3 Apr
1998
3 Apr
'98
7:38 p.m.
On Apr 3, 5:55, Tim Shoppa wrote:
So is the DECUS C compiler, I hear. Is there any native C compiler
for the PDP-11 which isn't derived from V6/V7?
Well, the obvious answer is DEC's (nowadays MENTEC's) own ANSI C
compiler, which runs under RSX and RSTS/e (not sure about RT-11
though...)
Johnny
Johnny Billquist || "I'm on a bus
CS student at Uppsala University || on a psychedelic trip
email: bqt(a)minsk.docs.uu.se || Reading murder books
pdp is alive! || tryin' to stay hip" - B. Idol
Received: (from major@localhost)
by minnie.cs.adfa.oz.au (8.8.5/8.8.5) id FAA22903
for pups-liszt; Sun, 5 Apr 1998 05:16:13 +1000 (EST)
X-Authentication-Warning: minnie.cs.adfa.oz.au: major set sender to
owner-pups(a)minnie.cs.adfa.oz.au using -f
Yes, it does run under RT-11 (that's the only version I've used.)
But I've no idea of the lineage of that particular compiler - it wouldn't
surprise me to find out that it was derived from V6/V7 in some way.
(Though clearly with entirely new run-time libraries.)
As long as we're on the subject: has anyone succesfully cross-compiled
using 'gcc' on some non-11 platform to produce PDP-11 object code, which
they than succesfully ran? While the compiler seems to work fine, I've
run into confusion when trying to use the *.h files from 2.11BSD to
do something useful.
Tim. (shoppa(a)triumf.ca)
Received: (from major@localhost)
by minnie.cs.adfa.oz.au (8.8.5/8.8.5) id GAA23137
for pups-liszt; Sun, 5 Apr 1998 06:43:45 +1000 (EST)
X-Authentication-Warning: minnie.cs.adfa.oz.au: major set sender to
owner-pups(a)minnie.cs.adfa.oz.au using -f
I suspect that the emulator will be quite slow on any math-heavy
benchmark - and your observations confirm this. Doesn't Bob's
emulator do the FP operations by converting everything to IEEE
and back for each and every operand?
On my cow-oreker's Pentium Pro, the line-time clock under Bob's emulator
appears to work fine, but it "misses" a lot of ticks when running on
my 7-year-old Alpha. I've never looked at the logic to figure out exactly
what is going on, but I suspect that I couldn't emulate the interrupt/
priority structure any better than Bob's already done!
> Yes to all of those, though there are three
standard recording densities
> (80bpi, 1600bpi, 6250bpi) and several recording methods (NRZ, NRZI, PE,
etc).
But in the 9-track world at least, 800 BPI was always NRZI, 1600 BPI
(and 3200 BPI) was always PE, and 6250 BPI was always a specific type
of GCR.
Yes, I didn't mean to imply you could have any mixture. It's always irritated
me that I can't read 800bpi tapes on my 1600bpi drive simply because it doesn't
have the (optional) NRZI board.
--
Pete Peter Turnbull
Dept. of Computer Science
University of York
Received: (from major@localhost)
by minnie.cs.adfa.oz.au (8.8.5/8.8.5) id GAA19782
for pups-liszt; Sat, 4 Apr 1998 06:30:31 +1000 (EST)
X-Authentication-Warning: minnie.cs.adfa.oz.au: major set sender to
owner-pups(a)minnie.cs.adfa.oz.au using -f
From "Steven M. Schultz"
<sms(a)moe.2bsd.com> Sat Apr 4 06:28:54 1998
Received: from moe.2bsd.com
(0(a)MOE.2BSD.COM [206.139.202.200])
by minnie.cs.adfa.oz.au (8.8.5/8.8.5) with ESMTP id GAA19776
for <pups(a)minnie.cs.adfa.oz.au>; Sat, 4 Apr 1998 06:30:24 +1000 (EST)
Received: (from sms@localhost)
by moe.2bsd.com (8.8.5/8.8.5) id MAA25193;
Fri, 3 Apr 1998 12:28:54 -0800 (PST)
Date: Fri, 3 Apr 1998 12:28:54 -0800 (PST)
From: "Steven M. Schultz" <sms(a)moe.2bsd.com>
Message-Id: <199804032028.MAA25193(a)moe.2bsd.com>
To: pups(a)minnie.cs.adfa.oz.au, shoppa(a)alph02.triumf.ca
Subject: Re: Bug in Bob Supnik's Emulator!
Sender: owner-pups(a)minnie.cs.adfa.oz.au
Precedence: bulk
Tim -
From: Tim Shoppa <shoppa(a)alph02.triumf.ca>
On a cow orker's 200 MHz Pentium Pro, Bob Supnik's emulator (compiled
He's in the "dairy business"? :-) :-)
with gcc and running under Linux) is about twice as
fast as a real
11/73 for most CPU-intensive operations. Speeds for I/O based
operations can range from incredibly faster to incredibly slower
Ok - I finally got around to retrying Bob's emulator. This is using
gcc 2.8.1 under BSD/OS 3.1 with a PPro 200 and the Dhrystone 2.1 (C
language version) program.
Running under the emulator I get 555 dhrystones/second. On a real
11/73 I see 664 dhrystones/sec.
I/O operations are faster but I suspect a some of that is
due to Ultra-Wide Barracuda drives vs. HP 3724 and an Emulex UC08.
than a real -11, of course, and a lot of the interrupt
and device
priority schemes seem seriously out of whack with how a real PDP-11
The line frequency clock seems to be acting strange. When running
the dhrystone program I see:
Measured time too small to obtain meaningful results
Please increase number of runs
EVEN THOUGH the (wall clock) run time for 20000 dhrystones was 36
seconds.
The same emulator running on a 7-year-old 133 MHz DEC
Alpha is about
I recall when the DEC rep here brought in one of the first 150mhz
Alpha systems. Thought it was awesome that a machine could do a
3 phase build of GCC in about 1 hour. Ummm, today a PPro can do it
in about 15 or 20 minutes ;)
Other benchmarks of possible interest:
A recompile of the 2.11BSD C compiler:
11/44 9min 20sec
11/73 9min 33sec
11/93 6min 43sec
emulated PDP-11 5min 25sec (BUT the 'time' reported with "time make"
was 10min
4 sec)
the 44 and 73 are suprisingly close because the 44 was hobbled with
RA81s on a UDA50 while the 73 had a HP3724S on Emulex UC08. Alas,
the RA81 died so I no longer have a 44 to test with (until I get a RA9x
or something myself since the support department refused to do it).
Interesting that the emulated one is faster on this test even though
the dhrystone rating is about 20% slower.
Steven
Received: (from major@localhost)
by minnie.cs.adfa.oz.au (8.8.5/8.8.5) id XAA22011
for pups-liszt; Sat, 4 Apr 1998 23:40:52 +1000 (EST)
X-Authentication-Warning: minnie.cs.adfa.oz.au: major set sender to
owner-pups(a)minnie.cs.adfa.oz.au using -f
From Johnny Billquist <bqt(a)minsk.docs.uu.se> Sat
Apr 4 23:40:02 1998
Received: from Radha.DoCS.UU.SE (Radha.DoCS.UU.SE
[130.238.9.99])
by minnie.cs.adfa.oz.au (8.8.5/8.8.5) with SMTP id XAA22006
for <pups(a)minnie.cs.adfa.oz.au>; Sat, 4 Apr 1998 23:40:41 +1000 (EST)
Received: from Minsk.DoCS.UU.SE (bqt(a)Minsk.DoCS.UU.SE [130.238.9.30]) by Radha.DoCS.UU.SE
(8.6.12/8.6.12) with SMTP id PAA10577; Sat, 4 Apr 1998 15:40:05 +0200
Received: from localhost by Minsk.DoCS.UU.SE (Sun-4/630, SunOS 4.1.2)
with sendmail 5.61-bind 1.5+ida/ICU/DoCS id AA15396; Sat, 4 Apr 98 15:40:03 +0200
Date: Sat, 4 Apr 1998 15:40:02 +0200 (MET DST)
From: Johnny Billquist <bqt(a)minsk.docs.uu.se>
To: wkt(a)cs.adfa.oz.au
Cc: PDP Unix Preservation <pups(a)minnie.cs.adfa.oz.au>
Subject: Re: Sunchip package [was Assember in C?]
In-Reply-To: <199803172059.HAA01365(a)henry.cs.adfa.oz.au>
Message-Id: <Pine.SUN.3.95q.980404153822.15388A-100000(a)Minsk.DoCS.UU.SE>
Mime-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: owner-pups(a)minnie.cs.adfa.oz.au
Precedence: bulk
P.S. As I suspected and feared,
% diff -r Trees/V7/usr/src/cmd/c Xinu/src/cmd/cc11
indicates the C compiler provided in all these archives (Xinu,
CHIP, sunCHIP) are directly derived from the V6/V7 compiler. From Tim Shoppa <shoppa(a)alph02.triumf.ca> Sun Apr
5 05:16:02 1998
Received: from alph02.triumf.ca (alph02.Triumf.CA [142.90.114.18])
by minnie.cs.adfa.oz.au (8.8.5/8.8.5) with SMTP id FAA22898
for <pups(a)minnie.CS.ADFA.OZ.au>; Sun, 5 Apr 1998 05:16:07 +1000 (EST)
Received: by alph02.triumf.ca; id AA21693; Sat, 4 Apr 1998 11:16:03 -0800
From: Tim Shoppa <shoppa(a)alph02.triumf.ca>
Message-Id: <9804041916.AA21693(a)alph02.triumf.ca>
Subject: Re: Sunchip package [was Assember in C?]
To: pups(a)minnie.cs.adfa.oz.au
Date: Sat, 4 Apr 1998 11:16:02 -0800 (PST)
Cc: shoppa(a)alph02.triumf.ca
In-Reply-To: <Pine.SUN.3.95q.980404153822.15388A-100000(a)Minsk.DoCS.UU.SE> from
"Johnny Billquist" at Apr 4, 98 03:40:02 pm
X-Mailer: ELM [version 2.4 PL22]
Content-Type: text
Sender: owner-pups(a)minnie.cs.adfa.oz.au
Precedence: bulk
So is the
DECUS C compiler, I hear. Is there any native C compiler
for the PDP-11 which isn't derived from V6/V7?
Well, the obvious answer is DEC's (nowadays MENTEC's) own ANSI C
compiler, which runs under RSX and RSTS/e (not sure about RT-11
though...) From Tim Shoppa <shoppa(a)alph02.triumf.ca> Sun Apr
5 06:43:25 1998
Received: from alph02.triumf.ca (alph02.Triumf.CA [142.90.114.18])
by minnie.cs.adfa.oz.au (8.8.5/8.8.5) with SMTP id GAA23132
for <pups(a)minnie.CS.ADFA.OZ.au>; Sun, 5 Apr 1998 06:43:40 +1000 (EST)
Received: by alph02.triumf.ca; id AA19446; Sat, 4 Apr 1998 12:43:25 -0800
From: Tim Shoppa <shoppa(a)alph02.triumf.ca>
Message-Id: <9804042043.AA19446(a)alph02.triumf.ca>
Subject: Re: Bug in Bob Supnik's Emulator!
To: sms(a)moe.2bsd.com (Steven M. Schultz)
Date: Sat, 4 Apr 1998 12:43:25 -0800 (PST)
Cc: pups(a)minnie.cs.adfa.oz.au
In-Reply-To: <199804032028.MAA25193(a)moe.2bsd.com> from "Steven M. Schultz"
at Apr 3, 98 12:28:54 pm
X-Mailer: ELM [version 2.4 PL22]
Content-Type: text
Sender: owner-pups(a)minnie.cs.adfa.oz.au
Precedence: bulk
with gcc and
running under Linux) is about twice as fast as a real
11/73 for most CPU-intensive operations. Speeds for I/O based
operations can range from incredibly faster to incredibly slower
Ok - I finally got around to retrying Bob's emulator. This is using
gcc 2.8.1 under BSD/OS 3.1 with a PPro 200 and the Dhrystone 2.1 (C
language version) program.
Running under the emulator I get 555 dhrystones/second. On a real
11/73 I see 664 dhrystones/sec. than a real
-11, of course, and a lot of the interrupt and device
priority schemes seem seriously out of whack with how a real PDP-11
The line frequency clock seems to be acting strange. When running
the dhrystone program I see:
Measured time too small to obtain meaningful results
Please increase number of runs
EVEN THOUGH the (wall clock) run time for 20000 dhrystones was 36
seconds. Other benchmarks of possible interest:
A recompile of the 2.11BSD C compiler:
11/44 9min 20sec
11/73 9min 33sec
11/93 6min 43sec
emulated PDP-11 5min 25sec
For most "real" PDP-11 emulation uses this is probably a more realistic
benchark than the Dhrystone. I know lots of currently-being-used-and-
maintained PDP-11 applications, and none of them are heavy on FP - all
the FP-specific stuff got migrated to a faster machine the instant
the faster machine became available. (You'd be amazed at the awful
machines that I've seen people use *just* because it did their integral
faster. Farms of I860's and I960's were the rage a couple of years ago,
and boy was that an icky development platform.)
(BUT the 'time' reported with "time
make" was 10min
4 sec)
The line-time-clock on Bob's emulator doesn't necessarily have anything
to do with reality. On my cow-orker's 200 MHz pentium Pro, it ticks
about twice as fast as real time, but on my Alpha it'll often not tick
at all if there's something else keeping the (emulated) CPU busy. I
think other emulators (like John Wilson's) put more emphasis on real-time
applications and probably emulate the line-time-clock more faithfully.
Interesting that the emulated one is faster on this
test even though
the dhrystone rating is about 20% slower.
Again, I think the C recompile is probably a better benchmark - unless
someone's specifically interested primarily in FP emulation, which I think
is likely to be the exception.
Tim. (shoppa(a)triumf.ca)
Received: (from major@localhost)
by minnie.cs.adfa.oz.au (8.8.5/8.8.5) id JAA23510
for pups-liszt; Sun, 5 Apr 1998 09:29:27 +1000 (EST)
X-Authentication-Warning: minnie.cs.adfa.oz.au: major set sender to
owner-pups(a)minnie.cs.adfa.oz.au using -f
From Warren Toomey <wkt(a)henry.cs.adfa.oz.au> Sun
Apr 5 09:30:24 1998
Received: from henry.cs.adfa.oz.au (henry.cs.adfa.oz.au
[131.236.21.158])
by minnie.cs.adfa.oz.au (8.8.5/8.8.5) with ESMTP id JAA23505
for <pups(a)minnie.cs.adfa.oz.au>; Sun, 5 Apr 1998 09:29:22 +1000 (EST)
Received: (from wkt@localhost) by henry.cs.adfa.oz.au (8.7.5/8.7.3) id JAA28084; Sun, 5
Apr 1998 09:30:24 +1000 (EST)
From: Warren Toomey <wkt(a)henry.cs.adfa.oz.au>
Message-Id: <199804042330.JAA28084(a)henry.cs.adfa.oz.au>
Subject: Re: licenses mail today
To: dionj(a)sco.COM (Dion Johnson)
Date: Sun, 5 Apr 1998 09:30:24 +1000 (EST)
In-Reply-To: <19980403095446.48700(a)sco.com> from Dion Johnson at "Apr 3, 98
09:54:46 am"
Reply-To: wkt(a)cs.adfa.oz.au
X-Mailer: ELM [version 2.4ME+ PL22 (25)]
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Sender: owner-pups(a)minnie.cs.adfa.oz.au
Precedence: bulk
In article by Dion Johnson:
I think I can get the licenses mailed today to the
licensees.
Ta!
Warren
Received: (from major@localhost)
by minnie.cs.adfa.oz.au (8.8.5/8.8.5) id JAA27137
for pups-liszt; Mon, 6 Apr 1998 09:45:53 +1000 (EST)
X-Authentication-Warning: minnie.cs.adfa.oz.au: major set sender to
owner-pups(a)minnie.cs.adfa.oz.au using -f
From Greg Lehey <grog(a)lemis.com> Mon Apr 6
09:45:32 1998
Received: from allegro.lemis.com (allegro.lemis.com
[192.109.197.134])
by minnie.cs.adfa.oz.au (8.8.5/8.8.5) with ESMTP id JAA27132
for <pups(a)minnie.cs.adfa.oz.au>; Mon, 6 Apr 1998 09:45:47 +1000 (EST)
Received: from freebie.lemis.com (freebie.lemis.com [192.109.197.137])
by allegro.lemis.com (8.8.7/8.8.5) with ESMTP id JAA10674;
Mon, 6 Apr 1998 09:15:34 +0930 (CST)
Received: (from grog@localhost)
by freebie.lemis.com (8.8.8/8.8.7) id JAA27639;
Mon, 6 Apr 1998 09:15:32 +0930 (CST)
(envelope-from grog)
Message-ID: <19980406091532.27504(a)freebie.lemis.com>
Date: Mon, 6 Apr 1998 09:15:32 +0930
From: Greg Lehey <grog(a)lemis.com>
To: pete(a)dunnington.u-net.com, pups(a)minnie.cs.adfa.oz.au
Subject: Re: Bug in Bob Supnik's Emulator!
References: <199804030750.XAA10664(a)moe.2bsd.com>
<19980403172621.30485(a)papillon.lemis.com> <grog(a)lemis.com>
<9804031317.ZM14102(a)indy.dunnington.york.ac.uk>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
X-Mailer: Mutt 0.89i
In-Reply-To: <9804031317.ZM14102(a)indy.dunnington.york.ac.uk>; from Pete Turnbull on
Fri, Apr 03, 1998 at 12:17:19PM +0000
WWW-Home-Page: http://www.lemis.com/~grog
Organization: LEMIS, PO Box 460, Echunga SA 5153, Australia
Phone: +61-8-8388-8286
Fax: +61-8-8388-8725
Mobile: +61-41-739-7062
Sender: owner-pups(a)minnie.cs.adfa.oz.au
Precedence: bulk
On Fri, 3 April 1998 at 12:17:19 +0000, Pete Turnbull wrote:
On Apr 3, 17:26, Greg Lehey wrote:
I don't have numbers for anything running under the emulator, but I do have
Dhrystone sources (and some figures for real PDP-11s of various sorts with
various operating systems and compilers). If anyone wants to try it, I can
post the source.
I'd be interested.
Greg
Received: (from major@localhost)
by minnie.cs.adfa.oz.au (8.8.5/8.8.5) id KAA27211
for pups-liszt; Mon, 6 Apr 1998 10:17:22 +1000 (EST)
X-Authentication-Warning: minnie.cs.adfa.oz.au: major set sender to
owner-pups(a)minnie.cs.adfa.oz.au using -f
On 2 April 1998 at 23:50:23 -0800, Steven M.
Schultz wrote:
Not
having any great need of an emulated PDP-11 I've not pursued
the (suspected) bug in Bob Supnik's emulator. Even on a PentiumPro
an emulated 11 is slower than a real 11/73 (and a lot slower than an
11/93 - which I should cease neglecting and stuff a SCSI card into
some day as I did with the 11/73).
Interesting. I was running this on an AMD K6/233, which should be
slower than a PPro, and I had the impression it was faster. Does
anybody have some benchmarks? From Greg Lehey <grog(a)lemis.com> Mon Apr 6
10:16:56 1998
Received: from allegro.lemis.com (allegro.lemis.com
[192.109.197.134])
by minnie.cs.adfa.oz.au (8.8.5/8.8.5) with ESMTP id KAA27206
for <pups(a)minnie.cs.adfa.oz.au>; Mon, 6 Apr 1998 10:17:17 +1000 (EST)
Received: from freebie.lemis.com (freebie.lemis.com [192.109.197.137])
by allegro.lemis.com (8.8.7/8.8.5) with ESMTP id JAA10698;
Mon, 6 Apr 1998 09:46:58 +0930 (CST)
Received: (from grog@localhost)
by freebie.lemis.com (8.8.8/8.8.7) id JAA27787;
Mon, 6 Apr 1998 09:46:56 +0930 (CST)
(envelope-from grog)
Message-ID: <19980406094656.23449(a)freebie.lemis.com>
Date: Mon, 6 Apr 1998 09:46:56 +0930
From: Greg Lehey <grog(a)lemis.com>
To: "Steven M. Schultz" <sms(a)moe.2bsd.com>, pups(a)minnie.cs.adfa.oz.au,
shoppa(a)alph02.triumf.ca
Subject: Re: Bug in Bob Supnik's Emulator!
References: <199804032028.MAA25193(a)moe.2bsd.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
X-Mailer: Mutt 0.89i
In-Reply-To: <199804032028.MAA25193(a)moe.2bsd.com>; from Steven M. Schultz on Fri,
Apr 03, 1998 at 12:28:54PM -0800
WWW-Home-Page: http://www.lemis.com/~grog
Organization: LEMIS, PO Box 460, Echunga SA 5153, Australia
Phone: +61-8-8388-8286
Fax: +61-8-8388-8725
Mobile: +61-41-739-7062
Sender: owner-pups(a)minnie.cs.adfa.oz.au
Precedence: bulk
On Fri, 3 April 1998 at 12:28:54 -0800, Steven M. Schultz wrote:
Ok - I finally got around to retrying Bob's
emulator. This is using
gcc 2.8.1 under BSD/OS 3.1 with a PPro 200 and the Dhrystone 2.1 (C
language version) program.
Other benchmarks of possible interest:
A recompile of the 2.11BSD C compiler:
11/44 9min 20sec
11/73 9min 33sec
11/93 6min 43sec
emulated PDP-11 5min 25sec (BUT the 'time' reported with "time make"
was 10min
4 sec)
I don't know which directories you compiled, but here are the results
on a K6/233 running FreeBSD 3.0 and the Begemot emulator:
/usr/src/lib/c2 39.4 real 30.5 user 8.4 sys
/usr/src/lib/ccom 223.6 real 186.9 user 36.2 sys
/usr/src/lib/cpp 55.6 real 41.9 user 13.3 sys
date(1) showed times consistent with time(1).
Greg
Received: (from major@localhost)
by minnie.cs.adfa.oz.au (8.8.5/8.8.5) id LAA27499
for pups-liszt; Mon, 6 Apr 1998 11:59:29 +1000 (EST)
X-Authentication-Warning: minnie.cs.adfa.oz.au: major set sender to
owner-pups(a)minnie.cs.adfa.oz.au using -f