From owner-freebsd-hardware  Mon Feb 24 08:21:50 1997
Return-Path: <owner-hardware>
Received: (from root@localhost)
          by freefall.freebsd.org (8.8.5/8.8.5) id IAA26715
          for hardware-outgoing; Mon, 24 Feb 1997 08:21:50 -0800 (PST)
Received: from godzilla.zeta.org.au (godzilla.zeta.org.au [203.2.228.19])
          by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id IAA26704
          for <hardware@freebsd.org>; Mon, 24 Feb 1997 08:21:42 -0800 (PST)
Received: (from bde@localhost) by godzilla.zeta.org.au (8.8.3/8.6.9) id DAA07615; Tue, 25 Feb 1997 03:18:17 +1100
Date: Tue, 25 Feb 1997 03:18:17 +1100
From: Bruce Evans <bde@zeta.org.au>
Message-Id: <199702241618.DAA07615@godzilla.zeta.org.au>
To: nate@mt.sri.com, skynyrd@opus.cts.cwu.edu
Subject: Re: Memory speed (was Re: _big_ IDE disks?)
Cc: bde@zeta.org.au, hardware@freebsd.org
Sender: owner-hardware@freebsd.org
X-Loop: FreeBSD.org
Precedence: bulk

>The triton-1 machine running 2.1.7 consistently showed ~74MB/sec, while
>the natoma p6-200 systems running ecc showed ~80MB/sec (both
>just-before-lite2-current and 2.2 from about 1/26.)
>
>the triton-2 machines (1 w/96MB edo, the other with 64MB fpm) both showed
>rates ~117MB when the systems were otherwise unloaded.  These machines
>both were running 2.2 from yesterday morning.

Not good :-).  I have Triton-1 (ASUS P55TP4XE) with non-EDO RAM and the
benchmark runs at about 119.2MB/sec (1MB = 1048576).  Oops, I forgot
that I run with minor improvements that reduce the overhead of the inner
loop from 59 cycles to 57.  This probably accounts for the 119.2/117
difference.  Triton-2 and EDO RAM probably don't make much difference.

>These results are with the standard bios parameters for 60ns memory.
>There are a few memory knobs besides normal timing in the p6np5 bios but I
>haven't experimented.  I suppose Rod Grimes would know what the optimal
>settings are :)

I use the standard knobs with everything turned up high.  An x-2-2-2
write burst cycle is most important for this benchmark.

Bruce

Script started on Tue Feb 25 03:04:55 1997
ttyv1:bde@alphplex:/tmp> dd if=/dev/zero of=/dev/null bs=1m count=1000
1000+0 records in
1000+0 records out
1048576000 bytes transferred in 8.389282 secs (124989958 bytes/sec)
ttyv1:bde@alphplex:/tmp> exit

Script done on Tue Feb 25 03:05:07 1997

Calibrating clock(s) relative to mc146818A clock ... i586 clock: 132622829 Hz, i8254 clock: 1193105 Hz
CPU: Pentium (132.62-MHz 586-class CPU)
  Origin = "GenuineIntel"  Id = 0x52b  Stepping=11
  Features=0x1bf<FPU,VME,DE,PSE,TSC,MSR,MCE,CX8>
real memory  = 33554432 (32768K bytes)
avail memory = 30412800 (29700K bytes)
DEVFS: ready for devices
Probing for devices on PCI bus 0:
chip0 <Intel 82437FX PCI cache memory controller> rev 2 on pci0:0:0