cavis/libnd4j/tests_cpu/layers_tests/ServerRelatedTests.cpp
raver119 3c4e959e21 [WIP] More of CUDA (#95)
* initial commit

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

* Implementation of hashcode cuda helper. Working edition.

* Fixed parallel test input arangements.

* Fixed tests for hashcode op.

* Fixed shape calculation for image:crop_and_resize op and test.

* NativeOps tests. Initial test suite.

* Added tests for indexReduce methods.

* Added test on execBroadcast with NDArray as dimensions.

* Added test on execBroadcastBool with NDArray as dimensions.

* Added tests on execPairwiseTransform and execPairwiseTransofrmBool.

* Added tests for execReduce with scalar results.

* Added reduce tests for non-empty dims array.

* Added tests for reduce3.

* Added tests for execScalar.

* Added tests for execSummaryStats.

* - provide cpu/cuda code for batch_to_space
- testing it

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

* - remove old test for batch_to_space (had wrong format and numbers were not checked)

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

* Fixed complilation errors with test.

* Added test for execTransformFloat.

* Added test for execTransformSame.

* Added test for execTransformBool.

* Added test for execTransformStrict.

* Added tests for execScalar/execScalarBool with TADs.

* Added test for flatten.

* - provide cpu/cuda code for space_to_Batch operaion

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

* Added test for concat.

* comment unnecessary stuff in s_t_b

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

* Added test for specialConcat.

* Added tests for memcpy/set routines.

* Fixed pullRow cuda test.

* Added pullRow test.

* Added average test.

* - correct typo in NDArray::applyPairwiseTransform(nd4j::pairwise::BoolOps op...)

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

* - debugging and fixing cuda tests in JavaInteropTests file

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

* - correct some tests

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

* Added test for shuffle.

* Fixed ops declarations.

* Restored omp and added shuffle test.

* Added convertTypes test.

* Added tests for execRandom. Eliminated usage of RandomBuffer with NativeOps.

* Added sort tests.

* Added tests for execCustomOp.

* - further debuging and fixing tests terminated with crash

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

* Added tests for calculateOutputShapes.

* Addded Benchmarks test.

* Commented benchmark tests.

* change assertion

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

* Added tests for apply_sgd op. Added cpu helper for that op.

* Implement cuda helper for aplly_sgd op. Fixed tests for NativeOps.

* Added test for assign broadcastable.

* Added tests for assign_bp op.

* Added tests for axpy op.

* - assign/execScalar/execTransformAny signature change
- minor test fix

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

* Fixed axpy op.

* meh

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

* - fix tests for nativeOps::concat

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

* sequential transform/scalar

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

* allow nested parallelism

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

* assign_bp leak fix

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

* block setRNG fix

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

* enable parallelism by default

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

* enable nested parallelism by default

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

* Added cuda implementation for row_count helper.

* Added implementation for tnse gains op helper.

* - take into account possible situations when input arrays are empty in reduce_ cuda stuff

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

* Implemented tsne/edge_forces op cuda-based helper. Parallelized cpu-based helper for edge_forces.

* Added kernel for tsne/symmetrized op heleper.

* Implementation of tsne/symmetrized op cuda helper. Working edition.

* Eliminated waste printfs.

* Added test for broadcastgradientargs op.

* host-only fallback for empty reduce float

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

* - some tests fixes

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

* - correct the rest of reduce_ stuff

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

* - further correction of reduce_ stuff

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

* Added test for Cbow op. Also added cuda implementation for cbow helpers.

* - improve code of stack operation for scalar case

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

* - provide cuda kernel for gatherND operation

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

* Implementation of cbow helpers with cuda kernels.

* minor tests tweaks

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

* minor tests tweaks

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

* - further correction of cuda stuff

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

* Implementatation of cbow op helper with cuda kernels. Working edition.

* Skip random testing for cudablas case.

* lstmBlockCell context fix

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

* Added tests for ELU and ELU_BP ops.

* Added tests for eq_scalar, gt_scalar, gte_scalar and lte_scalar ops.

* Added tests for neq_scalar.

* Added test for noop.

* - further work on clipbynorm_bp

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

* - get rid of concat op call, use instead direct concat helper call

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

* lstmBlockCell context fix

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

* Added tests for lrelu and lrelu_bp.

* Added tests for selu and selu_bp.

* Fixed lrelu derivative helpers.

* - some corrections in lstm

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

* operator * result shape fix

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

* - correct typo in lstmCell

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

* few tests fixed

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

* CUDA inverse broadcast bool fix

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

* disable MMAP test for CUDA

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

* BooleanOp syncToDevice

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

* meh

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

* additional data types for im2col/col2im

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

* Added test for firas_sparse op.

* one more RandomBuffer test excluded

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

* Added tests for flatten op.

* Added test for Floor op.

* bunch of tests fixed

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

* mmulDot tests fixed

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

* more tests fixed

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

* Implemented floordiv_bp op and tests.

* Fixed scalar case with cuda implementation for bds.

* - work on cuda kernel for clip_by_norm backprop op is completed

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

* Eliminate cbow crach.

* more tests fixed

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

* more tests fixed

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

* Eliminated abortion with batched nlp test.

* more tests fixed

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

* Fixed shared flag initializing.

* disabled bunch of cpu workspaces tests

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

* scalar operators fix: missing registerSpecialUse call

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

* Fixed logdet for cuda and tests.

* - correct clipBynorm_bp

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

* Fixed crop_and_resize shape datatype.

* - correct some mmul tests

Signed-off-by: Yurii <yurii@skymind.io>
2019-08-05 11:27:05 +10:00

189 lines
6.1 KiB
C++

/*******************************************************************************
* 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 <GraphExecutioner.h>
#include <graph/GraphHolder.h>
#include <graph/InferenceRequest.h>
using namespace nd4j;
using namespace nd4j::graph;
class ServerRelatedTests : public testing::Test {
public:
ServerRelatedTests() {
Environment::getInstance()->setDebug(true);
Environment::getInstance()->setVerbose(true);
}
~ServerRelatedTests() {
Environment::getInstance()->setDebug(false);
Environment::getInstance()->setVerbose(false);
}
};
/*
TEST_F(ServerRelatedTests, Basic_Output_Test_1) {
flatbuffers::FlatBufferBuilder builder(4096);
auto array1 = NDArrayFactory::create_<float>('c', {10, 10});
auto array2 = NDArrayFactory::create_<float>('c', {10, 10});
auto array3 = NDArrayFactory::create_<float>('c', {10, 10});
array1->assign(1.0f);
array2->assign(2.0f);
array3->assign(3.0f);
Variable var1(array1, "first", 1);
Variable var2(array2, "second", 2);
Variable var3(array3, "second indexed", 2, 1);
ExecutionResult result({&var1, &var2, &var3});
ASSERT_EQ(*array1, *result.at(0)->getNDArray());
ASSERT_EQ(*array2, *result.at(1)->getNDArray());
ASSERT_EQ(*array3, *result.at(2)->getNDArray());
ASSERT_EQ(*array1, *result.byId("first")->getNDArray());
ASSERT_EQ(*array2, *result.byId("second")->getNDArray());
ASSERT_EQ(*array3, *result.byId("second indexed")->getNDArray());
auto flatResult = result.asFlatResult(builder);
builder.Finish(flatResult);
auto ptr = builder.GetBufferPointer();
auto received = GetFlatResult(ptr);
ExecutionResult restored(received);
ASSERT_EQ(3, restored.size());
ASSERT_EQ(*array1, *restored.at(0)->getNDArray());
ASSERT_EQ(*array2, *restored.at(1)->getNDArray());
ASSERT_EQ(*array3, *restored.at(2)->getNDArray());
ASSERT_EQ(*array1, *restored.byId("first")->getNDArray());
ASSERT_EQ(*array2, *restored.byId("second")->getNDArray());
ASSERT_EQ(*array3, *restored.byId("second indexed")->getNDArray());
}
*/
#if GRAPH_FILES_OK
TEST_F(ServerRelatedTests, Basic_Execution_Test_1) {
flatbuffers::FlatBufferBuilder builder(4096);
auto oGraph = GraphExecutioner::importFromFlatBuffers("./resources/reduce_dim_false.fb");
oGraph->printOut();
auto exp = NDArrayFactory::create<float>('c', {3}, {3.f, 3.f, 3.f});
GraphHolder::getInstance()->registerGraph(11901L, oGraph);
auto cGraph = GraphHolder::getInstance()->cloneGraph(11901L);
ASSERT_TRUE(oGraph != cGraph);
auto flatResult = GraphExecutioner::execute(cGraph, builder, nullptr);
builder.Finish(flatResult);
auto ptr = builder.GetBufferPointer();
auto received = GetFlatResult(ptr);
ExecutionResult restored(received);
ASSERT_EQ(1, restored.size());
ASSERT_EQ(exp, *restored.at(0)->getNDArray());
delete cGraph;
GraphHolder::getInstance()->dropGraphAny(11901L);
}
TEST_F(ServerRelatedTests, Basic_Execution_Test_2) {
flatbuffers::FlatBufferBuilder builder(4096);
flatbuffers::FlatBufferBuilder otherBuilder(4096);
auto oGraph = GraphExecutioner::importFromFlatBuffers("./resources/reduce_dim_false.fb");
oGraph->printOut();
auto input0 = NDArrayFactory::create<float>('c', {3, 3}, {2.f,2.f,2.f, 2.f,2.f,2.f, 2.f,2.f,2.f});
auto exp = NDArrayFactory::create<float>('c', {3}, {6.f, 6.f, 6.f});
GraphHolder::getInstance()->registerGraph(11902L, oGraph);
auto cGraph = GraphHolder::getInstance()->cloneGraph(11902L);
ASSERT_TRUE(oGraph != cGraph);
// mastering InferenceRequest
InferenceRequest ir(11902L);
ir.appendVariable(1, 0, &input0);
auto af = ir.asFlatInferenceRequest(otherBuilder);
otherBuilder.Finish(af);
auto fptr = otherBuilder.GetBufferPointer();
auto fir = GetFlatInferenceRequest(fptr);
auto flatResult = GraphExecutioner::execute(cGraph, builder, fir);
builder.Finish(flatResult);
auto ptr = builder.GetBufferPointer();
auto received = GetFlatResult(ptr);
ExecutionResult restored(received);
ASSERT_EQ(1, restored.size());
ASSERT_EQ(exp, *restored.at(0)->getNDArray());
delete cGraph;
GraphHolder::getInstance()->dropGraphAny(11902L);
}
TEST_F(ServerRelatedTests, BasicExecutionTests_3) {
flatbuffers::FlatBufferBuilder builder(4096);
flatbuffers::FlatBufferBuilder otherBuilder(4096);
auto oGraph = GraphExecutioner::importFromFlatBuffers("./resources/reduce_dim_false.fb");
oGraph->printOut();
auto input0 = NDArrayFactory::create<float>('c', {3, 3}, {2.f,2.f,2.f, 2.f,2.f,2.f, 2.f,2.f,2.f});
auto exp = NDArrayFactory::create<float>('c', {3}, {6.f, 6.f, 6.f});
GraphHolder::getInstance()->registerGraph(11903L, oGraph);
// mastering InferenceRequest
InferenceRequest ir(11903L);
ir.appendVariable(1, 0, &input0);
auto af = ir.asFlatInferenceRequest(otherBuilder);
otherBuilder.Finish(af);
auto fptr = otherBuilder.GetBufferPointer();
auto fir = GetFlatInferenceRequest(fptr);
auto flatResult = GraphHolder::getInstance()->execute(fir->id(), builder, fir);
builder.Finish(flatResult);
auto ptr = builder.GetBufferPointer();
auto received = GetFlatResult(ptr);
ExecutionResult restored(received);
ASSERT_EQ(1, restored.size());
ASSERT_EQ(exp, *restored.at(0)->getNDArray());
GraphHolder::getInstance()->dropGraphAny(11903L);
}
#endif