caf@omen.UUCP (Chuck Forsberg WA7KGX) (12/30/86)
With all the high powered 386 benchmark results floating about, I
thought I'd post the results obtained with a honest to goodness real
live 386 system. The system used is a "Computer Dynamics 386", the main
ingredient of which is an Intel 386 motherboard running at 18 mHz and a
2 MB Intel 32 bit memory card (512 + 2048 k total memory).
The "Xenix 386 Toolkit" was used for the 32 bit runs. Its optimizer
reduces the text size of the siev main program from 189 to 131, a
smaller text size than most 32 bit 68000 compilers produce.
The dhrystone was compiled and run in several different configurations,
and the timings were verified. The results shown here were the best
obtained. Remember, this is on an operating computer system using
Intel's own 386 motherboard and memory expansion board, not a special
case toy system. This system benchmarks within several per cent of the
fastest 386 systems publicly shown to date, including Compaq and PC
Limited. The system runs reliably except for some software timing
related failure modes, some of which also appear on fast 286 systems.
* Version: C/1.1, 12/01/84
* ComputerDyn386 386-18mHz Xenix 386 Toolkit same 2808 3136
#define S 8190
char f[S+1];
main()
{
register int i,p,k,c,n;
for (n = 1; n <= 10; n++) {
c = 0;
for (i = 0; i <= S; i++) f[i] = 1;
for (i = 0; i <= S; i++) {
if (f[i]) {
p = i + i + 3; k = i + p;
while (k <= S) { f[k] = 0; k += p; }
c++;
}
}
}
printf("\n%d primes.\n", c);
}
Compile - Link Execute
Real User Real User Bytes System
(running in 32 bit mode)
0.78 0.13 0.13 0.08 - Amdahl 5870 + UTS 11/86
7.4 .8 .34 .3416 124 Definicom SYS 68020 25mHz SiVlly 11/86
11.8 2.8 .56 .56 131 CompDyn (Intel MB) + 386 Toolkit 12/86
(running in 16 mode)
- - 0.742 - 113 PC Limited 386 Xen/XC -M0 11/86
- - 0.745 - 113 Laser Pacer 386 Xen/XC -M0 11/86
- - 0.78 - 113 CompDyn 386 18mHz Xen/XC -M0 11/86
- - 0.81 - 108 CompDyn 386 18mHz Xen/XC -M2 11/86
7.5 2.24 0.84 .78 114 CompDyn 386 18mHz SCO SYSV 12/86
- - 0.852 - 113 Data Bank 386 Xen/XC -M0 11/86
- - 0.895 - 113 Kaypro 386 Xen/XC -M0 11/86
- - 0.972 - 113 ALR 386 16mHz Xen/XC -M0 11/86
7.05 2.15 1.14 1.13 136 CompDyn 386 18mHz SYS V/AT 12/86
26.9 4.2 1.51 1.49 108 8mHz 0ws QIC/AT 1mb SCO SYS V -K
- - 1.64 - - Macrotech 7.159mHz 0ws DRC v1.11 5/85
12.4 5.4 1.88 1.85 108 9mHz PC-AT Xenix 1.00 -K
15.6 5.4 1.9 1.9 113 9mHz PC-AT Xenix 1.00
18 1.1 2.0 1.5 96 11/70 + V7 (loaded)
- - 2.1 - 113 PC-AT 8mHz Microsoft C 3.0
39 - 2.1 - 135 Macrotech 80286 6mHz MPM DRI C 1.11
26 3.7 2.1 2.0 110 Zilog Model 11
11.7 6.2 2.32 2.26 108 Comp.Dynamics 386 18 mHz Xenix 11/86!
! User programs running from 16 bit memory (AST Advantage!)
An interesting note in the Computer Dynamics 18 mHz 386 System (Intel
Motherboard): The benchmark was compiled with both 8086 and 80286 code
generation. The 86 siev object file was 113 bytes of executable code,
and the 286 file was 108 bytes, a reduction of 5 per cent code space.
Yet the 8086 code consistiently ran about four per cent faster than the
more compact 286 code! It is also interesting (and disappointing) to
note that the Intel 386 Motherboard is 50 per cent slower than an 8mHz
AT clone when forced to use reasonably priced 16 bit memory.
Chuck Forsberg WA7KGX Author of Pro-YAM communications Tools for PCDOS and Unix
...!tektronix!reed!omen!caf Omen Technology Inc "The High Reliability Software"
Voice: 503-621-3406 17505-V Northwest Sauvie Island Road Portland OR 97231
TeleGodzilla BBS: 621-3746 2400/1200 CIS:70007,2304 Genie:CAF Source:TCE022
omen Any ACU 1200 1-503-621-3746 se:--se: link ord: Giznoid in:--in: uucp
omen!/usr/spool/uucppublic/FILES lists all uucp-able files, updated hourlyrentsch@unc.UUCP (Tim Rentsch) (01/01/87)
The benchmarks I would *really* like to see are ones comparing the Clipper based engines (e.g., from Intergraph) against 68020 and 80386 boxes. Anybody out there got an Intergraph Clipper box (don't know the name/number, sorry) willing to run a benchmark and post the results? cheers, txr
fouts@orville (Marty Fouts) (01/02/87)
The clipper chip set used in the Intergraph Box is a Fairchild product. This chip is the result of development Fairchild did based on technology they licensed from Cray Research. The original technology was developed at Cray for a product that would have become the Cray 2, except that Seymour Cray got his product done first. I too would like to see some results on this product.
davidsen@steinmetz.UUCP (01/02/87)
The results of the benchmarks using the 16 bit mode makes me optimistic
about running on my GV386 (when I get it). Can the 386 toolkit be used
on other machines? Also where did you get it? We ordered a Compaq
386-130 at work and got plain SCO Xeniv 2.1.3 as far as I can tell.
I will run the benchmark on a few additional machines and let you know
what results I get...
--
bill davidsen sixhub \
ihnp4!seismo!rochester!steinmetz -> crdos1!davidsen
chinet /
ARPA: davidsen%crdos1.uucp@crd.ge.com (or davidsen@crd.ge.com)bob@ahxenix.REL.COM (Bob Leffler) (01/06/87)
In article <1052@steinmetz.steinmetz.UUCP>, davidsen@steinmetz.UUCP writes: > > Can the 386 toolkit be used > on other machines? Also where did you get it? We ordered a Compaq The 386 Xenix toolkit can be purchased from SCO or any of their dealers. I believe that Compaq is also marketing a version of the SCO toolkit. It's generally a special order item, I haven't seen any stores that stock it as of yet. You can address any questions that you might have to {decvax!microsoft,ihnp4}sco!info They should be able to give you more precise information. -- Bob Leffler - bob@ahxenix.REL.COM ...!ihnp4!mb2c!edsdrd!ahxenix!bob
caf@omen.UUCP (Chuck Forsberg WA7KGX) (01/06/87)
In article <1052@steinmetz.steinmetz.UUCP> davidsen@kbsvax.UUCP (william E Davidsen) writes:
:
:The results of the benchmarks using the 16 bit mode makes me optimistic
:about running on my GV386 (when I get it). Can the 386 toolkit be used
:on other machines?
The 386 Toolkit is/will be available from SCO. It should run on any 386
box that runs Xenix.
The 386 Toolkit consists of 386 cross compiler and libraries, a 386 kernel
and a few 386 programs, including ps, fsck (understands sparse files), and
adb (sorry, no sdb or CodeView!). As the name implies, it's for hacking,
not intended to be the "real thing".
There are some bugs and limitations in the 386 kernel - no MultiScreen,
286 programs without separate I&D won't run, 386 programs with >64k
external data core dump, and some 286 programs such as "cc" core dump
under certain conditions. Most of these will be corrected soon.