Portable Acceleration of HPC Applications using ISO C++ — Part 2: Multi-GPU Applications
, GPU Architect, NVIDIA
This hands-on training lab teaches how to accelerate HPC applications using the portable parallelism and concurrency features of the C++17 and newer standards, without any language or vendor extensions, such that a single version of the code is portable to multi-core CPU and to heterogeneous accelerated systems. In the second part of the course we will learn more about C++ ranges and views, and accelerate a classical HPC mini-application using ISO C++ parallel algorithms: a two-dimensional solver for the unsteady heat equation. This exercise shows how to integrate ISO C++ parallelism into preexisting MPI applications to obtain a multi-GPU application.
Prerequisite(s):
Experience with the content of the Part 1 of this training lab.
Please disregard any reference to "Event Code" for access to training materials. "Event Codes" are only valid during the original live session. Explore more training options offered by the NVIDIA Deep Learning Institute (DLI). Choose from an extensive catalog of self-paced, online courses or instructor-led virtual workshops to help you develop key skills in AI, HPC, graphics & simulation, and more.