Re: [Gems-users] regd ruby results and magic instruction

[Dan Gibson <degibson@xxxxxxxx>]

Dave Z. wrote:
> Hello All,
>
> I have a few questions regarding Ruby results and
> magic instruction. In my configuration, there are two
> processors. For example, total_misses is shown as
> follows: total_misses: 39269 [39269 0]. Does each
> number in brackets refer to a processor? 
Yes, each bracket refers to a processor. In your example above, 
processor 0 had 39,269 L2 misses, processor 1 had zero.
> If so, does
> it mean the benchmark ran only on one of the
> processors? 
Not necessarily -- it means that Ruby didn't find any misses from that 
processor...which probably means that Ruby isn't fully installed. Are 
you using the "sarek" target? Using non-sarek targets or even sarek 
targets with some configuration options set can result in more than on 
physical memory object (often one per processor). Ruby installs itself 
of "phys_mem0", which can manifest as only showing accesses from cpu0. 
Find out if a "phys_mem0" object exists in your simulation, and also a 
"phys_mem1", "phys_mem2", etc.
Otherwise, have you set the cpu-switch-time in Simics to 1? You might 
have a very large cpu-switch-time and/or cpu1 might be in a disabled state.
> Is there a way to assign threads to
> processors? Like processor affinity in Linux?
>   
Yes...see the processor_bind() man page.
> There is a section called "Chip Stats" in Ruby
> statistics. I have been trying to find where "Chip
> Stats" (e.g. cache event counts, transitions) are
> analyzed, but I couldn't find them in any of the files
> located at ruby/profiler/. Could you please tell me
> where "Chip Stats" are taken care of?
>   
As Mike said, a lot of these are produced by the generated code, in 
$GEMS/ruby/generated/[protocol], which is derived from the SLICC 
specification of the protocol.
> I try to use the magic instruction in my benchmark,
> MAGIC(1) and MAGIC(2) as mentioned in simics user
> guide. But when I run the simulation, it doesn't stop
> at the magic breakpoint but continues until the end.
> (I'm using sarek with solaris 10). What could be the
> problem? 
>   
Have you given the command "magic-break-enable" to Simics?
> Thank you for your help.
>   
Regards,
Dan Gibson
> __________________________________________________
> Do You Yahoo!?
> Tired of spam?  Yahoo! Mail has the best spam protection around 
> http://mail.yahoo.com 
> _______________________________________________
> Gems-users mailing list
> Gems-users@xxxxxxxxxxx
> https://lists.cs.wisc.edu/mailman/listinfo/gems-users
> Use Google to search the GEMS Users mailing list by adding "site:https://lists.cs.wisc.edu/archive/gems-users/"; to your search.
>
>   
--
http://www.cs.wisc.edu/~gibson [esc]:wq!