[Numpy-svn] [numpy/numpy] c7fae3: ENH: add small kernel correlate function

[GitHub]

  Branch: refs/heads/master
  Home:   https://github.com/numpy/numpy
  Commit: c7fae327a79b95671833e641612ca87e1d6a6b48
      https://github.com/numpy/numpy/commit/c7fae327a79b95671833e641612ca87e1d6a6b48
  Author: Julian Taylor <jtaylor.debian at googlemail.com>
  Date:   2014-09-26 (Fri, 26 Sep 2014)

  Changed paths:
    M numpy/core/bscript
    M numpy/core/setup.py
    M numpy/core/src/multiarray/multiarraymodule.c
    A numpy/core/src/multiarray/templ_common.h.src
    M numpy/core/tests/test_numeric.py

  Log Message:
  -----------
  ENH: add small kernel correlate function

For cases like convolve/correlate with small kernel calling out to BLAS
dot is very slow as it goes through many wrappers and BLAS is typically
optimized for very large data.
So add a template utility file and add a special function for small dot
products.
2-4 times faster than openblas dot for kernel sizes < 11.


  Commit: 002b0de24d7c88cb97d16b9e8df6948fe4f07d5d
      https://github.com/numpy/numpy/commit/002b0de24d7c88cb97d16b9e8df6948fe4f07d5d
  Author: Charles Harris <charlesr.harris at gmail.com>
  Date:   2014-09-25 (Thu, 25 Sep 2014)

  Changed paths:
    M numpy/core/bscript
    M numpy/core/setup.py
    M numpy/core/src/multiarray/multiarraymodule.c
    A numpy/core/src/multiarray/templ_common.h.src
    M numpy/core/tests/test_numeric.py

  Log Message:
  -----------
  Merge pull request #5122 from juliantaylor/small-dot

ENH: add small kernel correlate function


Compare: https://github.com/numpy/numpy/compare/caeb88871516...002b0de24d7c