numpy - 确保 numpy 在 mac pro 上使用 MKL 库

Question

我正在使用 Enthought 的 Canopy/EPD 版本的 python，它带有与 MKL 链接的 numpy。我目前正在我的工作计算机(Windows 7、Quad Core i5 @ 3.33 Ghz、4 GB ram)和我的家庭工作站(Mac Pro 3.1、Ubuntu 12.04、2x Quad Core Xeon)上并行运行一组模拟(使用 PP) @ 2.8 Ghz，6 GB 内存)。

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运行得更快(每次迭代 35 秒，而在 mac pro 上为 60 秒)。问题是内核之间的完美平衡(令人尴尬的并行问题)，所以我怀疑家里 linux 工作站上的 MKL 库存在问题。有没有办法验证 MKL 库实际上正在 python 中使用。我读过一些帖子，说你可以检查 python 是否链接到它，但它不能确保它被正确构建并且实际上正在被使用。

Answer 1

>>> numpy.show_config()

您将看到类似这样的输出，表明 MKL 确实已链接。

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']