diff options
| author | Charles Harris <charlesr.harris@gmail.com> | 2013-06-15 15:39:39 -0700 |
|---|---|---|
| committer | Charles Harris <charlesr.harris@gmail.com> | 2013-06-15 15:39:39 -0700 |
| commit | 7dc65761e66913aa34cc8afee052e89cc983fd4e (patch) | |
| tree | 04713c17af80a352a880f2fc1895094f4b74f49d /numpy | |
| parent | e036deb49b74fc2432066497d7c1d4bb61a74caa (diff) | |
| parent | 9871460decba504013e68a16313efe052f3cb679 (diff) | |
| download | numpy-7dc65761e66913aa34cc8afee052e89cc983fd4e.tar.gz | |
Merge pull request #3445 from juliantaylor/revert-x86-unaligned-access
BUG: Revert "ENH: enable unaligned loads on x86"
Diffstat (limited to 'numpy')
| -rw-r--r-- | numpy/core/src/multiarray/lowlevel_strided_loops.c.src | 9 |
1 files changed, 7 insertions, 2 deletions
diff --git a/numpy/core/src/multiarray/lowlevel_strided_loops.c.src b/numpy/core/src/multiarray/lowlevel_strided_loops.c.src index b0770168f..0adb24c8d 100644 --- a/numpy/core/src/multiarray/lowlevel_strided_loops.c.src +++ b/numpy/core/src/multiarray/lowlevel_strided_loops.c.src @@ -21,10 +21,15 @@ #include "lowlevel_strided_loops.h" /* - * x86 platform works with unaligned access + * x86 platform works with unaligned access but the compiler is allowed to + * assume all data is aligned to its size by the C standard. This means it can + * vectorize instructions peeling only by the size of the type, if the data is + * not aligned to this size one ends up with data not correctly aligned for SSE + * instructions (16 byte). + * So this flag can only be enabled if autovectorization is disabled. */ #if (defined(NPY_CPU_X86) || defined(NPY_CPU_AMD64)) -# define NPY_USE_UNALIGNED_ACCESS 1 +# define NPY_USE_UNALIGNED_ACCESS 0 #else # define NPY_USE_UNALIGNED_ACCESS 0 #endif |