Space-Time Adaptive ADER-DG Finite Element Method with LST-DG Predictor and a posteriori Sub-cell WENO Finite-Volume Limiting for Simulation of Non …

IS Popov - Journal of Scientific Computing, 2023 - Springer
The space-time adaptive ADER finite element DG method with a posteriori correction
technique of solutions on subcells by the finite-volume ADER-WENO limiter was used to …

Enclave tasking for DG methods on dynamically adaptive meshes

DE Charrier, B Hazelwood, T Weinzierl - SIAM Journal on Scientific Computing, 2020 - SIAM
High-order discontinuous Galerkin (DG) methods promise to be an excellent discretization
paradigm for hyperbolic differential equation solvers running on supercomputers, since they …

Merchandiser: Data placement on heterogeneous memory for task-parallel hpc applications with load-balance awareness

Z Xie, J Liu, J Li, D Li - Proceedings of the 28th ACM SIGPLAN Annual …, 2023 - dl.acm.org
The emergence of heterogeneous memory (HM) provides a cost-effective and high-
performance solution to memory-consuming HPC applications. Deciding the placement of …

Callback-based completion notification using MPI Continuations

J Schuchart, P Samfass, C Niethammer, J Gracia… - Parallel Computing, 2021 - Elsevier
Asynchronous programming models (APM) are gaining more and more traction, allowing
applications to expose the available concurrency to a runtime system tasked with …

The Ultraluminous X-ray sources population of the galaxy NGC 7456

F Pintore, M Marelli, R Salvaterra… - The Astrophysical …, 2020 - iopscience.iop.org
Ultraluminous X-ray sources (ULXs) are a class of accreting compact objects with X-ray
luminosities above 10 39 erg s− 1. The ULX population counts several hundred objects but …

Predictive, reactive and replication-based load balancing of tasks in Chameleon and sam(oa)2

P Samfass, J Klinkenberg, MT Chung… - Proceedings of the …, 2021 - dl.acm.org
Increasingly complex hardware architectures as well as numerical algorithms make
balancing load in parallel numerical software for adaptive mesh refinement an inherently …

teaMPI—replication-based resilience without the (performance) pain

P Samfass, T Weinzierl, B Hazelwood… - … Conference, ISC High …, 2020 - Springer
In an era where we can not afford to checkpoint frequently, replication is a generic way
forward to construct numerical simulations that can continue to run even if hardware parts …

Reducción del consumo energético en sistemas heterogéneos mediante balanceo de carga

J González Caminero - 2022 - riunet.upv.es
[ES] El problema de balancear la carga computacional de una aplicación paralela que se
ejecuta sobre un conjunto de máquinas es interesante, y existen una gran cantidad de …

[引用][C] ExaHyPE's OpenMP GPGPU Port—Lessons Learned