wisconsin
Lecture 16: CUDA Kernel Execution Configuration

Lecture 16: CUDA Kernel Execution Configuration

Content locked

The catalog is public. Reading this content requires approved access.

Sign in to read
Lecture 16: CUDA Kernel Execution Configuration
Round up the number of blocks
Describe the launch geometry
Logical threads and physical resources
Built-in dimensions and indices
Quiz: change the first example’s launch
Matrix multiplication with one block
Several million array elements
Timing device work with events
Scheduling preview