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

147 lines
5.2 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
******************************************************************************/
//
// Created by raver119 on 13.10.2017.
//
#include "ops/declarable/BooleanOp.h"
#include <vector>
#include <initializer_list>
#include <NDArrayFactory.h>
namespace nd4j {
namespace ops {
BooleanOp::BooleanOp(const char *name, int numInputs, bool scalar) : DeclarableOp::DeclarableOp(name, numInputs, scalar) {
//
}
BooleanOp::~BooleanOp() {
//
}
/**
* Output shape of any BooleanOp is ALWAYS scalar
*/
ShapeList *BooleanOp::calculateOutputShape(ShapeList *inputShape, nd4j::graph::Context &block) {
return SHAPELIST(ConstantShapeHelper::getInstance()->scalarShapeInfo(DataType::BOOL));
}
bool BooleanOp::evaluate(nd4j::graph::Context &block) {
// check if scalar or not
// validation?
Nd4jStatus status = this->validateNonEmptyInput(block);
if (status != ND4J_STATUS_OK) {
nd4j_printf("Inputs should be not empty for BooleanOps","");
throw std::runtime_error("Bad inputs");
}
status = this->validateAndExecute(block);
if (status == ND4J_STATUS_TRUE)
return true;
else if (status == ND4J_STATUS_FALSE)
return false;
else {
nd4j_printf("Got error %i during [%s] evaluation: ", (int) status, this->getOpDescriptor()->getOpName()->c_str());
throw std::runtime_error("Internal error");
}
}
bool BooleanOp::evaluate(std::initializer_list<nd4j::NDArray *> args) {
std::vector<nd4j::NDArray *> vec(args);
return this->evaluate(vec);
}
bool BooleanOp::prepareOutputs(Context& ctx) {
auto variableSpace = ctx.getVariableSpace();
if (ctx.isFastPath())
return true;
for (int e = 0; e < this->getOpDescriptor()->getNumberOfOutputs(); e++) {
std::pair<int, int> pair(ctx.nodeId(), e);
if (!variableSpace->hasVariable(pair))
variableSpace->putVariable(pair, new Variable());
auto var = ctx.variable(pair);
if (!var->hasNDArray()) {
var->setNDArray(NDArrayFactory::create_<bool>(false, ctx.launchContext()));
var->markRemovable(true);
}
}
return true;
}
Nd4jStatus nd4j::ops::BooleanOp::execute(Context* block) {
// basic validation: ensure inputs are set
REQUIRE_OK(this->validateNonEmptyInput(*block));
// ensure number of IArgs, TArgs match our expectations
REQUIRE_OK(this->validateArguments(*block));
// this method will allocate output NDArrays for this op
this->prepareOutputs(*block);
auto timeStart = std::chrono::system_clock::now();
Nd4jStatus status = this->validateAndExecute(*block);
auto timeEnd = std::chrono::system_clock::now();
auto outerTime = std::chrono::duration_cast<std::chrono::nanoseconds> (timeEnd - timeStart).count();
block->setInnerTime(outerTime);
// basically we're should be putting 0.0 as FALSE, and any non-0.0 value will be treated as TRUE
std::pair<int,int> p(block->nodeId(), 0);
auto var = block->isFastPath() ? block->fastpath_out()[0] : block->variable(p)->getNDArray();
var->p(Nd4jLong(0), status == ND4J_STATUS_TRUE ? 1.0f : 0.0f);
// for CPU backend that's nop, but for CUDA-like archs this will update special buffer
var->syncToDevice();
if (status == ND4J_STATUS_FALSE || status == ND4J_STATUS_TRUE)
return ND4J_STATUS_OK;
nd4j_printf("%s: node_%i got unexpected result instead of boolean: [%i]\n", this->getOpName()->c_str(), block->nodeId(), status);
return ND4J_STATUS_KERNEL_FAILURE;
}
bool BooleanOp::evaluate(std::vector<nd4j::NDArray *> &args) {
VariableSpace variableSpace;
int cnt = -1;
std::vector<int> in;
for (auto v: args) {
auto var = new Variable(v);
var->markRemovable(false);
in.push_back(cnt);
variableSpace.putVariable(cnt--, var);
}
Context block(1, &variableSpace, false);
block.fillInputs(in);
return this->evaluate(block);
}
}
}