Question

我正在使用Enthought的Canopy / EPD版本的python，它附带了与MKL相关联的numpy。我目前在我的工作计算机（Windows 7，四核i5 @ 3.33 Ghz，4 GB RAM）和我的家庭工作站（Mac Pro 3.1，Ubuntu 12.04,2x四核Xeon）上并行运行一组模拟（使用PP） @ 2.8 Ghz，6 GB ram）。

但是当我对我的模拟进行基准测试时，它们在工作计算机上的运行速度更快（每次迭代35秒，而在mac pro上为60秒）。问题是在核心之间完全平衡（令人尴尬的并行问题），所以我怀疑在家里的linux工作站上存在MKL库的问题。有没有办法验证MKL库实际上是否在python中使用。我已经读过线程，说你可以查看python是否链接到它，但它不能确保它是正确构建的并且实际上正在使用。

Answer 1

>>> numpy.show_config()

你会看到类似这样的输出，表明MKL确实是链接的。

lapack_opt_info:
    libraries = ['mkl_lapack95_lp64', 'mkl_intel_lp64', 'mkl_intel_thread', 'mkl_core', 'mkl_mc', 'mkl_mc3', 'pthread']
    library_dirs = ['/Users/vagrant/src/master-env/Resources/Python.app/Contents/MacOS/../../../../lib']
    define_macros = [('SCIPY_MKL_H', None)]
    include_dirs = ['/Users/vagrant/src/master-env/Resources/Python.app/Contents/MacOS/../../../../include']
blas_opt_info:
    libraries = ['mkl_intel_lp64', 'mkl_intel_thread', 'mkl_core', 'mkl_mc', 'mkl_mc3', 'pthread']
    library_dirs = ['/Users/vagrant/src/master-env/Resources/Python.app/Contents/MacOS/../../../../lib']
    define_macros = [('SCIPY_MKL_H', None)]
    include_dirs = ['/Users/vagrant/src/master-env/Resources/Python.app/Contents/MacOS/../../../../include']
openblas_info:
NOT AVAILABLE
lapack_mkl_info:
    libraries = ['mkl_lapack95_lp64', 'mkl_intel_lp64', 'mkl_intel_thread', 'mkl_core', 'mkl_mc', 'mkl_mc3', 'pthread']
    library_dirs = ['/Users/vagrant/src/master-env/Resources/Python.app/Contents/MacOS/../../../../lib']
    define_macros = [('SCIPY_MKL_H', None)]
    include_dirs = ['/Users/vagrant/src/master-env/Resources/Python.app/Contents/MacOS/../../../../include']
blas_mkl_info:
    libraries = ['mkl_intel_lp64', 'mkl_intel_thread', 'mkl_core', 'mkl_mc', 'mkl_mc3', 'pthread']
    library_dirs = ['/Users/vagrant/src/master-env/Resources/Python.app/Contents/MacOS/../../../../lib']
    define_macros = [('SCIPY_MKL_H', None)]
    include_dirs = ['/Users/vagrant/src/master-env/Resources/Python.app/Contents/MacOS/../../../../include']
mkl_info:
    libraries = ['mkl_intel_lp64', 'mkl_intel_thread', 'mkl_core', 'mkl_mc', 'mkl_mc3', 'pthread']
    library_dirs = ['/Users/vagrant/src/master-env/Resources/Python.app/Contents/MacOS/../../../../lib']
    define_macros = [('SCIPY_MKL_H', None)]
    include_dirs = ['/Users/vagrant/src/master-env/Resources/Python.app/Contents/MacOS/../../../../include']

确保numpy在mac pro上使用MKL库

1 个答案: