add my benchmark for local execution

Author: timfel

graalpython/com.oracle.graal.python.benchmarks/python/meso/multiprocessing-benchmark.py

@@ -0,0 +1,85 @@
+# Copyright (c) 2021, 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 multiprocessing import Pool
+from time import time
+from itertools import permutations
+from pprint import pprint
+
+
+NGRAMS = 4
+
+
+def jaccard(fileA, fileB):
+    with open(fileA) as f:
+        x = f.read().split()
+        x = set(zip(*[x[i:] for i in range(NGRAMS)]))
+    with open(fileB) as f:
+        y = f.read().split()
+        y = set(zip(*[y[i:] for i in range(NGRAMS)]))
+    intersection_cardinality = len(x & y)
+    union_cardinality = len(x | y)
+    return (intersection_cardinality, union_cardinality, intersection_cardinality / union_cardinality)
+
+
+def parallel_jaccard(pair):
+    return pair, jaccard(*pair)
+
+
+if __name__ == '__main__':
+    import sys, os
+
+    iterations = 50
+    pairs = list(permutations([os.path.join(sys.argv[1], f) for f in os.listdir(sys.argv[1])], 2))
+
+    for i in range(4):
+        print(f"Warmup run #{i}")
+        start = time()
+        for res in map(parallel_jaccard, pairs):
+            print(f"\t{time() - start}s => {res[0]}: {res[1]}", flush=True)
+
+    with Pool(8) as p:
+        for i in range(iterations):
+            start = time()
+            print(f"#{i + 1}:", end="", flush=True)
+            for res in p.imap_unordered(parallel_jaccard, pairs):
+                print(f"\t{time() - start}s => {res[0]}: {res[1]}", flush=True)
+            # for pair in pairs:
+            #     value = jaccard(*pair)
+            #     print(f"\t{time() - start}s => {pair}: {value}", flush=True)