<br><font size=2 face="sans-serif">Hi again,</font>
<br>
<br><font size=2 face="sans-serif">thanks to everybody who already contributed to this thread.</font>
<br>
<br><font size=2 face="sans-serif">If I understood well :</font>
<br><font size=2 face="sans-serif"> - although Bluegene/L is basically a number-cruncher, it could be used as well with either a pure Erlang application, or with Erlang acting as a "distribution" glue to lower level languages, such as Fortran, C or C++ (not to mention that on the simpler case of clusters, Erlang could help a lot)</font>
<br><font size=2 face="sans-serif"> - the communication layer will be an issue on the platform, due to the lack of TCP/IP, but one could imagine using the available carriers (maybe MPI, or lower-level) to build Erlang communication on top of them</font>
<br><font size=2 face="sans-serif"> - threading would be another concern as only one user process per "logical node" would be allowed, but using green thread (i.e. in user space rather than in kernel space) could do the trick</font>
<br><font size=2 face="sans-serif"> - cross-compilation could be a difficulty, although it is a not too uncommon case with Bluegene and with Erlang (separately, though, for the moment)</font>
<br><font size=2 face="sans-serif"> - scalability of the simulation could be an issue, if it were really to be executed simultaneously on the 8000 nodes</font>
<br><font size=2 face="sans-serif"> - there exists a daring experimental Ruby implementation on Bluegene that somewhat proved the technical feasability of the port (quite impressive !), and that may share a lot with the Erlang port itself</font>
<br>
<br><font size=2 face="sans-serif">I like the idea of using Erlang on clusters and on Bluegene ! </font>
<br>
<br><font size=2 face="sans-serif">On our side we are in the process of developing a prototype of a large-scale Erlang-based distributed simulation, when it will be finished, we expect to run it at least on a cluster and, if possible, on a Bluegene too.</font>
<br>
<br><font size=2 face="sans-serif">Thanks again for the hints (please keep the mailing-list informed if ever there were some progress on the Bluegene/L Erlang port !)</font>
<br><font size=2 face="sans-serif">best regards,</font>
<br>
<br><font size=2 face="sans-serif">Olivier Boudeville.</font>
<br><font size=2 face="sans-serif">---------------------------<br>
Olivier Boudeville<br>
<br>
EDF R&D : 1, avenue du Général de Gaulle, 92140 Clamart, France<br>
Département SINETICS, groupe ASICS (I2A), bureau C-052<br>
Office : 33 1 47 65 59 58 / Mobile : 33 6 16 83 37 22 / Fax : 33 1 47 65 34 24</font>
<br>
<br>
<br>
<table width=100%>
<tr valign=top>
<td>
<td><font size=1 face="sans-serif"><b>erlang-questions-bounces@erlang.org</b></font>
<p><font size=1 face="sans-serif">20/04/2007 09:16</font>
<br>
<td><font size=1 face="Arial"> </font>
<br><font size=1 face="sans-serif"> Pour : erlang-questions@erlang.org</font>
<br><font size=1 face="sans-serif"> cc : (ccc : Olivier BOUDEVILLE/IMA/DER/EDFGDF/FR)</font>
<br><font size=1 face="sans-serif"> Objet : Re: [erlang-questions] Erlang on supercomputers</font></table>
<br>
<br>
<br><font size=2 face="Courier New">Chad Brewbaker wrote:<br>
> The problems with Bluegene/L are:<br>
> <br>
> 1. The compute node kernel only allows user process per CPU. I haven't<br>
> looked into the Erlang source much, but all threading must be "green".<br>
<br>
i believe the emulator threading can be turned off at run-time (afaik even <br>
the non-SMP emu (optionally) uses threads for io).<br>
<br>
> 2. Communication is done over MPI in C/C++/Fortran. There is no API for<br>
> doing TCP/IP communication I know of, but if you are feeling lucky you can<br>
> use un-documented low level communication API's.<br>
<br>
it is possible (and supposedly not very hard) to implement the erlang <br>
distribution over a different carrier than the default TCP/IP. documented in the <br>
ERTS manual.<br>
<br>
> 3. You need to cross compile, so all cross compilation problems with Erlang<br>
> apply.<br>
<br>
several people on the mailing list claims to cross-compile without major <br>
problems. see also the FAQ :> http://erlang.org/faq/x867.html#AEN963<br>
<br>
> I just got Ruby working on Bluegene/L and was thinking about doing Erlang<br>
> next:<br>
> http://www.ece.iastate.edu/~crb002/cnr.html<br>
> <br>
> I don't know if I am a fan of Erlang yet or not. I'm on the fence weather I<br>
> should try porting it or just implement Erlang message passing <br>
> functionality<br>
> I want as a Ruby library.<br>
<br>
not that i know anything about supercomputers or ruby, but i would bet real <br>
money that in a cluster of 2048 cpu's erlang would beat the pants off ruby. <br>
erlang is typically faster than ruby, and generally performs very well in a <br>
distributed environment.<br>
<br>
mats<br>
_______________________________________________<br>
erlang-questions mailing list<br>
erlang-questions@erlang.org<br>
http://www.erlang.org/mailman/listinfo/erlang-questions<br>
</font>
<br>
<br>