallel Computing and Optimization TechniquesAdvanced Data Storage TechnologiesDistributed and Parallel Computing Systems