cavis/libnd4j/include/ops/declarable/helpers/cpu/compare_elem.cpp

76 lines
3.1 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
******************************************************************************/
#include <ops/declarable/helpers/compare_elem.h>
#include <execution/Threads.h>
2019-06-06 14:21:15 +02:00
namespace nd4j {
namespace ops {
namespace helpers {
template<typename T>
static void _compare_elem(NDArray *input, bool isStrictlyIncreasing, bool& output) {
auto length = shape::length(input->getShapeInfo());
int elementsPerThread = length / ELEMENT_THRESHOLD;
int num_threads = nd4j::math::nd4j_max<int>(1, elementsPerThread);
num_threads = nd4j::math::nd4j_min<int>(num_threads, omp_get_max_threads());
Nd4jLong sumt = 0;
2019-06-06 14:21:15 +02:00
if(isStrictlyIncreasing) {
//PRAGMA_OMP_PARALLEL_FOR_SIMD_REDUCTION(+:sum)
auto func = PRAGMA_REDUCE_LONG {
Nd4jLong sum = 0;
for (auto i = start; i < stop; i++) {
auto val0 = input->t<T>(i);
auto val1 = input->t<T>(i + 1);
sum += val0 >= val1 ? -1 : 0;
}
return sum;
};
sumt = samediff::Threads::parallel_long(func, LAMBDA_SUML, 0, length - 1);
2019-06-06 14:21:15 +02:00
} else {
//PRAGMA_OMP_PARALLEL_FOR_SIMD_REDUCTION(+:sum)
auto func = PRAGMA_REDUCE_LONG {
Nd4jLong sum = 0;
for (auto i = start; i < stop; i++) {
auto val0 = input->t<T>(i);
auto val1 = input->t<T>(i + 1);
sum += val0 > val1 ? -1 : 0;
}
return sum;
};
sumt = samediff::Threads::parallel_long(func, LAMBDA_SUML, 0, length - 1);
2019-06-06 14:21:15 +02:00
}
Various fixes (#143) * #8568 ArrayUtil optimization Signed-off-by: AlexDBlack <blacka101@gmail.com> * #6171 Keras ReLU and ELU support Signed-off-by: AlexDBlack <blacka101@gmail.com> * Keras softmax layer import Signed-off-by: AlexDBlack <blacka101@gmail.com> * #8549 Webjars dependency management Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fix for TF import names ':0' suffix issue / NPE Signed-off-by: AlexDBlack <blacka101@gmail.com> * BiasAdd: fix default data format for TF import Signed-off-by: AlexDBlack <blacka101@gmail.com> * Update zoo test ignores Signed-off-by: AlexDBlack <blacka101@gmail.com> * #8509 SameDiff Listener API - provide frame + iteration Signed-off-by: AlexDBlack <blacka101@gmail.com> * #8520 ND4J Environment Signed-off-by: AlexDBlack <blacka101@gmail.com> * Deconv3d Signed-off-by: AlexDBlack <blacka101@gmail.com> * Deconv3d fixes + gradient check Signed-off-by: AlexDBlack <blacka101@gmail.com> * Conv3d fixes + deconv3d DType test Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fix issue with deconv3d gradinet check weight init Signed-off-by: AlexDBlack <blacka101@gmail.com> * #8579 Fix BaseCudaDataBuffer constructor fix for UINT16 Signed-off-by: AlexDBlack <blacka101@gmail.com> * DataType.isNumerical() returns false for BOOL type Signed-off-by: AlexDBlack <blacka101@gmail.com> * #8504 Reduce Spark log spam for tests Signed-off-by: AlexDBlack <blacka101@gmail.com> * Clean up DL4J gradient check test spam Signed-off-by: AlexDBlack <blacka101@gmail.com> * More Gradient check spam reduction Signed-off-by: AlexDBlack <blacka101@gmail.com> * SameDiff test spam reduction Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fixes for FlatBuffers mapping Signed-off-by: AlexDBlack <blacka101@gmail.com> * SameDiff log spam cleanup Signed-off-by: AlexDBlack <blacka101@gmail.com> * Tests should extend BaseNd4jTest Signed-off-by: AlexDBlack <blacka101@gmail.com> * Remove debug line in c++ op Signed-off-by: AlexDBlack <blacka101@gmail.com> * ND4J test spam cleanup Signed-off-by: AlexDBlack <blacka101@gmail.com> * DL4J test spam reduction Signed-off-by: AlexDBlack <blacka101@gmail.com> * More Dl4J and datavec test spam cleanup Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fix for bad conv3d test Signed-off-by: AlexDBlack <blacka101@gmail.com> * Additional test Signed-off-by: AlexDBlack <blacka101@gmail.com> * Embedding layers: don't inherit global default activation function Signed-off-by: AlexDBlack <blacka101@gmail.com> * Trigger CI Signed-off-by: AlexDBlack <blacka101@gmail.com> * Consolidate all BaseDL4JTest classes to single class used everywhere; make timeout configurable per class Signed-off-by: AlexDBlack <blacka101@gmail.com> * Test fixes and timeout increases Signed-off-by: AlexDBlack <blacka101@gmail.com> * Timeouts and PReLU fixes Signed-off-by: AlexDBlack <blacka101@gmail.com> * Restore libnd4j build threads arg for CUDA build Signed-off-by: AlexDBlack <blacka101@gmail.com> * Increase timeouts on a few tests to avoid spurious failures on some CI machines Signed-off-by: AlexDBlack <blacka101@gmail.com> * More timeout fixes Signed-off-by: AlexDBlack <blacka101@gmail.com> * More test timeout fixes Signed-off-by: AlexDBlack <blacka101@gmail.com> * Tweak timeout for one more test Signed-off-by: AlexDBlack <blacka101@gmail.com> * Final tweaks Signed-off-by: AlexDBlack <blacka101@gmail.com> * One more ignore Signed-off-by: AlexDBlack <blacka101@gmail.com>
2020-01-04 03:45:07 +01:00
//nd4j_printf("Sum: %lld\n", sumt)
output = (sumt > -1);
2019-06-06 14:21:15 +02:00
}
void compare_elem(nd4j::LaunchContext * context, NDArray *input, bool isStrictlyIncreasing, bool& output) {
auto xType = input->dataType();
BUILD_SINGLE_SELECTOR(xType, _compare_elem, (input, isStrictlyIncreasing, output), LIBND4J_TYPES);
}
BUILD_SINGLE_TEMPLATE(template void _compare_elem, (NDArray *A, bool isStrictlyIncreasing, bool& output);, LIBND4J_TYPES);
}
}
}