cavis/libnd4j/include/loops/cpu/reduce3.cpp

252 lines
11 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
******************************************************************************/
// @author raver119@gmail.com
// @author Yurii Shyrma (iuriish@yahoo.com), created on 19.11.2018
#include <types/types.h>
#include <op_boilerplate.h>
#include <loops/reduce3.h>
#include <loops/legacy_ops.h>
#include <helpers/ConstantTadHelper.h>
#include <Loops.h>
using namespace simdOps;
namespace functions {
namespace reduce3 {
//////////////////////////////////////////////////////////////////////////
template <typename X, typename Z>
template<typename OpType>
void Reduce3<X,Z>::execScalar(void *vx, Nd4jLong *xShapeInfo,
void *vextraParams,
void *vy, Nd4jLong *yShapeInfo,
void *vz, Nd4jLong *zShapeInfo) {
Dev branch merge: dev_20190606 (#7904) * correct logsoftmax looss (#2) * Small SameDiff listener fix (#4) * Various fixes (#6) * #7839 Fix for asXMatrix and tests * #7866 EmbeddingSequenceLayer dtype fix + test * #7856 SameDiff save/load stream methods * #7859 RegressionEvaluation rank 4 fix + tests + axis configuration * EvaluationBinary 3d/4d * More evaluation 3d/4d tests * #7847 Evaluation empty checks * Small test ifx * #7848 Fix median edge case * Improve DL4J samediff layer tests * [WIP] FastText wrapper implemented (#8) * FastText implemented * Some fixes * Fix shapes for wordsNearest * Validation of input vectors * Fixes * Fixed test * Thread tagged * Some tweaks * setContextClassLoader for DeallocatorServiceThread * Numpy format tests (#1) * Various fixes (#11) * #7852 SameDiff gather fix * #7892 SameDiff placeholder to constant conversion * #7890 validate input rank for MLN/CG init methods * Fix broken permute shape calculation * Permute and gather fixes * Tests * #7850 LogSumExp fix + test * Handful of test fixes * Empty arrays with non-scalar shapes (#10) * minor rearrangements for lambdas * empty tensors with non-scalar shapes * numpy empty tensors with non-scalar shapes * few more empty tweaks * Small fixes * conv3d signature update * micro fix in batchnorm mkldnn * Import fixes * Fix * MKL-DNN update * Small fill fix * fill with empty input + test * Fixes * Small error improvement * Fix * one special test * couple of fixes for lstm * Rewrite TFGraphMapper.getNDArrayFromTensor to be maintainable and less error prone * Fixes * FP16 * Unsigned * BFloat16 * Fill op - empty tweaks * - couple of fixes for empty arrays construction - stack updated * strided slice fix * one transform test * provide method for reducing shapeInfo in case of input array is empty * Fixed reduceAlongDimensions to use empty input properly. * couple of broadcast tests * couple of tests broadcast tests + tweak to make them pass * add check of non-empty to methods producing sub-arrays * Fixed reshapeC with zeros in shape. * complete empty check in reduce_... legacy ops * Concat and cumsum/prod * Tweak to empty shape inference on import * add empty check to the rest of reduce legacy ops * one more test * correct typo in evalReduceShapeInfoEmpty * Added tests for reduce_* ops to tests with zero shapes. * few more tests for empty reductions * Fixed strided_slice op with empty case and tests. * one more empty reduction test * Fixed strided_slice test. * add empty check to NDArray::reshapei * infOrMax * empty min/max with infinity tests * made unstack working correctly with empty arrays * few IndexReduce tests + tweaks for empty shapes * add test for empty concat * few tests fixed * Validation fix for reductions on empty shapes * Reverse fix * Reduction shape calc fixes * SameDiff.generateOutputVariable: don't use shape function to determine number of outputs * Range fix * - NDArray constructor updated for scalars/empty arrays - few tests fixed * More fixes * Empty creator fixes * concat fix * concat fix * TF import tests: allow 'both all NaN' and 'both all inf' to pass * Slice, zero fraction, and reshape fixes * transpose, gather * Zero fraction * scalar cast fix * Empty reduction axis support * few more tests fixed * Fixed input checks conforming with TF for concat op and tests. * few tests fixed * matmul scalar shape fix * Fixed checkout for data type and scalarity with concat to allow non-empty scalars with vector concats. * broadcast bool fix * few more tests * few more tests * correct evalReduceShapeInfoEmpty * argmax/argmin + tests * one more empty edge case + one more test * argmax/argmin/realdiv_bp tweaks * empty reshape test + fix * Helper fixes * Small fixes * Gather test fix * Gather test fix * Small fixes * reduce scalar zero values * scalar mean workaround * Remove debug code * along dim mean workaround * one more test * - equalsTo() tweak for empty arrays - one more test * broadcast tweaks
2019-06-15 13:34:34 +02:00
2019-06-06 14:21:15 +02:00
auto x = reinterpret_cast<X *>(vx);
auto y = reinterpret_cast<X *>(vy);
auto z = reinterpret_cast<Z *>(vz);
auto extraParams = reinterpret_cast<Z *>(vextraParams);
auto length = shape::length(xShapeInfo);
auto xEws = shape::elementWiseStride(xShapeInfo);
auto yEws = shape::elementWiseStride(yShapeInfo);
Dev branch merge: dev_20190606 (#7904) * correct logsoftmax looss (#2) * Small SameDiff listener fix (#4) * Various fixes (#6) * #7839 Fix for asXMatrix and tests * #7866 EmbeddingSequenceLayer dtype fix + test * #7856 SameDiff save/load stream methods * #7859 RegressionEvaluation rank 4 fix + tests + axis configuration * EvaluationBinary 3d/4d * More evaluation 3d/4d tests * #7847 Evaluation empty checks * Small test ifx * #7848 Fix median edge case * Improve DL4J samediff layer tests * [WIP] FastText wrapper implemented (#8) * FastText implemented * Some fixes * Fix shapes for wordsNearest * Validation of input vectors * Fixes * Fixed test * Thread tagged * Some tweaks * setContextClassLoader for DeallocatorServiceThread * Numpy format tests (#1) * Various fixes (#11) * #7852 SameDiff gather fix * #7892 SameDiff placeholder to constant conversion * #7890 validate input rank for MLN/CG init methods * Fix broken permute shape calculation * Permute and gather fixes * Tests * #7850 LogSumExp fix + test * Handful of test fixes * Empty arrays with non-scalar shapes (#10) * minor rearrangements for lambdas * empty tensors with non-scalar shapes * numpy empty tensors with non-scalar shapes * few more empty tweaks * Small fixes * conv3d signature update * micro fix in batchnorm mkldnn * Import fixes * Fix * MKL-DNN update * Small fill fix * fill with empty input + test * Fixes * Small error improvement * Fix * one special test * couple of fixes for lstm * Rewrite TFGraphMapper.getNDArrayFromTensor to be maintainable and less error prone * Fixes * FP16 * Unsigned * BFloat16 * Fill op - empty tweaks * - couple of fixes for empty arrays construction - stack updated * strided slice fix * one transform test * provide method for reducing shapeInfo in case of input array is empty * Fixed reduceAlongDimensions to use empty input properly. * couple of broadcast tests * couple of tests broadcast tests + tweak to make them pass * add check of non-empty to methods producing sub-arrays * Fixed reshapeC with zeros in shape. * complete empty check in reduce_... legacy ops * Concat and cumsum/prod * Tweak to empty shape inference on import * add empty check to the rest of reduce legacy ops * one more test * correct typo in evalReduceShapeInfoEmpty * Added tests for reduce_* ops to tests with zero shapes. * few more tests for empty reductions * Fixed strided_slice op with empty case and tests. * one more empty reduction test * Fixed strided_slice test. * add empty check to NDArray::reshapei * infOrMax * empty min/max with infinity tests * made unstack working correctly with empty arrays * few IndexReduce tests + tweaks for empty shapes * add test for empty concat * few tests fixed * Validation fix for reductions on empty shapes * Reverse fix * Reduction shape calc fixes * SameDiff.generateOutputVariable: don't use shape function to determine number of outputs * Range fix * - NDArray constructor updated for scalars/empty arrays - few tests fixed * More fixes * Empty creator fixes * concat fix * concat fix * TF import tests: allow 'both all NaN' and 'both all inf' to pass * Slice, zero fraction, and reshape fixes * transpose, gather * Zero fraction * scalar cast fix * Empty reduction axis support * few more tests fixed * Fixed input checks conforming with TF for concat op and tests. * few tests fixed * matmul scalar shape fix * Fixed checkout for data type and scalarity with concat to allow non-empty scalars with vector concats. * broadcast bool fix * few more tests * few more tests * correct evalReduceShapeInfoEmpty * argmax/argmin + tests * one more empty edge case + one more test * argmax/argmin/realdiv_bp tweaks * empty reshape test + fix * Helper fixes * Small fixes * Gather test fix * Gather test fix * Small fixes * reduce scalar zero values * scalar mean workaround * Remove debug code * along dim mean workaround * one more test * - equalsTo() tweak for empty arrays - one more test * broadcast tweaks
2019-06-15 13:34:34 +02:00
if(nd4j::ArrayOptions::arrayType(xShapeInfo) == nd4j::ArrayType::EMPTY || nd4j::ArrayOptions::arrayType(yShapeInfo) == nd4j::ArrayType::EMPTY) {
if(nd4j::ArrayOptions::arrayType(zShapeInfo) == nd4j::ArrayType::EMPTY)
return;
const auto startingVal = OpType::startingValue(x);
PRAGMA_OMP_PARALLEL_FOR_IF(length > nd4j::Environment::getInstance()->elementwiseThreshold())
for (uint i = 0; i < length; i++)
z[i] = startingVal;
return;
}
2019-06-06 14:21:15 +02:00
Z extraParamsVals[3] = {(Z) 0.0f, (Z) 0.0f, (Z) 0.0f};
// it's possible case for EqualsWithEps op
Dev branch merge: dev_20190606 (#7904) * correct logsoftmax looss (#2) * Small SameDiff listener fix (#4) * Various fixes (#6) * #7839 Fix for asXMatrix and tests * #7866 EmbeddingSequenceLayer dtype fix + test * #7856 SameDiff save/load stream methods * #7859 RegressionEvaluation rank 4 fix + tests + axis configuration * EvaluationBinary 3d/4d * More evaluation 3d/4d tests * #7847 Evaluation empty checks * Small test ifx * #7848 Fix median edge case * Improve DL4J samediff layer tests * [WIP] FastText wrapper implemented (#8) * FastText implemented * Some fixes * Fix shapes for wordsNearest * Validation of input vectors * Fixes * Fixed test * Thread tagged * Some tweaks * setContextClassLoader for DeallocatorServiceThread * Numpy format tests (#1) * Various fixes (#11) * #7852 SameDiff gather fix * #7892 SameDiff placeholder to constant conversion * #7890 validate input rank for MLN/CG init methods * Fix broken permute shape calculation * Permute and gather fixes * Tests * #7850 LogSumExp fix + test * Handful of test fixes * Empty arrays with non-scalar shapes (#10) * minor rearrangements for lambdas * empty tensors with non-scalar shapes * numpy empty tensors with non-scalar shapes * few more empty tweaks * Small fixes * conv3d signature update * micro fix in batchnorm mkldnn * Import fixes * Fix * MKL-DNN update * Small fill fix * fill with empty input + test * Fixes * Small error improvement * Fix * one special test * couple of fixes for lstm * Rewrite TFGraphMapper.getNDArrayFromTensor to be maintainable and less error prone * Fixes * FP16 * Unsigned * BFloat16 * Fill op - empty tweaks * - couple of fixes for empty arrays construction - stack updated * strided slice fix * one transform test * provide method for reducing shapeInfo in case of input array is empty * Fixed reduceAlongDimensions to use empty input properly. * couple of broadcast tests * couple of tests broadcast tests + tweak to make them pass * add check of non-empty to methods producing sub-arrays * Fixed reshapeC with zeros in shape. * complete empty check in reduce_... legacy ops * Concat and cumsum/prod * Tweak to empty shape inference on import * add empty check to the rest of reduce legacy ops * one more test * correct typo in evalReduceShapeInfoEmpty * Added tests for reduce_* ops to tests with zero shapes. * few more tests for empty reductions * Fixed strided_slice op with empty case and tests. * one more empty reduction test * Fixed strided_slice test. * add empty check to NDArray::reshapei * infOrMax * empty min/max with infinity tests * made unstack working correctly with empty arrays * few IndexReduce tests + tweaks for empty shapes * add test for empty concat * few tests fixed * Validation fix for reductions on empty shapes * Reverse fix * Reduction shape calc fixes * SameDiff.generateOutputVariable: don't use shape function to determine number of outputs * Range fix * - NDArray constructor updated for scalars/empty arrays - few tests fixed * More fixes * Empty creator fixes * concat fix * concat fix * TF import tests: allow 'both all NaN' and 'both all inf' to pass * Slice, zero fraction, and reshape fixes * transpose, gather * Zero fraction * scalar cast fix * Empty reduction axis support * few more tests fixed * Fixed input checks conforming with TF for concat op and tests. * few tests fixed * matmul scalar shape fix * Fixed checkout for data type and scalarity with concat to allow non-empty scalars with vector concats. * broadcast bool fix * few more tests * few more tests * correct evalReduceShapeInfoEmpty * argmax/argmin + tests * one more empty edge case + one more test * argmax/argmin/realdiv_bp tweaks * empty reshape test + fix * Helper fixes * Small fixes * Gather test fix * Gather test fix * Small fixes * reduce scalar zero values * scalar mean workaround * Remove debug code * along dim mean workaround * one more test * - equalsTo() tweak for empty arrays - one more test * broadcast tweaks
2019-06-15 13:34:34 +02:00
if (extraParams != nullptr)
2019-06-06 14:21:15 +02:00
extraParamsVals[2] = extraParams[0];
Dev branch merge: dev_20190606 (#7904) * correct logsoftmax looss (#2) * Small SameDiff listener fix (#4) * Various fixes (#6) * #7839 Fix for asXMatrix and tests * #7866 EmbeddingSequenceLayer dtype fix + test * #7856 SameDiff save/load stream methods * #7859 RegressionEvaluation rank 4 fix + tests + axis configuration * EvaluationBinary 3d/4d * More evaluation 3d/4d tests * #7847 Evaluation empty checks * Small test ifx * #7848 Fix median edge case * Improve DL4J samediff layer tests * [WIP] FastText wrapper implemented (#8) * FastText implemented * Some fixes * Fix shapes for wordsNearest * Validation of input vectors * Fixes * Fixed test * Thread tagged * Some tweaks * setContextClassLoader for DeallocatorServiceThread * Numpy format tests (#1) * Various fixes (#11) * #7852 SameDiff gather fix * #7892 SameDiff placeholder to constant conversion * #7890 validate input rank for MLN/CG init methods * Fix broken permute shape calculation * Permute and gather fixes * Tests * #7850 LogSumExp fix + test * Handful of test fixes * Empty arrays with non-scalar shapes (#10) * minor rearrangements for lambdas * empty tensors with non-scalar shapes * numpy empty tensors with non-scalar shapes * few more empty tweaks * Small fixes * conv3d signature update * micro fix in batchnorm mkldnn * Import fixes * Fix * MKL-DNN update * Small fill fix * fill with empty input + test * Fixes * Small error improvement * Fix * one special test * couple of fixes for lstm * Rewrite TFGraphMapper.getNDArrayFromTensor to be maintainable and less error prone * Fixes * FP16 * Unsigned * BFloat16 * Fill op - empty tweaks * - couple of fixes for empty arrays construction - stack updated * strided slice fix * one transform test * provide method for reducing shapeInfo in case of input array is empty * Fixed reduceAlongDimensions to use empty input properly. * couple of broadcast tests * couple of tests broadcast tests + tweak to make them pass * add check of non-empty to methods producing sub-arrays * Fixed reshapeC with zeros in shape. * complete empty check in reduce_... legacy ops * Concat and cumsum/prod * Tweak to empty shape inference on import * add empty check to the rest of reduce legacy ops * one more test * correct typo in evalReduceShapeInfoEmpty * Added tests for reduce_* ops to tests with zero shapes. * few more tests for empty reductions * Fixed strided_slice op with empty case and tests. * one more empty reduction test * Fixed strided_slice test. * add empty check to NDArray::reshapei * infOrMax * empty min/max with infinity tests * made unstack working correctly with empty arrays * few IndexReduce tests + tweaks for empty shapes * add test for empty concat * few tests fixed * Validation fix for reductions on empty shapes * Reverse fix * Reduction shape calc fixes * SameDiff.generateOutputVariable: don't use shape function to determine number of outputs * Range fix * - NDArray constructor updated for scalars/empty arrays - few tests fixed * More fixes * Empty creator fixes * concat fix * concat fix * TF import tests: allow 'both all NaN' and 'both all inf' to pass * Slice, zero fraction, and reshape fixes * transpose, gather * Zero fraction * scalar cast fix * Empty reduction axis support * few more tests fixed * Fixed input checks conforming with TF for concat op and tests. * few tests fixed * matmul scalar shape fix * Fixed checkout for data type and scalarity with concat to allow non-empty scalars with vector concats. * broadcast bool fix * few more tests * few more tests * correct evalReduceShapeInfoEmpty * argmax/argmin + tests * one more empty edge case + one more test * argmax/argmin/realdiv_bp tweaks * empty reshape test + fix * Helper fixes * Small fixes * Gather test fix * Gather test fix * Small fixes * reduce scalar zero values * scalar mean workaround * Remove debug code * along dim mean workaround * one more test * - equalsTo() tweak for empty arrays - one more test * broadcast tweaks
2019-06-15 13:34:34 +02:00
2019-06-06 14:21:15 +02:00
uint xShapeInfoCast[MAX_RANK];
const bool canCastX = nd4j::DataTypeUtils::castShapeInfo(xShapeInfo, xShapeInfoCast);
Z startingVal = OpType::startingValue(x);
const int maxThreads = nd4j::math::nd4j_min<int>(256, omp_get_max_threads());
nd4j::OmpLaunchHelper t(length, maxThreads);
Z intermediate[256];
Z extraParamsLocal[3 * 256];
PRAGMA_OMP_SIMD
for (int e = 0; e < maxThreads; e++)
intermediate[e] = startingVal;
memset(extraParamsLocal, 0, 3 * 256 * sizeof(Z));
if (extraParams != nullptr)
PRAGMA_OMP_SIMD
for (int e = 0; e < maxThreads; e++)
extraParamsLocal[3 * e + 2] = extraParams[0];
nd4j::LoopKind::Kind kindOfLoop = nd4j::LoopKind::deduceKindOfLoopXZ(xShapeInfo, yShapeInfo);
if (kindOfLoop == nd4j::LoopKind::EWS1) {
PRAGMA_OMP_PARALLEL_FOR_SIMD_THREADS(t._numThreads)
for(unsigned int i = 0; i < length; i++) {
const auto threadNum = omp_get_thread_num();
intermediate[threadNum] = OpType::update(intermediate[threadNum], OpType::op(x[i], y[i], extraParamsLocal + 3 * threadNum), extraParamsLocal + 3 * threadNum);
}
} else if(shape::haveSameShapeAndStrides(xShapeInfo, yShapeInfo)) {
PRAGMA_OMP_PARALLEL_FOR_SIMD_THREADS(t._numThreads)
for(unsigned int i = 0; i < length; i++) {
const auto threadNum = omp_get_thread_num();
auto offset = shape::indexOffset(i, xShapeInfo, xShapeInfoCast, length, canCastX);
intermediate[threadNum] = OpType::update(intermediate[threadNum], OpType::op(x[offset], y[offset], extraParamsLocal + 3 * threadNum), extraParamsLocal + 3 * threadNum);
}
} else {
uint yShapeInfoCast[MAX_RANK];
const bool canCastY = nd4j::DataTypeUtils::castShapeInfo(yShapeInfo, yShapeInfoCast);
PRAGMA_OMP_PARALLEL_FOR_SIMD_THREADS(t._numThreads)
for(unsigned int i = 0; i < length; i++) {
const auto threadNum = omp_get_thread_num();
auto xOffset = shape::indexOffset(i, xShapeInfo, xShapeInfoCast, length, canCastX);
auto yOffset = shape::indexOffset(i, yShapeInfo, yShapeInfoCast, length, canCastY);
intermediate[threadNum] = OpType::update(intermediate[threadNum], OpType::op(x[xOffset], y[yOffset], extraParamsLocal + 3 * threadNum), extraParamsLocal + 3 * threadNum);
}
}
// merge step
for (int e = 0; e < maxThreads; e++)
OpType::aggregateExtraParams(extraParamsVals, extraParamsLocal + 3 * e);
for (int e = 0; e < maxThreads; e++)
startingVal = OpType::update(startingVal, intermediate[e], extraParamsVals);
z[0] = OpType::postProcess(startingVal, length, extraParamsVals);
}
//////////////////////////////////////////////////////////////////////////
template <typename X, typename Y>
void Reduce3<X,Y>::execScalar(const int opNum,
void *vx, Nd4jLong *xShapeInfo,
void *extraParamsVals,
void *vy, Nd4jLong *yShapeInfo,
void *vz, Nd4jLong *zShapeInfo) {
Dev branch merge: dev_20190606 (#7904) * correct logsoftmax looss (#2) * Small SameDiff listener fix (#4) * Various fixes (#6) * #7839 Fix for asXMatrix and tests * #7866 EmbeddingSequenceLayer dtype fix + test * #7856 SameDiff save/load stream methods * #7859 RegressionEvaluation rank 4 fix + tests + axis configuration * EvaluationBinary 3d/4d * More evaluation 3d/4d tests * #7847 Evaluation empty checks * Small test ifx * #7848 Fix median edge case * Improve DL4J samediff layer tests * [WIP] FastText wrapper implemented (#8) * FastText implemented * Some fixes * Fix shapes for wordsNearest * Validation of input vectors * Fixes * Fixed test * Thread tagged * Some tweaks * setContextClassLoader for DeallocatorServiceThread * Numpy format tests (#1) * Various fixes (#11) * #7852 SameDiff gather fix * #7892 SameDiff placeholder to constant conversion * #7890 validate input rank for MLN/CG init methods * Fix broken permute shape calculation * Permute and gather fixes * Tests * #7850 LogSumExp fix + test * Handful of test fixes * Empty arrays with non-scalar shapes (#10) * minor rearrangements for lambdas * empty tensors with non-scalar shapes * numpy empty tensors with non-scalar shapes * few more empty tweaks * Small fixes * conv3d signature update * micro fix in batchnorm mkldnn * Import fixes * Fix * MKL-DNN update * Small fill fix * fill with empty input + test * Fixes * Small error improvement * Fix * one special test * couple of fixes for lstm * Rewrite TFGraphMapper.getNDArrayFromTensor to be maintainable and less error prone * Fixes * FP16 * Unsigned * BFloat16 * Fill op - empty tweaks * - couple of fixes for empty arrays construction - stack updated * strided slice fix * one transform test * provide method for reducing shapeInfo in case of input array is empty * Fixed reduceAlongDimensions to use empty input properly. * couple of broadcast tests * couple of tests broadcast tests + tweak to make them pass * add check of non-empty to methods producing sub-arrays * Fixed reshapeC with zeros in shape. * complete empty check in reduce_... legacy ops * Concat and cumsum/prod * Tweak to empty shape inference on import * add empty check to the rest of reduce legacy ops * one more test * correct typo in evalReduceShapeInfoEmpty * Added tests for reduce_* ops to tests with zero shapes. * few more tests for empty reductions * Fixed strided_slice op with empty case and tests. * one more empty reduction test * Fixed strided_slice test. * add empty check to NDArray::reshapei * infOrMax * empty min/max with infinity tests * made unstack working correctly with empty arrays * few IndexReduce tests + tweaks for empty shapes * add test for empty concat * few tests fixed * Validation fix for reductions on empty shapes * Reverse fix * Reduction shape calc fixes * SameDiff.generateOutputVariable: don't use shape function to determine number of outputs * Range fix * - NDArray constructor updated for scalars/empty arrays - few tests fixed * More fixes * Empty creator fixes * concat fix * concat fix * TF import tests: allow 'both all NaN' and 'both all inf' to pass * Slice, zero fraction, and reshape fixes * transpose, gather * Zero fraction * scalar cast fix * Empty reduction axis support * few more tests fixed * Fixed input checks conforming with TF for concat op and tests. * few tests fixed * matmul scalar shape fix * Fixed checkout for data type and scalarity with concat to allow non-empty scalars with vector concats. * broadcast bool fix * few more tests * few more tests * correct evalReduceShapeInfoEmpty * argmax/argmin + tests * one more empty edge case + one more test * argmax/argmin/realdiv_bp tweaks * empty reshape test + fix * Helper fixes * Small fixes * Gather test fix * Gather test fix * Small fixes * reduce scalar zero values * scalar mean workaround * Remove debug code * along dim mean workaround * one more test * - equalsTo() tweak for empty arrays - one more test * broadcast tweaks
2019-06-15 13:34:34 +02:00
2019-06-06 14:21:15 +02:00
DISPATCH_BY_OPNUM_TT(execScalar, PARAMS(vx, xShapeInfo, extraParamsVals, vy, yShapeInfo, vz, zShapeInfo), REDUCE3_OPS);
}
//////////////////////////////////////////////////////////////////////////
template <typename X, typename Z>
template<typename OpType>
void Reduce3<X,Z>::exec(void *vx, Nd4jLong *xShapeInfo,
void *vextraParams,
void *vy, Nd4jLong *yShapeInfo,
void *vz, Nd4jLong *zShapeInfo,
int *dimension, int dimensionLength) {
auto x = reinterpret_cast<X*>(vx);
auto y = reinterpret_cast<X*>(vy);
auto z = reinterpret_cast<Z*>(vz);
auto extraParams = reinterpret_cast<Z*>(vextraParams);
if(shape::isScalar(zShapeInfo)) {
execScalar<OpType>(vx, xShapeInfo, vextraParams, vy, yShapeInfo, vz, zShapeInfo);
return;
}
#ifdef INLINE_LOOPS
nd4j::Reduction3Loops<X,Z>::template loopReduce3<OpType>(x, xShapeInfo, y, yShapeInfo, z, zShapeInfo, dimension, dimensionLength, extraParams);
#else
nd4j::Reduction3Loops<X,Z>::template innerloopReduce3<OpType>(x, xShapeInfo, y, yShapeInfo, z, zShapeInfo, dimension, dimensionLength, extraParams);
#endif
}
//////////////////////////////////////////////////////////////////////////
template <typename X, typename Z>
template<typename OpType>
void Reduce3<X,Z>::exec(void *vx, Nd4jLong *xShapeInfo,
void *vextraParams,
void *vy, Nd4jLong *yShapeInfo,
void *vz, Nd4jLong *zShapeInfo,
int *dimension, int dimensionLength,
Nd4jLong *tadShapeInfo, Nd4jLong *tadOffsets) {
auto x = reinterpret_cast<X *>(vx);
auto y = reinterpret_cast<X *>(vy);
auto z = reinterpret_cast<Z *>(vz);
auto extraParams = reinterpret_cast<Z *>(vextraParams);
#ifdef INLINE_LOOPS
nd4j::Reduction3Loops<X,Z>::template loopReduce3<OpType>(x, xShapeInfo, y, yShapeInfo, z, zShapeInfo, dimension, dimensionLength, extraParams);
#else
nd4j::Reduction3Loops<X,Z>::template innerloopReduce3<OpType>(x, xShapeInfo, y, yShapeInfo, z, zShapeInfo, dimension, dimensionLength, extraParams);
#endif
}
//////////////////////////////////////////////////////////////////////////
template <typename X, typename Z>
template<typename OpType>
void Reduce3<X,Z>:: execAll(void *vx, Nd4jLong *xShapeInfo,
void *vextraParams,
void *vy, Nd4jLong *yShapeInfo,
void *vz, Nd4jLong *zShapeInfo,
Dev branch merge: dev_20190606 (#7904) * correct logsoftmax looss (#2) * Small SameDiff listener fix (#4) * Various fixes (#6) * #7839 Fix for asXMatrix and tests * #7866 EmbeddingSequenceLayer dtype fix + test * #7856 SameDiff save/load stream methods * #7859 RegressionEvaluation rank 4 fix + tests + axis configuration * EvaluationBinary 3d/4d * More evaluation 3d/4d tests * #7847 Evaluation empty checks * Small test ifx * #7848 Fix median edge case * Improve DL4J samediff layer tests * [WIP] FastText wrapper implemented (#8) * FastText implemented * Some fixes * Fix shapes for wordsNearest * Validation of input vectors * Fixes * Fixed test * Thread tagged * Some tweaks * setContextClassLoader for DeallocatorServiceThread * Numpy format tests (#1) * Various fixes (#11) * #7852 SameDiff gather fix * #7892 SameDiff placeholder to constant conversion * #7890 validate input rank for MLN/CG init methods * Fix broken permute shape calculation * Permute and gather fixes * Tests * #7850 LogSumExp fix + test * Handful of test fixes * Empty arrays with non-scalar shapes (#10) * minor rearrangements for lambdas * empty tensors with non-scalar shapes * numpy empty tensors with non-scalar shapes * few more empty tweaks * Small fixes * conv3d signature update * micro fix in batchnorm mkldnn * Import fixes * Fix * MKL-DNN update * Small fill fix * fill with empty input + test * Fixes * Small error improvement * Fix * one special test * couple of fixes for lstm * Rewrite TFGraphMapper.getNDArrayFromTensor to be maintainable and less error prone * Fixes * FP16 * Unsigned * BFloat16 * Fill op - empty tweaks * - couple of fixes for empty arrays construction - stack updated * strided slice fix * one transform test * provide method for reducing shapeInfo in case of input array is empty * Fixed reduceAlongDimensions to use empty input properly. * couple of broadcast tests * couple of tests broadcast tests + tweak to make them pass * add check of non-empty to methods producing sub-arrays * Fixed reshapeC with zeros in shape. * complete empty check in reduce_... legacy ops * Concat and cumsum/prod * Tweak to empty shape inference on import * add empty check to the rest of reduce legacy ops * one more test * correct typo in evalReduceShapeInfoEmpty * Added tests for reduce_* ops to tests with zero shapes. * few more tests for empty reductions * Fixed strided_slice op with empty case and tests. * one more empty reduction test * Fixed strided_slice test. * add empty check to NDArray::reshapei * infOrMax * empty min/max with infinity tests * made unstack working correctly with empty arrays * few IndexReduce tests + tweaks for empty shapes * add test for empty concat * few tests fixed * Validation fix for reductions on empty shapes * Reverse fix * Reduction shape calc fixes * SameDiff.generateOutputVariable: don't use shape function to determine number of outputs * Range fix * - NDArray constructor updated for scalars/empty arrays - few tests fixed * More fixes * Empty creator fixes * concat fix * concat fix * TF import tests: allow 'both all NaN' and 'both all inf' to pass * Slice, zero fraction, and reshape fixes * transpose, gather * Zero fraction * scalar cast fix * Empty reduction axis support * few more tests fixed * Fixed input checks conforming with TF for concat op and tests. * few tests fixed * matmul scalar shape fix * Fixed checkout for data type and scalarity with concat to allow non-empty scalars with vector concats. * broadcast bool fix * few more tests * few more tests * correct evalReduceShapeInfoEmpty * argmax/argmin + tests * one more empty edge case + one more test * argmax/argmin/realdiv_bp tweaks * empty reshape test + fix * Helper fixes * Small fixes * Gather test fix * Gather test fix * Small fixes * reduce scalar zero values * scalar mean workaround * Remove debug code * along dim mean workaround * one more test * - equalsTo() tweak for empty arrays - one more test * broadcast tweaks
2019-06-15 13:34:34 +02:00
int *dimension, int dimensionLength,
Nd4jLong *xTadShapeInfo, Nd4jLong *xOffsets,
2019-06-06 14:21:15 +02:00
Nd4jLong *yTadShapeInfo, Nd4jLong *yOffsets) {
auto x = reinterpret_cast<X *>(vx);
auto y = reinterpret_cast<X *>(vy);
auto z = reinterpret_cast<Z *>(vz);
auto extraParams = reinterpret_cast<Z*>(vextraParams);
#ifdef INLINE_LOOPS
nd4j::Reduction3Loops<X,Z>::template loopReduce3All<OpType>(x, xShapeInfo, y, yShapeInfo, z, zShapeInfo, xTadShapeInfo, xOffsets, yTadShapeInfo, yOffsets, extraParams);
#else
nd4j::Reduction3Loops<X,Z>::template innerloopReduce3All<OpType>(x, xShapeInfo, y, yShapeInfo, z, zShapeInfo, xTadShapeInfo, xOffsets, yTadShapeInfo, yOffsets, extraParams);
#endif
}
//////////////////////////////////////////////////////////////////////////
template <typename X, typename Y>
void Reduce3<X,Y>::exec( const int opNum,
void *vx, Nd4jLong *xShapeInfo,
void *extraParamsVals,
void *vy, Nd4jLong *yShapeInfo,
void *vz, Nd4jLong *zShapeInfo,
int *dimension, int dimensionLength) {
DISPATCH_BY_OPNUM_TT(exec, PARAMS(vx, xShapeInfo, extraParamsVals, vy, yShapeInfo, vz, zShapeInfo, dimension, dimensionLength), REDUCE3_OPS);
}
//////////////////////////////////////////////////////////////////////////
template <typename X, typename Y>
void Reduce3<X,Y>::exec( const int opNum,
void *vx, Nd4jLong *xShapeInfo,
void *extraParamsVals,
void *vy, Nd4jLong *yShapeInfo,
void *vz, Nd4jLong *zShapeInfo,
int *dimension, int dimensionLength,
Nd4jLong *tadShapeInfo, Nd4jLong *tadOffsets) {
DISPATCH_BY_OPNUM_TT(exec, PARAMS(vx,xShapeInfo,extraParamsVals,vy, yShapeInfo,vz,zShapeInfo, dimension, dimensionLength, tadShapeInfo, tadOffsets), REDUCE3_OPS);
}
//////////////////////////////////////////////////////////////////////////
template <typename X, typename Y>
void Reduce3<X,Y>::execAll(const int opNum,
void *vx, Nd4jLong *xShapeInfo,
void *extraParamsVals,
void *vy, Nd4jLong *yShapeInfo,
void *vz, Nd4jLong *zShapeInfo,
int *dimension, int dimensionLength,
Nd4jLong *xTadShapeInfo, Nd4jLong *xOffsets,
Nd4jLong *yTadShapeInfo, Nd4jLong *yOffsets) {
DISPATCH_BY_OPNUM_TT(execAll, PARAMS(vx, xShapeInfo, extraParamsVals, vy, yShapeInfo, vz, zShapeInfo, dimension, dimensionLength, xTadShapeInfo, xOffsets, yTadShapeInfo, yOffsets), REDUCE3_OPS);
}
BUILD_DOUBLE_TEMPLATE(template class ND4J_EXPORT Reduce3, , LIBND4J_TYPES, FLOAT_TYPES);
}
}