David Ahl's benchmark

Discuss the games, programs, utilities... and vaporware!
User avatar
MADrigal
Site Admin
Posts: 1189
Joined: Sun Sep 15, 2013 1:00 pm
Contact:

Re: David Ahl's benchmark

Post by MADrigal » Tue Dec 17, 2013 3:05 pm

@ scouter: it's quite funny because:
- we have your beautiful interface for the C2N
- now mobsie is thinking of interfacing the vic-20 keyboard
- and eventually a 1541 drive with a
- C64-like BASIC interpreter.

in the end it will be a C64 with 2MHz CPU :D

of course everything is welcome, but it's quite ironic ;)
User avatar
Mobsie
Posts: 708
Joined: Fri Jun 13, 2008 10:38 am
Location: Weinheim, Germany

Re: David Ahl's benchmark

Post by Mobsie » Tue Dec 17, 2013 3:29 pm

No!
To use stuff from other computer with the CV DONT make the CV to this computer. The Atari people use ALL from hard disk to USB, but not one people say "now we have a pc"

I know people who drive Mercedes and i know people who drive BMW, with the same wheels. Strange! BMW will be BMW and Mercedes will be Mercedes. Also the battery and some other parts are the same and from Bosch.

After all we will have maybe a CV with interesting stuff BUT we have the VDP, we have the own sound chip etc. The own Basic … Nothing to compare with the C-64. Only the CPU.

But if you go so deep, then yes ALL computer and consoles are C-64 because all use a cpu and ram and ...
User avatar
MADrigal
Site Admin
Posts: 1189
Joined: Sun Sep 15, 2013 1:00 pm
Contact:

Re: David Ahl's benchmark

Post by MADrigal » Tue Dec 17, 2013 3:33 pm

@mobsie
@scouter

...you're too serious! :D
User avatar
Mobsie
Posts: 708
Joined: Fri Jun 13, 2008 10:38 am
Location: Weinheim, Germany

Re: David Ahl's benchmark

Post by Mobsie » Tue Dec 17, 2013 4:07 pm

:o :oops: :lol:
User avatar
carlsson
Posts: 507
Joined: Fri Jun 13, 2008 7:39 am
Location: Västerås, Sweden

Re: David Ahl's benchmark

Post by carlsson » Tue Dec 17, 2013 5:31 pm

Seriously, yes I am looking forward to any hardware and software additions, in particular those bridging shortcomings and helping more people enjoy the machine. But you got to admit that an iterative process to add more and more items from another system would be a bit entertaining, in particular the last bit about feeding a different video source through the VDP without adding any of its own graphics.

Besides, I just dug up the Byte 1977 benchmark suite and might run that as well later on. It benchmarks slightly other elements of the BASIC interpreter, and is divided into eight programs so one can see the progress in time spent and compare with other models.
User avatar
Scouter3d
Posts: 646
Joined: Mon Jun 28, 2010 7:02 am
Location: Wien
Contact:

Re: David Ahl's benchmark

Post by Scouter3d » Tue Dec 17, 2013 6:54 pm

:lol:

Still thinking about the Atari Joystick Adapter ;0)
User avatar
carlsson
Posts: 507
Joined: Fri Jun 13, 2008 7:39 am
Location: Västerås, Sweden

Re: David Ahl's benchmark

Post by carlsson » Tue Dec 17, 2013 10:11 pm

New results on Ahl's benchmark:

Creativision with 1982 BASIC: about 3 min 10 sec, accuracy 0.37207
Creativision with 1983 BASIC: ditto, no difference in speed or accuracy
Creativision with Barry Klein's hacked 1983 BASIC: about 2 min 47 sec, accuracy still 0.37207

I haven't studied how long e.g. RND calls take, but on this particular benchmark the hacked version is about 12% faster, if I understand how to calculate percent: (190 - 167)/190.
User avatar
carlsson
Posts: 507
Joined: Fri Jun 13, 2008 7:39 am
Location: Västerås, Sweden

Re: David Ahl's benchmark

Post by carlsson » Tue Dec 17, 2013 10:58 pm

Here is the Byte Magazine benchmark suite from 1977, extended with the 8th benchmark by Creative Computing 1983:

Code: Select all

BENCHMARK 1 (new)
100 REM TEST 1
110 PRINT "START"
120 FOR K=1 TO 1000
130 NEXT K
500 PRINT "STOP"
550 END

BENCHMARK 2 (add/replace lines)
120 K=0
130 K=K+1
190 IF K<1000 THEN GOTO 130

BENCHMARK 3
140 A=K/K*K+K-K

BENCHMARK 4
140 A=K/2*3+4-5

BENCHMARK 5
150 GOSUB 600
600 RETURN

BENCHMARK 6
125 DIM M(5)
155 FOR L=1 TO 5
160 NEXT L

BENCHMARK 7
157 M(L)=A

BENCHMARK 8 by Creative Computing (new)
100 REM TEST 8
110 PRINT "START"
120 K=0
130 K=K+1
140 A=K^2
150 B=LOG(K)
160 C=SIN(K)
170 IF K<1000 THEN GOTO 130
180 PRINT "STOP"
190 END
To begin with, here are the results in seconds from a range of mostly 8-bit computers. The list does not contain the exact same examplse as in the Ahl benchmark, but gives you an idea what to expect:

Code: Select all

             BM1   BM2   BM3   BM4   BM5   BM6   BM7  BM8  Avg
             --------------------------------------------------
BBC (B ?)    0.6   3.2   8.1   8.8   9.9  14.3  21.9   48  14.3
Acorn Atom   0.5   5.1   9.5  10.8  13.9  19.1  31.1   92  22.8
Telestrat    0.5   3.6  11.4  13.2  13.4  18.7  26.3  109  24.6
VIC-20       1.4   8.3  15.5  17.1  18.3  27.2  42.7   99  28.7
Apple II     1.3   8.5  16.0  17.8  19.1  28.6  44.8  107  30.4
Dragon 32    1.6  10.2  19.7  21.6  23.3  34.3  50.0  129  36.2
Oric Atmos   1.6  15.2  25.4  27.4  33.0  45.6  68.5  136  44.1
SVI-328      1.6   5.4  17.9  19.6  20.6  30.7  42.2  236  46.7
ZX81 (fast)  4.5   6.9  16.4  15.8  18.6  49.7  68.5  229  51.2
Microtan 65  1.9  12.8  24.7  27.8  29.6  43.2  68.9  243  56.5
ZX Spectrum  4.8   8.7  21.1  20.4  24.0  55.3  80.7  253  58.5
Oric-1       1.8  17.1  29.0  31.4  38.0  51.8  77.8  230  59.6
Atari 600XL  2.2   7.2  19.1  22.8  25.8  37.6  58.3  412  73.1
TI-99/4A     2.9   8.8  22.8  24.5  26.1  61.6  84.4  382  76.6
Now how fast is the official CreatiVision BASIC? I ran these in the 1983 version, but I doubt the 1982 one is any faster. Obviously the hacked one would run a bit faster though. Prepare yourselves!

Benchmark 1: 20 seconds! Yes, a simple FOR-NEXT loop running for 1000 iterations takes more than four times as long as the slow ZX Spectrum.
Benchmark 2: 60 seconds using K=K+1 and IF statement instead of the loop
Benchmark 3: 79 seconds with the calculation using variables
Benchmark 4: 119 seconds with the calculation using constants
Benchmark 5: 180 seconds when adding an empty subroutine call
Benchmark 6: 298 seconds with the DIM and an additional empty loop
Benchmark 7: 398 seconds when assigning values to the DIM'd array

By now we can see that CreatiVision BASIC actually suffers a lot, and we brace ourselves for the final benchmark with the logarithm and trigonometric functions that all other computers get stuck at...

Benchmark 8: 120 seconds!!!! Suddenly the CreatiVision springs to life, and handles those K^2, LOG(K) and SIN(K) like there was no tomorrow.

I don't bother calculating an average, as it doesn't say very much and would anyway put it at the very bottom, but we learn one thing: to not be afraid of using aritmethic, logarithmic or trigonometric functions with CreatiVision BASIC as those are where it really shines. Regular loops, subroutines, assignments etc is what slows it down, as far as I can tell.

In a few days, I might run this suite on my Laser 2001. Perhaps someone else with e.g. a Salora Manager will get ahead of me. I expect it to perform fairly well. It reminds me that the source where I got the majority of benchmark numbers also had a row for IBM PC 4.77 MHz but at some point I omitted it as it is not a true 8-bit computer.
User avatar
Mobsie
Posts: 708
Joined: Fri Jun 13, 2008 10:38 am
Location: Weinheim, Germany

Re: David Ahl's benchmark

Post by Mobsie » Wed Dec 18, 2013 7:10 am

great test!
"Benchmark 8: 120 seconds!!!! Suddenly the CreatiVision springs to life, and handles those K^2, LOG(K) and SIN(K) like there was no tomorrow."
Yes this show us what the CV can do with a modified well programmed Basic :idea:
User avatar
Mobsie
Posts: 708
Joined: Fri Jun 13, 2008 10:38 am
Location: Weinheim, Germany

Re: David Ahl's benchmark

Post by Mobsie » Thu Dec 19, 2013 3:19 pm

as you write i am to serious, and that is ironic to use the commodore keyboard (stuff) i found now the ideal keyboard for me :lol:
Foto.JPG
Is vtech!
You do not have the required permissions to view the files attached to this post.
Post Reply