[Mpi-22] [MPI Forum] #109: Nonblocking Collective Operations

Torsten Hoefler htor at [hidden]
Tue Nov 2 12:31:16 CDT 2010



Bronis,
> It really seems to me that these changes exceed
> the guidelines that Rich and Bill have given
> for the release draft. While I understand the
> reasoon behind them, it is unclear that we will
> have reviewed them properly. For example, I think
> the wording below could use work.
This is a clear error and can cause significant confusion on the user's
and implementer's side. Most of the text is copied from the
point-to-point section and is thus consistent with the remainder of the
document (even though I don't like the wording there ("should") at
all!).

> I am in transit to ANL right now so I cannot go
> over it properly until at least tonight...
Please take your time and check. We are not intending to rush.

> Even then, this feels rushed.
I don't think there is rush. We can release the document without this
fix (with a known bug). That's why I commit each item separately.
However, I'm against a release with bugs but that's not my decision.

Thanks,
  Torsten


-- 
 bash$ :(){ :|:&};: --------------------- http://www.unixer.de/ -----
Torsten Hoefler         | Performance Modeling and Simulation Lead
Blue Waters Directorate | University of Illinois (UIUC)
1205 W Clark Street     | Urbana, IL, 61801
NCSA Building           | +01 (217) 244-7736




More information about the Mpi-22 mailing list