From owner-freebsd-current  Tue May  7 16:02:29 1996
Return-Path: owner-current
Received: (from root@localhost)
          by freefall.freebsd.org (8.7.3/8.7.3) id QAA20321
          for current-outgoing; Tue, 7 May 1996 16:02:29 -0700 (PDT)
Received: from GndRsh.aac.dev.com (GndRsh.aac.dev.com [198.145.92.241])
          by freefall.freebsd.org (8.7.3/8.7.3) with SMTP id QAA20303
          for <current@freebsd.org>; Tue, 7 May 1996 16:02:24 -0700 (PDT)
Received: (from rgrimes@localhost) by GndRsh.aac.dev.com (8.6.12/8.6.12) id QAA02669; Tue, 7 May 1996 16:00:29 -0700
From: "Rodney W. Grimes" <rgrimes@GndRsh.aac.dev.com>
Message-Id: <199605072300.QAA02669@GndRsh.aac.dev.com>
Subject: Re: more on fast bcopy
To: wscott@ichips.intel.com (Wayne Scott)
Date: Tue, 7 May 1996 16:00:29 -0700 (PDT)
Cc: asami@cs.berkeley.edu, bde@zeta.org.au, current@freebsd.org,
        nisha@cs.berkeley.edu, marc@bowtie.nl,
        ken@area238.residence.gatech.edu, wollman@lcs.mit.edu,
        pattrsn@cs.berkeley.edu, culler@cs.berkeley.edu
In-Reply-To: <199605071845.LAA03457@ichips.intel.com> from Wayne Scott at "May 7, 96 11:48:28 am"
X-Mailer: ELM [version 2.4ME+ PL11 (25)]
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Sender: owner-current@freebsd.org
X-Loop: FreeBSD.org
Precedence: bulk

> > Yes, indeed, this is very interesting.  I guess whatever I'm doing
> > with all this is going to be moot once we all move to P6's. ;)
> > 
> > By the way, I assume the external clock of the 200MHz P6 is 66MHz, is
> > this correct?  The memory copy speed of this machine seems to be
> > slower than the Triton-based P5-133 that we have (see below).  Do you
> > know where the "B-step" Orion stands on the maturity curve, in terms
> > of memory access speed?
> 
> The problem is that I gave you numbers on a lower performance desktop
> machine.
> 
> On a high performance box with 4-way interleaved memory I get the
> following:
> 
>     size    bandwidth
>       32  46.376812 MB/s
>       64  43.243243 MB/s	yes this dip is expected
>      128  46.376812 MB/s
>      256  57.142857 MB/s
>      512  64.000000 MB/s
>     1024  66.666667 MB/s
>     2048  69.565217 MB/s
>     4096  69.565217 MB/s
>     8192  71.111111 MB/s

Thats pretty cruddy for 4 way interleaved memory,
1/120nS * 8 bytes/leave * 4 leaves == 266MB/sec.

And I used the worst case there by using the 120nS full cycle time,
if these are sequentail accesses that hit the same DRAM page this
number should be up closer to 500MB/sec.

...

-- 
Rod Grimes                                      rgrimes@gndrsh.aac.dev.com
Accurate Automation Company                 Reliable computers for FreeBSD