One more thought on 1sided

Tony Kimball (alk@think.com)
Wed, 22 Nov 95 14:51:59 EST

Date: Wed, 22 Nov 95 14:31:44 EST
From: gdburns@tbag.osc.edu (Greg Burns)

If MPI on any of these machines actually handles progress by interrupting
the application's CPU, I would like to make a note of it.

An afterthought: Is there an MPI based on CMU's "direct deposit" for the
T3D? I suspect any such beast should be added to your list.