[Mpi-21] All REVIEWERS - Final 1.3 and 2.1 review

[Rolf Rabenseifner]

Dear reviewer,

this is the *final* review.
http://www.hlrs.de/mpi/mpi21/doc/
is updated with 
 - final version = official reading of MPI-1.3 (hopefully)
 - official reading version of MPI-2.1
One exception:
 - The authors and reviewers of Chap. Point-to-Point and Chap. Datatypes
   may work strongly together to have at the end of the week
   a version that will have a review at the meeting withou showing further
   needs.

Please, mark errors in your reviews clearly with ERR.
Please mark all other stuff with 22 because it will go into
MPI-2.2.

The resources for MPI-2.1 are now nearly fully consumed.

The shortest summary of open issues can be found at
http://www.hlrs.de/mpi/mpi21/doc/MPI-2.1draft-2008-02-23-review-openissues.pdf

Review format - please use:

----------------------------------------------------------------------------------
1234567890123456789012345678901234567890123456789012345678901234567890123456789012
          All references are based on MPI-2.1 Draft Apr. 19, 2008
ww.a __ pnnn.ll text (with nnn=page number and ll=line number
          text continued
          ...
ww.b __ pnnn.ll text ... and so on (total line length <= 82 characters.)
----------------------------------------------------------------------------------

PLEASE:
- Please check very carefully all red or magenta changes.
  Modifications are done by the chapter's author (red) or 
  by me (magenta).
  You may be the first reviewer who read and check this text.
- Please check carefully the cyan text.
  Those modifications are proposed by a reviewer and have been
  implemented by my
  You may be the second reviewer for those modifications.
- All green stuff should be fine, because it is based on
  Forum's decisions (Ballot 1-4).
- Original text is black (MPI-1.3) or blue (MPI-2.0).

Thanks and best regards
Rolf

Dr. Rolf Rabenseifner . . . . . . . . . .. email rabenseifner_at_[hidden]
High Performance Computing Center (HLRS) . phone ++49(0)711/685-65530
University of Stuttgart . . . . . . . . .. fax ++49(0)711 / 685-65832
Head of Dpmt Parallel Computing . . . www.hlrs.de/people/rabenseifner
Nobelstr. 19, D-70550 Stuttgart, Germany . (Office: Allmandring 30)