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
|
import numpy as np
from cykhash import unique_int64, unique_int32, unique_float64, unique_float32
from cykhash import unique_stable_int64, unique_stable_int32, unique_stable_float64, unique_stable_float32
UNIQUE={
np.float64 : unique_float64,
np.float32 : unique_float32,
np.int64 : unique_int64,
np.int32 : unique_int32,
}
UNIQUE_STABLE = {
np.float64 : unique_stable_float64,
np.float32 : unique_stable_float32,
np.int64 : unique_stable_int64,
np.int32 : unique_stable_int32,
}
class UniqueArange:
params = [
[np.float64, np.float32, np.int64, np.int32],
[1_000, 2_000, 8_000, 10_000, 100_000, 1_000_000, 10_000_000, 100_000_000],
]
param_names = ["dtype", "M"]
def setup(self, dtype, M):
self.array = np.arange(M, dtype=dtype)
def time_unique(self, dtype, M):
UNIQUE[dtype](self.array)
def time_unique_stable(self, dtype, M):
UNIQUE_STABLE[dtype](self.array)
def peakmem_unique(self, dtype, M):
UNIQUE[dtype](self.array)
def peakmem_unique_stable(self, dtype, M):
UNIQUE_STABLE[dtype](self.array)
class UniqueRandomDivFactor10:
params = [
[np.float64, np.float32, np.int64, np.int32],
[1_000, 2_000, 8_000, 10_000, 100_000, 1_000_000, 10_000_000, 100_000_000],
]
param_names = ["dtype", "M"]
def setup(self, dtype, M):
np.random.seed(42)
self.array = np.random.randint(0, M//10, M).astype(dtype)
def time_unique(self, dtype, M):
UNIQUE[dtype](self.array)
def time_unique_stable(self, dtype, M):
UNIQUE_STABLE[dtype](self.array)
def peakmem_unique(self, dtype, M):
UNIQUE[dtype](self.array)
def peakmem_unique_stable(self, dtype, M):
UNIQUE_STABLE[dtype](self.array)
class UniqueRandomDivFactor10Add220:
params = [
[np.float64, np.float32, np.int64, np.int32],
[1_000, 2_000, 8_000, 10_000, 100_000, 1_000_000, 10_000_000, 100_000_000],
]
param_names = ["dtype", "M"]
def setup(self, dtype, M):
np.random.seed(42)
self.array = (np.random.randint(0, M//10, M)+2**26).astype(dtype)
def time_unique(self, dtype, M):
UNIQUE[dtype](self.array)
def time_unique_stable(self, dtype, M):
UNIQUE_STABLE[dtype](self.array)
class UniqueRandomMulFactor10:
params = [
[np.float64, np.float32, np.int64, np.int32],
[1_000, 2_000, 8_000, 10_000, 100_000, 1_000_000, 10_000_000, 100_000_000],
]
param_names = ["dtype", "M"]
def setup(self, dtype, M):
np.random.seed(42)
self.array = np.random.randint(0, M*10, M).astype(dtype)
def time_unique(self, dtype, M):
UNIQUE[dtype](self.array)
def time_unique_stable(self, dtype, M):
UNIQUE_STABLE[dtype](self.array)
class UniqueSingle:
params = [
[np.float64, np.float32, np.int64, np.int32],
[10_000_000, 100_000_000],
]
param_names = ["dtype", "M"]
def setup(self, dtype, M):
self.array = np.ones(M, dtype=dtype)
def peakmem_unique(self, dtype, M):
UNIQUE[dtype](self.array)
def peakmem_unique_stable(self, dtype, M):
UNIQUE_STABLE[dtype](self.array)
|
