[Numpy-svn] [numpy/numpy] eb6cf4: ENH: Vectorize float min/max operation with sse2

GitHub noreply@github....
Tue Jun 11 12:39:23 CDT 2013


  Branch: refs/heads/master
  Home:   https://github.com/numpy/numpy
  Commit: eb6cf4beacbd79dd06573aee6ac33df3e27bd509
      https://github.com/numpy/numpy/commit/eb6cf4beacbd79dd06573aee6ac33df3e27bd509
  Author: Julian Taylor <jtaylor.debian@googlemail.com>
  Date:   2013-06-09 (Sun, 09 Jun 2013)

  Changed paths:
    M doc/release/1.8.0-notes.rst
    M numpy/core/src/umath/loops.c.src
    M numpy/core/src/umath/simd.inc.src
    M numpy/core/tests/test_umath.py

  Log Message:
  -----------
  ENH: Vectorize float min/max operation with sse2

Improves performance by ~1.5/3.0 for float/double.


  Commit: 6bcba96de9cead06c13d5a97e7cfe195f6cc20e5
      https://github.com/numpy/numpy/commit/6bcba96de9cead06c13d5a97e7cfe195f6cc20e5
  Author: Julian Taylor <jtaylor.debian@googlemail.com>
  Date:   2013-06-09 (Sun, 09 Jun 2013)

  Changed paths:
    M doc/release/1.8.0-notes.rst
    M numpy/core/src/umath/loops.c.src
    M numpy/core/src/umath/simd.inc.src
    M numpy/core/tests/test_scalarmath.py

  Log Message:
  -----------
  ENH: vectorize base math with SSE2

Improves performance by ~1.5/3.0 for float/double for inplace or cpu
cached operations


  Commit: c20531c22e6ddb7f2ccdefbcfc4f67eb1bd4b455
      https://github.com/numpy/numpy/commit/c20531c22e6ddb7f2ccdefbcfc4f67eb1bd4b455
  Author: Julian Taylor <jtaylor.debian@googlemail.com>
  Date:   2013-06-10 (Mon, 10 Jun 2013)

  Changed paths:
    M numpy/core/src/umath/simd.inc.src

  Log Message:
  -----------
  MAINT: guard prototypes with HAVE_EMMINTRIN_H

avoids declared but not defined warnings


  Commit: 88b459b7cd009db6f542d6d9e365a0ee311e96be
      https://github.com/numpy/numpy/commit/88b459b7cd009db6f542d6d9e365a0ee311e96be
  Author: Julian Taylor <jtaylor.debian@googlemail.com>
  Date:   2013-06-11 (Tue, 11 Jun 2013)

  Changed paths:
    M numpy/core/src/umath/simd.inc.src

  Log Message:
  -----------
  MAINT: fix an uninitialized use in the no fenv fallback


  Commit: ffa0130774242fb1b35a5f5a36366968d489d729
      https://github.com/numpy/numpy/commit/ffa0130774242fb1b35a5f5a36366968d489d729
  Author: Julian Taylor <jtaylor.debian@googlemail.com>
  Date:   2013-06-11 (Tue, 11 Jun 2013)

  Changed paths:
    M doc/release/1.8.0-notes.rst

  Log Message:
  -----------
  DOC: use full ufunc names


  Commit: d0f505004892e7d88c1d4f5c79c45eabf97ddd83
      https://github.com/numpy/numpy/commit/d0f505004892e7d88c1d4f5c79c45eabf97ddd83
  Author: Charles Harris <charlesr.harris@gmail.com>
  Date:   2013-06-11 (Tue, 11 Jun 2013)

  Changed paths:
    M doc/release/1.8.0-notes.rst
    M numpy/core/src/umath/loops.c.src
    M numpy/core/src/umath/simd.inc.src
    M numpy/core/tests/test_scalarmath.py
    M numpy/core/tests/test_umath.py

  Log Message:
  -----------
  Merge pull request #3419 from juliantaylor/vectorize-rest

min/max and base math vectorization


Compare: https://github.com/numpy/numpy/compare/15f2d6073bad...d0f505004892


More information about the Numpy-svn mailing list