* platform helpers draft Signed-off-by: raver119 <raver119@gmail.com> * typo Signed-off-by: raver119 <raver119@gmail.com> * disable platform cmake Signed-off-by: raver119 <raver119@gmail.com> * another draft Signed-off-by: raver119 <raver119@gmail.com> * mkldnn convolution refactored Signed-off-by: raver119 <raver119@gmail.com> * minor tweaks Signed-off-by: raver119 <raver119@gmail.com> * one more safety check Signed-off-by: raver119 <raver119@gmail.com> * prototype works Signed-off-by: raver119 <raver119@gmail.com> * meh Signed-off-by: raver119 <raver119@gmail.com> * force static library mode for mkldnn Signed-off-by: raver119 <raver119@gmail.com> * - ismax fix - experimental arg fix - don't enforce openblas on Apple hardware Signed-off-by: raver119 <raver119@gmail.com> * bunch of small fixes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * declare concurrent Signed-off-by: raver119@gmail.com <raver119@gmail.com> * - MKLDNN version upgrade to 1.0.2 - avgpool2d/maxpool2d APIs update Signed-off-by: raver119 <raver119@gmail.com> * - avgpool2d_bp/maxpool2d_bp APIs update Signed-off-by: raver119 <raver119@gmail.com> * - conv2d/batchnorm APIs update Signed-off-by: raver119 <raver119@gmail.com> * - lrn/conv2d_bp/conv3d/conv3d_bp APIs update Signed-off-by: raver119 <raver119@gmail.com> * all ops converted to MKLDNN 1.x Signed-off-by: raver119 <raver119@gmail.com> * bunch of tweaks Signed-off-by: raver119 <raver119@gmail.com> * namespace for platform helpers Signed-off-by: raver119 <raver119@gmail.com> * make sure platform helpers aren't opimized out Signed-off-by: raver119 <raver119@gmail.com> * build cpu_features on x86 systems Signed-off-by: raver119 <raver119@gmail.com> * build cpu_features on x86 systems Signed-off-by: raver119 <raver119@gmail.com> * more of cpu_features Signed-off-by: raver119 <raver119@gmail.com> * - mkldnn removed from java - cpu_features checks in CpuNDArrayFactory Signed-off-by: raver119 <raver119@gmail.com> * F16C definition renamed Signed-off-by: raver119 <raver119@gmail.com> * some mkldnn rearrangements Signed-off-by: raver119 <raver119@gmail.com> * check supported instructions before doing anything Signed-off-by: raver119 <raver119@gmail.com> * typo Signed-off-by: raver119 <raver119@gmail.com> * missied impl Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC option Signed-off-by: raver119 <raver119@gmail.com> * conv2d fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d_bp fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool2d_bp leak fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d_bp leak fix Signed-off-by: raver119 <raver119@gmail.com> * maxpool bp leaks fixed Signed-off-by: raver119 <raver119@gmail.com> * printf removed Signed-off-by: raver119 <raver119@gmail.com> * batchnorm fix Signed-off-by: raver119 <raver119@gmail.com> * AVX warning/error polishing Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fix Signed-off-by: AlexDBlack <blacka101@gmail.com> * More polish Signed-off-by: AlexDBlack <blacka101@gmail.com> * Polish Signed-off-by: AlexDBlack <blacka101@gmail.com> * remove previous MKL-DNN support layer Signed-off-by: raver119 <raver119@gmail.com> * avx2 tweak Signed-off-by: raver119 <raver119@gmail.com> * allow static for apple Signed-off-by: raver119@gmail.com <raver119@gmail.com> * exclude mkldnn in one more place Signed-off-by: raver119 <raver119@gmail.com> * exclude mkldnn in one more place Signed-off-by: raver119 <raver119@gmail.com> * restore OPENBLAS_PATH use Signed-off-by: raver119 <raver119@gmail.com> * add runtime check for avx/avx2 support Signed-off-by: raver119 <raver119@gmail.com> * convolution_auto Signed-off-by: raver119 <raver119@gmail.com> * Add logic for helper argument * minor test fix Signed-off-by: raver119 <raver119@gmail.com> * few tweaks Signed-off-by: raver119 <raver119@gmail.com> * few tweaks Signed-off-by: raver119 <raver119@gmail.com> * skip OpTracker props for non-x86 builds Signed-off-by: raver119 <raver119@gmail.com> * linux arm isn't x86 :) Signed-off-by: raver119 <raver119@gmail.com> * avx-512 Signed-off-by: raver119 <raver119@gmail.com> * CUDA presets fix Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC Signed-off-by: raver119 <raver119@gmail.com> * prefetchw for avx2 Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC again Signed-off-by: raver119 <raver119@gmail.com>
124 lines
3.6 KiB
C++
124 lines
3.6 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 <helpers/OpTracker.h>
|
|
#include <sstream>
|
|
#include <helpers/logger.h>
|
|
#include <NativeOps.h>
|
|
|
|
|
|
using namespace nd4j::ops;
|
|
using namespace nd4j::graph;
|
|
|
|
namespace nd4j {
|
|
|
|
OpTracker* OpTracker::getInstance() {
|
|
if (_INSTANCE == 0)
|
|
_INSTANCE = new OpTracker();
|
|
|
|
return _INSTANCE;
|
|
}
|
|
|
|
void OpTracker::storeOperation(nd4j::graph::OpType opType, const OpDescriptor& descriptor) {
|
|
// check out CPU features
|
|
if (!::isMinimalRequirementsMet()) {
|
|
|
|
auto binaryLevel = ::binaryLevel();
|
|
auto optimalLevel = ::optimalLevel();
|
|
|
|
switch (binaryLevel) {
|
|
case 3: {
|
|
nd4j_printf("libnd4j binary was built with AVX512 support, but current CPU doesn't have this instruction set. Exiting now...","");
|
|
}
|
|
break;
|
|
case 2: {
|
|
nd4j_printf("libnd4j binary was built with AVX/AVX2 support, but current CPU doesn't have this instruction set. Exiting now...","");
|
|
}
|
|
break;
|
|
default: {
|
|
nd4j_printf("Unknown binary validation error. Exiting now...","");
|
|
}
|
|
break;
|
|
}
|
|
|
|
// we're exiting now
|
|
exit(119);
|
|
}
|
|
//
|
|
if (_map.count(opType) < 1) {
|
|
std::vector<OpDescriptor> vec;
|
|
_map[opType] = vec;
|
|
}
|
|
|
|
_operations++;
|
|
|
|
auto vec = _map[opType];
|
|
|
|
if (std::find(vec.begin(), vec.end(), descriptor) == vec.end())
|
|
_map[opType].emplace_back(descriptor);
|
|
}
|
|
|
|
void OpTracker::storeOperation(nd4j::graph::OpType opType, const char* opName, const Nd4jLong opNum) {
|
|
OpDescriptor descriptor(0, opName, false);
|
|
descriptor.setOpNum((int) opNum);
|
|
descriptor.setHash(-1);
|
|
|
|
storeOperation(opType, descriptor);
|
|
}
|
|
|
|
|
|
template <typename T>
|
|
std::string OpTracker::local_to_string(T value) {
|
|
std::ostringstream os ;
|
|
os << value ;
|
|
return os.str() ;
|
|
}
|
|
|
|
|
|
int OpTracker::totalGroups() {
|
|
return (int) _map.size();
|
|
}
|
|
|
|
int OpTracker::totalOperations() {
|
|
return _operations;
|
|
}
|
|
|
|
const char* OpTracker::exportOperations() {
|
|
if (_export.length() == 0) {
|
|
for (auto &v: _map) {
|
|
std::string block = local_to_string(v.first) + " ";
|
|
|
|
for (auto &i: v.second) {
|
|
block += local_to_string(i.getHash()) + ":";
|
|
block += local_to_string(i.getOpNum()) + ":";
|
|
block += *i.getOpName() + "<<";
|
|
}
|
|
|
|
block += ">>";
|
|
_export += block;
|
|
}
|
|
}
|
|
|
|
return _export.c_str();
|
|
}
|
|
|
|
nd4j::OpTracker* nd4j::OpTracker::_INSTANCE = 0;
|
|
}
|