M
Massimiliano Fatica
Researcher at Nvidia
Publications - 61
Citations - 2001
Massimiliano Fatica is an academic researcher from Nvidia. The author has contributed to research in topics: CUDA & Reynolds number. The author has an hindex of 21, co-authored 55 publications receiving 1711 citations. Previous affiliations of Massimiliano Fatica include Center for Turbulence Research & National Research Council.
Papers
More filters
Journal ArticleDOI
Direct simulations of turbulent flow in a pipe rotating about its axis
TL;DR: In this article, the simulation of flow in a circular pipe rotating about its axis, at low Reynolds number, is performed by a finite difference scheme, second-order accurate in space and in time.
Posted Content
Exascale Deep Learning for Climate Analytics
Thorsten Kurth,Sean J. Treichler,Joshua Romero,Mayur Mudigonda,Nathan Luehr,Everett Phillips,Ankur Mahesh,Michael A. Matheson,Jack Deslippe,Massimiliano Fatica,Prabhat,Michael J. Houston +11 more
TL;DR: Improvements to the software frameworks, input pipeline, and the network training algorithms necessary to efficiently scale deep learning on the Piz Daint and Summit systems are described.
Journal ArticleDOI
Study of flow in a planar asymmetric diffuser using large-eddy simulation
TL;DR: In this paper, large-eddy simulation has been used to study the flow in a planar asymmetric diffuser and the results for mean flow, pressure recovery and skin friction are in excellent agreement with data from two recent experiments.
Proceedings ArticleDOI
Accelerating linpack with CUDA on heterogenous clusters
TL;DR: In this article, the authors describe the use of CUDA to accelerate the Linpack benchmark on heterogenous clusters, where both CPUs and GPUs are used in synergy with minor or no modifications to the original source code.
Proceedings ArticleDOI
Exascale deep learning for climate analytics
Thorsten Kurth,Sean J. Treichler,Joshua Romero,Mayur Mudigonda,Nathan Luehr,Everett Phillips,Ankur Mahesh,Michael A. Matheson,Jack Deslippe,Massimiliano Fatica,Prabhat Prabhat,Michael J. Houston +11 more
TL;DR: In this paper, the authors extract pixel-level masks of extreme weather patterns using variants of Tiramisu and DeepLabv3+ neural networks and describe improvements to the software frameworks, input pipeline, and network training algorithms necessary to efficiently scale deep learning on the Piz Daint and Summit systems.