[Python-Dev] Speeding up CPython 5-10% (original) (raw)

Yury Selivanov yselivanov.ml at gmail.com
Fri Jan 29 09:49:11 EST 2016

On 2016-01-29 5:00 AM, Stefan Behnel wrote:

Yury Selivanov schrieb am 27.01.2016 um 19:25:

[..]

LOADMETHOD looks at the object on top of the stack, and checks if the name resolves to a method or to a regular attribute. If it's a method, then we push the unbound method object and the object to the stack. If it's an attribute, we push the resolved attribute and NULL. When CALLMETHOD looks at the stack it knows how to call the unbound method properly (pushing the object as a first arg), or how to call a regular callable. This idea does make CPython faster around 2-4%. And it surely doesn't make it slower. I think it's a safe bet to at least implement this optimization in CPython 3.6. So far, the patch only optimizes positional-only method calls. It's possible to optimize all kind of calls, but this will necessitate 3 more opcodes (explained in the issue). We'll need to do some careful benchmarking to see if it's really needed. I implemented a similar but simpler optimisation in Cython a while back: http://blog.behnel.de/posts/faster-python-calls-in-cython-021.html Instead of avoiding the creation of method objects, as you proposed, it just normally calls getattr and if that returns a bound method object, it uses inlined calling code that avoids re-packing the argument tuple. Interestingly, I got speedups of 5-15% for some of the Python benchmarks, but I don't quite remember which ones (at least raytrace and richards, I think), nor do I recall the overall gain, which (I assume) is what you are referring to with your 2-4% above. Might have been in the same order. That's great!

I'm still working on the patch, but so far it looks like adding just LOAD_METHOD/CALL_METHOD (that avoid instantiating BoundMethods) gives us 10-15% faster method calls.

Combining them with my opcode cache makes them 30-35% faster.

Yury

More information about the Python-Dev mailing list