On Thu, 12 Aug 1999, Eric Scheirer wrote:
>>Is point 2 technically feasible ? Anything going on along these lines ?
>>(Forgive me if the questions have been raised before).
>
>It seems to me that latency issues are problematic if you want to
>do real-time processing in such a scenario. It requires two DMAs for
>each roundtrip cycle to and from the host, and so if you are trying
>to do several stages of processing, the DMA latency will add up
>quickly.
The obvious solution is pipelining - submit multiple blocks, gather results
back asynchronously.
Sampo Syreeni <decoy@iki.fi>, aka decoy, student/math/Helsinki university
This archive was generated by hypermail 2b29 : Wed May 10 2000 - 12:15:25 EDT