Files
composable_kernel/device_operation/include/reduction_operator_mapping.hpp
Qianfeng b13f7b1861 Reduction in Composable Kernel (#82)
* Initial adding of generic reduction

* Initial adding of generic reduction ...

* Updates to make compiling done

* clang-format all files

* clang-format some files again

* Renaming in profiler/include/profile_reduce.hpp

* Updates and make BlockWise cases passed

* Updates and make ThreadWise and MultiBlockTwoCall cases passed

* Remove the support for MUL and NORM1 reduceOp from the profiler and the device instances

* Change to replace the dim0_max_vector_size/dim1_max_vector_size template argument in the device reduce classes

* format

* adding pooling

* added max and average pooling

* comment out cout and kernel timing

* Tiny simplification in profiler/reduce_profiler.cpp

* Add example for reduce_blockwise

* Tiny updates

* Change to pass the ElementWiseOp from device layer to kernel

* Fix the vectorDim and vectorSize in Device layer

* Enable vector load on both dim0 and dim1 for Threadwise method

* Tiny updates

* Change to let the user to pass the preUnaryOp and posUnaryOp

* Make pooling example work

* split device_reduce_instance into two libraries

* Tiny update

* Replace nanPropaOpt enum by boolean propagate_nan

* Simplification in DeviceReduce layer codes

* update build

* Change to clarify the difference between ck::half_t and half_float::half

* Renaming in all the reduction codes

* Add VectorSize as template parameter for device layer

* Add BetaIsZero as kernel template and as AccDataType for alpha

* print

* Small updates for pooling

* Updates for host_generic_reduction for reference

* Update to make AVG pooling pass

* Update to make MAX pooling with indices output pass

* fix

* add OutDst vector store to threadwise reduction and pooling

* tweak

* turn off check_indices that caused build issue

* refactor pooling

* clean up

* turn off check_indices for building issue for php-compiler

* add more tile size for odd C

* tweak conv for odd C

* update script

* clean up elementwise op

* add hack in reduction_operator.hpp to avoid compile error. To fix it, need to use element_wise_op in reduction op

* Add OutVectorSize as device and kernel tunable, also update to Elementwise Operations

* Move reduce operator mapping to host layer file reduction_operator_mapping.hpp from reduction_operator.hpp

* Change to the unary operators

* Move the definitions of unary operations to element_wise_operation.hpp

* re-org files

* Refine in device interfaces and multiblock kernels

* Split the reduction configurations into instances for specific methods

* Update in getTypeString() of device pool2d

* Renaming in host and kernel

* Tiny update in profiler/src/profiler.cpp

* Uncomment in device_operation/CMakeLists.txt to enable the building of all operations

* Make check_indices a templated function to remove some linking issue

* Renaming in the profiler reduce module

* Add support for double Reduction (but disable MultiblockAtomicAdd for double)

* Tiny correction of literal string

* Rename DevicePoolFwd to DevicePool2dFwd

* Split device_reduce_instance_xxx.cpp files according to the data types to speed up compiling

* Add comments for lists of configurations, lists of instances and references of add_reduce_instances_xxx

* Remove un-used header file gridwise_generic_reduction_wrapper_common.hpp

* Renaming and refining in the Reduction codes

* Tiny change in the unary operators

* Renaming symbols and files

* Renaming symbols in the kernels

* Move kernel kernel_set_buffer_value to separate file

* Add IndexDataType template parameter for kernels and use int32_t as index data type in device layer

* Tiny update in the kernels

* Remove definition of sqrtf()/isnan()/abs() for half_t due to some ADL issue

* Simplify a helper function in device layer

* Tiny adjustment in testing data initialization

* Renaming in kernel/device/host

* Add two testing scripts for reduction

* Refine the Unary operators in element_wise_operation.hpp

* Update in the reduce profiler module

* Update to the reduction testing scripts

* reduce compile parallelism

* change CI docker to rocm5.0

* remove unused variables

* fix build

Co-authored-by: Chao Liu <chao.liu2@amd.com>

[ROCm/composable_kernel commit: e17c0d8008]
2022-03-05 16:46:51 -06:00

170 lines
5.5 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_OPERATOR_MAPPING_HPP
#define CK_REDUCTION_OPERATOR_MAPPING_HPP
#include "reduction_operator.hpp"
#include "reduction_enums.hpp"
#include "element_wise_operation.hpp"
namespace ck {
// The templated struct reduce_binary_operator maps the enum Ids of binary operators to their
// respective functor classes.
// The boolean member "indexable" are also provided in reduce_binary_operactor for
// easier checking by the upper-layer codes in the kernels.
template <typename T, ReduceTensorOp_t Op>
struct reduce_binary_operator;
template <typename T>
struct reduce_binary_operator<T, ReduceTensorOp_t::ADD>
{
using opType = reduce::Add<T>;
using dataType = T;
static constexpr bool indexable = false;
};
template <typename T>
struct reduce_binary_operator<T, ReduceTensorOp_t::MUL>
{
using opType = reduce::Mul<T>;
using dataType = T;
static constexpr bool indexable = false;
};
template <typename T>
struct reduce_binary_operator<T, ReduceTensorOp_t::MIN>
{
using opType = reduce::Min<T>;
using dataType = T;
static constexpr bool indexable = true;
};
template <typename T>
struct reduce_binary_operator<T, ReduceTensorOp_t::MAX>
{
using opType = reduce::Max<T>;
using dataType = T;
static constexpr bool indexable = true;
};
template <typename T>
struct reduce_binary_operator<T, ReduceTensorOp_t::AMAX>
{
using opType = reduce::AMax<T>;
using dataType = T;
static constexpr bool indexable = true;
};
template <typename T>
struct reduce_binary_operator<T, ReduceTensorOp_t::AVG>
{
using opType = reduce::Add<T>;
using dataType = T;
static constexpr bool indexable = false;
};
template <typename T>
struct reduce_binary_operator<T, ReduceTensorOp_t::NORM1>
{
using opType = reduce::Add<T>;
using dataType = T;
static constexpr bool indexable = false;
};
template <typename T>
struct reduce_binary_operator<T, ReduceTensorOp_t::NORM2>
{
using opType = reduce::Add<T>;
using dataType = T;
static constexpr bool indexable = false;
};
// The templated struct reduce_unary_operator maps the enum Ids of Reduce operators to two unary
// functor classes.
// The two unary functors are called before and afer the Reduction is executed respectively
template <typename T, ReduceTensorOp_t Op, bool IsFirstReduce, bool IsLastReduce>
struct reduce_unary_operator
{
using InElementwiseOperation = tensor_operation::element_wise::UnaryIdentic<T, T>;
using AccElementwiseOperation = tensor_operation::element_wise::UnaryIdentic<T, T>;
};
template <typename T, bool IsFirstReduce>
struct reduce_unary_operator<T, ReduceTensorOp_t::AVG, IsFirstReduce, true>
{
using InElementwiseOperation = tensor_operation::element_wise::UnaryIdentic<T, T>;
using AccElementwiseOperation = tensor_operation::element_wise::UnaryIdentic<T, T, true>;
};
template <typename T, bool IsLastReduce>
struct reduce_unary_operator<T, ReduceTensorOp_t::NORM1, true, IsLastReduce>
{
using InElementwiseOperation = tensor_operation::element_wise::UnaryAbs<T, T>;
using AccElementwiseOperation = tensor_operation::element_wise::UnaryIdentic<T, T>;
};
template <typename T, bool IsLastReduce>
struct reduce_unary_operator<T, ReduceTensorOp_t::AMAX, true, IsLastReduce>
{
using InElementwiseOperation = tensor_operation::element_wise::UnaryAbs<T, T>;
using AccElementwiseOperation = tensor_operation::element_wise::UnaryIdentic<T, T>;
};
template <typename T>
struct reduce_unary_operator<T, ReduceTensorOp_t::NORM2, true, false>
{
using InElementwiseOperation = tensor_operation::element_wise::UnarySquare<T, T>;
using AccElementwiseOperation = tensor_operation::element_wise::UnaryIdentic<T, T>;
};
template <typename T>
struct reduce_unary_operator<T, ReduceTensorOp_t::NORM2, true, true>
{
using InElementwiseOperation = tensor_operation::element_wise::UnarySquare<T, T>;
using AccElementwiseOperation = tensor_operation::element_wise::UnarySqrt<T, T>;
};
template <typename T>
struct reduce_unary_operator<T, ReduceTensorOp_t::NORM2, false, true>
{
using InElementwiseOperation = tensor_operation::element_wise::UnaryIdentic<T, T>;
using AccElementwiseOperation = tensor_operation::element_wise::UnarySqrt<T, T>;
};
} // end of namespace ck
#endif