This course provides tutorials on programming NVIDIA GPUs with CUDA, covering topics such as basics, kernels, memory management, parallel algorithms, shared memory, and the Thrust library. The course aims to teach participants how to effectively utilize CUDA for parallel programming on NVIDIA GPUs. The intended audience for this course is individuals interested in GPU programming and parallel computing.
Overview
Syllabus
NVIDIA CUDA Tutorial 1: Introduction.
NVIDIA CUDA Tutorial 2: Basics and a First Kernel.
NVIDIA CUDA Tutorial 3: Display Driver has Stopped Working and has Recovered.
NVIDIA CUDA Tutorial 4: Threads, Thread Blocks and Grids.
NVIDIA CUDA Tutorial 5: Memory Overview.
NVIDIA CUDA Tutorial 6: An Embarrassingly Parallel Algorithm 1.
NVIDIA CUDA Tutorial 7: An Embarrassingly Parallel Algorithm 2.
NVIDIA CUDA Tutorial 8: Intro to Shared Memory.
NVIDIA CUDA Tutorial 9: Bank Conflicts.
NVIDIA CUDA Tutorial 10: Blocking with Shared Memory.
CUDA Tutorial 11: Thrust Library Intro.
Taught by
Creel
