diff options
| author | Raymond Hettinger <python@rcn.com> | 2013-07-28 09:34:42 (GMT) |
|---|---|---|
| committer | Raymond Hettinger <python@rcn.com> | 2013-07-28 09:34:42 (GMT) |
| commit | 662908b5e536308713ffb4bcbe3a7a8f250e4003 (patch) | |
| tree | f558d5b52c35a612db104639e462617fead513fd /Modules | |
| parent | 16b10c64d719fed995ecfe01a1f18e4e184d0659 (diff) | |
| download | cpython-662908b5e536308713ffb4bcbe3a7a8f250e4003.zip cpython-662908b5e536308713ffb4bcbe3a7a8f250e4003.tar.gz cpython-662908b5e536308713ffb4bcbe3a7a8f250e4003.tar.bz2 | |
Restore the data block size to 62.
The former block size traded away good fit within cache lines in
order to gain faster division in deque_item(). However, compilers
are getting smarter and can now replace the slow division operation
with a fast integer multiply and right shift. Accordingly, it makes
sense to go back to a size that lets blocks neatly fill entire
cache-lines.
GCC-4.8 and CLANG 4.0 both compute "x // 62" with something
roughly equivalent to "x * 9520900167075897609 >> 69".
Diffstat (limited to 'Modules')
| -rw-r--r-- | Modules/_collectionsmodule.c | 9 |
1 files changed, 6 insertions, 3 deletions
diff --git a/Modules/_collectionsmodule.c b/Modules/_collectionsmodule.c index dc31cbc..26d8783 100644 --- a/Modules/_collectionsmodule.c +++ b/Modules/_collectionsmodule.c @@ -10,11 +10,14 @@ /* The block length may be set to any number over 1. Larger numbers * reduce the number of calls to the memory allocator, give faster * indexing and rotation, and reduce the link::data overhead ratio. - * Ideally, the block length should be a power-of-two for faster - * division/modulo computations during indexing. + * + * Ideally, the block length will be set to two less than some + * multiple of the cache-line length (so that the full block + * including the leftlink and rightlink will fit neatly into + * cache lines). */ -#define BLOCKLEN 64 +#define BLOCKLEN 62 #define CENTER ((BLOCKLEN - 1) / 2) /* A `dequeobject` is composed of a doubly-linked list of `block` nodes. |