Subject: Re: VS4000-60 dhrystones
To: Brian D Chase <email@example.com>
From: Ken Wellsch <firstname.lastname@example.org>
Date: 09/11/1998 09:25:12
| > | I haven't had a chance to get my 4000-60 running yet. Has anyone run the
| > | dhrystone benchmark on one of these machines yet?
| > I did so just last evening. I came up with just under 20,000. This
| > sure beats 1,500 or so on a uVAX-2 8-).
| You might try it with -O2 optimization as well. For a VS3100/M76 I was
| getting 12,000+ for no opt, and almost 21,000 with -O2. I'm guessing the
| VS4000/60 will zip along quite a bit faster than the M76.
| We should get linpack compiled and running as well for floating point
| performance comparisons.
Granted, such benchmarking will give us a feel for how well NetBSD & gcc
are doing at using VAXen cycles. For a more formal result, the SPEC info
may also be of interest. I've left in some Intel related stuff as that
tends to cover the experience of others (i.e. for comparison, presuming
it is not silly, even with SPEC results, to make such comparisons...).
System CPU ClkMHz Cache SPECint SPECfp Info Source
Name (NUMx)Type ext/in Ext+I/D 92 92 Date Obtained
================= ========== ======= ========== ======= ======= ===== =========
DEC VAX11/780 VAX 5 8 1.0 1.0 Jan89 SPEC Ref
DEC VAX3100/38 ? ? ? 3.5 3.8 Mar93 DECinfo
DEC VAX4000VLC SOC ? 25 5.8 6.3 Mar93 DECinfo
DEC VAX3100/76 REX520 ? 128 7.1 6.6 Mar93 DECinfo
DEC VAX4000/60 KA46 22.2 ? 11.1 12.6 Mar93 DECinfo
DEC VAX4000/90 NVAX 71 2/8 ? 30.2 Sep92 SPEC news
Compaq Deskpro 80487SX 16 0+8 9.3 4.3 Mar93 SPEC news
Compaq Deskpro 80487SX 25 64+8 14.2 6.7 Mar93 SPEC news
Compaq Deskpro 80486DX 33 128+8 18.2 8.3 Sep92 SPEC news
Compaq Deskpro 80486DX2 25/50 256+8 25.7 12.2 Mar93 SPEC news
Compaq Deskpro 80486DX2 33/66 256+8 32.2 16.0 Mar93 SPEC news
Compaq DeskproXL Pentium 66 256+8/8 65.1 63.6 Sep93 SPEC news