[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAG6aBkVN4U7zwxDvZOgJQ1M5adfoaEYO3wD10D1+MWBRct5AoA@mail.gmail.com>
Date: Tue, 8 Nov 2011 13:46:24 -0500
From: Nigel Sollars <nsollars@...il.com>
To: john-users@...ts.openwall.com
Subject: Re: Linux MIPS
Hi,
Sorry for the lag time between posts,
On Sat, Nov 5, 2011 at 10:52 AM, Solar Designer <solar@...nwall.com> wrote:
> On Sat, Nov 05, 2011 at 10:36:05AM -0400, Nigel Sollars wrote:
> > Ok, vanilla John builds with -mips3 , trying the same with Jumbo set.
>
> I meant "-mips3 -mgp64" (two options at once), not just -mips3. You
> need to check that you start getting "64/64" in --test output for DES.
>
-mpg64 complains about using a 32bit ABI
>
> > I was not sure if this one was 64bit or not, Ive been trying to get more
> > info on the architecture. Sorry for any confusion there.
>
> MIPS III is 64-bit.
>
> http://www.linux-mips.org/wiki/Instruction_Set_Architecture#MIPS_III
>
> "MIPS III was introduced 1992 in the R4000. It adds 64-bit registers and
> integer instructions and a square root FP instruction."
>
> R4600 is a MIPS III CPU, and I found no mentions of it lacking any part
> of the MIPS III architecture.
>
> http://www.linux-mips.org/wiki/R4600
> http://en.wikipedia.org/wiki/R4600
>
> Apparently, you're already running a 64-bit kernel (but a 32-bit userland?)
>
> Anyway, even with a 2x speed boost at DES from going 64-bit, you'll have
> poor performance overall, compared to modern machines. Your cluster
> will perform slower than a single core in a modern CPU does. But you're
> doing this just for fun, right?
>
>
Yeah its all fun here, since I have these units available thought id do
some experimentation with them.
> Alexander
>
--
“Science is a differential equation. Religion is a boundary condition.”
Alan Turing
Powered by blists - more mailing lists
Confused about mailing lists and their use?
Read about mailing lists on Wikipedia
and check out these
guidelines on proper formatting of your messages.
