cavis/libnd4j/blas/Environment.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

202 lines
5.1 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
******************************************************************************/
//
// Created by raver119 on 06.10.2017.
//
#include <iostream>
#include <cstdlib>
#include <stdexcept>
#include <string>
#include "Environment.h"
#include <helpers/StringUtils.h>
#ifdef _OPENMP
#include <omp.h>
#endif
#ifdef __CUDABLAS__
#include <cuda.h>
#include <cuda_runtime.h>
#endif
namespace nd4j {
nd4j::Environment::Environment() {
_tadThreshold.store(8);
_elementThreshold.store(1024);
_verbose.store(false);
_debug.store(false);
_profile.store(false);
_precBoost.store(false);
_leaks.store(false);
_dataType.store(nd4j::DataType::FLOAT32);
#ifndef ANDROID
const char* omp_threads = std::getenv("OMP_NUM_THREADS");
if (omp_threads != nullptr) {
try {
std::string omp(omp_threads);
int val = std::stoi(omp);
_maxThreads.store(val);
} catch (std::invalid_argument &e) {
// just do nothing
} catch (std::out_of_range &e) {
// still do nothing
}
}
#endif
#ifdef __CUDABLAS__
int devCnt = 0;
cudaGetDeviceCount(&devCnt);
auto devProperties = new cudaDeviceProp[devCnt];
for (int i = 0; i < devCnt; i++) {
cudaSetDevice(i);
cudaGetDeviceProperties(&devProperties[i], i);
//cudaDeviceSetLimit(cudaLimitStackSize, 4096);
Pair p(devProperties[i].major, devProperties[i].minor);
_capabilities.emplace_back(p);
printf("CUDA device %i: [%s]; cc: [%i.%i]; Total memory: [%lld];\n", i, devProperties[i].name, devProperties[i].major, devProperties[i].minor, (Nd4jLong) devProperties[i].totalGlobalMem);
}
fflush(stdout);
cudaSetDevice(0);
delete[] devProperties;
#else
#ifdef _OPENMP
omp_set_nested(1);
#endif
#endif
}
nd4j::Environment::~Environment() {
//
}
Environment *Environment::getInstance() {
if (_instance == 0)
_instance = new Environment();
return _instance;
}
bool Environment::isVerbose() {
return _verbose.load();
}
bool Environment::isExperimentalBuild() {
return _experimental;
}
nd4j::DataType Environment::defaultFloatDataType() {
return _dataType.load();
}
std::vector<Pair>& Environment::capabilities() {
return _capabilities;
}
void Environment::setDefaultFloatDataType(nd4j::DataType dtype) {
if (dtype != nd4j::DataType::FLOAT32 && dtype != nd4j::DataType::DOUBLE && dtype != nd4j::DataType::FLOAT8 && dtype != nd4j::DataType::HALF)
throw std::runtime_error("Default Float data type must be one of [FLOAT8, FLOAT16, FLOAT32, DOUBLE]");
_dataType.store(dtype);
}
void Environment::setVerbose(bool reallyVerbose) {
_verbose = reallyVerbose;
}
bool Environment::isDebug() {
return _debug.load();
}
bool Environment::isProfiling() {
return _profile.load();
}
bool Environment::isDetectingLeaks() {
return _leaks.load();
}
void Environment::setLeaksDetector(bool reallyDetect) {
_leaks.store(reallyDetect);
}
void Environment::setProfiling(bool reallyProfile) {
_profile.store(reallyProfile);
}
bool Environment::isDebugAndVerbose() {
return this->isDebug() && this->isVerbose();
}
void Environment::setDebug(bool reallyDebug) {
_debug = reallyDebug;
}
int Environment::tadThreshold() {
return _tadThreshold.load();
}
void Environment::setTadThreshold(int threshold) {
_tadThreshold = threshold;
}
int Environment::elementwiseThreshold() {
return _elementThreshold.load();
}
void Environment::setElementwiseThreshold(int threshold) {
_elementThreshold = threshold;
}
int Environment::maxThreads() {
return _maxThreads.load();
}
void Environment::setMaxThreads(int max) {
_maxThreads.store(max);
}
bool Environment::precisionBoostAllowed() {
return _precBoost.load();
}
void Environment::allowPrecisionBoost(bool reallyAllow) {
_precBoost.store(reallyAllow);
}
bool Environment::isCPU() {
#ifdef __CUDABLAS__
return false;
#else
return true;
#endif
}
nd4j::Environment *nd4j::Environment::_instance = 0;
}