<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META http-equiv=Content-Type content="text/html; charset=us-ascii">
<META content="MSHTML 6.00.2900.3268" name=GENERATOR></HEAD>
<BODY>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=988252015-10042008>Hi everybody,</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=988252015-10042008></SPAN></FONT> </DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=988252015-10042008>Due to scheduling constraints, we're not going to have
a special subset slot during the coming MPI Forum meeting. For that we'll have
about 2 hours to discuss MPI-3 structure where subsets should figure
prominently. If there's interest to talk subsets beyond this opportunity, I
suggest that we meet as a group at one of the dinners or 1:1 as we bump into
each other.</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=988252015-10042008></SPAN></FONT> </DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=988252015-10042008>Now, the action items from the last telecon. I need
your help on one of them:</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=988252015-10042008></SPAN></FONT> </DIV>
<DIV dir=ltr align=left><FONT size=2><SPAN class=988252015-10042008>
<DIV dir=ltr align=left><FONT face=Arial><FONT color=#0000ff>
- <SPAN class=988252015-10042008>C</SPAN>reate two <SPAN
class=971090415-09042008>query pages</SPAN></FONT></FONT></DIV>
<DIV dir=ltr align=left><SPAN class=971090415-09042008></SPAN><FONT
face=Arial><FONT color=#0000ff><SPAN
class=971090415-09042008> - F</SPAN>or users<SPAN
class=971090415-09042008> - </SPAN>what their minimum subset <SPAN
class=971090415-09042008>would look like (functionality,
performance)</SPAN></FONT></FONT></DIV>
<DIV dir=ltr align=left><FONT size=+0><SPAN
class=971090415-09042008></SPAN><FONT size=2><FONT face=Arial><FONT
color=#0000ff><SPAN class=971090415-09042008>
- F</SPAN>or implementors - what they can profit from<SPAN
class=971090415-09042008> (performance,
footprint)</SPAN></FONT></FONT></FONT></FONT></DIV>
<DIV dir=ltr align=left><FONT size=+0><FONT face=Arial color=#0000ff
size=2><SPAN class=971090415-09042008></SPAN></FONT></FONT> </DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff><SPAN
class=971090415-09042008><SPAN class=988252015-10042008>I remember someone at
the telecon had a very good suggestion about how to formulate this. Can you take
over this task now?</SPAN></SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff><SPAN
class=971090415-09042008><SPAN
class=988252015-10042008></SPAN></SPAN></FONT> </DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff><SPAN
class=971090415-09042008><SPAN class=988252015-10042008>I'm about to engage on
the following three and the final MPI-2.1
review:</SPAN></SPAN></FONT></SPAN></FONT></DIV></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=988252015-10042008><SPAN class=971090415-09042008><FONT
face="Times New Roman" color=#000000 size=3> </FONT>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Alexander will add the description
of the complexity matter upfront to make readers see their favorite pain
points</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Alexander will add the existing
laundry list of controllable features and ask for associated
perf/footprint data</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT size=+0><FONT face=Arial><FONT color=#0000ff><FONT
size=2><SPAN class=971090415-09042008> - Alexander will
prepare to participate in the MPI-3 structure discussion at the
meeting</SPAN></FONT></FONT></FONT></FONT></DIV></SPAN></SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=988252015-10042008></SPAN></FONT> </DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=988252015-10042008>Best regards.</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=988252015-10042008></SPAN></FONT> </DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=988252015-10042008>Alexander</SPAN></FONT></DIV><BR>
<DIV class=OutlookMessageHeader lang=en-us dir=ltr align=left>
<HR tabIndex=-1>
<FONT face=Tahoma size=2><B>From:</B> Supalov, Alexander <BR><B>Sent:</B>
Wednesday, April 09, 2008 6:23 PM<BR><B>To:</B> 'MPI 3.0 Sub-setting working
group'<BR><B>Subject:</B> RE: telecon, Wednesday, April 9, 8:00 am PDT/10:00
CDT/11:00 EDT/17:00 CEST<BR></FONT><BR></DIV>
<DIV></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008>Hi everybody,</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008></SPAN></FONT> </DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008>Thanks for your time today. Here's what we discussed (I
captured what I could, please add/modify):</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008></SPAN></FONT> </DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008>Present: Richard Graham, David Gingold, Keith
Underwood, Alexander Supalov</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008></SPAN></FONT> </DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008>- Opens</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008>- Discussion of the proposal (see <A
title=http://svn.mpi-forum.org/trac/mpi-forum-web/wiki/Subsets
href="http://svn.mpi-forum.org/trac/mpi-forum-web/wiki/Subsets">http://svn.mpi-forum.org/trac/mpi-forum-web/wiki/Subsets</A>)</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Complexity needs to be defined. Discussion on
the aspects:</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Many people only use a few calls,
don't need the rest; difficulty of learning is related to
this</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Sheer mass of the number of calls
expected in MPI-3 may make complexity unmanageable, requires
hierarchy</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Performance implications are not
considered primary motivation for subsetting, but removing them may
help</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008></SPAN></FONT><FONT face=Arial color=#0000ff
size=2><SPAN class=971090415-09042008>
- E.g., extra cache effects may be induced by complexity (e.g.,
communicators)</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - This can
in principle be defeated by prioritization of the hottest data
fields</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008><SPAN class=971090415-09042008>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - We'll add the existing laundry list of
things that may affect performance</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Inviting people to quantify
the performance benefits may help to identify promising
areas</SPAN></FONT></DIV></SPAN> - We may need hard facts to
gauge potential performance gains</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008></SPAN></FONT><FONT face=Arial color=#0000ff
size=2><SPAN class=971090415-09042008> - We may
need "fast stuff" subset people will safely be able to use</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008></SPAN></FONT><FONT face=Arial color=#0000ff
size=2><SPAN class=971090415-09042008><FONT face=Arial color=#0000ff
size=2><SPAN class=971090415-09042008> - Making parts of the standard
optional may be easier with subsets</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Dynamic processes seem to be a
good example - some may disagree</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - You may wait for the
pull or create it; anyway, there's no big pull on this in the volume market
yet</SPAN></FONT></DIV></SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - High end users are
starting to use dynamic processes, though</SPAN></FONT></DIV></SPAN></FONT>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Selection at compile- link-, and
runtime</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Compiler time is a little
controversial, but there are already some measurements that quantify
this</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Link time comes in 3
forms</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Static linker is smart
and will pull out of the .a only those components the program
uses</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Dynamic linker is not
smart, but there's chance to either</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Do dlopen
from within MPI to load extra modules (not everyone's favorite),
or</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Switch
on/off parts of functionality in a bigger library - this is where runtime comes
in</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Runtime (MPI_Init and/or
per-communicator basis)</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - E.g., disabling
MPI_ANY_SOURCE on a communicator may speed up processing</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Should a program that runs on a subset also
run on a full MPI implementation? Probably, yes</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - There's need to convince the community
that subsetting is a good idea, and portability will help</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - There should be one standard but
flexibility for MPI to adapt to a particular set of
applications</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - If applications are portable
across MPI, they won't actually care of the rest of MPI</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - The shape of MPI-3 may be strongly influenced
by subsets</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - The whole of the standard may be
split into subsets, some of which might be optional</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Vocal opponents may wrack subsets;
we need hard data before we bring this matter up</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008></SPAN></FONT><FONT size=+0><SPAN
class=971090415-09042008>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Should subsets be predefined or should MPI
provide a mechanism to define them</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Think error handling: mechanism is
there, as are several predefined handlers; this model works</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Danger of proliferation of
multiple mutually incompatible subsets will increase with the mechanism
definition</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008></SPAN></FONT> </DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Next steps</SPAN></FONT></DIV><SPAN
class=971090415-09042008>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Alexander will add the description
of the complexity matter upfront to make readers see their favorite pain
points</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008> - Alexander will add the existing
laundry list of controllable features and ask for associated
perf/footprint data</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial><FONT color=#0000ff><FONT
size=2> - Alexander create two <SPAN
class=971090415-09042008>query pages</SPAN></FONT></FONT></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial><FONT color=#0000ff><FONT size=2><SPAN
class=971090415-09042008></SPAN><SPAN
class=971090415-09042008> - F</SPAN>or users<SPAN
class=971090415-09042008> - </SPAN>what their minimum subset <SPAN
class=971090415-09042008>would look like (functionality,
performance)</SPAN></FONT></FONT></FONT></DIV>
<DIV dir=ltr align=left><FONT size=+0><SPAN
class=971090415-09042008></SPAN><FONT face=Arial><FONT color=#0000ff><FONT
size=2><SPAN class=971090415-09042008>
- F</SPAN>or implementors - what they can profit from<SPAN
class=971090415-09042008> (performance,
footprint)</SPAN></FONT></FONT></FONT></FONT></DIV>
<DIV dir=ltr align=left><FONT size=+0><FONT face=Arial><FONT color=#0000ff><FONT
size=2><SPAN class=971090415-09042008> - Alexander will
prepare to participate in the MPI-3 structure discussion at the
meeting</SPAN></FONT></FONT></FONT></FONT></DIV></SPAN>
<DIV dir=ltr align=left><SPAN class=971090415-09042008>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008></SPAN></FONT> </DIV></SPAN></DIV></SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008>Best regards.</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008></SPAN></FONT> </DIV>
<DIV dir=ltr align=left><FONT face=Arial color=#0000ff size=2><SPAN
class=971090415-09042008>Alexander</SPAN></FONT></DIV><BR>
<DIV class=OutlookMessageHeader lang=en-us dir=ltr align=left>
<HR tabIndex=-1>
<FONT face=Tahoma><FONT size=2><B>From:</B> Supalov, Alexander <BR><B>Sent:</B>
Tuesday, April 08, 2008 5:26 PM<BR><B>To:</B> 'MPI 3.0 Sub-setting working
group'<BR><B>Subject:</B> telecon, Wednesday, April 9, 8:00 am PDT/10:00
CDT/1<SPAN class=971090415-09042008><FONT face=Arial
color=#0000ff>1</FONT></SPAN>:00 EDT/17:00 CEST<BR></FONT></FONT><BR></DIV>
<DIV></DIV><FONT color=#0000ff>
<P><FONT face=Arial size=2>Hi everybody,</FONT></FONT><FONT face=Arial size=2>
</FONT></P>
<P><FONT face=Arial><FONT size=2><FONT color=#0000ff><SPAN
class=642352115-08042008>This is a reminder: the
subsetting</SPAN> telecon will <SPAN class=642352115-08042008>be held
</SPAN>on Wednesday, April 9, 8:00 am PDT/10:00 CDT/12:00 EDT/17:00 CEST. The
bridge details are as follows:</FONT> </FONT></FONT></P>
<P><FONT face=Arial color=#0000ff size=2>Outside Intel: +1-916-356-2663, Inside
Intel: 8-356-2663, Bridge: 5, Passcode: 2603880</FONT></P>
<P><FONT face=Arial><FONT size=2><FONT color=#0000ff>The primary goal will be to
go thru the draft proposal <SPAN class=642352115-08042008>available in the
Wiki (see <A title=http://svn.mpi-forum.org/trac/mpi-forum-web/wiki/Subsets
href="http://svn.mpi-forum.org/trac/mpi-forum-web/wiki/Subsets">http://svn.mpi-forum.org/trac/mpi-forum-web/wiki/Subsets</A>)</SPAN>,
and <SPAN class=642352115-08042008>to </SPAN>see what we can report to the
Forum end of April.</FONT> <FONT color=#0000ff>Please send to me <SPAN
class=642352115-08042008>additional </SPAN>agenda items you want to
discuss.</FONT></FONT></FONT></P><FONT color=#0000ff>
<P><FONT face=Arial size=2>Best regards.</FONT></FONT><FONT face=Arial size=2>
</FONT></P><FONT color=#0000ff>
<P><FONT face=Arial size=2>Alexander</FONT></FONT><FONT face=Arial size=2>
</FONT></P>
<DIV align=left><SPAN lang=DE
style="FONT-SIZE: 10pt; COLOR: blue; FONT-FAMILY: Arial; mso-bidi-font-size: 12.0pt; mso-bidi-font-family: 'Times New Roman'; mso-ansi-language: DE">
<DIV dir=ltr align=left><SPAN lang=DE
style="FONT-SIZE: 10pt; COLOR: blue; FONT-FAMILY: Arial; mso-bidi-font-size: 12.0pt; mso-bidi-font-family: 'Times New Roman'; mso-ansi-language: DE">--</SPAN></DIV>
<DIV><SPAN lang=DE
style="FONT-SIZE: 10pt; COLOR: blue; FONT-FAMILY: Arial; mso-bidi-font-size: 12.0pt; mso-bidi-font-family: 'Times New Roman'; mso-ansi-language: DE"></SPAN><SPAN
class=SpellE><SPAN lang=DE
style="FONT-SIZE: 10pt; COLOR: blue; FONT-FAMILY: Arial; mso-bidi-font-size: 12.0pt; mso-bidi-font-family: 'Times New Roman'; mso-ansi-language: DE">Dr</SPAN></SPAN><SPAN
lang=DE
style="FONT-SIZE: 10pt; COLOR: blue; FONT-FAMILY: Arial; mso-bidi-font-size: 12.0pt; mso-bidi-font-family: 'Times New Roman'; mso-ansi-language: DE">
Alexander Supalov</SPAN></DIV>
<DIV><SPAN lang=DE
style="FONT-SIZE: 10pt; COLOR: blue; FONT-FAMILY: Arial; mso-bidi-font-size: 12.0pt; mso-bidi-font-family: 'Times New Roman'; mso-ansi-language: DE"></SPAN><SPAN
lang=DE
style="FONT-SIZE: 10pt; COLOR: blue; FONT-FAMILY: Arial; mso-bidi-font-size: 12.0pt; mso-bidi-font-family: 'Times New Roman'; mso-ansi-language: DE">Intel
GmbH</SPAN></DIV>
<DIV><SPAN lang=DE
style="FONT-SIZE: 10pt; COLOR: blue; FONT-FAMILY: Arial; mso-bidi-font-size: 12.0pt; mso-bidi-font-family: 'Times New Roman'; mso-ansi-language: DE"></SPAN><SPAN
class=SpellE><SPAN lang=DE
style="FONT-SIZE: 10pt; COLOR: blue; FONT-FAMILY: Arial; mso-bidi-font-size: 12.0pt; mso-bidi-font-family: 'Times New Roman'; mso-ansi-language: DE">Hermuelheimer</SPAN></SPAN><SPAN
lang=DE
style="FONT-SIZE: 10pt; COLOR: blue; FONT-FAMILY: Arial; mso-bidi-font-size: 12.0pt; mso-bidi-font-family: 'Times New Roman'; mso-ansi-language: DE">
Strasse 8a</SPAN></DIV>
<DIV><SPAN lang=DE
style="FONT-SIZE: 10pt; COLOR: blue; FONT-FAMILY: Arial; mso-bidi-font-size: 12.0pt; mso-bidi-font-family: 'Times New Roman'; mso-ansi-language: DE"></SPAN><SPAN
lang=DE
style="FONT-SIZE: 10pt; COLOR: blue; FONT-FAMILY: Arial; mso-bidi-font-size: 12.0pt; mso-bidi-font-family: 'Times New Roman'; mso-ansi-language: DE">50321
<SPAN class=SpellE>Bruehl</SPAN>, Germany</SPAN></DIV>
<DIV><SPAN lang=DE
style="FONT-SIZE: 10pt; COLOR: blue; FONT-FAMILY: Arial; mso-bidi-font-size: 12.0pt; mso-bidi-font-family: 'Times New Roman'; mso-ansi-language: DE"></SPAN><SPAN
lang=DE
style="FONT-SIZE: 10pt; COLOR: blue; FONT-FAMILY: Arial; mso-bidi-font-size: 12.0pt; mso-bidi-font-family: 'Times New Roman'; mso-ansi-language: DE">Phone: +49
2232 209034</SPAN></DIV>
<DIV><SPAN lang=DE
style="FONT-SIZE: 10pt; COLOR: blue; FONT-FAMILY: Arial; mso-bidi-font-size: 12.0pt; mso-bidi-font-family: 'Times New Roman'; mso-ansi-language: DE"></SPAN><SPAN
lang=DE
style="FONT-SIZE: 10pt; COLOR: blue; FONT-FAMILY: Arial; mso-bidi-font-size: 12.0pt; mso-bidi-font-family: 'Times New Roman'; mso-ansi-language: DE">Mobile:
+49<I> </I>173 511 8735</SPAN></DIV>
<DIV><SPAN lang=DE
style="FONT-SIZE: 10pt; COLOR: blue; FONT-FAMILY: Arial; mso-bidi-font-size: 12.0pt; mso-bidi-font-family: 'Times New Roman'; mso-ansi-language: DE"></SPAN><SPAN
lang=DE
style="FONT-SIZE: 10pt; COLOR: blue; FONT-FAMILY: Arial; mso-bidi-font-size: 12.0pt; mso-bidi-font-family: 'Times New Roman'; mso-ansi-language: DE">Fax: <SPAN
style="mso-spacerun: yes"> </SPAN>+49 2232 209029</SPAN></DIV></SPAN></DIV>
<DIV><FONT face=Arial color=#0000ff size=2></FONT> </DIV><pre>---------------------------------------------------------------------
Intel GmbH
Dornacher Strasse 1
85622 Feldkirchen/Muenchen Germany
Sitz der Gesellschaft: Feldkirchen bei Muenchen
Geschaeftsfuehrer: Douglas Lusk, Peter Gleissner, Hannes Schwaderer
Registergericht: Muenchen HRB 47456 Ust.-IdNr.
VAT Registration No.: DE129385895
Citibank Frankfurt (BLZ 502 109 00) 600119052
This e-mail and any attachments may contain confidential material for
the sole use of the intended recipient(s). Any review or distribution
by others is strictly prohibited. If you are not the intended
recipient, please contact the sender and delete all copies.
</pre></BODY></HTML>