GPU Programming Part 2: Advanced GPU Programming

19 Jun 2023, 09:00 → 23 Jun 2023, 13:00 Europe/Berlin

Online

Andreas Herten (Forschungszentrum Jülich), Jan Meinke (Forschungszentrum Jülich)

GPU-accelerated computing drives current scientific research. Writing fast numeric algorithms for GPUs offers high application performance by offloading compute-intensive portions of the code to a GPU.

This advanced course consists of modules providing more in-depth coverage of multi-GPU programming, modern CUDA concepts, CUDA Fortran, and portable programming models such as OpenACC and C++ parallel STL algorithms.

Topics covered will include

A) Advanced Multi-GPU Programming with MPI
B) Advanced Multi-GPU Programming with NCCL and NVSHMEM
C) Advanced and Modern CUDA Concepts (Cooperative Groups, CUDA Graphs, CUB Primitives, Modern C++ Programming)
D) CUDA Fortran
E) GPU Programming with Abstractions (OpenACC, Standard Language Programming (pSTL))

Attendees are invited to pick and choose the parts of the advanced course (A - E) they want to attend. The advanced modules are mostly freestanding. 

The foundations of GPU programming are covered in a dedicated Basic Course which include an introduction to GPU/parallel computing, programming with CUDA, GPU libraries, tools for debugging and profiling, and performance optimizations. Please see the CUDA Basics course for registration.

 

Prerequisites: Participants either need to attend the basics course or prove equivalent knowledge of GPU programming in order to participate in the advanced course. Some knowledge about Linux, e.g. make, command line editor, Linux shell, experience in C/C++

 

Dates:
19-23 June 2022, 09:00-13:00 each day

 

Location: Online

 

Language: This course is given in English.

 

Instructors: Dr. Jan Meinke, Dr. Kaveh Haghighi-Mood, Dr. Andreas Herten, JSC; Jiri Kraus, Markus Hrywniak, NVIDIA
 

Contact 
For any questions concerning the course, please send an e-mail to j.meinke@fz-juelich.de

Monday, 19 June

09:00 → 10:45 Advanced Mutli-GPU Programming with MPI

11:15 → 13:00 Advanced Mutli-GPU Programming with MPI

Tuesday, 20 June

09:00 → 10:45 Advanced Multi-GPU Programming with NCCL and NVSHMEM

11:15 → 12:55 Advanced Multi-GPU Programming with NCCL and NVSHMEM

Wednesday, 21 June

09:00 → 10:45 Advanced and Modern CUDA Concepts: Cooperative Groups, CUDA Graphs

Cooperative Groups, CUDA Graphs, CUB Primitives, Modern C++ Programming

11:15 → 13:00 Advanced and Modern CUDA Concepts: CUB & Modern C++

Cooperative Groups, CUDA Graphs, CUB Primitives, Modern C++ Programming

Thursday, 22 June

09:00 → 10:45 CUDA Fortran

11:15 → 13:00 CUDA Fortran

Friday, 23 June

09:00 → 10:45 GPU Programming with Abstractions: OpenACC

OpenACC, Standard Language Programming (pSTL)

11:15 → 13:00 GPU Programming with Abstractions: Standard Language Programming with C++ (pSTL)

OpenACC, Standard Language Programming (pSTL)