Re: [Gems-users] Simics + Ruby slowdown


Date: Mon, 25 Sep 2006 17:19:01 -0500 (CDT)
From: Mike Marty <mikem@xxxxxxxxxxx>
Subject: Re: [Gems-users] Simics + Ruby slowdown
As shown in our ISCA tutorial slides, a typical slowdown with Simics +
Ruby for 8 processors is 45000x.

3 minutes x 45000 == 93.75 days

--Mike

> Hi all. I am trying to run some simulations of Ocean Benchmark over a
> Solaris/Sparc simulated machine (8 processors) using Simics + Ruby.
> The problem is that using only Simics the whole simulation takes me
> about three minutes but, using Ruby as Simics module, three days are
> not sufficient to simulate 2.4 billion of instructions (Simics command
> "continue 2400000000", I use that to clear Ruby stats after a warm-up
> phase).
> I am sure that number of instructions is less than the whole
> simulation, because the code I am running contains a MAGIC_BREAKPOINT
> which is never reached(and magic breaks are enabled).
>
> Is that slowdown natural? Does anybody know what could be wrong?
> Sorry to be a nuisance.
> Thank you very much.
> _______________________________________________
> 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.
>
[← Prev in Thread] Current Thread [Next in Thread→]