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
135
136
137
138
139
|
cimport numpy as cnp
from cython cimport final
from ...utils._typedefs cimport ITYPE_t, DTYPE_t, SPARSE_INDEX_TYPE_t
cnp.import_array()
{{for name_suffix, INPUT_DTYPE_t in [('64', 'DTYPE_t'), ('32', 'cnp.float32_t')]}}
from ._datasets_pair cimport DatasetsPair{{name_suffix}}
cpdef DTYPE_t[::1] _sqeuclidean_row_norms{{name_suffix}}(
X,
ITYPE_t num_threads,
)
cdef class BaseDistancesReduction{{name_suffix}}:
"""
Base float{{name_suffix}} implementation template of the pairwise-distances
reduction backends.
Implementations inherit from this template and may override the several
defined hooks as needed in order to easily extend functionality with
minimal redundant code.
"""
cdef:
readonly DatasetsPair{{name_suffix}} datasets_pair
# The number of threads that can be used is stored in effective_n_threads.
#
# The number of threads to use in the parallelization strategy
# (i.e. parallel_on_X or parallel_on_Y) can be smaller than effective_n_threads:
# for small datasets, fewer threads might be needed to loop over pair of chunks.
#
# Hence, the number of threads that _will_ be used for looping over chunks
# is stored in chunks_n_threads, allowing solely using what we need.
#
# Thus, an invariant is:
#
# chunks_n_threads <= effective_n_threads
#
ITYPE_t effective_n_threads
ITYPE_t chunks_n_threads
ITYPE_t n_samples_chunk, chunk_size
ITYPE_t n_samples_X, X_n_samples_chunk, X_n_chunks, X_n_samples_last_chunk
ITYPE_t n_samples_Y, Y_n_samples_chunk, Y_n_chunks, Y_n_samples_last_chunk
bint execute_in_parallel_on_Y
@final
cdef void _parallel_on_X(self) nogil
@final
cdef void _parallel_on_Y(self) nogil
# Placeholder methods which have to be implemented
cdef void _compute_and_reduce_distances_on_chunks(
self,
ITYPE_t X_start,
ITYPE_t X_end,
ITYPE_t Y_start,
ITYPE_t Y_end,
ITYPE_t thread_num,
) nogil
# Placeholder methods which can be implemented
cdef void compute_exact_distances(self) nogil
cdef void _parallel_on_X_parallel_init(
self,
ITYPE_t thread_num,
) nogil
cdef void _parallel_on_X_init_chunk(
self,
ITYPE_t thread_num,
ITYPE_t X_start,
ITYPE_t X_end,
) nogil
cdef void _parallel_on_X_pre_compute_and_reduce_distances_on_chunks(
self,
ITYPE_t X_start,
ITYPE_t X_end,
ITYPE_t Y_start,
ITYPE_t Y_end,
ITYPE_t thread_num,
) nogil
cdef void _parallel_on_X_prange_iter_finalize(
self,
ITYPE_t thread_num,
ITYPE_t X_start,
ITYPE_t X_end,
) nogil
cdef void _parallel_on_X_parallel_finalize(
self,
ITYPE_t thread_num
) nogil
cdef void _parallel_on_Y_init(
self,
) nogil
cdef void _parallel_on_Y_parallel_init(
self,
ITYPE_t thread_num,
ITYPE_t X_start,
ITYPE_t X_end,
) nogil
cdef void _parallel_on_Y_pre_compute_and_reduce_distances_on_chunks(
self,
ITYPE_t X_start,
ITYPE_t X_end,
ITYPE_t Y_start,
ITYPE_t Y_end,
ITYPE_t thread_num,
) nogil
cdef void _parallel_on_Y_synchronize(
self,
ITYPE_t X_start,
ITYPE_t X_end,
) nogil
cdef void _parallel_on_Y_finalize(
self,
) nogil
{{endfor}}
|
