Newsgroups: comp.parallel.pvm
From: shaikh@brando.ece.utexas.edu (Saghir Ahmed Shaikh)
Subject: Performance Issue in PVM
Organization: The University of Texas at Austin, Austin, Texas
Date: 21 Jun 1996 06:28:57 GMT
Message-ID: <4qdff9$6vn@geraldo.cc.utexas.edu>


Dear PVM User

I need some suggestions regarding my program using the PVM 3.3.10. 

I have developed a simulation program which spawns usually around 150
process. The processes communicate very heavily during the execution. I
want to do the performance comparison on the workstation cluster of 5 and
10.

Well, the results are against the expectations. The execution time on the
5 workstations is better than the 10 workstations! 

In my opinion this is happening because in the case of 5 workstations each
workstation gets around 30 processes thus all the communication between
the "blocks of 30 process assigned to a one workstation" communicate
faster (I think PVM daemon recognizes the fact that the destined process
is on the same host). Well in the case of 10 workstations, each
workstation get 15 processes only, thus now the block assigned to each
host is reduced and thus the "inter host communication" increases (while
inter-process communication remain the same). 


Well could you suggest a strategy where I can show the both sides of the
story. i.e. the actual happening (which I described earlier) and
theoretical case when the 10 hosts show better performance than 5 hosts.

Please let me know if you have any suggestions. 

My email is saghir@mail.utexas.edu

Thanks
 
-- 
--
peace, saghir
-------------------------------------------------------------------+
My Home Page: http://www.ece.utexas.edu/~shaikh/		   |
-------------------------------------------------------------------+
Saghir A. Shaikh	       | Email: saghir@mail.utexas.edu	   |
Dept. of Elec. & Comp. Engr.   | The University of Texas at Austin | 
-------------------------------------------------------------------+

