Yurii Shyrma 753ce28a92
Shyrma sqrtm (#429)
* - start working on implementation of sqrtm op

Signed-off-by: Yurii <iuriish@yahoo.com>

* - improving householder procedure

Signed-off-by: Yurii <iuriish@yahoo.com>

* - further polishing householder stuff

Signed-off-by: Yurii <iuriish@yahoo.com>

* - polishing hh pivoting qr procedure

Signed-off-by: Yurii <iuriish@yahoo.com>

* - polishing BiDiagonalUp procedure

Signed-off-by: Yurii <iuriish@yahoo.com>

* - polishing householder sequence class

Signed-off-by: Yurii <iuriish@yahoo.com>

* - polishing jacobi svd class

Signed-off-by: Yurii <iuriish@yahoo.com>

* - polishing svd stuff 1

Signed-off-by: Yurii <iuriish@yahoo.com>

* - polishing svd stuff 2

Signed-off-by: Yurii <iuriish@yahoo.com>

* - implementation and testing class which performs Hessenberg decomposition of square matrix

Signed-off-by: Yurii <iuriish@yahoo.com>

* - add static method to JacobiSVD class which makes the continuous Givens rotation generation algorithm

Signed-off-by: Yurii <iuriish@yahoo.com>

* - implementation and testing auxiliary methods of Schur decomp class

Signed-off-by: Yurii <iuriish@yahoo.com>

* some references here and there

Signed-off-by: raver119 <raver119@gmail.com>

* - trying figure out difference between eigen and our Schur alg

Signed-off-by: Yurii <iuriish@yahoo.com>

* - testing fixing bugs in Schur decomposition op

Signed-off-by: Yurii <iuriish@yahoo.com>

* - start to implement class which performs calculation of eigen values and vectors

Signed-off-by: Yurii <iuriish@yahoo.com>

* - add to EigenValsAndVecs method which calculates complex eigen vectors

Signed-off-by: Yurii <iuriish@yahoo.com>

* - testing and fixing bugs in EigenValsAndVecs class

Signed-off-by: Yurii <iuriish@yahoo.com>

* - implementation and testing triangularSolver class

Signed-off-by: Yurii <iuriish@yahoo.com>

* Added a 2D routine for triangular systems solve.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored triangularSolve2D routine and tests.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored another test for triangularSolve2D.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored test for triangularSolve for vector-bar case.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored triangularSolve2D routine and tests.

Signed-off-by: shugeo <sgazeos@gmail.com>

* - implementation of FullPivLU class

Signed-off-by: Yurii <iuriish@yahoo.com>

* - fix bugs in FullPivLU::solve method

Signed-off-by: Yurii <iuriish@yahoo.com>

* - correct permutation vector in FullPivLU::solve

Signed-off-by: Yurii <iuriish@yahoo.com>

* - correct include headers

Signed-off-by: Yurii <iuriish@yahoo.com>

* - implementation of Sqrtm class

Signed-off-by: Yurii <iuriish@yahoo.com>

* - testing and fixing bugs in Sqrtm class

Signed-off-by: Yurii <iuriish@yahoo.com>

* - include sqrtm classes to cuda folder, investigate in what places synchronization doesn't work

Signed-off-by: Yurii <iuriish@yahoo.com>

* Added implementation for cuda triangularSolve2D and also refactored triangularSolve2D for cpu.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Eliminated waste implementations.

Signed-off-by: shugeo <sgazeos@gmail.com>

* - make offset calculation faster in t<> methods

Signed-off-by: Yurii <iuriish@yahoo.com>

* - rename refference T& NDArray::t<> method

Signed-off-by: Yurii <iuriish@yahoo.com>

* - further work on cuda sqrtm

Signed-off-by: Yurii <iuriish@yahoo.com>

* - provide correct synchronization to device in Sqrtm class

Signed-off-by: Yurii <iuriish@yahoo.com>

* - add tests for sqrtm op

Signed-off-by: Yurii <iuriish@yahoo.com>

* - correct fails which appeared while testing on jenkins

Signed-off-by: Yurii <iuriish@yahoo.com>

* - trying to find out mistake in svd::deflation method

Signed-off-by: Yurii <iuriish@yahoo.com>

* Revert "- trying to find out mistake in svd::deflation method"

This reverts commit 19d37baddbc509028e4bc67bc932fe7449becdb6.

* Revert "- trying to find out mistake in svd::deflation method"

This reverts commit 19d37baddbc509028e4bc67bc932fe7449becdb6.

Signed-off-by: Yurii <iuriish@yahoo.com>

* - change call semantic of r<> and t<> methods

Signed-off-by: Yurii <iuriish@yahoo.com>

* - ged rid of ambiguity in * operator overloads for windows buikd

Signed-off-by: Yurii <iuriish@yahoo.com>

* - get rid of ambiguity in * operator overloads for windows build 2

Signed-off-by: Yurii <iuriish@yahoo.com>

* - get rid of ambiguity in * operator overloads for windows build 3

Signed-off-by: Yurii <iuriish@yahoo.com>

* - resolve conflicts with master

Signed-off-by: Yurii <iuriish@yahoo.com>

* cmakelists updated

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* - minor fix in merge cpu helper - make use of reference getter

Signed-off-by: Yurii <iuriish@yahoo.com>

Co-authored-by: raver119 <raver119@gmail.com>
Co-authored-by: shugeo <sgazeos@gmail.com>
2020-05-14 18:06:13 +03:00

119 lines
3.9 KiB
C++

/*******************************************************************************
* Copyright (c) 2015-2018 Skymind, Inc.
*
* This program and the accompanying materials are made available under the
* terms of the Apache License, Version 2.0 which is available at
* https://www.apache.org/licenses/LICENSE-2.0.
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
* WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
* License for the specific language governing permissions and limitations
* under the License.
*
* SPDX-License-Identifier: Apache-2.0
******************************************************************************/
//
// @author Yurii Shyrma (iuriish@yahoo.com), created on 20.01.2018
//
#include <system/op_boilerplate.h>
#if NOT_EXCLUDED(OP_svd)
#include <ops/declarable/CustomOperations.h>
#include <ops/declarable/helpers/svd.h>
namespace sd {
namespace ops {
CUSTOM_OP_IMPL(svd, 1, 1, false, 0, 3) {
auto x = INPUT_VARIABLE(0);
const int rank = x->rankOf();
REQUIRE_TRUE(rank >= 2 , 0, "SVD OP: the rank of input array must be >=2, but got %i instead!", rank);
bool fullUV = (bool)INT_ARG(0);
const bool calcUV = (bool)INT_ARG(1);
if(calcUV == false)
fullUV = false;
const int switchNum = INT_ARG(2);
// #ifndef __CUDABLAS__
helpers::svd(block.launchContext(), x, {OUTPUT_VARIABLE(0), calcUV ? OUTPUT_VARIABLE(1) : nullptr, calcUV ? OUTPUT_VARIABLE(2) : nullptr}, fullUV, calcUV, switchNum);
// #endif
return Status::OK();;
}
DECLARE_TYPES(svd) {
getOpDescriptor()
->setAllowedInputTypes(0, {DataType::FLOAT32, DataType ::DOUBLE, DataType::HALF})
->setSameMode(true);
}
DECLARE_SHAPE_FN(svd) {
auto inShapeInfo = inputShape->at(0);
bool fullUV = (bool)INT_ARG(0);
bool calcUV = (bool)INT_ARG(1);
const int rank = inShapeInfo[0];
REQUIRE_TRUE(rank >= 2 , 0, "SVD OP: the rank of input array must be >=2, but got %i instead!", rank);
const int diagSize = inShapeInfo[rank] < inShapeInfo[rank-1] ? inShapeInfo[rank] : inShapeInfo[rank-1];
Nd4jLong* sShapeInfo(nullptr);
if(rank == 2) {
ALLOCATE(sShapeInfo, block.getWorkspace(), shape::shapeInfoLength(1), Nd4jLong);
sShapeInfo[0] = 1;
sShapeInfo[1] = diagSize;
}
else {
ALLOCATE(sShapeInfo, block.getWorkspace(), shape::shapeInfoLength(rank-1), Nd4jLong);
sShapeInfo[0] = rank - 1;
for(int i=1; i <= rank-2; ++i)
sShapeInfo[i] = inShapeInfo[i];
sShapeInfo[rank-1] = diagSize;
}
ShapeUtils::updateStridesAndType(sShapeInfo, inShapeInfo, shape::order(inShapeInfo));
if(calcUV){
Nd4jLong *uShapeInfo(nullptr), *vShapeInfo(nullptr);
COPY_SHAPE(inShapeInfo, uShapeInfo);
COPY_SHAPE(inShapeInfo, vShapeInfo);
if(fullUV) {
uShapeInfo[rank] = uShapeInfo[rank-1];
vShapeInfo[rank-1] = vShapeInfo[rank];
}
else {
uShapeInfo[rank] = diagSize;
vShapeInfo[rank-1] = vShapeInfo[rank];
vShapeInfo[rank] = diagSize;
}
shape::updateStrides(uShapeInfo, shape::order(inShapeInfo));
shape::updateStrides(vShapeInfo, shape::order(inShapeInfo));
auto result = SHAPELIST(ConstantShapeHelper::getInstance()->createShapeInfo(ShapeDescriptor(sShapeInfo)), ConstantShapeHelper::getInstance()->createShapeInfo(ShapeDescriptor(uShapeInfo)), ConstantShapeHelper::getInstance()->createShapeInfo(ShapeDescriptor(vShapeInfo)));
RELEASE(sShapeInfo, block.workspace());
RELEASE(uShapeInfo, block.workspace());
RELEASE(vShapeInfo, block.workspace());
return result;
}
return SHAPELIST(ConstantShapeHelper::getInstance()->createFromExisting(sShapeInfo, block.workspace()));
}
}
}
#endif