Fundamentals of Accelerated Computing with CUDA Python
Monday, July 24, 2023 -
9:00 AM
Monday, July 24, 2023
9:00 AM
Welcome and Introduction
Welcome and Introduction
9:00 AM - 9:15 AM
- Meet the instructor. - Create an account at courses.nvidia.com/join
9:15 AM
Introduction to CUDA Python with Numba
Introduction to CUDA Python with Numba
9:15 AM - 11:15 AM
- Begin working with the Numba compiler and CUDA programming in Python. - Use Numba decorators to GPU-accelerate numerical Python functions. - Optimize host-to-device and device-to-host memory transfers.
11:15 AM
Break
Break
11:15 AM - 12:15 PM
12:15 PM
Custom CUDA Kernels in Python with Numba
Custom CUDA Kernels in Python with Numba
12:15 PM - 2:15 PM
- Learn CUDA’s parallel thread hierarchy and how to extend parallel program possibilities. - Launch massively parallel custom CUDA kernels on the GPU. - Utilize CUDA atomic operations to avoid race conditions during parallel execution.
2:15 PM
Break
Break
2:15 PM - 2:30 PM
2:30 PM
Multidimensional Grids, and Shared Memory for CUDA Python with Numba
Multidimensional Grids, and Shared Memory for CUDA Python with Numba
2:30 PM - 4:30 PM
- Learn multidimensional grid creation and how to work in parallel on 2D matrices. - Leverage on-device shared memory to promote memory coalescing while reshaping 2D matrices.
4:30 PM
Final Review
Final Review
4:30 PM - 4:45 PM
- Review key learnings and wrap up questions. - Complete the assessment to earn a certificate. - Take the workshop survey.