This title appears in the Scientific Report :
2019
GPU Programming with CUDA
GPU Programming with CUDA
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 an NVIDIA GPU. The course covers basic aspects of GPU architectures and programming. Focus is on the usag...
Saved in:
Personal Name(s): | Herten, Andreas (Corresponding author) |
---|---|
Meinke, Jan / Kreutz, Jochen / Kraus, Jiri | |
Contributing Institute: |
Jülich Supercomputing Center; JSC |
Imprint: |
2019
|
Conference: | PRACE Training Course, Jülich (Germany), 2019-04-01 - 2019-04-03 |
Document Type: |
Lecture |
Research Program: |
Supercomputer Facility Computational Science and Mathematical Methods |
Publikationsportal JuSER |
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 an NVIDIA GPU. The course covers basic aspects of GPU architectures and programming. Focus is on the usage of the parallel programming language CUDA-C which allows maximum control of NVIDIA GPU hardware. Examples of increasing complexity are used to demonstrate optimization and tuning of scientific applications. |