With their ROCm initiative AMD re-entered the HPC market with full glory. StreamComputing is developing trainings, where we get into the details of how to build HPC-software for AMD hardware.
During the training we focus on the following parts:
- Porting existing CUDA software to HIP, which runs without slowdown on both AMD and NVidia GPUs.
- Optimising OpenMP and OpenACC to run at maximum performance on AMD GPUs.
- Build C++-based software from scratch, fast, using HCC.
Trainings will be ready by September.