Related papers: Octo-Tiger's New Hydro Module and Performance Usin…
Sparse Tucker Decomposition (STD) algorithms learn a core tensor and a group of factor matrices to obtain an optimal low-rank representation feature for the \underline{H}igh-\underline{O}rder, \underline{H}igh-\underline{D}imension, and…
We present GAMERA-OP (Orthogonal-Plus), a three-dimensional finite-volume magnetohydrodynamics (MHD) solver for orthogonal curvilinear geometries. The solver advances magnetic fields using constrained transport to preserve…
The Orthoglide is a Delta-type PKM dedicated to 3-axis rapid machining applications that was originally developed at IRCCyN in 2000-2001 to meet the advantages of both serial 3-axis machines (regular workspace and homogeneous performances)…
We describe a high-order ADER-DG solver for the compressible Euler equations within the ExaHyPE framework. The implementation combines a high-order ADER-DG polynomial representation, a local space-time DG predictor, adaptive mesh…
A new cosmological multidimensional hydrodynamic and N-body code based on an Adaptive Mesh Refinement scheme is described and tested. The hydro part is based on modern high-resolution shock-capturing techniques, whereas N-body approach is…
Relativistic fluid dynamics is a major component in dynamical simulations of the quark-gluon plasma created in relativistic heavy-ion collisions. Simulations of the full three-dimensional dissipative dynamics of the quark-gluon plasma with…
Halo core tracking is a novel concept designed to efficiently follow halo substructure in large simulations. We have recently developed this concept in gravity-only simulations to investigate the galaxy-halo connection in the context of…
High-Performance Computing (HPC) systems provide input/output (IO) performance growing relatively slowly compared to peak computational performance and have limited storage capacity. Computational Fluid Dynamics (CFD) applications aiming to…
We present scalable hybrid-parallel algorithms for training large-scale 3D convolutional neural networks. Deep learning-based emerging scientific workflows often require model training with large, high-dimensional samples, which can make…
NVIDIA's CUDA Tile (CuTile) introduces a Python-based, tile-centric abstraction for GPU kernel development that aims to simplify programming while retaining Tensor Core and Tensor Memory Accelerator (TMA) efficiency on modern GPUs. We…
We provide a thorough comparison of the GMHD3D code and the PLUTO4.4 code for both two and three-dimensional hydrodynamic and magnetohydrodynamic problems. The open-source finite-volume solver PLUTO4.4 and the in-house developed…
We present the implementation and performance of a class of directionally unsplit Riemann-solver-based hydrodynamic schemes on Graphic Processing Units (GPU). These schemes, including the MUSCL-Hancock method, a variant of the MUSCL-Hancock…
We present a comparison of galaxy atomic and molecular gas properties in three recent cosmological hydrodynamic simulations, Simba, EAGLE, and Illustris-TNG, versus observations from $z\sim 0-2$. These simulations all rely on similar…
We introduce a new model for the spectral energy distribution of galaxies, GRASIL-3D, which includes a careful modelling of the dust component of the interstellar medium. GRASIL-3D is an entirely new model based on the formalism of an…
We ported to the GPU with CUDA the Astrometric Verification Unit-Global Sphere Reconstruction (AVU-GSR) Parallel Solver developed for the ESA Gaia mission, by optimizing a previous OpenACC porting of this application. The code aims to find,…
In this study, the gravitational octree code originally optimized for the Fermi, Kepler, and Maxwell GPU architectures is adapted to the Volta architecture. The Volta architecture introduces independent thread scheduling requiring either…
Experience shows that on today's high performance systems the utilization of different acceleration cards in conjunction with a high utilization of all other parts of the system is difficult. Future architectures, like exascale clusters,…
We present HTMPC, a Heavily Templated C++ library for large-scale simulations implementing multi-particle collision dynamics (MPC), a particle-based mesoscale hydrodynamic simulation method. The implementation is plugin-based, and designed…
Iterative steady-state solvers are widely used in computational fluid dynamics. Unfortunately, it is difficult to obtain steady-state solution for unstable problem caused by physical instability and numerical instability. Optimization is a…
A new modular code called BOUT++ is presented, which simulates 3D fluid equations in curvilinear coordinates. Although aimed at simulating Edge Localised Modes (ELMs) in tokamak X-point geometry, the code is able to simulate a wide range of…