
* Updates for 3.2.1 release. * Minor fix in gemm op profiler for raster order. * Add scheduler mapping for raster order in the kernels.
106 lines
3.3 KiB
C++
106 lines
3.3 KiB
C++
/***************************************************************************************************
|
|
* Copyright (c) 2017 - 2023 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
|
* SPDX-License-Identifier: BSD-3-Clause
|
|
*
|
|
* Redistribution and use in source and binary forms, with or without
|
|
* modification, are permitted provided that the following conditions are met:
|
|
*
|
|
* 1. Redistributions of source code must retain the above copyright notice, this
|
|
* list of conditions and the following disclaimer.
|
|
*
|
|
* 2. 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.
|
|
*
|
|
* 3. Neither the name of the copyright holder 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 THE COPYRIGHT HOLDER OR CONTRIBUTORS 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 TORT (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 Defines layout functions used for rank=1 vectors.
|
|
*/
|
|
#pragma once
|
|
|
|
#include "cutlass/cutlass.h"
|
|
#include "cutlass/coord.h"
|
|
|
|
namespace cutlass {
|
|
namespace layout {
|
|
|
|
/// Tensor layout for densely packed vectors.
|
|
class PackedVectorLayout {
|
|
public:
|
|
/// Logical rank of tensor
|
|
static int const kRank = 1;
|
|
|
|
/// Rank of stride vector
|
|
static int const kStrideRank = 1;
|
|
|
|
/// Index type used for coordinates
|
|
using Index = int32_t;
|
|
|
|
/// Long index type used for offsets
|
|
using LongIndex = int64_t;
|
|
|
|
/// Logical coordinate
|
|
using TensorCoord = Coord<kRank, Index>;
|
|
|
|
/// Stride vector
|
|
using Stride = Coord<kStrideRank, Index>;
|
|
|
|
private:
|
|
|
|
//
|
|
// No actual stride vector stored
|
|
//
|
|
|
|
public:
|
|
|
|
//
|
|
// Methods
|
|
//
|
|
|
|
CUTLASS_HOST_DEVICE
|
|
PackedVectorLayout() { }
|
|
|
|
/// Helper returns a layout to a tightly packed tensor
|
|
CUTLASS_HOST_DEVICE
|
|
static PackedVectorLayout packed(TensorCoord const &size) {
|
|
CUTLASS_UNUSED(size);
|
|
return PackedVectorLayout();
|
|
}
|
|
|
|
/// Returns the offset of a coordinate in linear memory
|
|
CUTLASS_HOST_DEVICE
|
|
LongIndex operator()(TensorCoord const &coord) const {
|
|
return coord[0];
|
|
}
|
|
|
|
/// Returns the stride of the layout
|
|
CUTLASS_HOST_DEVICE
|
|
Stride stride() const {
|
|
return make_Coord(1);
|
|
}
|
|
|
|
/// Compute the number of contiguous elements needed to store a tensor with the given size
|
|
CUTLASS_HOST_DEVICE
|
|
LongIndex capacity(TensorCoord const &size) const {
|
|
return size[0];
|
|
}
|
|
};
|
|
|
|
} // namespace layout
|
|
} // namespace cutlass
|