* - specifying template instantiation for certain types in float16 and bloat16 Signed-off-by: Yurii <iuriish@yahoo.com> * - polishing bfloat16 and float16 member functions template specialization Signed-off-by: Yurii <iuriish@yahoo.com> * - rewrite and overload array +-*/ scalar and scalar +-*/ arr in NDAray class Signed-off-by: Yurii <iuriish@yahoo.com> * - make corrections which have to do with and rvalue lvalue conversions Signed-off-by: Yurii <iuriish@yahoo.com> * - provide move semantic in NDArray operators array +-/* array Signed-off-by: Yurii <iuriish@yahoo.com> * float16/bfloat16 tweaks Signed-off-by: raver119 <raver119@gmail.com> * one more tweak Signed-off-by: raver119 <raver119@gmail.com> * - make float16 and bfloat16 to compile successfully on cuda Signed-off-by: Yurii <iuriish@yahoo.com> * - do not use resources of view-like arrays when move semantics is applied Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of pointers in signatures NDArray methods 1 Signed-off-by: Yurii <iuriish@yahoo.com> * - correction of signature of NDArray::dup method Signed-off-by: Yurii <iuriish@yahoo.com> * - correction of signature of NDArray::reduceAlongDimension method Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::applyIndexReduce and applyTrueBroadcast methods Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::applyReduce3 and varianceAlongDimension methods Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::tensorsAlongDimension and diagonal methods Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::allTensorsAlongDimension Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::reduceAlongDimension 2 Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::applyTransform 2 Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::applyPairwiseTransform 2 Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::applyBroadcast 2 Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::applyTrueBroadcast 2 Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::applyScalar and applyScalarArr Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::lambda methods Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::reduce3 methods 2 Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of following NDArray methods: add/sub/mul/div row/column and fillAsTriangular Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::tileToShape methods Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::isShapeSameStrict method Signed-off-by: Yurii <iuriish@yahoo.com> * minor corrections in tests Signed-off-by: Yurii <iuriish@yahoo.com> * - replace reduce op in batchnorm mkldnn Signed-off-by: Yurii <iuriish@yahoo.com> * - add explicit templates instantiations for operator+(NDArray&&. const scalar) Signed-off-by: Yurii <iuriish@yahoo.com> * - corrections of casts in float16/bfloat16 Signed-off-by: Yurii <iuriish@yahoo.com> * - provide move semantics in following NDArray methods: transform, applyTrueBroadcast, transpose, reshape, permute Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of input array A duplicate in svd cuda op Signed-off-by: Yurii <iuriish@yahoo.com> * - avoid available bug in svd cuda API Signed-off-by: Yurii <iuriish@yahoo.com> * - add temporary global memory buffer in svd cuda when calcUV = false and m != n Signed-off-by: Yurii <iuriish@yahoo.com> * - remove test with blfoat16 type for betainC Signed-off-by: Yurii <iuriish@yahoo.com> * - resolve conflicts after master has been merged in Signed-off-by: Yurii <iuriish@yahoo.com> * - changed type of affected input array in fused_batch_norm Signed-off-by: Yurii <iuriish@yahoo.com> * - add several explicit type castings Signed-off-by: Yurii <iuriish@yahoo.com> * - add ND4J_EXPORT to operators Signed-off-by: Yurii <iuriish@yahoo.com> * - add explicit template types in instantiations of template arithm operators of NDArray class Signed-off-by: Yurii <iuriish@yahoo.com> * - one more test fix Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com>
119 lines
3.9 KiB
C++
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 <op_boilerplate.h>
|
|
#if NOT_EXCLUDED(OP_svd)
|
|
|
|
#include <ops/declarable/CustomOperations.h>
|
|
#include <ops/declarable/helpers/svd.h>
|
|
|
|
namespace nd4j {
|
|
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 |