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

CUTLASS 2.2 (#96)

Browse Source 
Adds support for NVIDIA Ampere Architecture features. CUDA 11 Toolkit recommended.
This commit is contained in:
Andrew Kerr
2020-06-08 16:17:35 -07:00
committed by GitHub
parent e33d90b361
commit 86931fef85
584 changed files with 51080 additions and 3373 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
include/cutlass/transform/threadblock/predicated_tile_iterator.h
View File

@@ -1,5 +1,5 @@
/***************************************************************************************************
* Copyright (c) 2017-2019, NVIDIA CORPORATION. All rights reserved.
* Copyright (c) 2017-2020, NVIDIA CORPORATION. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without modification, are permitted
* provided that the following conditions are met:
@@ -319,9 +319,11 @@ class PredicatedTileIterator<Shape_, Element_, layout::PitchLinear, AdvanceRank,
AccessType const *access_ptr = reinterpret_cast<AccessType const *>(byte_ptr);
if (address_iterator_.valid()) {
frag_ptr[idx] = *access_ptr;
}
cutlass::arch::global_load<AccessType,
sizeof(AccessType)
>(
frag_ptr[idx], access_ptr, address_iterator_.valid());
++address_iterator_;
}
}