LBANN  0.103.0
LivermoreBigArtificialNeuralNetworkToolkit
hang.hpp
Go to the documentation of this file.
1 // Copyright (c) 2014-2023, Lawrence Livermore National Security, LLC.
3 // Produced at the Lawrence Livermore National Laboratory.
4 // Written by the LBANN Research Team (B. Van Essen, et al.) listed in
5 // the CONTRIBUTORS file. <lbann-dev@llnl.gov>
6 //
7 // LLNL-CODE-697807.
8 // All rights reserved.
9 //
10 // This file is part of LBANN: Livermore Big Artificial Neural Network
11 // Toolkit. For details, see http://software.llnl.gov/LBANN or
12 // https://github.com/LLNL/LBANN.
13 //
14 // Licensed under the Apache License, Version 2.0 (the "Licensee"); you
15 // may not use this file except in compliance with the License. You may
16 // obtain a copy of the License at:
17 //
18 // http://www.apache.org/licenses/LICENSE-2.0
19 //
20 // Unless required by applicable law or agreed to in writing, software
21 // distributed under the License is distributed on an "AS IS" BASIS,
22 // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
23 // implied. See the License for the specific language governing
24 // permissions and limitations under the license.
25 //
26 // hang .hpp .cpp - Callback to hang LBANN for debuggers
28 
29 #ifndef LBANN_CALLBACKS_CALLBACK_HANG_HPP_INCLUDED
30 #define LBANN_CALLBACKS_CALLBACK_HANG_HPP_INCLUDED
31 
33 
34 namespace lbann {
35 namespace callback {
36 
43 class hang : public callback_base
44 {
45 public:
49  hang(int rank_to_hang = -1) : m_rank_to_hang(rank_to_hang) {}
50  hang(const hang&) = default;
51  hang& operator=(const hang&) = default;
52  hang* copy() const override { return new hang(*this); }
53 
54  void setup(model* m) override;
55 
57  void on_train_begin(model* m) override;
58  std::string name() const override { return "hang"; }
59 
61 
64  template <class Archive>
65  void serialize(Archive& ar);
66 
68 
69 private:
71  void write_specific_proto(lbann_data::Callback& proto) const final;
72 
75 };
76 
77 // Builder function
78 std::unique_ptr<callback_base>
79 build_hang_callback_from_pbuf(const google::protobuf::Message&,
80  std::shared_ptr<lbann_summary> const&);
81 
82 } // namespace callback
83 } // namespace lbann
84 
85 #endif // LBANN_CALLBACKS_CALLBACK_HANG_HPP_INCLUDED
int m_rank_to_hang
The rank that will hang; -1 for every rank.
Definition: hang.hpp:74
void on_train_begin(model *m) override
Hang on train begin.
void write_specific_proto(lbann_data::Callback &proto) const final
Base class for callbacks during training/testing.
Definition: callback.hpp:76
Abstract base class for neural network models.
Definition: model.hpp:83
void serialize(Archive &ar)
Store state to archive for checkpoint and restart.
void setup(model *m) override
Called once to set up the callback on the model (after all layers are set up).
hang & operator=(const hang &)=default
std::unique_ptr< callback_base > build_hang_callback_from_pbuf(const google::protobuf::Message &, std::shared_ptr< lbann_summary > const &)
std::string name() const override
Return this callback&#39;s name.
Definition: hang.hpp:58
hang * copy() const override
Definition: hang.hpp:52
hang(int rank_to_hang=-1)
Definition: hang.hpp:49