Tree2 (#103)

* fix

* fix

* add tensorflow

* fix

* make op build optional

Makefile

@@ -10,7 +10,7 @@ ci:
 	bash ci/ci_test.sh
 
 op:
-	bash cc/build.sh
+	bash cc/build.sh || echo "WARN: make custom tf op failed!"
 
 protobuf:
 	python -m grpc_tools.protoc -I protocols -I$(TF_PATH) \

cc/build.sh

@@ -1,3 +1,6 @@
+#!/bin/bash
+set -ex
+
 TF_CFLAGS=$(python -c 'import tensorflow as tf; print(" ".join(tf.sysconfig.get_compile_flags()))')
 TF_LFLAGS=$(python -c 'import tensorflow as tf; print(" ".join(tf.sysconfig.get_link_flags()))')
 

fedlearner/trainer/operator.py

@@ -38,7 +38,7 @@ class custom_fedlearner_operators_failed_to_load(object):
     lagrange_lite_ops = tf.load_op_library(path)
 
 
-if lagrange_lite_ops is None:
+if lagrange_lite_ops is custom_fedlearner_operators_failed_to_load:
     logging.warning("Failed to load fedlearner operators from %s", path)
 
 

thirdparty/tensorflow/tensorflow/core/framework/allocation_description.proto

@@ -0,0 +1,28 @@
+syntax = "proto3";
+
+package tensorflow;
+option cc_enable_arenas = true;
+option java_outer_classname = "AllocationDescriptionProtos";
+option java_multiple_files = true;
+option java_package = "org.tensorflow.framework";
+option go_package = "github.com/tensorflow/tensorflow/tensorflow/go/core/framework";
+
+message AllocationDescription {
+  // Total number of bytes requested
+  int64 requested_bytes = 1;
+
+  // Total number of bytes allocated if known
+  int64 allocated_bytes = 2;
+
+  // Name of the allocator used
+  string allocator_name = 3;
+
+  // Identifier of the allocated buffer if known
+  int64 allocation_id = 4;
+
+  // Set if this tensor only has one remaining reference
+  bool has_single_reference = 5;
+
+  // Address of the allocation.
+  uint64 ptr = 6;
+};

thirdparty/tensorflow/tensorflow/core/framework/api_def.proto

@@ -0,0 +1,136 @@
+// Defines the text format for including per-op API definition and
+// overrides for client language op code generators.
+
+syntax = "proto3";
+
+package tensorflow;
+option cc_enable_arenas = true;
+option java_outer_classname = "ApiDefProtos";
+option java_multiple_files = true;
+option java_package = "org.tensorflow.framework";
+option go_package = "github.com/tensorflow/tensorflow/tensorflow/go/core/framework";
+import "tensorflow/core/framework/attr_value.proto";
+
+// Used to specify and override the default API & behavior in the
+// generated code for client languages, from what you would get from
+// the OpDef alone. There will be a set of ApiDefs that are common
+// to all client languages, and another set per client language.
+// The per-client-language ApiDefs will inherit values from the
+// common ApiDefs which it can either replace or modify.
+//
+// We separate the API definition from the OpDef so we can evolve the
+// API while remaining backwards compatible when interpretting old
+// graphs.  Overrides go in an "api_def.pbtxt" file with a text-format
+// ApiDefs message.
+//
+// WARNING: Be *very* careful changing the API for any existing op --
+// you can change the semantics of existing code.  These changes may
+// need to wait until a major release of TensorFlow to avoid breaking
+// our compatibility promises.
+message ApiDef {
+  // Name of the op (in the OpDef) to specify the API for.
+  string graph_op_name = 1;
+  // If this op is deprecated, set deprecation message to the message
+  // that should be logged when this op is used.
+  // The message should indicate alternative op to use, if any.
+  string deprecation_message = 12;
+  // Major version when the op will be deleted. For e.g. set this
+  // value to 2 if op API should be removed in TensorFlow 2.0 and
+  // deprecated in versions before that.
+  int32 deprecation_version = 13;
+
+  enum Visibility {
+    // Normally this is "VISIBLE" unless you are inheriting a
+    // different value from another ApiDef.
+    DEFAULT_VISIBILITY = 0;
+    // Publicly visible in the API.
+    VISIBLE = 1;
+    // Do not include this op in the generated API. If visibility is
+    // set to 'SKIP', other fields are ignored for this op.
+    SKIP = 2;
+    // Hide this op by putting it into an internal namespace (or whatever
+    // is appropriate in the target language).
+    HIDDEN = 3;
+  }
+  Visibility visibility = 2;
+
+  // If you specify any endpoint, this will replace all of the
+  // inherited endpoints.  The first endpoint should be the
+  // "canonical" endpoint, and should not be deprecated (unless all
+  // endpoints are deprecated).
+  message Endpoint {
+    // Name should be either like "CamelCaseName" or
+    // "Package.CamelCaseName". Client-language-specific ApiDefs may
+    // use a snake_case convention instead of CamelCase.
+    string name = 1;
+
+    // Set if this endpoint is deprecated. If set to true, a message suggesting
+    // to use a non-deprecated endpoint instead will be printed. If all
+    // endpoints are deprecated, set deprecation_message in ApiDef instead.
+    bool deprecated = 3;
+
+    // Major version when an endpoint will be deleted. For e.g. set this
+    // value to 2 if endpoint should be removed in TensorFlow 2.0 and
+    // deprecated in versions before that.
+    int32 deprecation_version = 4;
+  }
+  repeated Endpoint endpoint = 3;
+
+  message Arg {
+    string name = 1;
+
+    // Change the name used to access this arg in the API from what
+    // is used in the GraphDef.  Note that these names in `backticks`
+    // will also be replaced in the summary & description fields.
+    string rename_to = 2;
+
+    // Note: this will replace any inherited arg doc. There is no
+    // current way of modifying arg descriptions (other than replacing
+    // them entirely) as can be done with op descriptions.
+    string description = 3;
+  }
+  repeated Arg in_arg = 4;
+  repeated Arg out_arg = 5;
+  // List of original in_arg names to specify new argument order.
+  // Length of arg_order should be either empty to keep current order
+  // or match size of in_arg.
+  repeated string arg_order = 11;
+
+  // Description of the graph-construction-time configuration of this
+  // Op.  That is to say, this describes the attr fields that will
+  // be specified in the NodeDef.
+  message Attr {
+    string name = 1;
+
+    // Change the name used to access this attr in the API from what
+    // is used in the GraphDef.  Note that these names in `backticks`
+    // will also be replaced in the summary & description fields.
+    string rename_to = 2;
+
+    // Specify a new default value to use for this attr.  This default
+    // will be used when creating new graphs, as opposed to the
+    // default in the OpDef, which will be used when interpreting old
+    // GraphDefs.
+    AttrValue default_value = 3;
+
+    // Note: this will replace any inherited attr doc, there is no current
+    // way of modifying attr descriptions as can be done with op descriptions.
+    string description = 4;
+  }
+  repeated Attr attr = 6;
+
+  // One-line human-readable description of what the Op does.
+  string summary = 7;
+
+  // Additional, longer human-readable description of what the Op does.
+  string description = 8;
+
+  // Modify an existing/inherited description by adding text to the beginning
+  // or end.
+  string description_prefix = 9;
+  string description_suffix = 10;
+}
+
+message ApiDefs {
+  repeated ApiDef op = 1;
+}

thirdparty/tensorflow/tensorflow/core/framework/attr_value.proto

@@ -0,0 +1,62 @@
+syntax = "proto3";
+
+package tensorflow;
+option cc_enable_arenas = true;
+option java_outer_classname = "AttrValueProtos";
+option java_multiple_files = true;
+option java_package = "org.tensorflow.framework";
+option go_package = "github.com/tensorflow/tensorflow/tensorflow/go/core/framework";
+import "tensorflow/core/framework/tensor.proto";
+import "tensorflow/core/framework/tensor_shape.proto";
+import "tensorflow/core/framework/types.proto";
+
+// Protocol buffer representing the value for an attr used to configure an Op.
+// Comment indicates the corresponding attr type.  Only the field matching the
+// attr type may be filled.
+message AttrValue {
+  // LINT.IfChange
+  message ListValue {
+    repeated bytes s = 2;                        // "list(string)"
+    repeated int64 i = 3 [packed = true];        // "list(int)"
+    repeated float f = 4 [packed = true];        // "list(float)"
+    repeated bool b = 5 [packed = true];         // "list(bool)"
+    repeated DataType type = 6 [packed = true];  // "list(type)"
+    repeated TensorShapeProto shape = 7;         // "list(shape)"
+    repeated TensorProto tensor = 8;             // "list(tensor)"
+    repeated NameAttrList func = 9;              // "list(attr)"
+  }
+  // LINT.ThenChange(https://www.tensorflow.org/code/tensorflow/c/c_api.cc)
+
+  oneof value {
+    bytes s = 2;                 // "string"
+    int64 i = 3;                 // "int"
+    float f = 4;                 // "float"
+    bool b = 5;                  // "bool"
+    DataType type = 6;           // "type"
+    TensorShapeProto shape = 7;  // "shape"
+    TensorProto tensor = 8;      // "tensor"
+    ListValue list = 1;          // any "list(...)"
+
+    // "func" represents a function. func.name is a function's name or
+    // a primitive op's name. func.attr.first is the name of an attr
+    // defined for that function. func.attr.second is the value for
+    // that attr in the instantiation.
+    NameAttrList func = 10;
+
+    // This is a placeholder only used in nodes defined inside a
+    // function.  It indicates the attr value will be supplied when
+    // the function is instantiated.  For example, let us suppose a
+    // node "N" in function "FN". "N" has an attr "A" with value
+    // placeholder = "foo". When FN is instantiated with attr "foo"
+    // set to "bar", the instantiated node N's attr A will have been
+    // given the value "bar".
+    string placeholder = 9;
+  }
+}
+
+// A list of attr names and their values. The whole list is attached
+// with a string name.  E.g., MatMul[T=float].
+message NameAttrList {
+  string name = 1;
+  map<string, AttrValue> attr = 2;
+}

thirdparty/tensorflow/tensorflow/core/framework/cost_graph.proto

@@ -0,0 +1,77 @@
+syntax = "proto3";
+
+package tensorflow;
+option cc_enable_arenas = true;
+option java_outer_classname = "CostGraphProtos";
+option java_multiple_files = true;
+option java_package = "org.tensorflow.framework";
+option go_package = "github.com/tensorflow/tensorflow/tensorflow/go/core/framework";
+import "tensorflow/core/framework/tensor_shape.proto";
+import "tensorflow/core/framework/types.proto";
+
+message CostGraphDef {
+  message Node {
+    // The name of the node. Names are globally unique.
+    string name = 1;
+
+    // The device of the node. Can be empty if the node is mapped to the
+    // default partition or partitioning hasn't been run yet.
+    string device = 2;
+
+    // The id of the node. Node ids are only unique inside a partition.
+    int32 id = 3;
+
+    // Inputs of this node. They must be executed before this node can be
+    // executed. An input is a particular output of another node, specified
+    // by the node id and the output index.
+    message InputInfo {
+      int32 preceding_node = 1;
+      int32 preceding_port = 2;
+    }
+    repeated InputInfo input_info = 4;
+
+    // Outputs of this node.
+    message OutputInfo {
+      int64 size = 1;
+      // If >= 0, the output is an alias of an input. Note that an alias input
+      // may itself be an alias. The algorithm will therefore need to follow
+      // those pointers.
+      int64 alias_input_port = 2;
+      TensorShapeProto shape = 3;
+      DataType dtype = 4;
+    }
+    repeated OutputInfo output_info = 5;
+
+    // Temporary memory used by this node.
+    int64 temporary_memory_size = 6;
+
+    // Persistent memory used by this node.
+    int64 persistent_memory_size = 12;
+
+    int64 host_temp_memory_size = 10 [deprecated = true];
+    int64 device_temp_memory_size = 11 [deprecated = true];
+    int64 device_persistent_memory_size = 16 [deprecated = true];
+
+    // Estimate of the computational cost of this node, in microseconds.
+    int64 compute_cost = 9;
+
+    // Analytical estimate of the computational cost of this node, in
+    // microseconds.
+    int64 compute_time = 14;
+
+    // Analytical estimate of the memory access cost of this node, in
+    // microseconds.
+    int64 memory_time = 15;
+
+    // If true, the output is permanent: it can't be discarded, because this
+    // node is part of the "final output". Nodes may depend on final nodes.
+    bool is_final = 7;
+
+    // Ids of the control inputs for this node.
+    repeated int32 control_input = 8;
+
+    // Are the costs inaccurate?
+    bool inaccurate = 17;
+  }
+  repeated Node node = 1;
+}

thirdparty/tensorflow/tensorflow/core/framework/device_attributes.proto

@@ -0,0 +1,52 @@
+syntax = "proto3";
+
+package tensorflow;
+option cc_enable_arenas = true;
+option java_outer_classname = "DeviceAttributesProtos";
+option java_multiple_files = true;
+option java_package = "org.tensorflow.framework";
+option go_package = "github.com/tensorflow/tensorflow/tensorflow/go/core/framework";
+
+message InterconnectLink {
+  int32 device_id = 1;
+  string type = 2;
+  int32 strength = 3;
+};
+
+message LocalLinks {
+  repeated InterconnectLink link = 1;
+};
+
+message DeviceLocality {
+  // Optional bus locality of device.  Default value of 0 means
+  // no specific locality.  Specific localities are indexed from 1.
+  int32 bus_id = 1;
+
+  // Optional NUMA locality of device.
+  int32 numa_node = 2;
+
+  // Optional local interconnect links to other devices.
+  LocalLinks links = 3;
+};
+
+message DeviceAttributes {
+  // Fully specified name of the device within a cluster.
+  string name = 1;
+
+  // String representation of device_type.
+  string device_type = 2;
+
+  // Memory capacity of device in bytes.
+  int64 memory_limit = 4;
+
+  // Platform-specific data about device that may be useful
+  // for supporting efficient data transfers.
+  DeviceLocality locality = 5;
+
+  // A device is assigned a global unique number each time it is
+  // initialized. "incarnation" should never be 0.
+  fixed64 incarnation = 6;
+
+  // String representation of the physical device that this device maps to.
+  string physical_device_desc = 7;
+}