Message155086
| Author |
skrah |
| Recipients |
Amaury.Forgeot.d'Arc, Jim.Jewett, Ramchandra Apte, amaury.forgeotdarc, benjamin.peterson, casevh, ced, eric.smith, eric.snow, jjconti, lemburg, mark.dickinson, pitrou, rhettinger, skrah, vstinner |
| Date |
2012年03月07日.13:49:44 |
| SpamBayes Score |
3.0194391e-09 |
| Marked as misclassified |
No |
| Message-id |
<20120307134943.GA4928@sleipnir.bytereef.org> |
| In-reply-to |
<1331123950.3435.5.camel@localhost.localdomain> |
| Content |
Antoine Pitrou <report@bugs.python.org> wrote:
> You could use Py_LOCAL_INLINE, but most compilers should inline small
> functions automatically, AFAIK.
At the time I wrote it I benchmarked everything. I'm pretty sure
that gcc did not inline larger functions like mpd_qresize_zero()
and mpd_word_digits() and even some smaller ones that are declared
ALWAYS_INLINE. Also, the static inline functions in the header
files are absolutely crucial for speed.
I recall that Mark initially said that in the Modules hierarchy
not every module would need to compile. Now, _decimal is already
tested with gcc, clang, icc, suncc, Visual Studio, and success
has been reported with xlc[1]. CompCert compiles libmpdec but not
Python.
_ctypes does not compile with icc and suncc. Unlike _ctypes, _decimal
has a fallback in the form of decimal.py. So, perhaps as an alternative
we could leave the inlines and wait for build failure reports?
[1] compilation success, one of the numerous AIX issues on
bugs.python.org with loading the module was encountered IIRC. |
|
History
|
|---|
| Date |
User |
Action |
Args |
| 2012年03月07日 13:49:45 | skrah | set | recipients:
+ skrah, lemburg, rhettinger, amaury.forgeotdarc, mark.dickinson, pitrou, vstinner, casevh, eric.smith, benjamin.peterson, jjconti, ced, Amaury.Forgeot.d'Arc, eric.snow, Ramchandra Apte, Jim.Jewett |
| 2012年03月07日 13:49:44 | skrah | link | issue7652 messages |
| 2012年03月07日 13:49:44 | skrah | create |
|