cavis/libnd4j/include/ops/declarable/helpers/impl/sparse_to_dense.cpp

123 lines
5.3 KiB
C++
Raw Normal View History

String changes (#3) * initial commit * additional data types & tensor type Signed-off-by: raver119 <raver119@gmail.com> * next step Signed-off-by: raver119 <raver119@gmail.com> * missing include * sparse_to_dense Signed-off-by: raver119 <raver119@gmail.com> * few more tests files Signed-off-by: raver119 <raver119@gmail.com> * draft Signed-off-by: raver119 <raver119@gmail.com> * numeric sparse_to_dense Signed-off-by: raver119 <raver119@gmail.com> * comment Signed-off-by: raver119 <raver119@gmail.com> * string sparse_to_dense version Signed-off-by: raver119 <raver119@gmail.com> * CUDA DataBuffer expand Signed-off-by: raver119 <raver119@gmail.com> * few tweaks for CUDA build Signed-off-by: raver119 <raver119@gmail.com> * shape fn for string_split Signed-off-by: raver119 <raver119@gmail.com> * one more comment Signed-off-by: raver119 <raver119@gmail.com> * string_split indices Signed-off-by: raver119 <raver119@gmail.com> * next step Signed-off-by: raver119 <raver119@gmail.com> * test passes Signed-off-by: raver119 <raver119@gmail.com> * few rearrangements for databuffer implementations Signed-off-by: raver119 <raver119@gmail.com> * DataBuffer: move inline methods to common implementations Signed-off-by: raver119 <raver119@gmail.com> * add native DataBuffer to Nd4j presets Signed-off-by: raver119 <raver119@gmail.com> * DataBuffer creation Signed-off-by: raver119 <raver119@gmail.com> * use DataBuffer for allocation Signed-off-by: raver119 <raver119@gmail.com> * cpu databuffer as deallocatable Signed-off-by: raver119 <raver119@gmail.com> * DataBuffer setters for bufers Signed-off-by: raver119 <raver119@gmail.com> * couple of wrappers Signed-off-by: raver119 <raver119@gmail.com> * DataBuffers being passed around Signed-off-by: raver119 <raver119@gmail.com> * Bunch of ByteBuffer-related signatures gone Signed-off-by: raver119 <raver119@gmail.com> * - few more Nd4j signatures removed - minor fix for bfloat16 Signed-off-by: raver119 <raver119@gmail.com> * nullptr pointer is still a pointer, but 0 as address :) Signed-off-by: raver119 <raver119@gmail.com> * one special test Signed-off-by: raver119 <raver119@gmail.com> * empty string array init Signed-off-by: raver119 <raver119@gmail.com> * one more test in cpp Signed-off-by: raver119 <raver119@gmail.com> * memcpy instead of databuffer swap Signed-off-by: raver119 <raver119@gmail.com> * special InteropDataBuffer for front-end languages Signed-off-by: raver119 <raver119@gmail.com> * few tweaks for java Signed-off-by: raver119 <raver119@gmail.com> * pointer/indexer actualization Signed-off-by: raver119 <raver119@gmail.com> * CustomOp returns list for inputArumgents and outputArguments instead of array Signed-off-by: raver119 <raver119@gmail.com> * redundant call Signed-off-by: raver119 <raver119@gmail.com> * print_variable op Signed-off-by: raver119 <raver119@gmail.com> * - view handling (but wrong one) - print_variable java wrapper Signed-off-by: raver119 <raver119@gmail.com> * one more test Signed-off-by: raver119 <raver119@gmail.com> * - empty arrays handling Signed-off-by: raver119 <raver119@gmail.com> * - deserialization works now Signed-off-by: raver119 <raver119@gmail.com> * minor fix Signed-off-by: raver119 <raver119@gmail.com> * meh Signed-off-by: raver119 <raver119@gmail.com> * one more fix Signed-off-by: raver119 <raver119@gmail.com> * initial cuda commit Signed-off-by: raver119 <raver119@gmail.com> * print_variable message validation Signed-off-by: raver119 <raver119@gmail.com> * CUDA views Signed-off-by: raver119 <raver119@gmail.com> * CUDA special buffer size Signed-off-by: raver119 <raver119@gmail.com> * minor update to match master changes Signed-off-by: raver119 <raver119@gmail.com> * - consider arrays always actual on device for CUDA - additional PrintVariable constructor - CudaUtf8Buffer now allocates host buffer by default Signed-off-by: raver119 <raver119@gmail.com> * meh Signed-off-by: raver119 <raver119@gmail.com> * - print_variable now allows print from device Signed-off-by: raver119 <raver119@gmail.com> * InteropDataBuffer data type fix Signed-off-by: raver119 <raver119@gmail.com> * ... Signed-off-by: raver119 <raver119@gmail.com> * disable some debug messages Signed-off-by: raver119 <raver119@gmail.com> * master pulled in Signed-off-by: raver119 <raver119@gmail.com> * couple of new methods for DataBuffer interop Signed-off-by: raver119 <raver119@gmail.com> * java side Signed-off-by: raver119 <raver119@gmail.com> * offsetted constructor Signed-off-by: raver119 <raver119@gmail.com> * new CUDA deallocator Signed-off-by: raver119 <raver119@gmail.com> * CUDA backend torn apart Signed-off-by: raver119 <raver119@gmail.com> * CUDA backend torn apart 2 Signed-off-by: raver119 <raver119@gmail.com> * CUDA backend torn apart 3 Signed-off-by: raver119 <raver119@gmail.com> * - few new tests - few new methods for DataBuffer management Signed-off-by: raver119 <raver119@gmail.com> * few more tests + few more tweaks Signed-off-by: raver119 <raver119@gmail.com> * two failing tests Signed-off-by: raver119 <raver119@gmail.com> * one more test Signed-off-by: raver119 <raver119@gmail.com> * two failing tests pass Signed-off-by: raver119 <raver119@gmail.com> * now we pass DataBuffer to legacy ops too Signed-off-by: raver119 <raver119@gmail.com> * Native DataBuffer for legacy ops, Java side Signed-off-by: raver119 <raver119@gmail.com> * CPU java side update Signed-off-by: raver119 <raver119@gmail.com> * CUDA java side update Signed-off-by: raver119 <raver119@gmail.com> * no more prepare/register action on java side Signed-off-by: raver119 <raver119@gmail.com> * NDArray::prepare/register use now accepts vectors Signed-off-by: raver119 <raver119@gmail.com> * InteropDataBuffer now has few more convenience methods Signed-off-by: raver119 <raver119@gmail.com> * java bindings update Signed-off-by: raver119 <raver119@gmail.com> * tick device in NativeOps Signed-off-by: raver119 <raver119@gmail.com> * Corrected usage of OpaqueBuffer for tests. * Corrected usage of OpaqueBuffer for java tests. * NativeOpsTests fixes. * print_variable now returns scalar Signed-off-by: raver119 <raver119@gmail.com> * one more test Signed-off-by: raver119 <raver119@gmail.com> * compat_string_split fix for CUDA Signed-off-by: raver119 <raver119@gmail.com> * - CUDA execScalar fix - CUDA lazyAllocateHostPointer now checks java indexer/pointer instead of native pointer Signed-off-by: raver119 <raver119@gmail.com> * legacy ops DataBuffer migration prototype Signed-off-by: raver119 <raver119@gmail.com> * ignore device shapeinfo coming from java Signed-off-by: raver119 <raver119@gmail.com> * minor fix Signed-off-by: raver119 <raver119@gmail.com> * minor transformAny fix Signed-off-by: raver119 <raver119@gmail.com> * minor tweak for lazy host allocation Signed-off-by: raver119 <raver119@gmail.com> * - DataBuffer::memcpy method - bitcast now uses memcpy Signed-off-by: raver119 <raver119@gmail.com> * - IndexReduce CUDA dimension buffer fix Signed-off-by: raver119 <raver119@gmail.com> * views for CPU and CUDA Signed-off-by: raver119 <raver119@gmail.com> * less spam Signed-off-by: raver119 <raver119@gmail.com> * optional memory init Signed-off-by: raver119 <raver119@gmail.com> * async memset Signed-off-by: raver119 <raver119@gmail.com> * - SummaryStats CUDA fix - DataBuffer.sameUnderlyingData() impl - execBroadcast fix Signed-off-by: raver119 <raver119@gmail.com> * - reduce3All fix switch to CUDA 10 temporarily Signed-off-by: raver119 <raver119@gmail.com> * CUDA version Signed-off-by: raver119 <raver119@gmail.com> * proper memory deallocator registration Signed-off-by: raver119 <raver119@gmail.com> * HOST_ONLY workspace allocation Signed-off-by: raver119 <raver119@gmail.com> * temp commit Signed-off-by: raver119 <raver119@gmail.com> * few conflicts resolved Signed-off-by: raver119 <raver119@gmail.com> * few minor fixes Signed-off-by: raver119 <raver119@gmail.com> * one more minor fix Signed-off-by: raver119 <raver119@gmail.com> * NDArray permute should operate on JVM primitives Signed-off-by: raver119 <raver119@gmail.com> * - create InteropDataBuffer for shapes as well - update pointers after view creation in Java Signed-off-by: raver119 <raver119@gmail.com> * - addressPointer temporary moved to C++ Signed-off-by: raver119 <raver119@gmail.com> * CUDA: don't account offset twice Signed-off-by: raver119 <raver119@gmail.com> * CUDA: DataBuffer pointer constructor updated Signed-off-by: raver119 <raver119@gmail.com> * CUDA NDArray.unsafeDuplication() simplified Signed-off-by: raver119 <raver119@gmail.com> * CUDA minor workspace-related fixes Signed-off-by: raver119 <raver119@gmail.com> * CPU DataBuffer.reallocate() Signed-off-by: raver119 <raver119@gmail.com> * print_affinity op Signed-off-by: raver119 <raver119@gmail.com> * print_affinity java side Signed-off-by: raver119 <raver119@gmail.com> * CUDA more tweaks for data locality Signed-off-by: raver119 <raver119@gmail.com> * - compat_string_split tweak - CudaUtf8Buffer update Signed-off-by: raver119 <raver119@gmail.com> * INDArray.close() mechanic restored Signed-off-by: raver119 <raver119@gmail.com> * one more test fixed Signed-off-by: raver119 <raver119@gmail.com> * - CUDA DataBuffer.reallocate() updated - cudaMemcpy (synchronous) restored Signed-off-by: raver119 <raver119@gmail.com> * one last fix Signed-off-by: raver119 <raver119@gmail.com> * bad import removed Signed-off-by: raver119 <raver119@gmail.com> * another small fix Signed-off-by: raver119 <raver119@gmail.com> * one special test Signed-off-by: raver119 <raver119@gmail.com> * fix bad databuffer size Signed-off-by: raver119 <raver119@gmail.com> * release primaryBuffer on replace Signed-off-by: raver119 <raver119@gmail.com> * higher timeout Signed-off-by: raver119 <raver119@gmail.com> * disable timeouts Signed-off-by: raver119 <raver119@gmail.com> * dbCreateView now validates offset and length of a view Signed-off-by: raver119 <raver119@gmail.com> * additional validation for dbExpand Signed-off-by: raver119 <raver119@gmail.com> * restore timeout back again Signed-off-by: raver119 <raver119@gmail.com> * smaller distribution for rng test to prevent timeouts Signed-off-by: raver119 <raver119@gmail.com> * CUDA DataBuffer::memcpy now copies to device all the time Signed-off-by: raver119 <raver119@gmail.com> * OpaqueDataBuffer now contains all required methods for interop Signed-off-by: raver119 <raver119@gmail.com> * some javadoc Signed-off-by: raver119 <raver119@gmail.com> * GC on failed allocations Signed-off-by: raver119 <raver119@gmail.com> * minoe memcpu tweak Signed-off-by: raver119 <raver119@gmail.com> * one more bitcast test Signed-off-by: raver119 <raver119@gmail.com> * - NDArray::deviceId() propagation - special multi-threaded test for data locality checks Signed-off-by: raver119 <raver119@gmail.com> * DataBuffer additional syncStream Signed-off-by: raver119 <raver119@gmail.com> * DataBuffer additional syncStream Signed-off-by: raver119 <raver119@gmail.com> * one ignored test Signed-off-by: raver119 <raver119@gmail.com> * skip host alloc for empty arrays Signed-off-by: raver119 <raver119@gmail.com> * ByteBuffer support is back Signed-off-by: raver119 <raver119@gmail.com> * DataBuffer::memcpy minor fix Signed-off-by: raver119 <raver119@gmail.com> * few minor prelu/bp tweaks Signed-off-by: raver119 <raver119@gmail.com> * nullify-related fixes Signed-off-by: raver119 <raver119@gmail.com> * PReLU fixes (#157) Signed-off-by: Alex Black <blacka101@gmail.com> * Build fixed * Fix tests * one more ByteBuffer signature restored Signed-off-by: raver119 <raver119@gmail.com> * nd4j-jdbc-hsql profiles fix Signed-off-by: raver119 <raver119@gmail.com> * nd4j-jdbc-hsql profiles fix Signed-off-by: raver119 <raver119@gmail.com> * PReLU weight init fix Signed-off-by: Alex Black <blacka101@gmail.com> * Small PReLU fix Signed-off-by: Alex Black <blacka101@gmail.com> * - INDArray.migrate() reactivated - DataBuffer::setDeviceId(...) added - InteropDataBuffer Z syncToDevice added for views Signed-off-by: raver119 <raver119@gmail.com> * missed file Signed-off-by: raver119 <raver119@gmail.com> * Small tweak Signed-off-by: Alex Black <blacka101@gmail.com> * cuda 10.2 Signed-off-by: raver119 <raver119@gmail.com> * minor fix Signed-off-by: raver119 <raver119@gmail.com> Co-authored-by: shugeo <sgazeos@gmail.com> Co-authored-by: Alex Black <blacka101@gmail.com> Co-authored-by: Alexander Stoyakin <alexander.stoyakin@gmail.com>
2020-01-04 11:27:50 +01:00
/*******************************************************************************
* Copyright (c) 2015-2019 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 raver119@gmail.com
//
#include <ops/declarable/helpers/sparse_to_dense.h>
#include <helpers/StringUtils.h>
#include <helpers/ShapeUtils.h>
namespace nd4j {
namespace ops {
namespace helpers {
template <typename X, typename I>
static void fill_(const void *vvalues, const void *vindices, void *voutput, const Nd4jLong *zShapeInfo, uint8_t rank, uint64_t length) {
auto values = reinterpret_cast<const X*>(vvalues);
auto indices = reinterpret_cast<const I*>(vindices);
auto output = reinterpret_cast<X*>(voutput);
Nd4jLong coords[MAX_RANK];
uint64_t pos = 0;
for (uint64_t e = 0L; e < length; e++) {
// indices come in blocks
for (uint8_t p = 0; p < rank; p++) {
coords[p] = indices[pos++];
}
// fill output at given coords with sparse value
output[shape::getOffset(zShapeInfo, coords)] = values[e];
}
}
void compat_sparse_to_dense(const NDArray &values, const NDArray &indices, NDArray *def, NDArray &output) {
// make sure host buffer is updated
values.syncToHost();
indices.syncToHost();
auto rank = output.rankOf();
if (output.isS()) {
// string case is not so trivial, since elements might, and probably will, have different sizes
auto numValues = values.lengthOf();
auto numElements = output.lengthOf();
// first of all we calculate final buffer sizes and offsets
auto defaultLength = def == nullptr ? 0 : StringUtils::byteLength(*def);
auto valuesLength = StringUtils::byteLength(values);
auto bufferLength = defaultLength * (output.lengthOf() - numValues) + valuesLength;
auto headerLength = ShapeUtils::stringBufferHeaderRequirements(numElements);
// now we make sure our output buffer can hold results
output.dataBuffer()->expand( bufferLength + headerLength);
std::vector<Nd4jLong> outputCoords(rank);
std::vector<Nd4jLong> valueCoords(rank);
auto offsetsBuffer = output.bufferAsT<Nd4jLong>();
auto dataBuffer = reinterpret_cast<uint8_t*>(offsetsBuffer + output.lengthOf());
offsetsBuffer[0] = 0;
// getting initial value coords
for (int e = 0; e < rank; e++)
valueCoords[e] = indices.e<Nd4jLong>(e);
// write results individually
for (uint64_t e = 0; e < numElements; e++) {
auto vIndex = shape::coords2index(output.shapeInfo(), valueCoords.data());
auto cLength = 0L;
std::string str;
if (vIndex == e) {
// we're writing down sparse value here
str = values.e<std::string>(e);
} else {
// we're writing down default value if it exists
if (def != nullptr)
str = def->e<std::string>(0);
else
str = "";
}
// TODO: make it unicode compliant
memcpy(&dataBuffer[offsetsBuffer[e]], str.c_str(), str.length());
// writing down offset
offsetsBuffer[e+1] = cLength;
}
} else {
// numeric case is trivial, since all elements have equal sizes
// write out default values, if they are present
if (def != nullptr) {
output.assign(def);
// make sure output is synced back
output.syncToHost();
}
// write out values
BUILD_DOUBLE_SELECTOR(values.dataType(), indices.dataType(), fill_, (values.getBuffer(), indices.getBuffer(), output.buffer(), output.getShapeInfo(), rank, values.lengthOf()), LIBND4J_TYPES, INDEXING_TYPES);
}
// copy back to device, if there's any
output.syncToDevice();
}
}
}
}