> Date: Sun, 02 Feb 1997 14:14:17 CST
> From: Raja Daoud <raja@tbag.rsn.hp.com>
> To: mpi-coll@mcs.anl.gov
> Subject: Re: Proposal to modify two-phase...
>
>
> > Tags are added to two-phase collective operations
> > in order to permit multiple two-phase operations per
> > communicator.
>
> If I remember correctly, Lloyd objected to the restricted two-phase
> collectives (1 per comm) saying that an optimal implementation would
> require shared-memory O(#comm) and that was too much on his system.
> I agree with that, though on my system that's acceptable.
>
> By adding tags, now it's also proportional to # of concurrent tags per
> communicator. That starts being too much memory even "on systems with
> lots of shmem." To detect at runtime the out-of-shmem case and
> collectively degrade back to point-to-point requires a collective step
> gathering each process' no-shmem flag. The same problem exists even if
> we use a fixed # of shmem areas per communicator (for the first N tags),
> since users can start these tagged-two-phase collectives in different
> orders.
>
> > Advice to implementors.
> > For systems that implement collective on top of point-to-point,
> > this poses no special penalty. For systems that propose to
> > use hardware for collective, I suspect there can be objections,
> > but these same objections apply to overlapping groups posing
> > non-blocking collectives as well, or any case where the special
> > hardware must be multiplexed between activities.
>
> This design penalizes optimized implementations but adds no burden on
> point-to-point implementations, which anyway are no better than what the
> user can hand-code. In the case of shmem collectives, "hardware
> multiplexing" is a collective pre-step unless users are forced to start
> the tagged-two-phase collectives in the same tag order within each
> communicator. In this case the tag would be nothing more than a
> glorified index to the shmem areas, and cannot be used for matching.
> Feasible, but no better than telling users they can start N two-phased
> collectives instead of 1, where N is system-dependent (set in some
> attribute).
>
> All in all, I still prefer the non-tagged two-phase collectives.
>
> --Raja
>
> -=-
> Raja Daoud Hewlett-Packard Co.
> raja@rsn.hp.com Convex Division
>
Anthony Skjellum, PhD, Associate Professor of Computer Science;
Mississippi State University, Department of Computer Science & NSF ERC
Butler, Rm 300, PO Box 9637, Corner of Perry&Barr, Mississippi State,MS 39762
(601)325-8435 FAX: (601)325-8997; http://www.erc.msstate.edu/~tony;
"Persistence is fertile." ; e-mail: tony@cs.msstate.edu; Try MPI!