Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
flatten_bench.py 3.04 KB
Newer Older
aiss's avatar
push Deepspeed 0.6.3 rocm version  
aiss committed
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
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134 
#!/usr/bin/env python
# run the benchmark under timeit (-t), cProfile (-c), line_profiler (-l)
#
# usage:
# ./flatten_bench.py -t
# ./flatten_bench.py -c
# kernprof -l flatten_bench.py -l; python -m line_profiler  flatten_bench.py.lprof

import argparse

import gc

import torch
from torch._utils import _flatten_dense_tensors, _unflatten_dense_tensors
from deepspeed.ops.op_builder import UtilsBuilder

from apex_C import flatten as flatten_apex

util_ops = UtilsBuilder().load()
flatten = util_ops.flatten
unflatten = util_ops.unflatten

torch.manual_seed(0)
# emulate a small typical model weights
x = [
    torch.rand((512,
                512)).cuda(),
    torch.rand((512,
                1024)).cuda(),
    torch.rand((512,
                30000)).cuda()
]
t = x * 30

# warm up and check that the same output is produced
flat_py = _flatten_dense_tensors(t)
flat_cpp = flatten(t)
flat_apex = flatten_apex(t)
#numel = flat_cpp.numel()
assert torch.eq(flat_py, flat_cpp).all(), "both produce the same tensor"
assert torch.eq(flat_py, flat_apex).all(), "both produce the same tensor"

TIMES = 1000


# the programs being tested
def py():
    for i in range(TIMES):
        flat = _flatten_dense_tensors(t)


def cpp():
    for i in range(TIMES):
        flat = flatten(t)


def apex():
    for i in range(TIMES):
        flat = flatten_apex(t)


#### cProfile ####

import cProfile


def cprofileme():
    print("--------------- cProfile -----------------")
    print("py")
    cProfile.run("py()", sort=-1)
    gc.collect()
    torch.cuda.empty_cache()
    print("cpp")
    cProfile.run("cpp()", sort=-1)
    gc.collect()
    torch.cuda.empty_cache()
    print("apex")
    cProfile.run("apex()", sort=-1)
    gc.collect()
    torch.cuda.empty_cache()


#### timeit ####

import timeit


def timeme():
    print("--------------- timeit -----------------")
    print(f'py  ={timeit.Timer("py()", globals=globals()).timeit(number=1)}')
    gc.collect()
    torch.cuda.empty_cache()
    print(f'cpp ={timeit.Timer("cpp()", globals=globals()).timeit(number=1)}')
    gc.collect()
    torch.cuda.empty_cache()
    print(f'apex={timeit.Timer("apex()", globals=globals()).timeit(number=1)}')
    gc.collect()
    torch.cuda.empty_cache()


#### line_profiler ####
# this one requires a special way to be called
# pip install line_profiler
# kernprof -l flatten_bench.py -l; python -m line_profiler  flatten_bench.py.lprof


def line_profileme():
    print("--------------- line_profiler -----------------")
    print("py")
    profile(py)()
    gc.collect()
    torch.cuda.empty_cache()
    print("cpp")
    profile(cpp)()
    gc.collect()
    torch.cuda.empty_cache()
    print("apex")
    profile(apex)()
    gc.collect()
    torch.cuda.empty_cache()


if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("-l", action='store_true')
    parser.add_argument("-c", action='store_true')
    parser.add_argument("-t", action='store_true')
    args = parser.parse_args()
    if args.l:
        line_profileme()
    elif args.c:
        cprofileme()
    elif args.t:
        timeme()