[Gems-users] ruby results


Date: Wed, 13 Sep 2006 13:31:42 -0700 (PDT)
From: "Dave Z." <zhu_dave@xxxxxxxxx>
Subject: [Gems-users] ruby results
Hello All,

I've been trying to figure out how to get ruby results
based on per processor. I'm using MOESI_SMP_hammer and
simulating 2 processors. Some of the stats provide
results based on per processor, but my results are
always zero for the second processor. I set the cpu
switch time to 1, but it doesn't change anything.
Besides, the profiler functions use "NodeID" so I
can't get results based on per processor without
modifying the profiler. 

To make sure I have two processors per chip, I set the
following:

simics> ruby0.setparam g_NUM_PROCESSORS 2             
               
simics> ruby0.setparam g_PROCS_PER_CHIP 2

But I get the following error when I initialize ruby:

simics> ruby0.init                                    
               
Ruby Timing Mode
Warning: optimizations not enabled.
Fatal Error: in fn static void RubyConfig::init() in
config/RubyConfig.C:164: Non-CMP protocol should set
g_PROCS_PER_CHIP to 1
***  Simics getting shaky, switching to 'safe' mode.
Simics (main thread) received a segmentation fault.
Will try to recuperate.

So, I draw two conclusions: First, it's not possible
to simulate more than 1 processor per chip using SMP
protocols. So, I can't get ruby results based on per
processor as long as I use MOESI_SMP_hammer or any SMP
protocol. I would like to simulate a dual-core
machine, similar to dual-core AMD Opteron. That's why
I'm using MOESI_SMP_hammer. Second, I still don't
understand why my results are always zero for the
second processor.

Your comments will be greatly appreciated.

Thank you.

__________________________________________________
Do You Yahoo!?
Tired of spam?  Yahoo! Mail has the best spam protection around 
http://mail.yahoo.com 
[← Prev in Thread] Current Thread [Next in Thread→]