27 Mar
2009
27 Mar
'09
4:53 p.m.
Hi joel,
Le Ven 27 mars 2009 03:00, Fernando Cacciola a écrit :
To measure the convenience of using the GPU against the slow down of the bus bottleneck depends on what you offload to the GPU.
The OP want to offoad 4 element vector operation ont he GPU, one at a time ...
Where do you get this idea? I couldn't find anything in this thread implying that this is what the OP wants.
It doesn't requir emuch more analysis to see it'll fail.
Of course... that would be silly.
Offloading a few 1x4 vector multiply won't cut it
Indeed. Yet I don't think this was the idea behind considering GPGPU in the conext of this proposal. Best -- Fernando Cacciola SciSoft Consulting, Founder http://www.scisoft-consulting.com