Re: [OMPI devel] RFC: sm Latency

Wed, 21 Jan 2009 01:32:11 -0500

Richard Graham wrote: 
On 1/20/09 8:53 PM, "Jeff Squyres" <[email protected]> wrote:
  
Eugene: you mentioned that there are other possibilities to having the
BTL understand match headers, such as a callback into the PML.  Have
you tried this approach to see what the performance cost would be,
perchance?
    
How is this different from the way matching is done today ?
I think it would be very similar to how matching is done today.  Again, however, trying to keep data structures to a minimum to shave latency off wherever we can.

Reply via email to