Kernel and Algorithm Patterns for CUDA
- Reductions and Memory Patterns
- Reduction Patterns in CUDA
- Mapping Data into CUDA's Memories
- Input/Output Convolution
- Generic Algorithm Description
- What could each thread be assigned?
- Thread Assignment Trade-offs
- What memory Space does the Data use?
- Stencil Computation: Fluid Dynamics, Image Convolution
- Bonded Input/Output Convolutions
These lecture were breezed by Carl Pearson and Daniel Borup and then reviewed, edited ,and Uploaded by Omar Sobh.
Cite this work
Researchers should cite this work as follows: