mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-20 12:59:49 +00:00
b315c39b11
* add solver ConvIgemmFwdV6r1DlopsNchwKcyxNkhw; rename static ck source files
* make inner product compatible on gfx900
* Update src/include/miopen/solver/ck_utility_common.hpp
* compiler parameter use stream
* use int instead of index_t in kernel wrapper
* DynamicBuffer, StaticBuffer, amd_buffer_load support customized value for invalid element
* Add dynamic generic reduction kernel layer (kernel wrappers, kernel implementations and utilities)
* Some updates to dynamic composable kernel facility for the need of dynamic generic reduction
* Update to generic reduction C++ host interface layer to support dynamic generic reduction
* Update to remove tidy complaints in host interface layer
* Change the unary operator form from void op(T &x) to T op(T x)
* Update to pass single workspace pointer for all kernels (fix for OpenCL backend)
* Use cppcheck-suppress to prevent some strange warnings
* Re-use operator [] and () for DynamicBuffer and update to depending codes
* Remove useless codes in first call threadwise/warpwise/blockwise kernel wrappers
* [performance] Remove un-needed local buffer initialization
Co-authored-by: Chao Liu <chao.liu2@amd.com>
Co-authored-by: JD <Jehandad.Khan@amd.com>
[ROCm/composable_kernel commit: 9e80cdceb7]
105 lines
2.7 KiB
C++
105 lines
2.7 KiB
C++
/*******************************************************************************
|
|
*
|
|
* MIT License
|
|
*
|
|
* Copyright (c) 2020 Advanced Micro Devices, Inc.
|
|
*
|
|
* Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
* of this software and associated documentation files (the "Software"), to deal
|
|
* in the Software without restriction, including without limitation the rights
|
|
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
* copies of the Software, and to permit persons to whom the Software is
|
|
* furnished to do so, subject to the following conditions:
|
|
*
|
|
* The above copyright notice and this permission notice shall be included in all
|
|
* copies or substantial portions of the Software.
|
|
*
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
|
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
|
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
|
* SOFTWARE.
|
|
*
|
|
*******************************************************************************/
|
|
#ifndef CK_REDUCTION_COMMON_HPP
|
|
#define CK_REDUCTION_COMMON_HPP
|
|
|
|
// this enumerate should be synchronized with include/miopen/reduce_common.hpp
|
|
namespace ck {
|
|
enum class ReductionMethod_t
|
|
{
|
|
DirectThreadWise = 1,
|
|
DirectWarpWise = 2,
|
|
BlockWise = 3,
|
|
MultiBlock = 4
|
|
}; // end of namespace ck
|
|
|
|
enum class ReduceTensorOp_t
|
|
{
|
|
ADD = 0,
|
|
MUL = 1,
|
|
MIN = 2,
|
|
MAX = 3,
|
|
AMAX = 4,
|
|
AVG = 5,
|
|
NORM1 = 6,
|
|
NORM2 = 7,
|
|
// MUL_NO_ZEROS = 8,
|
|
};
|
|
|
|
enum class NanPropagation_t
|
|
{
|
|
NOT_PROPAGATE_NAN = 0,
|
|
PROPAGATE_NAN = 1,
|
|
};
|
|
|
|
enum class ReduceTensorIndices_t
|
|
{
|
|
NO_INDICES = 0,
|
|
FLATTENED_INDICES = 1,
|
|
};
|
|
|
|
enum class IndicesType_t
|
|
{
|
|
INDICES_32BIT = 0,
|
|
INDICES_64BIT = 1,
|
|
INDICES_16BIT = 2,
|
|
INDICES_8BIT = 3,
|
|
};
|
|
|
|
struct float_equal_one
|
|
{
|
|
template <class T>
|
|
__device__ static inline bool apply(T x)
|
|
{
|
|
return x <= type_convert<T>{}(1.0f) and x >= type_convert<T>{}(1.0f);
|
|
}
|
|
|
|
template <class T>
|
|
__device__ inline bool operator()(T x)
|
|
{
|
|
return (float_equal_one::apply(x));
|
|
};
|
|
};
|
|
|
|
struct float_equal_zero
|
|
{
|
|
template <class T>
|
|
__device__ static inline bool apply(T x)
|
|
{
|
|
return x <= type_convert<T>{}(0.0f) and x >= type_convert<T>{}(0.0f);
|
|
}
|
|
|
|
template <class T>
|
|
__device__ inline bool operator()(T x)
|
|
{
|
|
return (float_equal_zero::apply(x));
|
|
};
|
|
};
|
|
|
|
}; // end of namespace ck
|
|
|
|
#endif
|