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

More updates for 3.1 (#958)

Browse Source 
* Updates for 3.1

* Minor change

* doc link fix

* Minor updates
This commit is contained in:
ANIKET SHIVAM
2023-05-24 07:17:16 -07:00
committed by GitHub
parent 13f413493a
commit f079619f5e
48 changed files with 1611 additions and 1858 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
include/cutlass/transform/threadblock/predicated_tile_access_iterator.h
View File

@@ -524,10 +524,10 @@ class PredicatedTileAccessIterator<Shape_, Element_, layout::PitchLinear,
if (kAdvanceRank) {
pointer_ += params_.inc_advance_ * LongIndex(tile_offset.strided() - 1);
pointer_ += Shape::kContiguous * tile_offset.contiguous();
pointer_ += Shape::kContiguous * tile_offset.contiguous() * sizeof_bits<Element>::value / 8;
} else {
pointer_ += params_.inc_advance_ * LongIndex(tile_offset.contiguous() - 1);
pointer_ += Shape::kStrided * tile_offset.strided();
pointer_ += Shape::kStrided * tile_offset.strided() * sizeof_bits<Element>::value / 8;
}
} else {
coord_offset_.strided() = the_predicates.thread_offset_.strided() + Shape::kStrided * (tile_offset.strided() - kAdvanceRank);