Add a view that organize results by operation type:

tfprof> op -select micros,bytes,occurrence -order_by micros
SoftmaxCrossEntropyWithLogits      36.58MB (100.00%, 0.05%),      1.37sec
(100.00%, 23.56%),         30
MatMul                        2720.57MB (99.95%, 3.66%),      988.90ms (76.44%,
17.05%),       3450
ConcatV2                       741.37MB (96.29%, 1.00%),       421.44ms
(59.38%, 7.27%),       6098
Mul                           3957.24MB (95.29%, 5.33%),       418.90ms
(52.12%, 7.22%),       9427
Add                            740.05MB (89.96%, 1.00%),       335.26ms
(44.89%, 5.78%),       2180
Sub                             32.46MB (88.97%, 0.04%),       216.44ms

The CL also:
1. Unify code view and op view implementation and rename.
2. Clean up a few unused features.
3. Unify the option semantics of all views.

PiperOrigin-RevId: 157043043

3 files changed, 80 insertions, 36 deletions

diff --git a/tensorflow/contrib/tfprof/python/tools/tfprof/model_analyzer.py b/tensorflow/contrib/tfprof/python/tools/tfprof/model_analyzer.py
index 17dff69edd..fcce3cd45b 100644
--- a/tensorflow/contrib/tfprof/python/tools/tfprof/model_analyzer.py
+++ b/tensorflow/contrib/tfprof/python/tools/tfprof/model_analyzer.py
@@ -22,6 +22,7 @@ from __future__ import print_function
 
 from tensorflow.contrib.tfprof.python.tools.tfprof import pywrap_tensorflow_print_model_analysis_lib as print_mdl
 from tensorflow.contrib.tfprof.python.tools.tfprof import tfprof_logger
+from tensorflow.python.framework import errors
 from tensorflow.tools.tfprof import tfprof_options_pb2
 from tensorflow.tools.tfprof import tfprof_output_pb2
 
@@ -36,7 +37,6 @@ TRAINABLE_VARS_PARAMS_STAT_OPTIONS = {
     'min_micros': 0,
     'min_params': 0,
     'min_float_ops': 0,
-    'device_regexes': ['.*'],
     'order_by': 'name',
     'account_type_regexes': [tfprof_logger.TRAINABLE_VARIABLES],
     'start_name_regexes': ['.*'],
@@ -56,7 +56,6 @@ FLOAT_OPS_OPTIONS = {
     'min_micros': 0,
     'min_params': 0,
     'min_float_ops': 1,
-    'device_regexes': ['.*'],
     'order_by': 'float_ops',
     'account_type_regexes': ['.*'],
     'start_name_regexes': ['.*'],
@@ -78,7 +77,6 @@ PRINT_PARAMS_ON_DEVICE = {
     'min_micros': 0,
     'min_params': 0,
     'min_float_ops': 0,
-    'device_regexes': ['.*'],
     'order_by': 'name',
     'account_type_regexes': ['.*ps.*task:0.*'],
     'start_name_regexes': ['.*'],
@@ -98,7 +96,6 @@ PRINT_ALL_TIMING_MEMORY = {
     'min_micros': 1,  # Only >=1
     'min_params': 0,
     'min_float_ops': 0,
-    'device_regexes': ['.*'],
     'order_by': 'name',
     'account_type_regexes': ['.*'],
     'start_name_regexes': ['.*'],
@@ -122,19 +119,10 @@ def print_model_analysis(graph,
                          tfprof_options=TRAINABLE_VARS_PARAMS_STAT_OPTIONS):
   """Print model statistics.
 
-    Prints the model statistics to stdout. Also returns the results
-    in a TFGraphNodeProto proto. See go/tfprof or run tfprof tool:
+    See go/tfprof or README for examples and tutorials.
+    Run tfprof tool for help:
     'bazel run third_party/tensorflow/tools/tfprof help'
 
-    Examples:
-      Show the parameter/shape statistics of tf.trainable_variables().
-        print_model_analysis(sess.graph).
-
-      Show number of float ops. Only ops with RegisterStatistics defined
-      are counted.
-        show_float_op_opts = model_analyzer.FLOAT_OPS_OPTIONS
-        print_model_analysis(sess.graph, tfprof_options=show_float_op_opts)
-
   Args:
     graph: tf.Graph.
     run_meta: tensorflow::RunMetadata proto. When provided, also shows valid
@@ -142,15 +130,16 @@ def print_model_analysis(graph,
               'micros' and 'bytes'.
     op_log: tensorflow::tfprof::OpLog proto. users can use this proto to
             group together ops and use a op_type to select the group.
-    tfprof_cmd: string. Either 'scope', 'graph', 'code'.
-                'scope' view organize outputs using ops' name scope.
-                'graph' view organize outputs using op's inputs/outputs.
+    tfprof_cmd: string. Either 'op', 'scope', 'graph', 'code'.
+                'op' view organize outputs using operation type. (e.g. MatMul)
+                'scope' view organize outputs using graph node name scope.
+                'graph' view organize outputs using graph node inputs/outputs.
                 'code' view organize outputs using Python call stack.
     tfprof_options: See 'tfprof help' for details.
   Returns:
     If tfprof_cmd is 'scope' or 'graph', returns TFGraphNodeProto proto.
-    If tfprof_cmd is 'code', returns TFCodeNodeProto proto.
-    Side effect: a formatted output to stdout.
+    If tfprof_cmd is 'op' or 'code', returns TFMultiGraphNodeProto proto.
+    Side effect: stdout/file/timeline.json depending on tfprof_options['output']
   """
   # pylint: disable=protected-access
   op_log = tfprof_logger._merge_default_with_oplog(
@@ -162,8 +151,11 @@ def print_model_analysis(graph,
   opts.min_micros = tfprof_options['min_micros']
   opts.min_params = tfprof_options['min_params']
   opts.min_float_ops = tfprof_options['min_float_ops']
-  for p in tfprof_options['device_regexes']:
-    opts.device_regexes.append(p)
+  if 'min_occurrence' in tfprof_options:
+    opts.min_occurrence = tfprof_options['min_occurrence']
+  else:
+    opts.min_occurrence = 0
+
   opts.order_by = tfprof_options['order_by']
   for p in tfprof_options['account_type_regexes']:
     opts.account_type_regexes.append(p)
@@ -183,8 +175,8 @@ def print_model_analysis(graph,
 
   run_meta_str = run_meta.SerializeToString() if run_meta else b''
 
-  if tfprof_cmd == 'code':
-    tfprof_node = tfprof_output_pb2.TFCodeNodeProto()
+  if tfprof_cmd == 'code' or tfprof_cmd == 'op':
+    tfprof_node = tfprof_output_pb2.TFMultiGraphNodeProto()
     tfprof_node.ParseFromString(
         print_mdl.PrintModelAnalysis(
             graph.as_graph_def().SerializeToString(),
@@ -192,7 +184,7 @@ def print_model_analysis(graph,
             op_log.SerializeToString(),
             tfprof_cmd.encode('utf-8'),
             opts.SerializeToString()))
-  else:
+  elif tfprof_cmd == 'graph' or tfprof_cmd == 'scope':
     tfprof_node = tfprof_output_pb2.TFGraphNodeProto()
     tfprof_node.ParseFromString(
         print_mdl.PrintModelAnalysis(
@@ -201,5 +193,8 @@ def print_model_analysis(graph,
             op_log.SerializeToString(),
             tfprof_cmd.encode('utf-8'),
             opts.SerializeToString()))
+  else:
+    raise errors.InvalidArgumentError(
+        None, None, 'unknown tfprof_cmd: %s\n' % tfprof_cmd)
 
   return tfprof_node
diff --git a/tensorflow/contrib/tfprof/python/tools/tfprof/model_analyzer_test.py b/tensorflow/contrib/tfprof/python/tools/tfprof/model_analyzer_test.py
index 561e0a8577..14f8fcff9d 100644
--- a/tensorflow/contrib/tfprof/python/tools/tfprof/model_analyzer_test.py
+++ b/tensorflow/contrib/tfprof/python/tools/tfprof/model_analyzer_test.py
@@ -43,7 +43,8 @@ class PrintModelAnalysisTest(test.TestCase):
       model_analyzer.print_model_analysis(sess.graph, tfprof_options=opts)
 
       with gfile.Open(outfile, 'r') as f:
-        self.assertEqual(u'_TFProfRoot (--/451 params)\n'
+        self.assertEqual(u'node name | # parameters\n'
+                         '_TFProfRoot (--/451 params)\n'
                          '  DW (3x3x3x6, 162/162 params)\n'
                          '  DW2 (2x2x6x12, 288/288 params)\n'
                          '  ScalarW (1, 1/1 params)\n',
@@ -56,7 +57,8 @@ class PrintModelAnalysisTest(test.TestCase):
     opts['output'] = 'file:outfile=' + outfile
     opts['account_type_regexes'] = ['.*']
     opts['select'] = [
-        'bytes', 'params', 'float_ops', 'num_hidden_ops', 'device', 'op_types'
+        'bytes', 'params', 'float_ops', 'occurrence',
+        'device', 'op_types'
     ]
 
     with session.Session() as sess, ops.device('/cpu:0'):
@@ -75,7 +77,7 @@ class PrintModelAnalysisTest(test.TestCase):
       with gfile.Open(outfile, 'r') as f:
         # pylint: disable=line-too-long
         self.assertEqual(
-            '_TFProfRoot (0/451 params, 0/10.44k flops, 0B/5.28KB, _kTFScopeParent)\n  Conv2D (0/0 params, 5.83k/5.83k flops, 432B/432B, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Conv2D)\n  Conv2D_1 (0/0 params, 4.61k/4.61k flops, 384B/384B, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Conv2D)\n  DW (3x3x3x6, 162/162 params, 0/0 flops, 648B/1.30KB, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|VariableV2|_trainable_variables)\n    DW/Assign (0/0 params, 0/0 flops, 0B/0B, Assign)\n    DW/Initializer (0/0 params, 0/0 flops, 0B/0B, _kTFScopeParent)\n      DW/Initializer/random_normal (0/0 params, 0/0 flops, 0B/0B, Add)\n        DW/Initializer/random_normal/RandomStandardNormal (0/0 params, 0/0 flops, 0B/0B, RandomStandardNormal)\n        DW/Initializer/random_normal/mean (0/0 params, 0/0 flops, 0B/0B, Const)\n        DW/Initializer/random_normal/mul (0/0 params, 0/0 flops, 0B/0B, Mul)\n        DW/Initializer/random_normal/shape (0/0 params, 0/0 flops, 0B/0B, Const)\n        DW/Initializer/random_normal/stddev (0/0 params, 0/0 flops, 0B/0B, Const)\n    DW/read (0/0 params, 0/0 flops, 648B/648B, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Identity)\n  DW2 (2x2x6x12, 288/288 params, 0/0 flops, 1.15KB/2.30KB, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|VariableV2|_trainable_variables)\n    DW2/Assign (0/0 params, 0/0 flops, 0B/0B, Assign)\n    DW2/Initializer (0/0 params, 0/0 flops, 0B/0B, _kTFScopeParent)\n      DW2/Initializer/random_normal (0/0 params, 0/0 flops, 0B/0B, Add)\n        DW2/Initializer/random_normal/RandomStandardNormal (0/0 params, 0/0 flops, 0B/0B, RandomStandardNormal)\n        DW2/Initializer/random_normal/mean (0/0 params, 0/0 flops, 0B/0B, Const)\n        DW2/Initializer/random_normal/mul (0/0 params, 0/0 flops, 0B/0B, Mul)\n        DW2/Initializer/random_normal/shape (0/0 params, 0/0 flops, 0B/0B, Const)\n        DW2/Initializer/random_normal/stddev (0/0 params, 0/0 flops, 0B/0B, Const)\n    DW2/read (0/0 params, 0/0 flops, 1.15KB/1.15KB, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Identity)\n  ScalarW (1, 1/1 params, 0/0 flops, 0B/0B, VariableV2|_trainable_variables)\n    ScalarW/Assign (0/0 params, 0/0 flops, 0B/0B, Assign)\n    ScalarW/Initializer (0/0 params, 0/0 flops, 0B/0B, _kTFScopeParent)\n      ScalarW/Initializer/random_normal (0/0 params, 0/0 flops, 0B/0B, Add)\n        ScalarW/Initializer/random_normal/RandomStandardNormal (0/0 params, 0/0 flops, 0B/0B, RandomStandardNormal)\n        ScalarW/Initializer/random_normal/mean (0/0 params, 0/0 flops, 0B/0B, Const)\n        ScalarW/Initializer/random_normal/mul (0/0 params, 0/0 flops, 0B/0B, Mul)\n        ScalarW/Initializer/random_normal/shape (0/0 params, 0/0 flops, 0B/0B, Const)\n        ScalarW/Initializer/random_normal/stddev (0/0 params, 0/0 flops, 0B/0B, Const)\n    ScalarW/read (0/0 params, 0/0 flops, 0B/0B, Identity)\n  init (0/0 params, 0/0 flops, 0B/0B, NoOp)\n  zeros (0/0 params, 0/0 flops, 864B/864B, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Const)\n',
+            'node name | # parameters | # float_ops | output bytes | assigned devices | op types\n_TFProfRoot (--/451 params, --/10.44k flops, --/5.28KB, _kTFScopeParent)\n  Conv2D (0/0 params, 5.83k/5.83k flops, 432B/432B, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Conv2D)\n  Conv2D_1 (0/0 params, 4.61k/4.61k flops, 384B/384B, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Conv2D)\n  DW (3x3x3x6, 162/162 params, 0/0 flops, 648B/1.30KB, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|VariableV2|_trainable_variables)\n    DW/Assign (0/0 params, 0/0 flops, 0B/0B, Assign)\n    DW/Initializer (0/0 params, 0/0 flops, 0B/0B, _kTFScopeParent)\n      DW/Initializer/random_normal (0/0 params, 0/0 flops, 0B/0B, Add)\n        DW/Initializer/random_normal/RandomStandardNormal (0/0 params, 0/0 flops, 0B/0B, RandomStandardNormal)\n        DW/Initializer/random_normal/mean (0/0 params, 0/0 flops, 0B/0B, Const)\n        DW/Initializer/random_normal/mul (0/0 params, 0/0 flops, 0B/0B, Mul)\n        DW/Initializer/random_normal/shape (0/0 params, 0/0 flops, 0B/0B, Const)\n        DW/Initializer/random_normal/stddev (0/0 params, 0/0 flops, 0B/0B, Const)\n    DW/read (0/0 params, 0/0 flops, 648B/648B, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Identity)\n  DW2 (2x2x6x12, 288/288 params, 0/0 flops, 1.15KB/2.30KB, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|VariableV2|_trainable_variables)\n    DW2/Assign (0/0 params, 0/0 flops, 0B/0B, Assign)\n    DW2/Initializer (0/0 params, 0/0 flops, 0B/0B, _kTFScopeParent)\n      DW2/Initializer/random_normal (0/0 params, 0/0 flops, 0B/0B, Add)\n        DW2/Initializer/random_normal/RandomStandardNormal (0/0 params, 0/0 flops, 0B/0B, RandomStandardNormal)\n        DW2/Initializer/random_normal/mean (0/0 params, 0/0 flops, 0B/0B, Const)\n        DW2/Initializer/random_normal/mul (0/0 params, 0/0 flops, 0B/0B, Mul)\n        DW2/Initializer/random_normal/shape (0/0 params, 0/0 flops, 0B/0B, Const)\n        DW2/Initializer/random_normal/stddev (0/0 params, 0/0 flops, 0B/0B, Const)\n    DW2/read (0/0 params, 0/0 flops, 1.15KB/1.15KB, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Identity)\n  ScalarW (1, 1/1 params, 0/0 flops, 0B/0B, VariableV2|_trainable_variables)\n    ScalarW/Assign (0/0 params, 0/0 flops, 0B/0B, Assign)\n    ScalarW/Initializer (0/0 params, 0/0 flops, 0B/0B, _kTFScopeParent)\n      ScalarW/Initializer/random_normal (0/0 params, 0/0 flops, 0B/0B, Add)\n        ScalarW/Initializer/random_normal/RandomStandardNormal (0/0 params, 0/0 flops, 0B/0B, RandomStandardNormal)\n        ScalarW/Initializer/random_normal/mean (0/0 params, 0/0 flops, 0B/0B, Const)\n        ScalarW/Initializer/random_normal/mul (0/0 params, 0/0 flops, 0B/0B, Mul)\n        ScalarW/Initializer/random_normal/shape (0/0 params, 0/0 flops, 0B/0B, Const)\n        ScalarW/Initializer/random_normal/stddev (0/0 params, 0/0 flops, 0B/0B, Const)\n    ScalarW/read (0/0 params, 0/0 flops, 0B/0B, Identity)\n  init (0/0 params, 0/0 flops, 0B/0B, NoOp)\n  zeros (0/0 params, 0/0 flops, 864B/864B, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Const)\n',
             f.read())
         # pylint: enable=line-too-long
 
@@ -107,9 +109,8 @@ class PrintModelAnalysisTest(test.TestCase):
           sess.graph, run_meta, tfprof_cmd='code', tfprof_options=opts)
 
       with gfile.Open(outfile, 'r') as f:
-        # pylint: disable=line-too-long
-        self.assertEqual('_TFProfRoot (', f.read()[0:13])
-        # pylint: enable=line-too-long
+        self.assertEqual('node name | output bytes | # parameters | # float_',
+                         f.read()[0:50])
 
   def testComplexCodeView(self):
     ops.reset_default_graph()
@@ -136,7 +137,10 @@ class PrintModelAnalysisTest(test.TestCase):
 
       # pylint: disable=line-too-long
       with gfile.Open(outfile, 'r') as f:
-        self.assertEqual('_TFProfRoot (0', f.read()[:14])
+        lines = f.read().split('\n')
+        result = '\n'.join([l[:min(len(l), 80)] for l in lines])
+        self.assertEqual('node name | # parameters | # float_ops\n_TFProfRoot (--/2.84k params, --/54.08k flops)\n  model_analyzer_testlib.py:58:BuildFullModel:seq.append(array_... (0/1.80k para\n    model_analyzer_testlib.py:35:BuildSmallModel:image = array_ops... (0/0 param\n    model_analyzer_testlib.py:39:BuildSmallModel:initializer=init_... (0/4 param\n    model_analyzer_testlib.py:43:BuildSmallModel:initializer=init_... (0/648 par\n    model_analyzer_testlib.py:44:BuildSmallModel:x = nn_ops.conv2d... (0/0 param\n    model_analyzer_testlib.py:48:BuildSmallModel:initializer=init_... (0/1.15k p\n    model_analyzer_testlib.py:49:BuildSmallModel:x = nn_ops.conv2d... (0/0 param\n  model_analyzer_testlib.py:62:BuildFullModel:cell, array_ops.c... (0/1.04k para\n  model_analyzer_testlib.py:64:BuildFullModel:target = array_op... (0/0 params, \n  model_analyzer_testlib.py:65:BuildFullModel:loss = nn_ops.l2_... (0/0 params, \n  model_analyzer_testlib.py:67:BuildFullModel:return sgd_op.min... (0/0 params, \n',
+                         result)
 
       self.assertLess(0, tfprof_node.total_exec_micros)
       self.assertEqual(2844, tfprof_node.total_parameters)
@@ -166,7 +170,7 @@ class PrintModelAnalysisTest(test.TestCase):
     opts['account_type_regexes'] = ['.*']
     opts['account_displayed_op_only'] = False
     opts['select'] = [
-        'bytes', 'params', 'float_ops', 'num_hidden_ops', 'device'
+        'bytes', 'params', 'float_ops', 'device'
     ]
 
     with session.Session() as sess, ops.device('/cpu:0'):
@@ -214,6 +218,54 @@ class PrintModelAnalysisTest(test.TestCase):
         # Test that a json file is created.
         self.assertLess(1000, len(f.read()))
 
+  def testOpView(self):
+    ops.reset_default_graph()
+    opts = model_analyzer.TRAINABLE_VARS_PARAMS_STAT_OPTIONS
+    outfile = os.path.join(test.get_temp_dir(), 'dump')
+    opts['output'] = 'file:outfile=' + outfile
+    opts['account_type_regexes'] = ['.*']
+    opts['min_occurrence'] = 10
+    opts['select'] = [
+        'params', 'micros', 'occurrence',
+    ]
+    opts['order_by'] = 'occurrence'
+
+    with session.Session() as sess, ops.device('/cpu:0'):
+      x = lib.BuildFullModel()
+
+      sess.run(variables.global_variables_initializer())
+      run_meta = config_pb2.RunMetadata()
+      _ = sess.run(x,
+                   options=config_pb2.RunOptions(
+                       trace_level=config_pb2.RunOptions.FULL_TRACE),
+                   run_metadata=run_meta)
+
+      tfprof_node = model_analyzer.print_model_analysis(
+          sess.graph, run_meta, tfprof_cmd='op', tfprof_options=opts)
+
+      with gfile.Open(outfile, 'r') as f:
+        self.assertEqual(
+            'nodename|executiontime|#parameters|opocc',
+            f.read().replace('\t', '').replace(' ', '')[0:40])
+
+      total_children = 0
+      last_occurrence = 1e32
+      last_total_micros = tfprof_node.total_exec_micros
+      last_micros = tfprof_node.exec_micros
+      while tfprof_node.children:
+        self.assertEqual(len(tfprof_node.children), 1)
+        tfprof_node = tfprof_node.children[0]
+
+        self.assertEqual(
+            last_total_micros, tfprof_node.total_exec_micros + last_micros)
+        last_total_micros = tfprof_node.total_exec_micros
+        last_micros = tfprof_node.exec_micros
+
+        total_children += 1
+        self.assertLessEqual(len(tfprof_node.graph_nodes), last_occurrence)
+        last_occurrence = len(tfprof_node.graph_nodes)
+      self.assertEqual(total_children, 15)
+
 
 if __name__ == '__main__':
   test.main()
diff --git a/tensorflow/contrib/tfprof/python/tools/tfprof/print_model_analysis_test.py b/tensorflow/contrib/tfprof/python/tools/tfprof/print_model_analysis_test.py
index c3e9fc9cc0..41154d552b 100644
--- a/tensorflow/contrib/tfprof/python/tools/tfprof/print_model_analysis_test.py
+++ b/tensorflow/contrib/tfprof/python/tools/tfprof/print_model_analysis_test.py
@@ -42,7 +42,6 @@ TEST_OPTIONS = {
     'min_micros': 0,
     'min_params': 0,
     'min_float_ops': 0,
-    'device_regexes': ['.*'],
     'order_by': 'name',
     'account_type_regexes': ['.*'],
     'start_name_regexes': ['.*'],
@@ -76,8 +75,6 @@ class PrintModelAnalysisTest(test.TestCase):
     opts.min_micros = TEST_OPTIONS['min_micros']
     opts.min_params = TEST_OPTIONS['min_params']
     opts.min_float_ops = TEST_OPTIONS['min_float_ops']
-    for p in TEST_OPTIONS['device_regexes']:
-      opts.device_regexes.append(p)
     opts.order_by = TEST_OPTIONS['order_by']
     for p in TEST_OPTIONS['account_type_regexes']:
       opts.account_type_regexes.append(p)