add article on kernel launch configuration #44 - #98
Open
kohsheen1234 wants to merge 1 commit into
Open
Conversation
Adds a device-software article on the kernel launch configuration (NVIDIA's "execution configuration"): the triple-chevron arguments and their types and defaults, the built-in variables device code reads them back from, the grid and block size limits and the launch-time errors for exceeding them, heuristics for choosing a configuration (warp-size multiples, waves and the tail effect, the occupancy trade-off), and what sits below the chevrons (cudaLaunchKernel/cuLaunchKernel, PTX special registers, cudaLaunchKernelEx and cluster dimensions). Cross-links it from kernel, thread hierarchy, thread block, thread block grid, CUDA C++, CUDA Graph, occupancy, and register pressure.
kohsheen1234
changed the title
kohsheen1234
changed the title
kohsheen1234
changed the title
Author
|
Hi @charlesfrye, |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Closes #44
Adds a device-software article on the kernel launch configuration (NVIDIA's "execution configuration"): the triple-chevron arguments and their types and defaults, the built-in variables device code reads them back from, the grid and block size limits and the launch-time errors for exceeding them, heuristics for choosing a configuration (warp-size multiples, waves and the tail effect, the occupancy trade-off), and what sits below the chevrons (cudaLaunchKernel/cuLaunchKernel, PTX special registers, cudaLaunchKernelEx and cluster dimensions).
Cross-links it from kernel, thread hierarchy, thread block, thread block grid, CUDA C++, CUDA Graph, occupancy, and register pressure.