GR-21734: add simple pickle / cPickle micro benchmarks

Author: cosminbasca

graalpython/benchmarks/src/pickle/dicts.py

@@ -0,0 +1,66 @@
+# Copyright (c) 2020, Oracle and/or its affiliates. All rights reserved.
+# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+#
+# The Universal Permissive License (UPL), Version 1.0
+#
+# Subject to the condition set forth below, permission is hereby granted to any
+# person obtaining a copy of this software, associated documentation and/or
+# data (collectively the "Software"), free of charge and under any and all
+# copyright rights in the Software, and any and all patent rights owned or
+# freely licensable by each licensor hereunder covering either (i) the
+# unmodified Software as contributed to or provided by such licensor, or (ii)
+# the Larger Works (as defined below), to deal in both
+#
+# (a) the Software, and
+#
+# (b) any piece of software and/or hardware listed in the lrgrwrks.txt file if
+# one is included with the Software each a "Larger Work" to which the Software
+# is contributed by such licensors),
+#
+# without restriction, including without limitation the rights to copy, create
+# derivative works of, display, perform, and distribute the Software and make,
+# use, sell, offer for sale, import, export, have made, and have sold the
+# Software and the Larger Work(s), and to sublicense the foregoing rights on
+# either these or other terms.
+#
+# This license is subject to the following condition:
+#
+# The above copyright notice and either this complete permission notice or at a
+# minimum a reference to the UPL must be included in all copies or substantial
+# portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+import random
+from utils import get_pickler, random_dict
+
+
+DATA = []
+dumps = None
+loads = None
+
+
+def __setup__(size=100, size_min=10, size_max=100, module="pickle"):
+    global DATA, dumps, loads
+    dumps, loads = get_pickler(module)
+    DATA = [random_dict(random.randint(size_min, size_max)) for _ in range(size)]
+
+
+def __process_args__(size=100, size_min=10, size_max=100, module="pickle"):
+    return int(size), int(size_min), int(size_max), module
+
+
+def __teardown__():
+    pass
+
+
+def __benchmark__(size=100, size_min=10, size_max=100, module="pickle"):
+    dumped = [dumps(s) for s in DATA]
+    loaded = [loads(b) for b in dumped]
+    print("loaded DATA are the same as dumped DATA: ", loaded == DATA)

graalpython/benchmarks/src/pickle/funcs.py

@@ -0,0 +1,66 @@
+# Copyright (c) 2020, Oracle and/or its affiliates. All rights reserved.
+# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+#
+# The Universal Permissive License (UPL), Version 1.0
+#
+# Subject to the condition set forth below, permission is hereby granted to any
+# person obtaining a copy of this software, associated documentation and/or
+# data (collectively the "Software"), free of charge and under any and all
+# copyright rights in the Software, and any and all patent rights owned or
+# freely licensable by each licensor hereunder covering either (i) the
+# unmodified Software as contributed to or provided by such licensor, or (ii)
+# the Larger Works (as defined below), to deal in both
+#
+# (a) the Software, and
+#
+# (b) any piece of software and/or hardware listed in the lrgrwrks.txt file if
+# one is included with the Software each a "Larger Work" to which the Software
+# is contributed by such licensors),
+#
+# without restriction, including without limitation the rights to copy, create
+# derivative works of, display, perform, and distribute the Software and make,
+# use, sell, offer for sale, import, export, have made, and have sold the
+# Software and the Larger Work(s), and to sublicense the foregoing rights on
+# either these or other terms.
+#
+# This license is subject to the following condition:
+#
+# The above copyright notice and either this complete permission notice or at a
+# minimum a reference to the UPL must be included in all copies or substantial
+# portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+from utils import get_pickler, random_func
+
+
+DATA = []
+dumps = None
+loads = None
+
+
+def __setup__(size=100, module="pickle"):
+    global DATA, dumps, loads
+    dumps, loads = get_pickler(module)
+    DATA = [random_func() for _ in range(size)]
+
+
+def __process_args__(size=100, module="pickle"):
+    return int(size), module
+
+
+def __teardown__():
+    pass
+
+
+def __benchmark__(size=100, module="pickle"):
+    # TODO: we need to serialize functions ala dill or cloudpickle from pyspark here.
+    dumped = [dumps(s) for s in DATA]
+    loaded = [loads(b) for b in dumped]
+    print("loaded DATA are the same as dumped DATA: ", loaded == DATA)

graalpython/benchmarks/src/pickle/lists.py

@@ -0,0 +1,66 @@
+# Copyright (c) 2020, Oracle and/or its affiliates. All rights reserved.
+# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+#
+# The Universal Permissive License (UPL), Version 1.0
+#
+# Subject to the condition set forth below, permission is hereby granted to any
+# person obtaining a copy of this software, associated documentation and/or
+# data (collectively the "Software"), free of charge and under any and all
+# copyright rights in the Software, and any and all patent rights owned or
+# freely licensable by each licensor hereunder covering either (i) the
+# unmodified Software as contributed to or provided by such licensor, or (ii)
+# the Larger Works (as defined below), to deal in both
+#
+# (a) the Software, and
+#
+# (b) any piece of software and/or hardware listed in the lrgrwrks.txt file if
+# one is included with the Software each a "Larger Work" to which the Software
+# is contributed by such licensors),
+#
+# without restriction, including without limitation the rights to copy, create
+# derivative works of, display, perform, and distribute the Software and make,
+# use, sell, offer for sale, import, export, have made, and have sold the
+# Software and the Larger Work(s), and to sublicense the foregoing rights on
+# either these or other terms.
+#
+# This license is subject to the following condition:
+#
+# The above copyright notice and either this complete permission notice or at a
+# minimum a reference to the UPL must be included in all copies or substantial
+# portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+import random
+from utils import get_pickler, random_list
+
+
+DATA = []
+dumps = None
+loads = None
+
+
+def __setup__(size=500, size_min=10, size_max=100, module="pickle"):
+    global DATA, dumps, loads
+    dumps, loads = get_pickler(module)
+    DATA = [random_list(random.randint(size_min, size_max)) for _ in range(size)]
+
+
+def __process_args__(size=500, size_min=10, size_max=100, module="pickle"):
+    return int(size), int(size_min), int(size_max), module
+
+
+def __teardown__():
+    pass
+
+
+def __benchmark__(size=500, size_min=10, size_max=100, module="pickle"):
+    dumped = [dumps(s) for s in DATA]
+    loaded = [loads(b) for b in dumped]
+    print("loaded DATA are the same as dumped DATA: ", loaded == DATA)

graalpython/benchmarks/src/pickle/objects.py

@@ -0,0 +1,65 @@
+# Copyright (c) 2020, Oracle and/or its affiliates. All rights reserved.
+# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+#
+# The Universal Permissive License (UPL), Version 1.0
+#
+# Subject to the condition set forth below, permission is hereby granted to any
+# person obtaining a copy of this software, associated documentation and/or
+# data (collectively the "Software"), free of charge and under any and all
+# copyright rights in the Software, and any and all patent rights owned or
+# freely licensable by each licensor hereunder covering either (i) the
+# unmodified Software as contributed to or provided by such licensor, or (ii)
+# the Larger Works (as defined below), to deal in both
+#
+# (a) the Software, and
+#
+# (b) any piece of software and/or hardware listed in the lrgrwrks.txt file if
+# one is included with the Software each a "Larger Work" to which the Software
+# is contributed by such licensors),
+#
+# without restriction, including without limitation the rights to copy, create
+# derivative works of, display, perform, and distribute the Software and make,
+# use, sell, offer for sale, import, export, have made, and have sold the
+# Software and the Larger Work(s), and to sublicense the foregoing rights on
+# either these or other terms.
+#
+# This license is subject to the following condition:
+#
+# The above copyright notice and either this complete permission notice or at a
+# minimum a reference to the UPL must be included in all copies or substantial
+# portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+from utils import get_pickler, random_instance
+
+
+DATA = []
+dumps = None
+loads = None
+
+
+def __setup__(size=100, module="pickle"):
+    global DATA, dumps, loads
+    dumps, loads = get_pickler(module)
+    DATA = [random_instance() for _ in range(size)]
+
+
+def __process_args__(size=100, module="pickle"):
+    return int(size), module
+
+
+def __teardown__():
+    pass
+
+
+def __benchmark__(size=100, module="pickle"):
+    dumped = [dumps(s) for s in DATA]
+    loaded = [loads(b) for b in dumped]
+    print("loaded DATA are the same as dumped DATA: ", loaded == DATA)

graalpython/benchmarks/src/pickle/strings.py

@@ -0,0 +1,66 @@
+# Copyright (c) 2020, Oracle and/or its affiliates. All rights reserved.
+# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+#
+# The Universal Permissive License (UPL), Version 1.0
+#
+# Subject to the condition set forth below, permission is hereby granted to any
+# person obtaining a copy of this software, associated documentation and/or
+# data (collectively the "Software"), free of charge and under any and all
+# copyright rights in the Software, and any and all patent rights owned or
+# freely licensable by each licensor hereunder covering either (i) the
+# unmodified Software as contributed to or provided by such licensor, or (ii)
+# the Larger Works (as defined below), to deal in both
+#
+# (a) the Software, and
+#
+# (b) any piece of software and/or hardware listed in the lrgrwrks.txt file if
+# one is included with the Software each a "Larger Work" to which the Software
+# is contributed by such licensors),
+#
+# without restriction, including without limitation the rights to copy, create
+# derivative works of, display, perform, and distribute the Software and make,
+# use, sell, offer for sale, import, export, have made, and have sold the
+# Software and the Larger Work(s), and to sublicense the foregoing rights on
+# either these or other terms.
+#
+# This license is subject to the following condition:
+#
+# The above copyright notice and either this complete permission notice or at a
+# minimum a reference to the UPL must be included in all copies or substantial
+# portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+import random
+from utils import get_pickler, random_string
+
+
+DATA = []
+dumps = None
+loads = None
+
+
+def __setup__(size=10000, size_min=10, size_max=1000, module="pickle"):
+    global DATA, dumps, loads
+    dumps, loads = get_pickler(module)
+    DATA = [random_string(random.randint(size_min, size_max)) for _ in range(size)]
+
+
+def __process_args__(size=10000, size_min=10, size_max=1000, module="pickle"):
+    return int(size), int(size_min), int(size_max), module
+
+
+def __teardown__():
+    pass
+
+
+def __benchmark__(size=10000, size_min=10, size_max=1000, module="pickle"):
+    dumped = [dumps(s) for s in DATA]
+    loaded = [loads(b) for b in dumped]
+    print("loaded DATA are the same as dumped DATA: ", loaded == DATA)