diff options
Diffstat (limited to 'Python/hamt.c')
| -rw-r--r-- | Python/hamt.c | 25 |
1 files changed, 3 insertions, 22 deletions
diff --git a/Python/hamt.c b/Python/hamt.c index 8801c5e..e272e88 100644 --- a/Python/hamt.c +++ b/Python/hamt.c @@ -1,5 +1,6 @@ #include "Python.h" +#include "pycore_bitutils.h" // _Py_popcount32 #include "pycore_hamt.h" #include "pycore_object.h" // _PyObject_GC_TRACK() #include <stddef.h> // offsetof() @@ -434,29 +435,9 @@ hamt_bitpos(int32_t hash, uint32_t shift) } static inline uint32_t -hamt_bitcount(uint32_t i) -{ - /* We could use native popcount instruction but that would - require to either add configure flags to enable SSE4.2 - support or to detect it dynamically. Otherwise, we have - a risk of CPython not working properly on older hardware. - - In practice, there's no observable difference in - performance between using a popcount instruction or the - following fallback code. - - The algorithm is copied from: - https://graphics.stanford.edu/~seander/bithacks.html - */ - i = i - ((i >> 1) & 0x55555555); - i = (i & 0x33333333) + ((i >> 2) & 0x33333333); - return (((i + (i >> 4)) & 0xF0F0F0F) * 0x1010101) >> 24; -} - -static inline uint32_t hamt_bitindex(uint32_t bitmap, uint32_t bit) { - return hamt_bitcount(bitmap & (bit - 1)); + return (uint32_t)_Py_popcount32(bitmap & (bit - 1)); } @@ -820,7 +801,7 @@ hamt_node_bitmap_assoc(PyHamtNode_Bitmap *self, else { /* There was no key before with the same (shift,hash). */ - uint32_t n = hamt_bitcount(self->b_bitmap); + uint32_t n = (uint32_t)_Py_popcount32(self->b_bitmap); if (n >= 16) { /* When we have a situation where we want to store more |