[Mpi3-tools] Tools WG TelCon tomorrow (1/24)

[Marc-André Hermanns]

Hi all,

sorry for missing the last meeting. As not to waste precious time during today's calls with initial questions regarding the current draft, I want to post the via email first:


-------------------

Wording: page 2, table 1.1
It is discouraged earlier that application developers use the MPIT interface, as it would come close to creating a performance tool within the 'self-tuning' application. Who is the 'end user' here? If it is an application developer, how does the desired information differ from what a performance tool (tuner) would like to see? Can anyone give an example?

-------------------

Wording: page 3, line 38
" … created and maintained …"
Creation sounds like "instantiation" to me, which might be a misleading here. Would '… specified …' be more clear?

-------------------

With all those query functions on page 4-5, do we have/need a function that can classify an MPI_Resource* to be of MPIT_MPI_RESOURCE_<some_type>?

-------------------

API: Page 5, line 6:
Shouldn't it be "MPI_Op" in the C prototype?

-------------------

API: Page 5, line 25:
Shouldn't it be "MPI_Win" in the C prototype?

-------------------

Wording: page 6, line 12:
… has to … -> … have to …

-------------------

Wording: in general, what is the exact meaning of "shall" in the standard. Is it equal to "must" or is it weaker?
(example: page 6, line 32)

-------------------

Wording: there are several passages where an "instance is instantiated" which reads a little tautologous. Wouldn't instances be 'created' (I would define instantiation as the creation of on instance). Might 'binding' be a word easier to understand what needs to be done as in "… a handle needs to be bound to a resource before first use …"
(example: page 11, line 29)

-------------------

Naming: page 11, line 35:
what is the exact meaning of 'index' here. What is it indexing? Is it an ID? If it is an index, which array does it refer to?

-------------------

Syntax: page 11, line 46:
superfluous whitespace before ','

-------------------

I haven't finished the complete draft yet, but wanted to post the mail sufficiently in advance to our call. If anything else is unclear, I will place that into a different email.

Cheers,
Marc-Andre


On 23.01.2011, at 23:04, Martin Schulz wrote:

> Hi all,
> 
> Sorry for the late notice, but I assume that this is on your
> calendars anyway :) : the next tools WG TelCon is 
> tomorrow as usual at 8am PDT, 11am EDT, 5pm MZ.
> As usual, Jeff has setup a Webex session. The link is:
> 
> https://cisco.webex.com/cisco/j.php?ED=155386812&UID=0&PW=NMTJhNWQxOTdj&RT=MiMxMQ%3D%3D
> Password: tools
> 
> We will discuss any more comments on the MPIT document.
> I have uploaded the latest version, which only has some minor
> changes compared to the version from two weeks ago.
> 
> If you can't make it tomorrow, please send me any comments
> in the next few days. I will create a final draft by the end of
> the week and send it out to the forum as a whole to prepare
> them for the presentation at the next MPI forum meeting in
> two weeks.
> 
> Talk to you all tomorrow,
> 
> Martin
> 
> 
> ________________________________________________________________________
> Martin Schulz, schulzm at llnl.gov, http://people.llnl.gov/schulzm
> CASC @ Lawrence Livermore National Laboratory, Livermore, USA
> 
> 
> 
> _______________________________________________
> Mpi3-tools mailing list
> Mpi3-tools at lists.mpi-forum.org
> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-tools

--
Marc-Andre Hermanns
German Research School for
Simulation Sciences GmbH
c/o Laboratory for Parallel Programming
52056 Aachen | Germany

Tel +49 241 80 99753
Fax +49 241 80 6 99753
Web www.grs-sim.de

Members: Forschungszentrum Jülich GmbH | RWTH Aachen University
Registered in the commercial register of the local court of
Düren (Amtsgericht Düren) under registration number HRB 5268
Registered office: Jülich
Executive board: Prof. Marek Behr Ph.D. | Dr. Norbert Drewes

-------------- next part --------------
A non-text attachment was scrubbed...
Name: smime.p7s
Type: application/pkcs7-signature
Size: 4427 bytes
Desc: not available
URL: <http://lists.mpi-forum.org/pipermail/mpiwg-tools/attachments/20110124/5d7a341b/attachment-0001.bin>