Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Collé, Anthony"'
A novel parallelization paradigm has been developed for multi-GPU architectures. Classical multi-GPU parallelization for SPH rely on domain decomposition. In our approach each particle can be assigned to a GPU independently of its position in space.
Externí odkaz:
http://arxiv.org/abs/2310.03596
Publikováno v:
EPJ Web of Conferences. 2018, Vol. 183, p1-6. 6p.
