From a29dfb1c635d6a1295c042a9cb38bd8f07c36a10 Mon Sep 17 00:00:00 2001
From: Pei Sun <peis@waymo.com>
Date: Fri, 3 Jun 2022 19:54:52 -0700
Subject: [PATCH] Fix a bug to increment stride tile correctly (#503)

* 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>
---
 .../threadblock/regular_tile_access_iterator_tensor_op.h        | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/cutlass/transform/threadblock/regular_tile_access_iterator_tensor_op.h b/include/cutlass/transform/threadblock/regular_tile_access_iterator_tensor_op.h
index a812018b..7c848c77 100644
--- a/include/cutlass/transform/threadblock/regular_tile_access_iterator_tensor_op.h
+++ b/include/cutlass/transform/threadblock/regular_tile_access_iterator_tensor_op.h
@@ -614,7 +614,7 @@ class RegularTileAccessIterator<Shape_, Element_,
     add_pointer_offset(coord.contiguous() * sections_per_stage_ * stride_ *
                            ThreadMap::kElementsPerAccess / sections_ +
                        coord.strided() * Shape::kStrided * stride_ *
-                           Layout::kElementsPerAccess);
+                           Layout::kElementsPerAccess / Layout::kFactor);
   }
 };