Andrew Kerr
86931fef85
Adds support for NVIDIA Ampere Architecture features. CUDA 11 Toolkit recommended.
61 lines
2.6 KiB
C++
61 lines
2.6 KiB
C++
/***************************************************************************************************
|
|
* 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:
|
|
* * Redistributions of source code must retain the above copyright notice, this list of
|
|
* conditions and the following disclaimer.
|
|
* * Redistributions in binary form must reproduce the above copyright notice, this list of
|
|
* conditions and the following disclaimer in the documentation and/or other materials
|
|
* provided with the distribution.
|
|
* * Neither the name of the NVIDIA CORPORATION nor the names of its contributors may be used
|
|
* to endorse or promote products derived from this software without specific prior written
|
|
* permission.
|
|
*
|
|
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR
|
|
* IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND
|
|
* FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE
|
|
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
|
|
* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
|
|
* OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
|
|
* STRICT LIABILITY, OR TOR (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
|
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
*
|
|
**************************************************************************************************/
|
|
/*! \file
|
|
\brief Directives related to cache operations
|
|
*/
|
|
#pragma once
|
|
|
|
#include "cutlass/cutlass.h"
|
|
|
|
namespace cutlass {
|
|
namespace arch {
|
|
|
|
////////////////////////////////////////////////////////////////////////////////////////////////////
|
|
|
|
/// Controls PTX cache operations
|
|
struct CacheOperation {
|
|
enum Kind {
|
|
/// Cache at all levels - accessed again
|
|
Always,
|
|
/// Cache at global level
|
|
Global,
|
|
/// Streaming - likely to be accessed once
|
|
Streaming,
|
|
/// Indicates the line will not be used again
|
|
LastUse,
|
|
/// Don't cache, and fetch again
|
|
Volatile,
|
|
/// Write back at all coherent levels
|
|
WriteBack,
|
|
/// Write through to system memory
|
|
WriteThrough
|
|
};
|
|
};
|
|
|
|
////////////////////////////////////////////////////////////////////////////////////////////////////
|
|
|
|
} // namespace arch
|
|
} // namespace cutlass
|