FM / core

/usr/local/lib64/python3.6/site-packages/torch/include/caffe2/core/

/usr/local/lib64/python3.6/site-packages/torch/include/caffe2/core

Name	Size	Mode	Actions
allocator.h	136	0644	edit dl rm
blob.h	4168	0644	edit dl rm
blob_serialization.h	10791	0644	edit dl rm
blob_serializer_base.h	3905	0644	edit dl rm
blob_stats.h	1127	0644	edit dl rm
common.h	4329	0644	edit dl rm
common_cudnn.h	9893	0644	edit dl rm
common_gpu.h	21414	0644	edit dl rm
common_omp.h	156	0644	edit dl rm
context.h	6174	0644	edit dl rm
context_base.h	4382	0644	edit dl rm
context_gpu.h	11014	0644	edit dl rm
cudnn_wrappers.h	6956	0644	edit dl rm
db.h	9352	0644	edit dl rm
distributions_stubs.h	2161	0644	edit dl rm
event.h	12420	0644	edit dl rm
event_cpu.h	1192	0644	edit dl rm
export_c10_op_to_caffe2.h	9487	0644	edit dl rm
export_caffe2_op_to_c10.h	11101	0644	edit dl rm
flags.h	74	0644	edit dl rm
graph.h	5258	0644	edit dl rm
init.h	6496	0644	edit dl rm
logging.h	75	0644	edit dl rm
macros.h	3426	0644	edit dl rm
memonger.h	817	0644	edit dl rm
module.h	2473	0644	edit dl rm
net.h	4634	0644	edit dl rm
net_async_base.h	7397	0644	edit dl rm
net_async_scheduling.h	993	0644	edit dl rm
net_async_task.h	833	0644	edit dl rm
net_async_task_future.h	1925	0644	edit dl rm
net_async_task_graph.h	2253	0644	edit dl rm
net_async_tracing.h	5093	0644	edit dl rm
net_dag_utils.h	2146	0644	edit dl rm
net_parallel.h	2144	0644	edit dl rm
net_simple.h	2606	0644	edit dl rm
net_simple_refcount.h	2097	0644	edit dl rm
numa.h	72	0644	edit dl rm
observer.h	3809	0644	edit dl rm
operator.h	58872	0644	edit dl rm
operator_gradient.h	10222	0644	edit dl rm
operator_schema.h	18477	0644	edit dl rm
plan_executor.h	219	0644	edit dl rm
prof_dag_counters.h	2751	0644	edit dl rm
qtensor.h	6615	0644	edit dl rm
qtensor_serialization.h	2624	0644	edit dl rm
scope_guard.h	4675	0644	edit dl rm
static_tracepoint.h	398	0644	edit dl rm
static_tracepoint_elfx86.h	5555	0644	edit dl rm
stats.h	10365	0644	edit dl rm
storage.h	733	0644	edit dl rm
tensor.h	18668	0644	edit dl rm
tensor_impl.h	351	0644	edit dl rm
tensor_int8.h	450	0644	edit dl rm
test_utils.h	6285	0644	edit dl rm
timer.h	1218	0644	edit dl rm
transform.h	5741	0644	edit dl rm
types.h	2248	0644	edit dl rm
workspace.h	11305	0644	edit dl rm

Edit: /usr/local/lib64/python3.6/site-packages/torch/include/caffe2/core/net_dag_utils.h (2146B)

#ifndef CAFFE2_CORE_NET_DAG_UTILS_H_
#define CAFFE2_CORE_NET_DAG_UTILS_H_

#include <atomic>
#include <climits>
#include <cstddef>
#include <thread> // NOLINT
#include <typeinfo>
#include <unordered_map>
#include <unordered_set>
#include <vector>

#include "c10/util/Registry.h"
#include "caffe2/core/blob.h"
#include "caffe2/core/common.h"
#include "caffe2/core/logging.h"
#include "caffe2/core/net.h"
#include "caffe2/core/observer.h"
#include "caffe2/core/operator_schema.h"
#include "caffe2/core/tensor.h"
#include "caffe2/core/workspace.h"
#include "caffe2/proto/caffe2_pb.h"
#include "caffe2/utils/simple_queue.h"

namespace caffe2 {
namespace dag_utils {

struct OperatorNode {
  unique_ptr<OperatorBase> operator_;
  vector<int> children_;
  vector<int> parents_;
  std::atomic<int> runtime_parent_count_;
  bool is_chain_start_ = false;
  std::atomic_flag scheduled_ = ATOMIC_FLAG_INIT;
};

struct OpGraphNode {
  vector<int> children_;
  vector<int> parents_;
  int visited_inputs = 0;
  int num_orig_parents;
};

using ExecutionChains = std::unordered_map<int, std::vector<int>>;

C10_EXPORT ExecutionChains computeChains(std::vector<OperatorNode>& orig_nodes);

// Instead of breaking down the DAG into chains, we partition it into clusters
// of sync ops and individual async op. This is useful for disturbuted inference
// case where we have sync and async cpu ops. Note that we have go sync each
// aysnc op instead of put them into the chain and sync its tail like GPU op,
// because CPU async ops are typically rpc calls and are not guaranteed to be
// linearized at remote site.
C10_EXPORT ExecutionChains computeGroups(std::vector<OperatorNode>& orig_nodes);

C10_EXPORT ExecutionChains singleChains(std::vector<OperatorNode>& nodes);

C10_EXPORT std::vector<OperatorNode> prepareOperatorNodes(
    const std::shared_ptr<const NetDef>& net_def,
    Workspace* ws);

std::vector<OpGraphNode> prepareChainGraphNodes(
    const std::vector<dag_utils::OperatorNode>& operator_nodes,
    const std::vector<std::vector<int>>& execution_chains);

} // namespace dag_utils
} // namespace caffe2

#endif // CAFFE2_CORE_NET_DAG_UTILS_H_

#ifndef CAFFE2_CORE_NET_DAG_UTILS_H_ #define CAFFE2_CORE_NET_DAG_UTILS_H_ #include #include #include #include // NOLINT #include #include #include #include #include "c10/util/Registry.h" #include "caffe2/core/blob.h" #include "caffe2/core/common.h" #include "caffe2/core/logging.h" #include "caffe2/core/net.h" #include "caffe2/core/observer.h" #include "caffe2/core/operator_schema.h" #include "caffe2/core/tensor.h" #include "caffe2/core/workspace.h" #include "caffe2/proto/caffe2_pb.h" #include "caffe2/utils/simple_queue.h" namespace caffe2 { namespace dag_utils { struct OperatorNode { unique_ptr operator_; vector children_; vector parents_; std::atomic runtime_parent_count_; bool is_chain_start_ = false; std::atomic_flag scheduled_ = ATOMIC_FLAG_INIT; }; struct OpGraphNode { vector children_; vector parents_; int visited_inputs = 0; int num_orig_parents; }; using ExecutionChains = std::unordered_map>; C10_EXPORT ExecutionChains computeChains(std::vector& orig_nodes); // Instead of breaking down the DAG into chains, we partition it into clusters // of sync ops and individual async op. This is useful for disturbuted inference // case where we have sync and async cpu ops. Note that we have go sync each // aysnc op instead of put them into the chain and sync its tail like GPU op, // because CPU async ops are typically rpc calls and are not guaranteed to be // linearized at remote site. C10_EXPORT ExecutionChains computeGroups(std::vector& orig_nodes); C10_EXPORT ExecutionChains singleChains(std::vector& nodes); C10_EXPORT std::vector prepareOperatorNodes( const std::shared_ptr& net_def, Workspace* ws); std::vector prepareChainGraphNodes( const std::vector& operator_nodes, const std::vector>& execution_chains); } // namespace dag_utils } // namespace caffe2 #endif // CAFFE2_CORE_NET_DAG_UTILS_H_