def testBasics(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), "dump")
opts = builder(
builder.time_and_memory()).with_file_output(outfile).build()
x = lib.BuildFullModel()
profile_str = None
profile_step50 = os.path.join(test.get_temp_dir(), "profile_50")
with profile_context.ProfileContext(test.get_temp_dir()) as pctx:
pctx.add_auto_profiling("op",
options=opts,
profile_steps=[15, 50, 100])
with session.Session() as sess:
sess.run(variables.global_variables_initializer())
total_steps = 101 if test.is_gpu_available() else 50
for i in range(total_steps):
sess.run(x)
if i == 14 or i == 99:
self.assertTrue(gfile.Exists(outfile))
gfile.Remove(outfile)
if i == 49:
self.assertTrue(gfile.Exists(profile_step50))
with gfile.Open(outfile, "r") as f:
profile_str = f.read()
gfile.Remove(outfile)
with lib.ProfilerFromFile(
os.path.join(test.get_temp_dir(), "profile_50")) as profiler:
profiler.profile_operations(options=opts)
with gfile.Open(outfile, "r") as f:
self.assertEqual(profile_str, f.read())
def testBasics(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), "dump")
opts = builder(
builder.time_and_memory()).with_file_output(outfile).build()
x = lib.BuildFullModel()
profile_str = None
profile_step100 = os.path.join(test.get_temp_dir(), "profile_100")
with profile_context.ProfileContext(test.get_temp_dir()) as pctx:
pctx.add_auto_profiling("op",
options=opts,
profile_steps=[15, 50, 100])
with session.Session() as sess:
sess.run(variables.global_variables_initializer())
total_steps = 101
for i in range(total_steps):
sess.run(x)
if i == 14 or i == 49:
self.assertTrue(gfile.Exists(outfile))
gfile.Remove(outfile)
if i == 99:
self.assertTrue(gfile.Exists(profile_step100))
with gfile.Open(outfile, "r") as f:
profile_str = f.read()
gfile.Remove(outfile)
self.assertEqual(set([15, 50, 100]),
set(pctx.get_profiles("op").keys()))
with lib.ProfilerFromFile(
os.path.join(test.get_temp_dir(), "profile_100")) as profiler:
profiler.profile_operations(options=opts)
with gfile.Open(outfile, "r") as f:
if test.is_built_with_rocm():
# The profiler output for ROCm mode, includes an extra warning related
# to the lack of stream tracing in ROCm moed. Need to skip this warning
# when doing the diff in ROCm mode
profile_str = "\n".join(profile_str.split("\n")[7:])
self.assertEqual(profile_str, f.read())
def testSelectEverythingDetail(self):
ops.reset_default_graph()
dev = '/device:GPU:0' if test.is_gpu_available() else '/device:CPU:0'
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts = (builder(
builder.trainable_variables_parameter()).with_file_output(
outfile).with_accounted_types(['.*']).select([
'micros', 'bytes', 'params', 'float_ops', 'occurrence',
'device', 'op_types', 'input_shapes'
]).build())
with profile_context.ProfileContext(test.get_temp_dir(),
trace_steps=[],
dump_steps=[]) as pctx:
with session.Session() as sess, ops.device(dev):
x = lib.BuildSmallModel()
sess.run(variables.global_variables_initializer())
pctx.trace_next_step()
pctx.dump_next_step()
_ = sess.run(x)
pctx.profiler.profile_name_scope(options=opts)
with gfile.Open(outfile, 'r') as f:
# pylint: disable=line-too-long
dump_str = lib.CheckAndRemoveDoc(f.read())
outputs = dump_str.split('\n')
self.assertEqual(
outputs[0],
'node name | # parameters | # float_ops | requested bytes | total execution time | accelerator execution time | cpu execution time | assigned devices | op types | op count (run|defined) | input shapes'
)
for o in outputs[1:]:
if o.find('Conv2D ') > 0:
metrics = o[o.find('(') + 1:o.find(')')].split(',')
# Make sure time is profiled.
gap = 1 if test.is_gpu_available() else 2
for i in range(3, 6, gap):
mat = re.search('(.*)[um]s/(.*)[um]s',
metrics[i])
self.assertGreater(float(mat.group(1)), 0.0)
self.assertGreater(float(mat.group(2)), 0.0)
# Make sure device is profiled.
if test.is_gpu_available():
self.assertTrue(metrics[6].find('gpu') > 0)
self.assertFalse(metrics[6].find('cpu') > 0)
else:
self.assertFalse(metrics[6].find('gpu') > 0)
self.assertTrue(metrics[6].find('cpu') > 0)
# Make sure float_ops is profiled.
mat = re.search('(.*)k/(.*)k flops',
metrics[1].strip())
self.assertGreater(float(mat.group(1)), 0.0)
self.assertGreater(float(mat.group(2)), 0.0)
# Make sure op_count is profiled.
self.assertEqual(metrics[8].strip(), '1/1|1/1')
# Make sure input_shapes is profiled.
self.assertEqual(metrics[9].strip(),
'0:2x6x6x3|1:3x3x3x6')
if o.find('DW (3x3x3x6') > 0:
metrics = o[o.find('(') + 1:o.find(')')].split(',')
mat = re.search('(.*)/(.*) params',
metrics[1].strip())
self.assertGreater(float(mat.group(1)), 0.0)
self.assertGreater(float(mat.group(2)), 0.0)
# pylint: enable=line-too-long
# Test that profiler restored from profile file gives the same result.
gfile.Remove(outfile)
profile_file = os.path.join(test.get_temp_dir(), 'profile_1')
with lib.ProfilerFromFile(profile_file) as profiler:
profiler.profile_name_scope(options=opts)
with gfile.Open(outfile, 'r') as f:
self.assertEqual(dump_str, lib.CheckAndRemoveDoc(f.read()))
