Sure, the MATLAB code is now here: 
http://pastebin.com/PiA3gtNZ

I used MATLAB R2014a, though this is only relevant insofar as they've 
optimized their JIT compiler (which is still horrible for unvectorized 
loops, sadly), syntax-wise the code should be compatible with very old 
versions. Feel free to suggest further optimizations, by the way, I mostly 
focused on making it as identical as possible to the Python / Julia 
versions for comparison purposes.


On Thursday, October 2, 2014 3:25:09 PM UTC+3, Hans W Borchers wrote:
>
> Which version of MATLAB did you use?
> Could you publish the MATLAB code as well?
> I am interested in testing MATLAB's JIT compiler.
> Thanks, Hans Werner
>
>
> On Thursday, October 2, 2014 1:14:47 PM UTC+2, [email protected] wrote:
>>
>> Thanks for the quick feedback, I appreciate it. I had indeed somehow 
>> missed Julia's arrays being column-major and taking that into account 
>> essentially yields equal performance between Numba and Julia in this 
>> benchmark. I'll compare it to Fortran/C++ just to see how large the 
>> difference is, but the current performance does seem to be the limit of 
>> LLVM-based approaches in general. 
>>
>> To answer Tim Holy's point, Numba does do SIMD vectorization, but I 
>> haven't tested it extensively in the latest releases. For now, I'll port 
>> some of the more compact simulations I'm doing to Julia and Python/Numba 
>> for a less trivial benchmark and see how the performance compares then. 
>>
>

Reply via email to