cavis/libnd4j/include/graph/impl/FlatUtils.cpp

116 lines
4.8 KiB
C++
Raw Normal View History

2019-06-06 14:21:15 +02:00
/*******************************************************************************
* 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
******************************************************************************/
//
// Created by raver119 on 22.11.2017.
//
#include <graph/FlatUtils.h>
#include <array/ByteOrder.h>
#include <array/DataTypeConversions.h>
#include <array/DataTypeUtils.h>
#include <array/ByteOrderUtils.h>
#include <NDArrayFactory.h>
namespace nd4j {
namespace graph {
std::pair<int, int> FlatUtils::fromIntPair(IntPair *pair) {
return std::pair<int, int>(pair->first(), pair->second());
}
std::pair<Nd4jLong, Nd4jLong> FlatUtils::fromLongPair(LongPair *pair) {
return std::pair<Nd4jLong, Nd4jLong>(pair->first(), pair->second());
}
NDArray* FlatUtils::fromFlatArray(const nd4j::graph::FlatArray *flatArray) {
auto rank = static_cast<int>(flatArray->shape()->Get(0));
auto newShape = new Nd4jLong[shape::shapeInfoLength(rank)];
memcpy(newShape, flatArray->shape()->data(), shape::shapeInfoByteLength(rank));
auto length = shape::length(newShape);
auto dtype = DataTypeUtils::fromFlatDataType(flatArray->dtype());
// empty arrays is special case, nothing to restore here
if (shape::isEmpty(newShape)) {
delete[] newShape;
return NDArrayFactory::empty_(dtype, nullptr);
}
Oleh convert (#200) * StringUtils for utf convertor raw implementation of all possible combinations, need to be add counter of bytes per symbol for any type and add api to call convertors and store data Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor more corrections to support convertors Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor some corrections and bug fixes, need review to discuss how to add multi-threading Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 some corrections to move to multi-threading, add one test need discussion data inputs/outputs array presentation, need discussion the way of multi-threading * StringUtils for utf convertor #8613 tests added some corrections to optimize build Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 some corrections and code clean up Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 code clean up and optimize usage, need update ndarray factory before replace std usage Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 some staff to integrate converters into NDArrayFactory, update tests and add some functionality Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 minor corrections and bug fix before discussion * StringUtils for utf convertor #8613 some fixes and tets * StringUtils for utf convertor #8613 some more staff to support different unicode Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 fix linking bug * StringUtils for utf convertor #8613 corrected several tests as defaults for string ndarray changed * StringUtils for utf convertor #8613 replace some incorrect implementation, revert some test changes, need sync before testing * StringUtils for utf convertor #8613 fixed several thing that were badly implemented yesterday, need optimization, testing (before testing have to be add support of u32 and u16 buffer visualization) * StringUtils for utf convertor #8613 fixed to support u16 and u32, and convertor in ndarray, fix buffer print, etc Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 merge master and sync with server Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 some correction for string cast, need print check only asci support Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 merge master, remove copies and add cast, need test, refactoring according review and clean up * StringUtils for utf convertor #8613 fixed cast and copy issues Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 fixed cuda and update tests * StringUtils for utf convertor #8613 integration into NdArray, fix several tests for build pass, refactoring, etc * - avoid ambiguity of NDArray ctrs overloading in some tests Signed-off-by: Yurii <iuriish@yahoo.com> * StringUtils for utf convertor #8613 NDArray string constructors added, updated NDArrayFactory, refactoring unicode and tests, etc Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 fixed cuda build and test, refactoring and void* added to some functions Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 void* integration, removed copy operation, refactoring, added tests for NDArray string constructors, etc Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 several more fixes, improvements and updates Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 master merge, code clean up and optimization before review Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 minor fixes string element size define Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 revert last changes as mistake Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 fixed NDArray constructor build problem, remove order from string factory, fixed order use for factory via project, added catch of incorrect sync in cast of arrays to data types, fixed e method for strings, etc Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 added javacpp hack, added multi-threading, minor corrections in license agreement Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 windows builds fix, as "sting" is not treated as utf8 Signed-off-by: Oleg <oleg.semeniv@gmail.com> Co-authored-by: Yurii Shyrma <iuriish@yahoo.com>
2020-01-31 14:30:49 +01:00
// TODO fix UTF16 and UTF32
2019-06-06 14:21:15 +02:00
if (dtype == UTF8) {
bool isBe = BitwiseUtils::isBE();
bool canKeep = (isBe && flatArray->byteOrder() == nd4j::graph::ByteOrder_BE) || (!isBe && flatArray->byteOrder() == nd4j::graph::ByteOrder_LE);
Oleh convert (#200) * StringUtils for utf convertor raw implementation of all possible combinations, need to be add counter of bytes per symbol for any type and add api to call convertors and store data Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor more corrections to support convertors Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor some corrections and bug fixes, need review to discuss how to add multi-threading Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 some corrections to move to multi-threading, add one test need discussion data inputs/outputs array presentation, need discussion the way of multi-threading * StringUtils for utf convertor #8613 tests added some corrections to optimize build Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 some corrections and code clean up Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 code clean up and optimize usage, need update ndarray factory before replace std usage Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 some staff to integrate converters into NDArrayFactory, update tests and add some functionality Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 minor corrections and bug fix before discussion * StringUtils for utf convertor #8613 some fixes and tets * StringUtils for utf convertor #8613 some more staff to support different unicode Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 fix linking bug * StringUtils for utf convertor #8613 corrected several tests as defaults for string ndarray changed * StringUtils for utf convertor #8613 replace some incorrect implementation, revert some test changes, need sync before testing * StringUtils for utf convertor #8613 fixed several thing that were badly implemented yesterday, need optimization, testing (before testing have to be add support of u32 and u16 buffer visualization) * StringUtils for utf convertor #8613 fixed to support u16 and u32, and convertor in ndarray, fix buffer print, etc Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 merge master and sync with server Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 some correction for string cast, need print check only asci support Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 merge master, remove copies and add cast, need test, refactoring according review and clean up * StringUtils for utf convertor #8613 fixed cast and copy issues Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 fixed cuda and update tests * StringUtils for utf convertor #8613 integration into NdArray, fix several tests for build pass, refactoring, etc * - avoid ambiguity of NDArray ctrs overloading in some tests Signed-off-by: Yurii <iuriish@yahoo.com> * StringUtils for utf convertor #8613 NDArray string constructors added, updated NDArrayFactory, refactoring unicode and tests, etc Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 fixed cuda build and test, refactoring and void* added to some functions Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 void* integration, removed copy operation, refactoring, added tests for NDArray string constructors, etc Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 several more fixes, improvements and updates Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 master merge, code clean up and optimization before review Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 minor fixes string element size define Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 revert last changes as mistake Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 fixed NDArray constructor build problem, remove order from string factory, fixed order use for factory via project, added catch of incorrect sync in cast of arrays to data types, fixed e method for strings, etc Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 added javacpp hack, added multi-threading, minor corrections in license agreement Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 windows builds fix, as "sting" is not treated as utf8 Signed-off-by: Oleg <oleg.semeniv@gmail.com> Co-authored-by: Yurii Shyrma <iuriish@yahoo.com>
2020-01-31 14:30:49 +01:00
2019-06-06 14:21:15 +02:00
std::vector<std::string> substrings(length);
std::vector<Nd4jLong> shapeVector(rank);
for (int e = 0; e < rank; e++)
shapeVector[e] = newShape[e+1];
auto rawPtr = (void *)flatArray->buffer()->data();
auto longPtr = reinterpret_cast<Nd4jLong *>(rawPtr);
auto charPtr = reinterpret_cast<char *>(longPtr + length + 1);
auto offsets = new Nd4jLong[length+1];
for (Nd4jLong e = 0; e <= length; e++) {
2019-06-06 14:21:15 +02:00
auto o = longPtr[e];
// FIXME: BE vs LE on partials
//auto v = canKeep ? o : BitwiseUtils::swap_bytes<Nd4jLong>(o);
offsets[e] = o;
}
for (Nd4jLong e = 0; e < length; e++) {
2019-06-06 14:21:15 +02:00
auto start = offsets[e];
auto end = offsets[e+1];
auto len = end - start;
auto c = (char *) malloc(len+1);
CHECK_ALLOC(c, "Failed temp allocation", len + 1);
memset(c, '\0', len + 1);
memcpy(c, charPtr + start, len);
std::string val(c);
substrings[e] = val;
free(c);
}
delete[] offsets;
delete[] newShape;
Oleh convert (#200) * StringUtils for utf convertor raw implementation of all possible combinations, need to be add counter of bytes per symbol for any type and add api to call convertors and store data Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor more corrections to support convertors Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor some corrections and bug fixes, need review to discuss how to add multi-threading Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 some corrections to move to multi-threading, add one test need discussion data inputs/outputs array presentation, need discussion the way of multi-threading * StringUtils for utf convertor #8613 tests added some corrections to optimize build Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 some corrections and code clean up Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 code clean up and optimize usage, need update ndarray factory before replace std usage Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 some staff to integrate converters into NDArrayFactory, update tests and add some functionality Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 minor corrections and bug fix before discussion * StringUtils for utf convertor #8613 some fixes and tets * StringUtils for utf convertor #8613 some more staff to support different unicode Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 fix linking bug * StringUtils for utf convertor #8613 corrected several tests as defaults for string ndarray changed * StringUtils for utf convertor #8613 replace some incorrect implementation, revert some test changes, need sync before testing * StringUtils for utf convertor #8613 fixed several thing that were badly implemented yesterday, need optimization, testing (before testing have to be add support of u32 and u16 buffer visualization) * StringUtils for utf convertor #8613 fixed to support u16 and u32, and convertor in ndarray, fix buffer print, etc Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 merge master and sync with server Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 some correction for string cast, need print check only asci support Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 merge master, remove copies and add cast, need test, refactoring according review and clean up * StringUtils for utf convertor #8613 fixed cast and copy issues Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 fixed cuda and update tests * StringUtils for utf convertor #8613 integration into NdArray, fix several tests for build pass, refactoring, etc * - avoid ambiguity of NDArray ctrs overloading in some tests Signed-off-by: Yurii <iuriish@yahoo.com> * StringUtils for utf convertor #8613 NDArray string constructors added, updated NDArrayFactory, refactoring unicode and tests, etc Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 fixed cuda build and test, refactoring and void* added to some functions Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 void* integration, removed copy operation, refactoring, added tests for NDArray string constructors, etc Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 several more fixes, improvements and updates Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 master merge, code clean up and optimization before review Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 minor fixes string element size define Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 revert last changes as mistake Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 fixed NDArray constructor build problem, remove order from string factory, fixed order use for factory via project, added catch of incorrect sync in cast of arrays to data types, fixed e method for strings, etc Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 added javacpp hack, added multi-threading, minor corrections in license agreement Signed-off-by: Oleg <oleg.semeniv@gmail.com> * StringUtils for utf convertor #8613 windows builds fix, as "sting" is not treated as utf8 Signed-off-by: Oleg <oleg.semeniv@gmail.com> Co-authored-by: Yurii Shyrma <iuriish@yahoo.com>
2020-01-31 14:30:49 +01:00
// string order always 'c'
return NDArrayFactory::string_(shapeVector, substrings);
2019-06-06 14:21:15 +02:00
}
auto newBuffer = new int8_t[length * DataTypeUtils::sizeOf(dtype)];
BUILD_SINGLE_SELECTOR(dtype, DataTypeConversions, ::convertType(newBuffer, (void *)flatArray->buffer()->data(), dtype, ByteOrderUtils::fromFlatByteOrder(flatArray->byteOrder()), length), LIBND4J_TYPES);
auto array = new NDArray(newBuffer, newShape, nd4j::LaunchContext::defaultContext(), true);
delete[] newShape;
return array;
}
flatbuffers::Offset<FlatArray> FlatUtils::toFlatArray(flatbuffers::FlatBufferBuilder &builder, NDArray &array) {
auto byteVector = array.asByteVector();
auto fBuffer = builder.CreateVector(byteVector);
auto fShape = builder.CreateVector(array.getShapeInfoAsFlatVector());
auto bo = static_cast<nd4j::graph::ByteOrder>(BitwiseUtils::asByteOrder());
return CreateFlatArray(builder, fShape, fBuffer, static_cast<nd4j::graph::DType>(array.dataType()), bo);
}
2019-06-06 14:21:15 +02:00
}
}