Article: Parallelism at HotPar 2010
By: Gabriele Svelto (gabriele.svelto.delete@this.gmail.com), August 5, 2010 11:42 pm
Room: Moderated Discussions
David Kanter (dkanter@realworldtech.com) on 8/5/10 wrote:
---------------------------
>This is an excellent point, but it also neglects the bandwidth that Intel and AMD
>achieve from their forwarding networks.
In that case we should take into account also the bandwidth coming from so-called pipeline registers in R8xx but we'd be really splitting hairs :-)
---------------------------
>This is an excellent point, but it also neglects the bandwidth that Intel and AMD
>achieve from their forwarding networks.
In that case we should take into account also the bandwidth coming from so-called pipeline registers in R8xx but we'd be really splitting hairs :-)
