1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
|
import argparse
import numpy as np
from caffe2.python import core, workspace
def benchmark_mul_gradient(args):
workspace.FeedBlob("dC", np.random.rand(args.m, args.n).astype(np.float32))
workspace.FeedBlob("A", np.random.rand(args.m, args.n).astype(np.float32))
workspace.FeedBlob("B", np.random.rand(args.n).astype(np.float32))
net = core.Net("mynet")
net.MulGradient(
["dC", "A", "B"],
["dC" if args.inplace else "dA", "dB"],
broadcast=True,
axis=1,
allow_broadcast_fastpath=args.allow_broadcast_fastpath,
)
workspace.CreateNet(net)
workspace.BenchmarkNet(net.Name(), 1, args.iteration, True)
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="benchmark for MulGradient.")
parser.add_argument(
'-m', type=int, default=9508,
help="The number of rows of A")
parser.add_argument(
"-n", type=int, default=80,
help="The number of columns of A")
parser.add_argument(
'-i', "--iteration", type=int, default=100,
help="The number of iterations.")
parser.add_argument(
"--inplace",
action='store_true', help="Whether to perform the op in-place.")
parser.add_argument(
"--allow-broadcast-fastpath",
action='store_true', help="Whether the broadcast fastpath is enabled.")
args, extra_args = parser.parse_known_args()
core.GlobalInit(['python'] + extra_args)
benchmark_mul_gradient(args)
|
