A collection of Atari BASIC benchmarks

[+Stephen]

So what would you do in the case of a benchmark that specifically requires the screen be turned on because it was graphical in nature?  How would you cheat that one?

[Faicuai]

58 minutes ago, Stephen said:

How would you cheat that one?

It's a rhetorical question. You already have the essence of the answer here:

 

 

Have you ever tried running anything across A8's own OS-defined graphics modes, and measure effective throughput? Have you noticed how much CPU utilization varies, even with Antic-ON?

 

It will all depend on what the intended graphical output requires to be rendered as planned.

 

The (central) point in hand is that on the A8 there is always an option to use MORE cpu-power, depending on the task involved. On some other "newer" systems, however, such option does not really exist, and that is causing severe psychological distress.

 

That is the whole, central issue of this discussion.

 

 

 

 

[ClausB]

2 hours ago, Stephen said:

So what would you do in the case of a benchmark that specifically requires the screen be turned on because it was graphical in nature?  How would you cheat that one?

The programmer can choose a lower res screen to balance CPU and DMA. Is that cheating or is it flexibility?

[ClausB]

Fwiw I made some benchmark programs to test multiplication, trig and log functions a while back:

 

[thorfdbg]

On 6/3/2021 at 3:51 PM, Faicuai said:

No, you did not.

 

You ran Bench64.bas, not FPTEST34.bas (unless I missed the latter's screenshot, which I could not find...)

 

FPTEST34 *also* fails on my end with one of the FP packs I have here (I had already tested long before). Just wanted to see those specific results with YOUR FP-pack, and maybe build an OS image with your FP rom (if we can have access to it), so we all can run Basic++ to its intended / full potential (no Basic package on Atari will get anywhere with stock FP rom).

You can have access to it, obviously, and it's part of Atari++, you find it on its home page:

 

http://xl-project.com/

 

I'm not sure what you mean by "you won't get anywhere with stock FP rom". You get exactly what Atari Basic delivered, and it does what it does. That's based on a couple of poor decisions made back then, but you cannot undo history.

 

Thus, I'm not hiding anything, but in the type of tone you responded, I'd suggest you probably test yourself.

[+Stephen]

6 hours ago, Faicuai said:

It's a rhetorical question. You already have the essence of the answer here:

 

 

Have you ever tried running anything across A8's own OS-defined graphics modes, and measure effective throughput? Have you noticed how much CPU utilization varies, even with Antic-ON?

 

It will all depend on what the intended graphical output requires to be rendered as planned.

 

The (central) point in hand is that on the A8 there is always an option to use MORE cpu-power, depending on the task involved. On some other "newer" systems, however, such option does not really exist, and that is causing severe psychological distress.

 

That is the whole, central issue of this discussion.

 

 

 

 

Of course I have - I've been using the machine since 1982.  I'm aware of nearly everything that turned off the screen and the reason for doing so.  I've never said it's a bad feature, it's actually damn versatile.  My only point was the fact that you do it in all of your benchmarks when the other systems do not, and you often do not state it.  You clearly do this as you are so unconditionally biased that your little Atari is great and everything else is a shitty joke.  Most of us got over that attitude 40 years ago.

[+Stephen]

5 hours ago, ClausB said:

The programmer can choose a lower res screen to balance CPU and DMA. Is that cheating or is it flexibility?

Flexibility of a wonderful design, way ahead of its time, and a fact I have known about for 39.5 years now, and used often.  We all know what is actually being argued here, and it's pretty pointless as at this point I am convinced the one doing it is 110% full on autistic and either can't see that point, or does it to piss other people off.

[Faicuai]

21 minutes ago, Stephen said:

My only point was the fact that you do it in all of your benchmarks when the other systems do not, and you often do not state it. 

Accepted and acknowledged several posts ago.

 

Hope you had a chance to read them. 

[Faicuai]

20 minutes ago, Stephen said:

Flexibility of a wonderful design, way ahead of its time, and a fact I have known about for 39.5 years now, and used often

Very well, then.. Cased closed.

[Mazzspeed]

10 hours ago, Faicuai said:

That is FALSE. Citing from GitHub:

 

" Reporting results

1. Please use the machine exactly as it would appear when turned on. Tricks like turning off interrupts to get better results should not be done."

• What does TURNED ON mean? What state? What condition? 
• When we "turn on" the Atari, there is no Turbo Basic anywhere to be seen!! On that (dumb-ass) basis, we should warn Maury to stop wasting his time testing ALL other interpreters (!!) ?
• When the GitHub author turns on his "glorious MinZ v1.1 (36.864 Z180, CP/M 2.2, BBC BASIC [Z80] v3)" WHERE is BBC Basic for Z80 (which I also have for CP/M 2.2 on the IndusGT? When I turn on my CP/M computer, there is no CP/M or BBC/Basic to be seen anywhere (!!) Does "turned on" means "after being booted?" Because if not, how does the bizarre MinZ comes into the picture? ?
• My system boots fully-automatically (entirely SDX-driven) into 80-cols. session, directly from a stack of SDX drivers loaded before getting control back at command prompt for the first time! So where exactly is that I must define "turned on" here? How is this different from booting the MinZ? ??
• ANSWER: "turned on" stems from the author's resentment regarding how ClockSp benchmark is simply defined: " (...) ClockSp is calibrated so that a BBC model B with most interupts turned off gives 2.00MHz". He thinks that turning off most interrupts makes look BBC's Basic "deliberately" better: "(...) Assumes some system tweaking to make the BBC Micro appear slightly faster than its default setting..."  ??

 

 

This (third) time, there is no need to wait for wisdom to kindly kick you around, as it is already written, and BEFORE driving the XEP at ultra-speed...  And guess who were involved... ?

 

Quoting myself: " (...) my current environment (ran and operated with Atari products, through-and-through) requires DMA disabled to fully access the A8's CPU power-band, and thus operate correctly "

 

Here you go (in case you forgot your milk-and-pijamas before going to bed).

 

 

"Won't ever run correctly on Atari BASIC, because it doesn't have user- defined functions. Soz, Maury … ☹"

 

It turns out that it DOES RUN, and with a penalty factor (on Atari runs) of up to x(1/1.5) during execution of emulated DEF calls, as measured already in MS-Basic by running the core calls with DEF or via [gosub/return/assignment] emulation. It's just that the Author could not make it run, because he defeated his very own "portability" goal, the one he explicitly complained about BBC-Basic benchmarks !! ??

 

 

 

 

9 hours ago, Faicuai said:

 

Normalizing Atari results to the please the PAL-c64 princess (by factor of 100/103)

 

BBC Miicro:                   202 (original), now 196

Atari Altirra Basic + FP: 209 (original). now 203

Atari TurboBasic:           240 (original), now 233.

 

I'm sure she now feels relieved of not being left so behind. 

 

Dude, it's done, discussion's over.

 

Three people in this thread all stated that your results with DMA off were invalid, I'm not at all interested in hearing your definition of tricks like interrupts, as the concept seems pretty clear to me as well as the other two people in this thread that pulled up up on your insistent desire to quote benchmarks with DMA off, and as stated earlier I'm not interested in normalizing results as they state what we already know.

 

The author of the benchmark states that BASIC much match C64 BASIC in operation and according to the author himself standard ATARI basic does not support user defined functions along the lines of C64 BASIC, it's there highlighted in a screenshot - Discussion over.

 

Therefore, that BBC is a hell of a machine. But, as always, we already knew that. The C64 isn't the fastest at CPU bound tasks, however BASIC v2 is in some ways faster than Atari BASIC and the C64 has what I consider to be the best graphics and sound of the era with interesting architecture, and the A8 as always is impressive for it's age, IMHO better than the Apple II and awesome with modern upgrades and SDX.

 

6 hours ago, ClausB said:

The programmer can choose a lower res screen to balance CPU and DMA. Is that cheating or is it flexibility?

 

It's cheating in the context of this benchmark, the rules are pretty clear.

Edited June 4, 2021 by Mazzspeed

[Faicuai]

3 minutes ago, Mazzspeed said:

Three people in this thread all stated that your results with DMA off were invalid

No.

[Mazzspeed]

2 minutes ago, Faicuai said:

No.

Yes. Repeating the same thing over and over again does not make it right.

 

You constantly post benchmarks with DMA off while skirting around words trying to make it sound like this is the way the A8 always runs on a daily basis. The rules are clear in the case of this benchmark. <--That's a full stop, meaning the end.

[Faicuai]

8 minutes ago, Mazzspeed said:

The rules are clear in the case of this benchmark

No, as clearly seen in post #74.

[Mazzspeed]

Just now, Faicuai said:

No, as clearly seen in post #74.

Discussion's over. The performance of any 8 bit machine will never be as great as that huge superiority complex you harbor.

[Faicuai]

7 minutes ago, Mazzspeed said:

Discussion's over.

 

More DMA=OFF results (on-topic) coming for Basic++ 1.08, which is another good interpreter and a good piece of work.

 

The Ultra Basic 1.8X, which everyone seems to ignore, while being very flexible and a solid improvement over Atari Basic.

 

Now we are ready to go back to the real substance / fun.

 

 

[Mazzspeed]

10 minutes ago, Faicuai said:

 

More DMA=OFF results (on-topic) coming for Basic++ 1.08, which is another good interpreter and a good piece of work.

 

The Ultra Basic 1.8X, which everyone seems to ignore, while being very flexible and a solid improvement over Atari Basic.

 

Now we can go back to the real substance / fun.

 

 

And falls outside the context of the benchmark in question making any results invalid. At the end of the day, this benchmark is pretty pointless, as it simply highlights what any true retro enthusiast already knows. Certain designs needed a faster clock speed to overcome inefficiencies of their design, no different to the situation regarding the Z80 vs the 6502, and certain designs did not need outright clock speed to make maximum use of their capabilities. Naturally, faster clock speed on a given processor should mean faster CPU bound results - There's no surprises here whatsoever, it's all perfectly logical.

 

As far as substance is concerned, you've been forced, kicking and screaming, to learn about an architecture you constantly have an opinion of but know little about - Personally I see that as productive discussion and a good thing.

 

Furthermore, I don't hold grudges, as a manager of 25 years I learned not to - I'm simply intolerable of bullshit as I feel like modern society is literally drowning in it.

Edited June 4, 2021 by Mazzspeed

[Faicuai]

19 hours ago, ClausB said:

Fwiw I made some benchmark programs to test multiplication, trig and log functions a while back:

 

Nice...

 

Do you have by any chance the actual 2K FP rom? (saw your FP benchmarks on the thread, as well)

 

I will  set up an OS-load with it and run the tests.

[+CharlieChaplin]

23 hours ago, Faicuai said:

No.

 

Maybe you should still leave DMA=off when the benchmark results are presented, so the results are invalid and invisible (and thus useless) at the same time?

 

[Faicuai]

3 hours ago, CharlieChaplin said:

Maybe you should still leave DMA=off when the benchmark results are presented

No.

 

Results are always visible, or visible at will, at any point in time.

[+Stephen]

24 minutes ago, Faicuai said:

3 hours ago, CharlieChaplin said:

Maybe you should still leave DMA=off when the benchmark results are presented

No.

 

Results are always visible, or visible at will, at any point in time.

ONLY with additional equipment.  I don't care if it's BIT3, XEP-80, VBXE, etc.  Standard bare machine, you turn off DMA, you get no screen.  Directly banging GRAFP registers doesn't count either - that is not a standard way of putting text on the screen.  Again, keep twisting words, ideas, everything to suit your autistic always have to be right view.

[Mazzspeed]

Look everyone, my C64's the fastest.

 

[Faicuai]

5 minutes ago, Stephen said:

ONLY with additional equipment. 

No.

 

I will post a video, so everyone can see.

[Mazzspeed]

2 minutes ago, Faicuai said:

No.

 

I will post a video, so everyone can see.

Will you show us all the script you use as well?

[Faicuai]

Just now, Mazzspeed said:

Will you show us all the script you use as well?

No.

 

There are no scripts involved.

[+Stephen]

7 minutes ago, Mazzspeed said:

Look everyone, my C64's the fastest.

 

Wow - I bet you rocket shifted that CPU down into the power band.  Look how super clear your video is - how did you achieve such a clean video rendering path.  Do you know what the super-optimized bandwidth is?