-
Raymond Hettinger yazdı
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".
77578204
Adı |
Son kayıt (commit)
|
Son güncelleme |
---|---|---|
Doc | ||
Grammar | ||
Include | ||
Lib | ||
Mac | ||
Misc | ||
Modules | ||
Objects | ||
PC | ||
PCbuild | ||
Parser | ||
Python | ||
Tools | ||
.bzrignore | ||
.gitignore | ||
.hgeol | ||
.hgignore | ||
.hgtags | ||
.hgtouch | ||
LICENSE | ||
Makefile.pre.in | ||
README | ||
config.guess | ||
config.sub | ||
configure | ||
configure.ac | ||
install-sh | ||
pyconfig.h.in | ||
setup.py |