7abc574eeb
* fix double consumption of rng on cpu Signed-off-by: raver119 <raver119@gmail.com> * Shyrma docs (#222) * - documenting and profiling matrix_set_diag cuda kernel Signed-off-by: Yurii <yurii@skymind.io> * - correct formula of pnorm pooling in cuda 2d/3d kernels - remove helper matrix_diag which duplicates work of helper matrix_set_diag Signed-off-by: Yurii <yurii@skymind.io> * cublasHandle sharing + lock Signed-off-by: raver119 <raver119@gmail.com> * cublasHandle sharing + lock Signed-off-by: raver119 <raver119@gmail.com> * Documentation from serialization/deserialization in NLP (#221) * refactoring Signed-off-by: Alexander Stoyakin <alexander.stoyakin@gmail.com> * Javadocs Signed-off-by: Alexander Stoyakin <alexander.stoyakin@gmail.com> * Javadoc fixed Signed-off-by: Alexander Stoyakin <alexander.stoyakin@gmail.com> * Cleanup Signed-off-by: Alexander Stoyakin <alexander.stoyakin@gmail.com> * dedicated lock for getCudaCublasHandle Signed-off-by: raver119 <raver119@gmail.com> * Small fixes (#223) Signed-off-by: AlexDBlack <blacka101@gmail.com> * ELU DL4J fixes (#224) Signed-off-by: AlexDBlack <blacka101@gmail.com> * javadoc (#225) Signed-off-by: Robert Altena <Rob@Ra-ai.com> * Small test compilation fix (#226) Signed-off-by: AlexDBlack <blacka101@gmail.com> * #8182 remove spark version suffix (#227) Signed-off-by: AlexDBlack <blacka101@gmail.com> * [WIP] Thread safety (#229) * sync after cublas*gemm Signed-off-by: raver119 <raver119@gmail.com> * mutex for CublasHelper Signed-off-by: raver119 <raver119@gmail.com> * don't store cublasHandle in LaunchContext, it's per-device anyway Signed-off-by: raver119 <raver119@gmail.com> * some printout Signed-off-by: raver119 <raver119@gmail.com> * check for field instead Signed-off-by: raver119 <raver119@gmail.com> * pew-pew Signed-off-by: raver119 <raver119@gmail.com> * don't release ContextBuffers until device changed Signed-off-by: raver119 <raver119@gmail.com> * small tweak Signed-off-by: raver119 <raver119@gmail.com> * some logging in sgemm Signed-off-by: raver119 <raver119@gmail.com> * stream sync Signed-off-by: raver119 <raver119@gmail.com> * some more logging Signed-off-by: raver119 <raver119@gmail.com> * some more error checks Signed-off-by: raver119 <raver119@gmail.com> * one fancy test Signed-off-by: raver119 <raver119@gmail.com> * one fancy test Signed-off-by: raver119 <raver119@gmail.com> * minor AffinityManager fix Signed-off-by: raver119 <raver119@gmail.com> * cudaEvent error logging improvement Signed-off-by: raver119 <raver119@gmail.com> * ConstantHelper thread safety Signed-off-by: raver119 <raver119@gmail.com> * - minor corrections in ConstantTadHelper Signed-off-by: Yurii <yurii@skymind.io> * ConstantShapeHelper thread safety Signed-off-by: raver119 <raver119@gmail.com> * ConstantTadHelper.cu updated Signed-off-by: raver119 <raver119@gmail.com> * logging off Signed-off-by: raver119 <raver119@gmail.com> * logging off Signed-off-by: raver119 <raver119@gmail.com>
59 lines
2.4 KiB
C++
59 lines
2.4 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)
|
|
//
|
|
|
|
#include <op_boilerplate.h>
|
|
#if NOT_EXCLUDED(OP_matrix_set_diag)
|
|
|
|
#include <ops/declarable/CustomOperations.h>
|
|
#include <ops/declarable/helpers/matrixSetDiag.h>
|
|
|
|
namespace nd4j {
|
|
namespace ops {
|
|
|
|
CONFIGURABLE_OP_IMPL(matrix_set_diag, 2, 1, false, 0, 0) {
|
|
auto input = INPUT_VARIABLE(0);
|
|
auto diagonal = INPUT_VARIABLE(1);
|
|
|
|
auto output = OUTPUT_VARIABLE(0);
|
|
|
|
REQUIRE_TRUE(diagonal->rankOf() == input->rankOf()-1, 0, "MATRIX_SET_DIAG op: rank of diagonal array must be smaller by one compared to rank of input array, but got %i and %i correspondingly !", diagonal->rankOf(), input->rankOf());
|
|
|
|
for(int i = 0; i < diagonal->rankOf() - 1; ++i)
|
|
REQUIRE_TRUE(diagonal->sizeAt(i) == input->sizeAt(i), 0, "MATRIX_SET_DIAG op: the shapes of diagonal and input arrays must be equal till last diagonal dimension but one, however got diagonal=%s and input=%s instead !", ShapeUtils::shapeAsString(diagonal).c_str(), ShapeUtils::shapeAsString(input).c_str());
|
|
|
|
REQUIRE_TRUE(diagonal->sizeAt(-1) == (int)nd4j::math::nd4j_min<Nd4jLong>(input->sizeAt(-1), input->sizeAt(-2)), 0, "MATRIX_SET_DIAG op: the value of last dimension of diagonal array must be equal to min(input_last_shape=%i, input_last_but_one_shape=%i), but got %i instead !", input->sizeAt(-1), input->sizeAt(-2), diagonal->sizeAt(-1));
|
|
|
|
helpers::matrixSetDiag(block.launchContext(), *input, *diagonal, *output, false);
|
|
|
|
return Status::OK();
|
|
}
|
|
|
|
DECLARE_SYN(MatrixSetDiag, matrix_set_diag);
|
|
|
|
DECLARE_TYPES(matrix_set_diag) {
|
|
getOpDescriptor()
|
|
->setAllowedInputTypes(nd4j::DataType::ANY)
|
|
->setSameMode(true);
|
|
}
|
|
|
|
}
|
|
}
|
|
|
|
#endif |