This repository has been archived by the owner on Mar 12, 2021. It is now read-only.
-
-
Notifications
You must be signed in to change notification settings - Fork 83
Commits on Sep 23, 2019
-
Configuration menu - View commit details
-
Copy full SHA for da8960b - Browse repository at this point
Copy the full SHA da8960bView commit details -
Configuration menu - View commit details
-
Copy full SHA for 6149161 - Browse repository at this point
Copy the full SHA 6149161View commit details -
Configuration menu - View commit details
-
Copy full SHA for 21d44f8 - Browse repository at this point
Copy the full SHA 21d44f8View commit details -
Configuration menu - View commit details
-
Copy full SHA for 27bbc33 - Browse repository at this point
Copy the full SHA 27bbc33View commit details -
Configuration menu - View commit details
-
Copy full SHA for 0fcbf0c - Browse repository at this point
Copy the full SHA 0fcbf0cView commit details -
Configuration menu - View commit details
-
Copy full SHA for e9d4abb - Browse repository at this point
Copy the full SHA e9d4abbView commit details -
Configuration menu - View commit details
-
Copy full SHA for 008760f - Browse repository at this point
Copy the full SHA 008760fView commit details -
Configuration menu - View commit details
-
Copy full SHA for 0893ba3 - Browse repository at this point
Copy the full SHA 0893ba3View commit details -
Configuration menu - View commit details
-
Copy full SHA for b7a7556 - Browse repository at this point
Copy the full SHA b7a7556View commit details -
Configuration menu - View commit details
-
Copy full SHA for 0ad5491 - Browse repository at this point
Copy the full SHA 0ad5491View commit details -
Unify in-place and out-of-place kernels.
Using shared memory for out-of-place is better since that enables memory coalescing on the output write.
Configuration menu - View commit details
-
Copy full SHA for ba586b9 - Browse repository at this point
Copy the full SHA ba586b9View commit details
Commits on Sep 24, 2019
-
Drop the shared memory, use separate inplace/outofplace kernels.
Wrt. shared memory: newer hardware can coalesce both forward and backward access patterns, which we would get without shared memory in the 1D case, while for the ND case we don't get either of those if just writing backwards in the shared memory buffer. Wrt. separate kernels: the in-place version would trample over values to be read by other blocks. Grid synchronization is much to costly, so just swap numbers on half the number of threads.
Configuration menu - View commit details
-
Copy full SHA for 1966169 - Browse repository at this point
Copy the full SHA 1966169View commit details
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.