3de3cd8277
* one small test Signed-off-by: raver119 <raver119@gmail.com> * one small test Signed-off-by: raver119 <raver119@gmail.com> * bert test Signed-off-by: raver119 <raver119@gmail.com> * Graph FlowPath fix Signed-off-by: raver119 <raver119@gmail.com> * - GraphProfiler tweaks - NodeProfile now includes shapes Signed-off-by: raver119 <raver119@gmail.com> * RELU_layer inplace tweak Signed-off-by: raver119 <raver119@gmail.com> * meh Signed-off-by: raver119 <raver119@gmail.com> * identity tweaks Signed-off-by: raver119 <raver119@gmail.com> * bert result validation Signed-off-by: raver119 <raver119@gmail.com> * - bunch of Shape ops have inplace exec forbidden now - Legacy ops have inplace exec disabled by default now Signed-off-by: raver119 <raver119@gmail.com> * ffast-math enabled Signed-off-by: raver119 <raver119@gmail.com> * ffast-math enabled Signed-off-by: raver119 <raver119@gmail.com> * allow some legacy ops to be inplace Signed-off-by: raver119 <raver119@gmail.com> * disable -fast_math Signed-off-by: raver119 <raver119@gmail.com> * disable expensive test for cuda Signed-off-by: raver119 <raver119@gmail.com>
72 lines
2.2 KiB
C++
72 lines
2.2 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 21.02.18.
|
|
//
|
|
|
|
#include <graph/profiling/GraphProfilingHelper.h>
|
|
#include <GraphExecutioner.h>
|
|
|
|
namespace nd4j {
|
|
namespace graph {
|
|
GraphProfile *GraphProfilingHelper::profile(Graph *graph, int iterations) {
|
|
|
|
// saving original workspace
|
|
auto varSpace = graph->getVariableSpace()->clone();
|
|
|
|
// printing out graph structure
|
|
// graph->printOut();
|
|
|
|
// warm up
|
|
for (int e = 0; e < iterations; e++) {
|
|
FlowPath fp;
|
|
|
|
auto _vs = varSpace->clone();
|
|
//_vs->workspace()->expandTo(100000);
|
|
_vs->setFlowPath(&fp);
|
|
GraphExecutioner::execute(graph, _vs);
|
|
|
|
delete _vs;
|
|
}
|
|
|
|
|
|
auto profile = new GraphProfile();
|
|
for (int e = 0; e < iterations; e++) {
|
|
FlowPath fp;
|
|
|
|
// we're always starting from "fresh" varspace here
|
|
auto _vs = varSpace->clone();
|
|
//_vs->workspace()->expandTo(100000);
|
|
_vs->setFlowPath(&fp);
|
|
GraphExecutioner::execute(graph, _vs);
|
|
|
|
auto p = fp.profile();
|
|
if (e == 0)
|
|
profile->assign(p);
|
|
else
|
|
profile->merge(p);
|
|
|
|
delete _vs;
|
|
}
|
|
|
|
delete varSpace;
|
|
|
|
return profile;
|
|
}
|
|
}
|
|
}
|