[mpiwg-coll] Review implementation of #419+420 in chapter 7

Daniel Holmes dholmes at epcc.ed.ac.uk
Wed Feb 11 06:03:53 CST 2015

Hi Torsten,

I have reviewed the changes for #420 - all looks good to me.

My only comments are that the diff shows changes to most of the lines of 
the example, even lines that have not apparently changed, which makes 
picking out the actual changes a little more difficult than necessary. 
Also, the alignment of the first set numbers in the "[s/r]displs = ( xxx 
+ ..." lines is off by one character for the single digit numbers. Minor 
quibbles that do not need to be fixed unless you have lots of free time!


On 07/02/2015 21:35, Torsten Hoefler wrote:
> Dear Chapter Committee (and anybody interested),
> Could you please review the implementation of tickets 419 and 420 [1] in
> the new pdf [2] or the diff [3] (which includes some more ticket-0
> changes) before February 16.
> I don't have Chulho Kim's email address but I hope he's subscribed here.
> Martin, can you please update the table on
> http://meetings.mpi-forum.org/MPI_3.1_main_page.php . I rely on this
> table that there is nothing else missing in chapters 5 or 7. Please let
> me know if there is still something open.
> Thanks & Best,
>     Torsten
> [1]: https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/419
> https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/420
> [2]: http://htor.inf.ethz.ch/sec/chap-topol-mpi-3_1.pdf
> [3]: http://htor.inf.ethz.ch/sec/chap-topol-diff-r1806.diff

Dan Holmes
Applications Consultant in HPC Research
EPCC, The University of Edinburgh
James Clerk Maxwell Building
The Kings Buildings
Peter Guthrie Tait Road
T: +44(0)131 651 3465
E: dholmes at epcc.ed.ac.uk

*Please consider the environment before printing this email.*

The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.

More information about the mpiwg-coll mailing list