17 Sep
2013
17 Sep
'13
2:11 p.m.
On Tue, Sep 17, 2013 at 4:58 PM, yuri kilochek <yuri.kilochek@gmail.com>wrote:
On Sep 17, 2013 4:46 PM, "Santiago Tapia" <santiago.tapia@upm.es> wrote:
Hi all,
I have design a new concept of container to be part of the cpo library.
In summary, those containers will break down the inserted objects into some elementary parts.
Why do that? Short answer: to save memory.
I do believe this will also kill the cache in most cases.
It depends on data processing pattern. If this container performs AoS <-> SoA transformation, it can be useful for parallel/vectorized data processing. However, I don't see how this container could be implemented generically for arbitrary types. I would be interested to see such implementation.