我正在尝试在2台不同的计算机上运行 sklearn.decomposition.TruncatedSVD() 并了解性能差异。
计算机1 （Windows 7，物理计算机）
OS Name Microsoft Windows 7 Professional
System Type x64-based PC
Processor Intel(R) Core(TM) i7-3770 CPU @ 3.40GHz, 3401 Mhz, 4 Core(s),
8 Logical Installed Physical Memory (RAM) 8.00 GB
Total Physical Memory 7.89 GB
计算机2 （Debian，在亚马逊云上）
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
CPU(s): 8
width: 64 bits
capabilities: ldt16 vsyscall32
*-core
description: Motherboard
physical id: 0
*-memory
description: System memory
physical id: 0
size: 29GiB
*-cpu
product: Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz
vendor: Intel Corp.
physical id: 1
bus info: cpu@0
width: 64 bits
计算机3 （Windows 2008R2，在亚马逊云上）
OS Name Microsoft Windows Server 2008 R2 Datacenter
Version 6.1.7601 Service Pack 1 Build 7601
System Type x64-based PC
Processor Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz, 2500 Mhz,
4 Core(s), 8 Logical Processor(s)
Installed Physical Memory (RAM) 30.0 GB
两台计算机都运行Python 3.2和相同的sklearn，numpy，scipy版本
我按如下方式运行 cProfile ：
print(vectors.shape)
>>> (7500, 2042)
_decomp = TruncatedSVD(n_components=680, random_state=1)
global _o
_o = _decomp
cProfile.runctx('_o.fit_transform(vectors)', globals(), locals(), sort=1)
计算机1输出
>>> 833 function calls in 1.710 seconds
Ordered by: internal time
ncalls tottime percall cumtime percall filename:lineno(function)
1 0.767 0.767 0.782 0.782 decomp_svd.py:15(svd)
1 0.249 0.249 0.249 0.249 {method 'enable' of '_lsprof.Profiler' objects}
1 0.183 0.183 0.183 0.183 {method 'normal' of 'mtrand.RandomState' objects}
6 0.174 0.029 0.174 0.029 {built-in method csr_matvecs}
6 0.123 0.021 0.123 0.021 {built-in method csc_matvecs}
2 0.110 0.055 0.110 0.055 decomp_qr.py:14(safecall)
1 0.035 0.035 0.035 0.035 {built-in method dot}
1 0.020 0.020 0.589 0.589 extmath.py:185(randomized_range_finder)
2 0.018 0.009 0.019 0.010 function_base.py:532(asarray_chkfinite)
24 0.014 0.001 0.014 0.001 {method 'ravel' of 'numpy.ndarray' objects}
1 0.007 0.007 0.009 0.009 twodim_base.py:427(triu)
1 0.004 0.004 1.710 1.710 extmath.py:232(randomized_svd)
计算机2输出
>>> 858 function calls in 40.145 seconds
Ordered by: internal time
ncalls tottime percall cumtime percall filename:lineno(function)
2 32.116 16.058 32.116 16.058 {built-in method dot}
1 6.148 6.148 6.156 6.156 decomp_svd.py:15(svd)
2 0.561 0.281 0.561 0.281 decomp_qr.py:14(safecall)
6 0.561 0.093 0.561 0.093 {built-in method csr_matvecs}
1 0.337 0.337 0.337 0.337 {method 'normal' of 'mtrand.RandomState' objects}
6 0.202 0.034 0.202 0.034 {built-in method csc_matvecs}
1 0.052 0.052 1.633 1.633 extmath.py:183(randomized_range_finder)
1 0.045 0.045 0.054 0.054 _methods.py:73(_var)
1 0.023 0.023 0.023 0.023 {method 'argmax' of 'numpy.ndarray' objects}
1 0.023 0.023 0.046 0.046 extmath.py:531(svd_flip)
1 0.016 0.016 40.145 40.145 <string>:1(<module>)
24 0.011 0.000 0.011 0.000 {method 'ravel' of 'numpy.ndarray' objects}
6 0.009 0.002 0.009 0.002 {method 'reduce' of 'numpy.ufunc' objects}
2 0.008 0.004 0.009 0.004 function_base.py:532(asarray_chkfinite)
计算机3输出
>>> 858 function calls in 2.223 seconds
Ordered by: internal time
ncalls tottime percall cumtime percall filename:lineno(function)
1 0.956 0.956 0.972 0.972 decomp_svd.py:15(svd)
2 0.306 0.153 0.306 0.153 {built-in method dot}
1 0.274 0.274 0.274 0.274 {method 'normal' of 'mtrand.RandomState' objects}
6 0.205 0.034 0.205 0.034 {built-in method csr_matvecs}
6 0.151 0.025 0.151 0.025 {built-in method csc_matvecs}
2 0.133 0.067 0.133 0.067 decomp_qr.py:14(safecall)
1 0.032 0.032 0.043 0.043 _methods.py:73(_var)
1 0.030 0.030 0.030 0.030 {method 'argmax' of 'numpy.ndarray' objects}
24 0.026 0.001 0.026 0.001 {method 'ravel' of 'numpy.ndarray' objects}
2 0.019 0.010 0.020 0.010 function_base.py:532(asarray_chkfinite)
1 0.019 0.019 0.773 0.773 extmath.py:183(randomized_range_finder)
1 0.019 0.019 0.049 0.049 extmath.py:531(svd_flip)
请注意 {内置方法点} 差异从0.035秒/调用到16.058秒/调用，慢450倍!!
------+---------+---------+---------+---------+---------------------------------------
ncalls| tottime | percall | cumtime | percall | filename:lineno(function) HARDWARE
------+---------+---------+---------+---------+---------------------------------------
1 | 0.035 | 0.035 | 0.035 | 0.035 | {built-in method dot} Computer 1
2 | 32.116 | 16.058 | 32.116 | 16.058 | {built-in method dot} Computer 2
2 | 0.306 | 0.153 | 0.306 | 0.153 | {built-in method dot} Computer 3
我知道应该存在性能差异，但我应该这么高吗？
有没有办法可以进一步调试这个性能问题？
修改
我测试了一台新计算机，计算机3，其硬件类似于计算机2，具有不同的操作系统
结果是0.153秒/ {内置方法点}的调用仍然比Linux快100倍
编辑2
计算机1 numpy config
>>> np.__config__.show()
lapack_opt_info:
libraries = ['mkl_lapack95_lp64', 'mkl_blas95_lp64', 'mkl_intel_lp64', 'mkl_intel_thread', 'mkl_core', 'libiomp5md', 'libifportmd', 'mkl_lapack95_lp64', 'mkl_blas95_lp64', 'mkl_intel_lp64', 'mkl_intel_thread', 'mkl_core', 'libiomp5md', 'libifportmd']
library_dirs = ['C:/Program Files (x86)/Intel/Composer XE/mkl/lib/intel64']
define_macros = [('SCIPY_MKL_H', None)]
include_dirs = ['C:/Program Files (x86)/Intel/Composer XE/mkl/include']
blas_opt_info:
libraries = ['mkl_lapack95_lp64', 'mkl_blas95_lp64', 'mkl_intel_lp64', 'mkl_intel_thread', 'mkl_core', 'libiomp5md', 'libifportmd']
library_dirs = ['C:/Program Files (x86)/Intel/Composer XE/mkl/lib/intel64']
define_macros = [('SCIPY_MKL_H', None)]
include_dirs = ['C:/Program Files (x86)/Intel/Composer XE/mkl/include']
openblas_info:
NOT AVAILABLE
lapack_mkl_info:
libraries = ['mkl_lapack95_lp64', 'mkl_blas95_lp64', 'mkl_intel_lp64', 'mkl_intel_thread', 'mkl_core', 'libiomp5md', 'libifportmd', 'mkl_lapack95_lp64', 'mkl_blas95_lp64', 'mkl_intel_lp64', 'mkl_intel_thread', 'mkl_core', 'libiomp5md', 'libifportmd']
library_dirs = ['C:/Program Files (x86)/Intel/Composer XE/mkl/lib/intel64']
define_macros = [('SCIPY_MKL_H', None)]
include_dirs = ['C:/Program Files (x86)/Intel/Composer XE/mkl/include']
blas_mkl_info:
libraries = ['mkl_lapack95_lp64', 'mkl_blas95_lp64', 'mkl_intel_lp64', 'mkl_intel_thread', 'mkl_core', 'libiomp5md', 'libifportmd']
library_dirs = ['C:/Program Files (x86)/Intel/Composer XE/mkl/lib/intel64']
define_macros = [('SCIPY_MKL_H', None)]
include_dirs = ['C:/Program Files (x86)/Intel/Composer XE/mkl/include']
mkl_info:
libraries = ['mkl_lapack95_lp64', 'mkl_blas95_lp64', 'mkl_intel_lp64', 'mkl_intel_thread', 'mkl_core', 'libiomp5md', 'libifportmd']
library_dirs = ['C:/Program Files (x86)/Intel/Composer XE/mkl/lib/intel64']
define_macros = [('SCIPY_MKL_H', None)]
include_dirs = ['C:/Program Files (x86)/Intel/Composer XE/mkl/include']
计算机2 numpy config
>>> np.__config__.show()
lapack_info:
NOT AVAILABLE
lapack_opt_info:
NOT AVAILABLE
blas_info:
libraries = ['blas']
library_dirs = ['/usr/lib']
language = f77
atlas_threads_info:
NOT AVAILABLE
atlas_blas_info:
NOT AVAILABLE
lapack_src_info:
NOT AVAILABLE
openblas_info:
NOT AVAILABLE
atlas_blas_threads_info:
NOT AVAILABLE
blas_mkl_info:
NOT AVAILABLE
blas_opt_info:
libraries = ['blas']
library_dirs = ['/usr/lib']
language = f77
define_macros = [('NO_ATLAS_INFO', 1)]
atlas_info:
NOT AVAILABLE
lapack_mkl_info:
NOT AVAILABLE
mkl_info:
NOT AVAILABLE
答案 0 :(得分：5)
{built-in method dot}是np.dot函数，它是围绕CBLAS例程的NumPy包装器，用于矩阵 - 矩阵，矩阵 - 向量和向量 - 向量乘法。您的Windows计算机使用经过大量调整的Intel MKL版本的CBLAS。 Linux机器正在使用缓慢的旧参考实现。
如果您安装ATLAS或OpenBLAS（两者都可以通过Linux软件包管理器提供），或者实际上是英特尔MKL，您可能会看到大量的加速。尝试sudo apt-get install libatlas-dev，再次检查NumPy配置以查看它是否选择了ATLAS，然后重新测量。
一旦您决定使用正确的CBLAS库，您可能需要重新编译scikit-learn。大多数只是使用NumPy来满足其线性代数需求，但是一些算法（特别是k-means）直接使用CBLAS。
操作系统与此无关。
答案 1 :(得分：1)
注意{内置方法点}差异从0.035秒/调用到16.058秒/调用，慢450倍!!
时钟速度和缓存命中率是需要考虑的两个重要因素。 Xeon E5-2670的缓存比Core i7-3770多得多。 i7-3770具有更高的峰值时钟速度和turbo模式。虽然您的Xeon在硬件中有很大的缓存，但在EC2上，您可能会有效地与其他客户共享该缓存。
有没有办法可以进一步调试这个性能问题？
嗯，您在输入（操作系统和硬件）上有不同的测量（输出）和多个差异。鉴于不同的投入，可能会产生这些不同的产出。
CPU性能计数器将更好地隔离算法在不同系统上的性能影响。 Xeons拥有更丰富的性能计数器，但它们都应该有CPU_CLK_UNHALTED和LLC_MISSES。这些工作通过将指令指针映射到正在执行的代码或缓存未命中等事件。因此，您可以看到代码的哪些部分是CPU和缓存绑定。由于目标速度和缓存大小因目标而异，您可能会发现一个是缓存绑定而另一个是CPU绑定。
Linux有一个名为perf的工具（有时为perf_events）。另请参阅http://www.brendangregg.com/perf.html
在Linux和Windows上，您也可以使用英特尔VTune。