mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-10 20:08:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 11

Restore the data block size to 62.

Browse source 
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".
This commit is contained in:
Raymond Hettinger 2013-07-28 02:39:49 -07:00
parent 1f1d0a57fa
commit 77578204d6
2 changed files with 7 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

2
Lib/test/test_deque.py
View file

@ -536,7 +536,7 @@ class TestBasic(unittest.TestCase):
@support.cpython_only @support.cpython_only
def test_sizeof(self): def test_sizeof(self):
BLOCKLEN = 64 BLOCKLEN = 62
basesize = support.calcobjsize('2P4nlP') basesize = support.calcobjsize('2P4nlP')
blocksize = struct.calcsize('2P%dP' % BLOCKLEN) blocksize = struct.calcsize('2P%dP' % BLOCKLEN)
self.assertEqual(object.__sizeof__(deque()), basesize) self.assertEqual(object.__sizeof__(deque()), basesize)

9
Modules/_collectionsmodule.c
View file

@ -10,11 +10,14 @@
/* The block length may be set to any number over 1. Larger numbers /* The block length may be set to any number over 1. Larger numbers
* reduce the number of calls to the memory allocator, give faster * reduce the number of calls to the memory allocator, give faster
* indexing and rotation, and reduce the link::data overhead ratio. * indexing and rotation, and reduce the link::data overhead ratio.
* If the block length is a power-of-two, we also get 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) #define CENTER ((BLOCKLEN - 1) / 2)
/* A `dequeobject` is composed of a doubly-linked list of `block` nodes. /* A `dequeobject` is composed of a doubly-linked list of `block` nodes.