cavis/libnd4j/tests_cpu/layers_tests/SortCudaTests.cu
raver119 763a225c6a [WIP] More of CUDA operations (#69)
* initial commit

Signed-off-by: raver119 <raver119@gmail.com>

* - gruCell_bp further

Signed-off-by: Yurii <yurii@skymind.io>

* - further work on gruCell_bp

Signed-off-by: Yurii <yurii@skymind.io>

* Inverse matrix cublas implementation. Partial working revision.

* Separation of segment ops helpers. Max separation.

* Separated segment_min ops.

* Separation of segment_mean/sum/prod/sqrtN ops heleprs.

* Fixed diagonal processing with LUP decomposition.

* Modified inversion approach using current state of LU decomposition.

* Implementation of matrix_inverse op with cuda kernels. Working revision.

* Implemented sequence_mask cuda helper. Eliminated waste printf with matrix_inverse implementation. Added proper tests.

* - further work on gruCell_bp (ff/cuda)

Signed-off-by: Yurii <yurii@skymind.io>

* comment one test for gruCell_bp

Signed-off-by: Yurii <yurii@skymind.io>

* - provide cuda static_rnn

Signed-off-by: Yurii <yurii@skymind.io>

* Refactored random_shuffle op to use new random generator.

* Refactored random_shuffle op helper.

* Fixed debug tests with random ops tests.

* Implement random_shuffle op cuda kernel helper and tests.

* - provide cuda scatter_update

Signed-off-by: Yurii <yurii@skymind.io>

* Implementation of random_shuffle for linear case with cuda kernels and tests.

* Implemented random_shuffle with cuda kernels. Final revision.

* - finally gruCell_bp is completed

Signed-off-by: Yurii <yurii@skymind.io>

* Dropout op cuda helper implementation.

* Implemented dropout_bp cuda helper.

* Implemented alpha_dropout_bp with cuda kernel helpers.

* Refactored helper.

* Implementation of suppresion helper with cuda kernels.

* - provide cpu code fot hsvToRgb, rgbToHsv, adjustHue

Signed-off-by: Yurii <yurii@skymind.io>

* Using sort by value method.

* Implementation of image.non_max_suppression op cuda-based helper.

* - correcting and testing adjust_hue, adjust_saturation cpu/cuda code

Signed-off-by: Yurii <yurii@skymind.io>

* Added cuda device prefixes to declarations.

* Implementation of hashcode op with cuda helper. Initital revision.

* rnn cu impl removed

Signed-off-by: raver119 <raver119@gmail.com>
2019-07-20 23:20:41 +10:00

129 lines
5.7 KiB
Plaintext

/*******************************************************************************
* 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
//
#include "testlayers.h"
#include <ops/declarable/CustomOperations.h>
#include <NDArray.h>
#include <NativeOps.h>
#include <helpers/BitwiseUtils.h>
using namespace nd4j;
using namespace nd4j::graph;
class SortCudaTests : public testing::Test {
public:
};
TEST_F(SortCudaTests, test_linear_sort_by_key_1) {
auto k = NDArrayFactory::create<Nd4jLong>('c', {10}, {1, 3, 5, 9, 0, 2, 4, 6, 7, 8});
auto v = NDArrayFactory::create<double>('c', {10}, {1.5, 3.5, 5.5, 9.5, 0.5, 2.5, 4.5, 6.5, 7.5, 8.5});
auto ek = NDArrayFactory::create<Nd4jLong>('c', {10}, {0, 1, 2, 3, 4, 5, 6, 7, 8, 9});
auto ev = NDArrayFactory::create<double>('c', {10}, {0.5, 1.5, 2.5, 3.5, 4.5, 5.5, 6.5, 7.5, 8.5, 9.5});
Nd4jPointer extras[2] = {nullptr, LaunchContext::defaultContext()->getCudaStream()};
NativeOps nativeOps;
nativeOps.sortByKey(extras, k.buffer(), k.shapeInfo(), k.specialBuffer(), k.specialShapeInfo(), v.buffer(), v.shapeInfo(), v.specialBuffer(), v.specialShapeInfo(), false);
k.tickWriteDevice();
v.tickWriteDevice();
ASSERT_EQ(ek, k);
ASSERT_EQ(ev, v);
}
TEST_F(SortCudaTests, test_linear_sort_by_val_1) {
auto k = NDArrayFactory::create<Nd4jLong>('c', {10}, {1, 3, 5, 9, 0, 2, 4, 6, 7, 8});
auto v = NDArrayFactory::create<double>('c', {10}, {1.5, 3.5, 5.5, 9.5, 0.5, 2.5, 4.5, 6.5, 7.5, 8.5});
auto ek = NDArrayFactory::create<Nd4jLong>('c', {10}, {0, 1, 2, 3, 4, 5, 6, 7, 8, 9});
auto ev = NDArrayFactory::create<double>('c', {10}, {0.5, 1.5, 2.5, 3.5, 4.5, 5.5, 6.5, 7.5, 8.5, 9.5});
Nd4jPointer extras[2] = {nullptr, LaunchContext::defaultContext()->getCudaStream()};
NativeOps nativeOps;
nativeOps.sortByValue(extras, k.buffer(), k.shapeInfo(), k.specialBuffer(), k.specialShapeInfo(), v.buffer(), v.shapeInfo(), v.specialBuffer(), v.specialShapeInfo(), false);
k.tickWriteDevice();
v.tickWriteDevice();
ASSERT_EQ(ek, k);
ASSERT_EQ(ev, v);
}
TEST_F(SortCudaTests, test_linear_sort_by_val_2) {
auto k = NDArrayFactory::create<int>('c', {6}, {0, 1, 2, 3, 4, 5});
// auto v = NDArrayFactory::create<double>('c', {6}, {1.5, 3.5, 5.5, 9.5, 0.5, 2.5, 4.5, 6.5, 7.5, 8.5});
NDArray v = NDArrayFactory::create<double>('c', {6}, {0.9f, .75f, .6f, .95f, .5f, .3f});
auto ek = NDArrayFactory::create<int>('c', {6}, {3, 0, 1, 2, 4, 5});
auto ev = NDArrayFactory::create<double>('c', {6}, {0.95, 0.9, 0.75, 0.6, 0.5, 0.3});
Nd4jPointer extras[2] = {nullptr, LaunchContext::defaultContext()->getCudaStream()};
NativeOps nativeOps;
nativeOps.sortByValue(extras, k.buffer(), k.shapeInfo(), k.specialBuffer(), k.specialShapeInfo(), v.buffer(), v.shapeInfo(), v.specialBuffer(), v.specialShapeInfo(), true);
k.tickWriteDevice();
v.tickWriteDevice();
k.printIndexedBuffer("KEYS");
ASSERT_EQ(ek, k);
ASSERT_EQ(ev, v);
}
TEST_F(SortCudaTests, test_tad_sort_by_key_1) {
auto k = NDArrayFactory::create<Nd4jLong>('c', {2, 10}, {1, 3, 5, 9, 0, 2, 4, 6, 7, 8, 1, 3, 5, 9, 0, 2, 4, 6, 7, 8});
auto v = NDArrayFactory::create<double>('c', {2, 10}, {1.5, 3.5, 5.5, 9.5, 0.5, 2.5, 4.5, 6.5, 7.5, 8.5, 1.5, 3.5, 5.5, 9.5, 0.5, 2.5, 4.5, 6.5, 7.5, 8.5});
auto ek = NDArrayFactory::create<Nd4jLong>('c', {2, 10}, {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9});
auto ev = NDArrayFactory::create<double>('c', {2, 10}, {0.5, 1.5, 2.5, 3.5, 4.5, 5.5, 6.5, 7.5, 8.5, 9.5, 0.5, 1.5, 2.5, 3.5, 4.5, 5.5, 6.5, 7.5, 8.5, 9.5});
Nd4jPointer extras[2] = {nullptr, LaunchContext::defaultContext()->getCudaStream()};
int axis = 1;
NativeOps nativeOps;
nativeOps.sortTadByKey(extras, k.buffer(), k.shapeInfo(), k.specialBuffer(), k.specialShapeInfo(), v.buffer(), v.shapeInfo(), v.specialBuffer(), v.specialShapeInfo(), &axis, 1, false);
k.tickWriteDevice();
v.tickWriteDevice();
k.printIndexedBuffer("k");
v.printIndexedBuffer("v");
ASSERT_EQ(ek, k);
ASSERT_EQ(ev, v);
}
TEST_F(SortCudaTests, test_tad_sort_by_val_1) {
auto k = NDArrayFactory::create<Nd4jLong>('c', {2, 10}, {1, 3, 5, 9, 0, 2, 4, 6, 7, 8, 1, 3, 5, 9, 0, 2, 4, 6, 7, 8});
auto v = NDArrayFactory::create<double>('c', {2, 10}, {1.5, 3.5, 5.5, 9.5, 0.5, 2.5, 4.5, 6.5, 7.5, 8.5, 1.5, 3.5, 5.5, 9.5, 0.5, 2.5, 4.5, 6.5, 7.5, 8.5});
auto ek = NDArrayFactory::create<Nd4jLong>('c', {2, 10}, {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9});
auto ev = NDArrayFactory::create<double>('c', {2, 10}, {0.5, 1.5, 2.5, 3.5, 4.5, 5.5, 6.5, 7.5, 8.5, 9.5, 0.5, 1.5, 2.5, 3.5, 4.5, 5.5, 6.5, 7.5, 8.5, 9.5});
Nd4jPointer extras[2] = {nullptr, LaunchContext::defaultContext()->getCudaStream()};
int axis = 1;
NativeOps nativeOps;
nativeOps.sortTadByValue(extras, k.buffer(), k.shapeInfo(), k.specialBuffer(), k.specialShapeInfo(), v.buffer(), v.shapeInfo(), v.specialBuffer(), v.specialShapeInfo(), &axis, 1, false);
k.tickWriteDevice();
v.tickWriteDevice();
ASSERT_EQ(ek, k);
ASSERT_EQ(ev, v);
}