Re: Data oriented programming

I'd say that it's because copying has a latency of only one cache miss no
matter how much you're copying, as you can start processing the next read
straight away as it's not dependent on the arrival of previous data. The
"processing" is just doing more of the same load and store, load and store.
So you're running at memory bandwidth the whole time rather than waiting on
data before doing something.

On 8 October 2010 14:52, Richard <[email protected]> wrote:

>
> In article <[email protected]>,
>     Warrick Buchanan <[email protected]> writes:
>
> > Also I would add to that and say don't be afraid of copying data around
> > [...]
>
> The reasoning behind this being that the cache misses during copying is
> paid for by the repeated cache hits during subsequent processing?
>
> Does this assume that the data needs to be accessed more than once
> during processing?
> --
> "The Direct3D Graphics Pipeline" -- DirectX 9 draft available for download
>  <http://legalizeadulthood.wordpress.com/the-direct3d-graphics-pipeline/>
>
>       Legalize Adulthood! <http://legalizeadulthood.wordpress.com>
> _______________________________________________
> Sweng-Gamedev mailing list
> [email protected]
> http://lists.midnightryder.com/listinfo.cgi/sweng-gamedev-midnightryder.com
>



-- 
fabs();
Just because the world is full of people that think just like you, doesn't
mean the other ones can't be right.

_______________________________________________
Sweng-Gamedev mailing list
[email protected]
http://lists.midnightryder.com/listinfo.cgi/sweng-gamedev-midnightryder.com