Porting the multi-GPU SELF-Fluids code to HIPFort
In this presentation by Dr. Joseph Schoonover of Fluid Numerics LLC, Joe shares their experience with the porting process for SELF-Fluids from multi-GPU CUDA-Fortran to multi-GPU HIPFort.
The presentation covers the design principles and roadmap for SELF and the strategy to port from...
Keywords: AMD, GPUs, supercomputer, supercomputing
Resource type: presentation
Porting the multi-GPU SELF-Fluids code to HIPFort
https://docs.google.com/presentation/d/1JUwFkrHLx5_hgjxsix8h498_YqvFkkcefNYbu-DsHio/edit#slide=id.g10626504d53_0_0
https://dresa.org.au/materials/porting-the-multi-gpu-self-fluids-code-to-hipfort
In this presentation by Dr. Joseph Schoonover of Fluid Numerics LLC, Joe shares their experience with the porting process for SELF-Fluids from multi-GPU CUDA-Fortran to multi-GPU HIPFort.
The presentation covers the design principles and roadmap for SELF and the strategy to port from Nvidia-only platforms to AMD & Nvidia GPUs. Also discussed are the hurdles encountered along the way and considerations for developing multi-GPU accelerated applications in Fortran.
SELF is an object-oriented Fortran library that supports the implementation of Spectral Element Methods for solving partial differential equations. SELF-Fluids is an implementation of SELF that solves the compressible Navier Stokes equations on CPU only and GPU accelerated compute platforms using the Discontinuous Galerkin Spectral Element Method. The SELF API is designed based on the assumption that SEM developers and researchers need to be able to implement derivatives in 1-D and divergence, gradient, and curl in 2-D and 3-D on scalar, vector, and tensor functions using spectral collocation, continuous Galerkin, and discontinuous Galerkin spectral element methods.
The presentation discussion is placed in context of the Exascale era, where we're faced with a zoo of available compute hardware. Because of this, SELF routines provide support for GPU acceleration through AMD’s HIP and support for multi-core, multi-node, and multi-GPU platforms with MPI.
training@pawsey.org.au
Joe Schoonover
AMD, GPUs, supercomputer, supercomputing