[MINC-users] MINC 2 api and RAM/HD access

Soren Christensen sorench at gmail.com
Sun Sep 16 05:40:53 EDT 2012


It seems you are right. A simple loop extracting the coronal direction
(ie no copying of more than one value at a time in my case) takes
about 30 ms from RAM (vs ~500 ms via the API be it via disk or
/dev/shm) -  that is fine for what I need it to do.


Thanks for the advice.
Soren

On Sun, Sep 16, 2012 at 3:57 AM, Andrew Janke <a.janke at gmail.com> wrote:
> I'm afraid I'll have to agree on this one.
>
>
> a
>
> On 15 September 2012 17:05, Vladimir S. FONOV <vladimir.fonov at gmail.com> wrote:
>> I don't think that anything you will do using MINC2 api will get you
>> close to the performance of accessing float[x*y*z*t] memory array.
> _______________________________________________
> MINC-users at bic.mni.mcgill.ca
> http://www.bic.mni.mcgill.ca/mailman/listinfo/minc-users


More information about the MINC-users mailing list