NVIDIA HPC SDK Training: Jan 12-13, 2022


NVIDIA will present the 2-day training for NERSC, ALCF, and OLCF users about the various GPU programming models supported by NVIDIA’s HPC SDK compilers, including Standard Language Acceleration and Libraries, OpenACC, OpenMP offload, and CUDA. The basic GPU architecture and HPC SW developer considerations and the profiling tools will also be presented. Attendees will have the opportunity to do hands-on and homework exercises on Perlmutter Phase 1 GPUs (NERSC and ALCF users) and on Summit (OLCF users).

This event will be presented online only using Zoom.

Draft Agenda

Day 1, 12:00 pm – 3:30 pm (EST), January 12, Wednesday

Time (PDT) Topic Presenters
12:00 am Introduction (10 min) NERSC/OLCF/ALCF
12:10 am Introduction and Updates to NVHPC SDK (55 min) Tim Costa
1:05 am GPU Architecture and HPC SW Developer Considerations (25 min) Brent Leback / Max Katz
1:30 am Break (15 min)
1:45 am NVHPC Standard Language Acceleration, Libraries (30 min) Brent Leback / Max Katz / Matt Stack
2:15 am Introduction to Nsight Systems and Nsight Compute (30 min) Max Katz
2:45 am Break + Lab + Demo: stdpar, profiling (45 min) Brent Leback / Max Katz /Robert Searles
3:30 pm End of Day 1

Day 2, 12:00 am – 3:30 pm (EST ), January 13, Thursday

Time (PDT) Topic Presenters
12:00 am NVHPC OpenACC (45 min) Brent Leback
12:45 am NVHPC OpenMP (45 min) Brent Leback
1:30 am Break (15 min)
1:45 am Introduction to CUDA (30 min) Max Katz
2:15 am Putting it Together (15 min) Brent Leback
2:30 am Break + Lab + Demo: OpenACC, OpenMP, and more (60 min) Brent Leback / Max Katz /Robert Searles
3:30 pm End of Day 2


Please use this form to register.

Remote Connection Information



Jan 12 2022 - Jan 13 2022


Eastern Standard Time
12:00 pm - 3:30 pm


Suzanne Parete-Koon
QR Code

Comments are closed.