/usr/lib/python2.7/dist-packages/numexpr/utils.py is in python-numexpr 2.6.1-4.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 | ###################################################################
# Numexpr - Fast numerical array expression evaluator for NumPy.
#
# License: MIT
# Author: See AUTHORS.txt
#
# See LICENSE.txt and LICENSES/*.txt for details about copyright and
# rights to use.
####################################################################
import os
import subprocess
from numexpr.interpreter import _set_num_threads
from numexpr import use_vml
if use_vml:
from numexpr.interpreter import (
_get_vml_version, _set_vml_accuracy_mode, _set_vml_num_threads)
def get_vml_version():
"""Get the VML/MKL library version."""
if use_vml:
return _get_vml_version()
else:
return None
def set_vml_accuracy_mode(mode):
"""
Set the accuracy mode for VML operations.
The `mode` parameter can take the values:
- 'high': high accuracy mode (HA), <1 least significant bit
- 'low': low accuracy mode (LA), typically 1-2 least significant bits
- 'fast': enhanced performance mode (EP)
- None: mode settings are ignored
This call is equivalent to the `vmlSetMode()` in the VML library.
See:
http://www.intel.com/software/products/mkl/docs/webhelp/vml/vml_DataTypesAccuracyModes.html
for more info on the accuracy modes.
Returns old accuracy settings.
"""
if use_vml:
acc_dict = {None: 0, 'low': 1, 'high': 2, 'fast': 3}
acc_reverse_dict = {1: 'low', 2: 'high', 3: 'fast'}
if mode not in acc_dict.keys():
raise ValueError(
"mode argument must be one of: None, 'high', 'low', 'fast'")
retval = _set_vml_accuracy_mode(acc_dict.get(mode, 0))
return acc_reverse_dict.get(retval)
else:
return None
def set_vml_num_threads(nthreads):
"""
Suggests a maximum number of threads to be used in VML operations.
This function is equivalent to the call
`mkl_domain_set_num_threads(nthreads, MKL_DOMAIN_VML)` in the MKL
library. See:
http://www.intel.com/software/products/mkl/docs/webhelp/support/functn_mkl_domain_set_num_threads.html
for more info about it.
"""
if use_vml:
_set_vml_num_threads(nthreads)
def set_num_threads(nthreads):
"""
Sets a number of threads to be used in operations.
Returns the previous setting for the number of threads.
During initialization time Numexpr sets this number to the number
of detected cores in the system (see `detect_number_of_cores()`).
If you are using Intel's VML, you may want to use
`set_vml_num_threads(nthreads)` to perform the parallel job with
VML instead. However, you should get very similar performance
with VML-optimized functions, and VML's parallelizer cannot deal
with common expresions like `(x+1)*(x-2)`, while Numexpr's one
can.
"""
old_nthreads = _set_num_threads(nthreads)
return old_nthreads
def detect_number_of_cores():
"""
Detects the number of cores on a system. Cribbed from pp.
"""
# Linux, Unix and MacOS:
if hasattr(os, "sysconf"):
if "SC_NPROCESSORS_ONLN" in os.sysconf_names:
# Linux & Unix:
ncpus = os.sysconf("SC_NPROCESSORS_ONLN")
if isinstance(ncpus, int) and ncpus > 0:
return ncpus
else: # OSX:
return int(subprocess.check_output(["sysctl", "-n", "hw.ncpu"]))
# Windows:
if os.environ.has_key("NUMBER_OF_PROCESSORS"):
ncpus = int(os.environ["NUMBER_OF_PROCESSORS"]);
if ncpus > 0:
return ncpus
return 1 # Default
def detect_number_of_threads():
"""
If this is modified, please update the note in: https://github.com/pydata/numexpr/wiki/Numexpr-Users-Guide
"""
try:
nthreads = int(os.environ['NUMEXPR_NUM_THREADS'])
except KeyError:
nthreads = int(os.environ.get('OMP_NUM_THREADS', detect_number_of_cores()))
# Check that we don't activate too many threads at the same time.
# 8 seems a sensible value.
if nthreads > 8:
nthreads = 8
# Check that we don't surpass the MAX_THREADS in interpreter.cpp
if nthreads > 4096:
nthreads = 4096
return nthreads
class CacheDict(dict):
"""
A dictionary that prevents itself from growing too much.
"""
def __init__(self, maxentries):
self.maxentries = maxentries
super(CacheDict, self).__init__(self)
def __setitem__(self, key, value):
# Protection against growing the cache too much
if len(self) > self.maxentries:
# Remove a 10% of (arbitrary) elements from the cache
entries_to_remove = self.maxentries // 10
for k in self.keys()[:entries_to_remove]:
super(CacheDict, self).__delitem__(k)
super(CacheDict, self).__setitem__(key, value)
|