py26-numpy is much slower than NumPy compiled for MacPython

[Konrad Hinsen]

On 08.12.2010, at 00:31, Frank Schima wrote:

> Wow, interesting result. I just ran the benchmark on my Mac Pro 2008 and got 44 s with py26-numpy. I rebuilt it just to take a look. I noticed it is using -O3 in the configure flags which is good, but it was using gcc-4.2 to build. I have the gcc44 variant selected and that is the default, so it's possible that is the problem but maybe I'm just misunderstanding the gcc4x variants. 

My installation uses the default, gcc 4.4, and my numbers are for a MacBook Pro running at 2.53 GHz.

Does gcc-4.2 mean you used the gcc from Apple's Xcode package?


On 08.12.2010, at 00:46, Ned Deily wrote:

> Could it be 64-bit vs 32-bit?  The python 2.6 from a python.org 
> installer (I assume that's what you mean by MacPython) is built as 
> 32-bit only.  If you build python 2.6 with MacPorts it will likely be 
> 64-bit by default on OS X 10.6.

Indeed. I have another machine still running MacOS 10.5 and thus a 32-bit MacPorts build, that would be interesting to compare to. Unfortunately I can't do that before next week.

Konrad.