squall/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Fix a bug to increment stride tile correctly (#503)

Browse Source 
* Fix a bug to increment stride tile correctly

* Update regular_tile_access_iterator_tensor_op.h

Co-authored-by: peisun1115 <peis@google.com>
Co-authored-by: Haicheng Wu <57973641+hwu36@users.noreply.github.com>
This commit is contained in:
Pei Sun 2022-06-03 19:54:52 -07:00 committed by GitHub
parent 0abaac84ea
commit a29dfb1c63
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
include/cutlass/transform/threadblock/regular_tile_access_iterator_tensor_op.h
View File

@ -614,7 +614,7 @@ class RegularTileAccessIterator<Shape_, Element_,
add_pointer_offset(coord.contiguous() * sections_per_stage_ * stride_ * add_pointer_offset(coord.contiguous() * sections_per_stage_ * stride_ *
ThreadMap::kElementsPerAccess / sections_ + ThreadMap::kElementsPerAccess / sections_ +
coord.strided() * Shape::kStrided * stride_ * coord.strided() * Shape::kStrided * stride_ *
Layout::kElementsPerAccess); Layout::kElementsPerAccess / Layout::kFactor);
} }
}; };