PC still playing Amiga catchup

[amigaksi]

That's an entirely arbitrary statement. My PC boots MS-DOS in less than one second (after POST, which takes a bit longer--system firmware is quite complex these days, with more features than your average Amiga). That's much faster than any of my Amigas. Is it a useful measurement? No, because there's no direct correlation between the two systems, and ...

... here's where someone argues that no one uses MS-DOS. Well, no one uses AmigaOS, either. I'd wager there are more active MS-DOS users (millions, even) than there are active AmigaOS users. If you don't believe me, then you don't spend enough time in front of embedded systems.

Everyone really does need to straighten out their definitions of real-time. Karlos is talking computer science, everyone else is talking user perception. There is no "real-time" in user perception. Humans are neat, but we have lots of built-in latency. Milliseconds have passed before I know I've pricked my finger, for example.

Personally, I can do more useful work in a shorter amount of time on my Windows system (Core i7 920, 6GB RAM, GeForce 8800 GTS 512 (G92), blah blah blah). The Amigas are just for fun.

I use MSDOS still and I can state that Amiga boots up faster since it needs to load a 1024 byte boot block to be ready to accept commands.  It's main functions in ROM.  MSDOS on the other hand reads a boot block followed by the OS functions (MSDOS.SYS/IO.SYS/COMMAND.COM/etc.) before you can actually use the OS functions.  Actually Atari/C64 with cartridge based software boot up with software faster than both.  Boot-up time is useful in some cases where you just want to try testing some stuff.  I still use Atari 800 for testing external devices connected to joystick ports with simple PEEK/POKE 54016.  

Also useful for doing some simple math.  Don't we still use calculators because they boot up faster than booting up a PC although you can get the functionality of the calculator in a laptop/desktop.  I find Atari/Amigas retro-machines easy to analyze for video/real-time stuff and fun for games since their code is highly efficient and optimized and perfectly synched up to video rates.  And you know you are the only thing running and there won't be any viruses or any Wifi doing background bullcrap.

[amigaksi]

I don't think anyone's attempting to argue that a synthesized violin is a better instrument than a Stradivarius; however, the Amiga is not a Stradivarius.

I'm not an advocate of upgrading for upgrading's sake, so if a process designed for the Amiga still does the job it was meant to do, good for the process and the Amiga. There comes a time, however, when that system's total cost of ownership (or the risks associated with a possible failure of that system) will outweigh its return. Anyone that doesn't upgrade at that point in time (or really, slightly before) is putting their livelihood at risk.

EDIT: Let's also not forget Amiga.org's own recent history re: PHP obsolescence.

Good point-- not upgrading for upgrading's sake.  If it serves the purpose, why bother with a new machine.  Actually, my Toshiba 366Mhz laptop outperformed the HP 1.4Ghz laptop in watching DVDs since it had hardware decoding vs. software decoding.  That should tell you the basic picture that clock speed isn't everything.  

And from the standards point of view, small subset of hardware features among PCs worldwide are being used in software out there in order to support the most customer base.

[amigaksi]

Wrong. There were > 100 CPU processes, not GPU processes. There was precisely one CPU process for that simulation. "ps aux wwwf | less" is hardly going to report on GPU processes, now is it? :roflmao:

Four of those CPU processes are capable of being in the run state concurrently provided they aren't making atomic operations on the same area of memory. Which is highly unlikely because this is a virtual memory system. Most of the processes have no idea the others exist, let alone have the opportunity to lock something they own.

Just for you, I've dumped the current process list. Too big to post here, so here it is: process.txt

I make that 171 processes at the moment. You should see it when it is actually busy.
...

So you maintain that running 1 process or 171 processes does not affect the response time at all?  That's where your blunder was.  It was a simple point not really that significant compared to the point of you not understanding I/O transfers of joystick ports.

>-edit-

I got lucky and I noticed this edit while looking for something else in the thread.

>Oh, and as for the rest of your objection:

>My god, you are living so far in the past it's hilarious. EUAE runs just fine, even on top of that CUDA simulation.

You keep missing the point.  Your point is running all those processes DID NOT affect the user responsiveness at all.  That is violation of law of conservation.

>If you can't time a 500khz event properly on your PC without sync going off it's probably because you are either

>1) Using a crap OS (which given the rest of your assertion I'm assuming is windows)
>2) Using a crap PC. Harder to verify, but not impossible.

It's easier to do in Windows 98SE or older OSes where you can take over the system.  And it's easier to do with older systems than newer ones since newer systems have problems installing Windows 98SE because they have too much nonstandard hardware requiring whole slew of new driver database that are more bloated than previous versions.

>As for your claim the machine is somehow too maxed out with the simulation to run EUAE. try reading the specifications for PCI Express 2.0 16-lane and then come back when you've ...

Never made that claim.  Straw-man argument.

>I'm using a decent OS on good hardware. It may have escaped your attention back there in the 1980's, but present day POSIX compliant systems now require nanosecond accuracy for timing. The Linux kernel uses a busy loop to calibrate the maximum execution speed of your CPU at boot time. With this, you can, if you need it, have a busy wait that is accurate to a few machine cycles, though it will cost you load.

I was wondering when you would ever get around to replying to my point of timing accuracy.  Demanding some nanosecond and people having it NOW in their PCs are two different things.  Current timers (up to Windows XP era) relied on PIT (8253) using 1.19318Mhz which comes to 840ns.  And even that is unuseable given other things happening in the system.  And once again you fail to understand I/O bottlenecks interfering with your so-called nanosecond accuracy.  Amiga does the 558ns accurate register modifications with little effect on anything else running in the system since it's done via the Copper.  For Amiga it's a breeze; for PC, you need to get one of the latest PCs that has implemented the "nanosecond" accuracy which inexorably will have problems given the support for backward compatibility.

>Well, again, you are failing to differentiate the OS from the machine. For the nth time, Windows != PC. Use a decent OS, you don't get these problems.

You replied to the same message twice; but anyway, my answer is the same as well-- you need to understand what a PC is.  I am a low-level programmer; I hardly use the OS for anything.  Whatever software I write is what is potentially possible with the PC.

[amigaksi]

You still didn't clarify how you were doing this timing, or on which OS. Therefore your assertion cannot at this stage be solely blamed on the hardware. For example, if you disable speedstep in your application and wrote your delay loop in assembler, you can pretty much get it down to bus cycle level of accuracy.

If you were relying on OS level sleep()/usleep() type functions you aren't going to get accuracy any more than you get from a DoIO() on the timer.device, probably worse, in fact.


...

It works on all Windows platforms unmodified since it's using inline ASM-- IN AL,DX with DX set to port of joystick.  Dynamic frequency is disabled which by the way you should know affects the RDTSC timer as well.

>If it makes you happy to believe that, carry on.

You miss that point again.  You can't talk about some video cards' capabilities unless it's standard among majority of PCs out there.  Otherwise, I'll hook up some custom hardware to my Amiga like a laptop motherboard and use it for slave processing.

>Well, you got me there. I don't have a parallel port. I'm really up the creek without a paddle now. I wonder whether or not USB would make a reasonable alternative for control applications? I have about 12 of those to play with.

That's a lame excuse and selfish one.  So you don't see any use for a parallel port-- try searching the web-- you'll see thousands of people who have done parallel port based projects.  USB requires hardware to do parallel signal processing.  With a parallel port,  you have the digital lines to use for control lines.  

>FWIW, I don't have a joystick port either. Tragic, really.

It is.  Joystick ports are also very useful for Amiga users so dismissing one of it's strengths by thinking it's not that useful is a lame excuse.  Look at your absurd style of arguing-- first you claim there's nothing superior on Amiga; now that it's staring you in the face that there are things still superior on Amiga, you want to downplay them or make them seem that they are useless.

[amigaksi]

You don't say...



Good grief. AGP is obsolete, PCI Express 2 is the standard now and has been for some time. Devices talk to each other via high speed point to point serial communication, multiple devices can be using the bus at the same time. It's all a far cry from PCI and AGP.

Your reply is irrelevant to the point.  Standard joystick gameport still uses slow I/O regardless of whether you have PCI/AGP/PCI Express.  Just because you put a new bus in doesn't make all the devices in the system automatically run at that rate.

And no, AGP is not obsolete as far as people out there having AGP.  It may no longer be put into motherboards, but it's present in millions of homes.  Just because A4000 introduced AGA that didn't mean that people stopped writing for OCS/ECS.

[amigaksi]

p3 600? LOL.  get with the times.  Yea its great going on a long trip in a 1974 VW Beetle but its not as fun and comfortable as my wife's 2008 Chevy Tahoe.



Actually, that never crossed my mind.  Systems nowadays, if you build your own, are VERY affordable.  If you're using a p3 600, then its your own fault, go wallow in your own sorrow.  I have no sympathy for you.

Its not my fault XP is 7 years old.  I upgrade my systems to keep up with the times.  I'm glad XP runs well on my systems at work.   At home, I'm ballin' with a HP laptop runnin openSuSE 11.

Too many people bash XP when its their dinosaur hardware causing the bottleneck.

Most non-technical fields use PCs for word processing, Database, and communications and going from 600Mhz to 1Ghz hardly makes any difference.  I know these hospitals that still are using DOS-based software on the ancient PCs.  They don't see any reason to upgrade if everything is working well especially if they have to BUY new PCs, BUY new versions of software, LEARN new interfaces, etc.  Some areas don't upgrade unless they get FORCED into it.  And I don't see any reason why they should either.

[amigaksi]

And of course a Vax has a punch card reader attached to it, which is arguably more useful that a parallel port, so Vax still rules!

As some people have stated in this thread, if it serves the purpose why bother with the upgrade.  I hope you know many printing places still use parallel-port based printers.  It's usefull and especially for testing custom circuits and stuff.  I know the Willem EPROM programmer I use works perfectly with parallel port on my old laptop.  And my argument isn't that that makes the Amiga superior, but that's another useful thing.

[amigaksi]

Yeah, true... And this refusal to see and embrace evolution is what helped to kill the Amiga... People always refused to accept newer technologies. AGA sucks, GfxCard sucks, AHI sucks, paula can do better,... and in the software side: memory protection is performance killing,...
...

It's NOT refusal to see newer technologies, but looking at REALITY as it is.  Just because a few big companies got together and made some superior graphics card and declared the previous standard "obsolete" does not make it obsolete in the REAL WORLD.  Millions of people that still do not have that graphics card still have to be supported.  Not everyone follows (nor should they follow) this vicious cycle of computer technology having to be upgraded every year or so.  So the original point that when AGA came out, people still wrote for OCS/ECS is good and valid.

>And that's why people using an OS and a computer outdated in almost every aspect keep thinking it's better than monsters of technology created today...

It depends on what you want to do with it.  If all I want to do is make some video titles on a video and I have the software on Amiga, there's no reason for me to go buy a PC because they just introduced a new graphics card that does 256MB/second over a new PCI Federal Express overnight delivery.

>Yeah, OS of today are heavier than Exec written 24 years ago... But there's no way Amiga could be used for anything productive. You do not reboot because a program crashed anymore. And guess what ? even Apple is doing multitasking nowadays...

That's your opinion.  You have to maintain PCs as well as Amigas.  In some cases, you better reboot when a program crashes in XP.  But program crashing has nothing to do with hardware; well-behaved applications don't crash on Amiga nor on Windows XP.

>If you ask me, the lack of memory protection is an heavier handicap than having extra processes doing nothing (especially when seeing the power/memory we have today).

Even with memory protection, you still get spyware/viruses/etc.  Misbehaved programs still exist and can be written.

[amigaksi]

There is no fscking "standard joystick gameport" on current PC hardware. Along with the parallel port, it has vanished into the hazy world of yesteryear. Where you live :p  In case you didn't notice, it has all moved to USB in recent years. Now, USB is very slow compared to any internal bus, yes. However that makes absolutely no difference on a system where the communication with the USB device is arbitrated by hardware. My USB device sends a packet, the controller handles it, puts it into memory somewhere and issues an interrupt. Magic. It might not be ideal for your specific polling needs but I think you'll find its ideal for most peripherals.

...

Take it as USB or port I/O, they are both inferior to Amiga reading the joystick I/O port.  Don't get pssed off now by cursing; you underestimated the Amiga; but it's okay, people make mistakes.  You have to live with it.  USB is better for block transfers.  If you do single byte read of the status of a joystick, there's more overhead involved than reading an I/O port location (as is case with Amiga).

>There are people out there with 8-bit home computers still. It doesn't mean they aren't obsolete. A given technology essentially becomes obsolete when it ceases to be manufactured or improved upon.AGP was better than PCI for graphics specific applications, PCIe is better than both, is fully generic and has subsequently rendered them obsolete.

I defined what I meant by obsolete in previous message and in msg #113 which you are replying to.  There are millions of users using AGP so it's not obsolete.  Ideally, you want to support all machines being used, but companies make mistakes-- they can't get it right the first time so they have to keep improving their designs (or perhaps it's a marketing set-up in some cases).

>I'm fully understanding your argument that the Amiga's native hardware is ideal for your purpose of polling the joystick port at a precise interval and that you couldn't, for whatever reason, duplicate this on a PC. It's quite amusing that you assert this as your premier example of the Amiga is still in some way streets ahead of the PC, yet complained that my particle simulation was "too specific" a metric.

It wasn't my prime example; it's just one example that I thought would be easier to understand given Amiga users are familiar with joysticks.  I stated that your particle simulation didn't address the point of joystick I/O (it was unrelated).

[amigaksi]

...
And no, TV sets aren't usually locked to 22 fps.
...

One thing interesting to note is that Amiga did do 30fps/60fps full screen (overscanned) and ran animations loaded from a floppy disk (880K).  Although PC horsepower allows it do 30fs/60fps, not many people spend the time to optimize and make their code/videos efficient since so much memory/hard drive storage is available.  I just saw a "hello world" example on modern OSes give an executable output of 1 MB since it was linked and tied to some multi-function crap (MFC).

[amigaksi]

...
Nowadays, I just hate Macs
...

Hey we have something in common.  Macs should never have gone to intel processors because now it just boils down to which OS is better.  They gave up that their hardware can compete with PCs.  

>Finally, even though I would sooner spit on one at the time, I'd even have an Atari

Getting an Atari 800 may be an upgrade for you if you want to play games that are cycle exact and easier to control.  By the way, Atari 800 joysticks read two joystick ports with one LDA instruction (LDA 54016) and takes 4 cycles at 1.78979Mhz.  It beats any USB/Game Port joystick out there.

[amigaksi]

Well, reality is that Commodore may not have been dead if people had bought and developped for (new) AGA machines in mass... But I guess this is also Commodore's fault... They had to convince people, they failed to do so...

Of course it's not valid. When people still wrote 32 colours games, anything concurrent was displaying more colourful pics (be it the PC, SNES,...), and way more powerfull... How could the Amiga be compettitive this way ? Well, it couldn't. And that's what reality is about. This is just market/business. Of course people still used it. And of course people still bought ECS games (for a limited amount of time though). But a market that isn't dynamic is a dead market... Guess that's what happened.

It's always going to be hard for smaller companies to keep up with bigger companies in dynamic situations.  Amiga didn't become obsolete-- it's just the company went bankrupt so further development/research stopped.  People can do their research, but the current innovations aren't making that big of an impact on the average user like going from 16-bit to 32-bit processors or ISA to VESA/PCI or EGA -> VGA.  I have a 2.8Ghz system, 32-bit system.  I don't see much point in going for a 64-bit system if it has problems with backward compatibility and isn't going to have much impact on what I currently use the system for.

[amigaksi]

My question here is, who other than yourself actually cares about how fast they can read the joyport? This is one thing about your argument I really don't quite understand.

What is it you are doing that requires you to poll the joyport on a precision interval? Are you using some sort of homebrew measuring device on it?

That's one example where it's a breeze to not only read the joystick on Amiga but also read it with high precision timing.  Gaming with joysticks was an afterthought on PCs as even gameport was usually on an add-on board.  Gaming was a central concept on Amiga/Atari machines so more relevant.  It all adds up-- joystick I/O, timer IRQs, etc.  not just for me, for everyone.  Don't worry, "I have not yet begun to fight."   Just going to finish up this point before addressing other points.   A gameport uses analog joysticks and requires 1ms+ worse case read-time to get status of joystick directions.  This at 1 Khz would use up all the CPU time whereas on Amiga, it would hardly effect system performance even if performed with high precision timing.  Typical games with fast motion require 1Khz+ sampling of joystick motion.  Joystick ports can also be used for general purpose parallel I/O especially on older platforms like Atari/C64.

[amigaksi]

Sorry, but what does size optimization have to do with speed? That misconception takes away any relevance your argument might have had. Mind you, though, most of the games I play update the screen well faster than the monitor is able to. The reason that there might be some slowdown is that there is generally a lot more going on behind Far Cry 2 than Lotus III. And why would anyone link MFC to a "simple" Hello World?
...

Do you bother to read the posts that you reply to?  Looks like not in this case.  I stated not many people optimize programs (which is a fact): "Although PC horsepower allows it do 30fs/60fps, not many people spend the time to optimize and make their code/videos efficient since so much memory/hard drive storage is available. I just saw a "hello world" example on modern OSes give an executable output of 1 MB since it was linked and tied to some multi-function crap (MFC)."

I just compiled a hello world program and it was 1 MB; doesn't mean all compilers do that or you can't change the settings and eliminate the MFC.  As far as your blunder that size has no relation to speed, ever check MPEG videos.  If they were uncompressed, it would affect the speed.  I am surprised to hear this argument from a PC enthusiast since PC memory speed is slower than processor speed so dealing with compressed animations and decompressing them with a fast algorithm would be preferred over uncompressed animations.

>Regarding "running animations from a floppy disk"... The PC too has a demo scene, and some of the best programmers cram down pretty damn impressive (real-time) animations with sound and music in less than 1k. Pretty hard to imagine happening on the Amiga, no?

I'll guarantee that it won't work with nonstandard hardware on everyone's PCs.

>The A1200 was pretty weak compared to contemporary PC's which had already done fluid 256 color graphics and 16 bit multi-channel sound for some time (even an 8 channel 16-bit stereo consumer sound card had popped up a few months before).

You seemed to missed some posts in this thread (or ignored them).  Just because some 8-channel 16-bit card is available does NOT mean that everyone has it or that you can utilize it in comparing Amiga with PC.  With new hardware add-ons, any computer can do anything.  Talk about hardware that's available to most homes and compare with that-- then you can write some application and know that it will work on 99% of PCs out there.

>Really? And no, doing it wouldn't have much of an impact on performance on a multi GHz multi-core processor either way, but it would certainly be a waste of cycles to sample it that often.

Bullcrap.  You have NO understanding of the gameport nor I/O timing on PCs.  I/O is much much slower than even memory.  I suggest you try to time the gameport yourself.  And no, gameport is NOT obsolete because Vista doesn't have a driver for it.  It exists out there in millions of homes.  It was on the PCI surround sound Mag Dog Audio board I purchased a couple of years ago.  It's NOT a waste of cycles to sample at 1Khz or above.  I wrote a joystick recorder program and the time between changes of direction/firing goes to less than 1 ms in some cases for games like River-raid and others.  I can say sampling audio at 44Khz is a WASTE of space, but it's required to capture all possible audible frequencies.  Similarly, sampling joystick at 60Hz is NOT good enough.

>If we are going to look at it like a general purpose I/O port (and yes, I've done that too.) why not compare it to USB 3.0? Let's just say that it's in a different league when it comes to high precision timing.

Are you like confused?  USB 3.0 has NOTHING to do with high precision timing.  USB 3.0 is a specification; it's not out there in any joysticks.  Show me a joystick that uses USB 2.0!  Once again comparing Amiga with nonexistent products or products that hardly anyone has.  Get real.

[amigaksi]

I have stayed out of this topic, but I agree with Karlos quite a bit on what he's been saying. There are a lot of modern pitfalls in both PCs and Mac that don't exist with Amigas, but honestly if I had to say it my PC today lets me do 1000 times more (and when you boot up actually doing 1000 more things in the background that you don't know about)  and working faster in realtime than I could ever do on Classic Amiga hardware and still quite a bit on newer A1 technology.
...

Nice story (with some speculations), but the point was is PC playing catch-up in some areas when compared to Amiga.  For example, what has been mentioned so far is in split-screens VGA standard only supports two split screens.  Amiga joystick ports are superior to PCs.  Amiga boots up faster.  And a few more things will be mentioned...

>The people who complain the loudest about the PC are usually fanboys of other platforms who are "religious" about their OS experience, and people who have gaps in knowledge about their OS and how to get help not to have issues..

Usually.  And in other cases its people who know more about both platforms.

>There are user groups and places they could go to learn.

Or teach.

[amigaksi]

@amigaski



As I said in the same post you have just failed to comprehend before replying to, if you don't use the OS and bang the hardware, then WTF is stopping you using the CPU for precision timing?

http://en.wikipedia.org/wiki/Time_Stamp_Counter

Turn off clockspeed altering power saving modes or use the constant TSC if present. Create an asm function for timing. Lock your code to one core (on multicore) and write a busy loop with a suitable instruction to prevent OOO execution and count the bloody ticks until you hit the magic number you've determined based on the reported frequency of your TSC.
...

You forget the other problems associated with RDTSC.  I am familiar with RDTSC as I mentioned it in the very post you are replying to (post #113).  You claimed it's accurate to a few machine cycles but that's complete rubbish.  In order to use in a generic way, you have to calibrate the RDTSC to the processor you are running on.  The calibration requires another timer; thus dropping your accuracy down to the accuracy of the 2ndary timer.  RDTSC is not always running at CPU frequency; some have tied to bus clock.  Power management affects it and there's no way to shut that down on some systems and on a Toshiba Tecra where I did shut down the power management the system became hot as the fan did not turn on and the system shut-down.  There are also SMIs implemented in some systems which cannot be disabled via applications and they cause frequency shifts and also halt tick counts during some C-states of the processor.  What constant TSC are you talking about?  So far on all the processors I have tried, RDTSC varies according to processor speed and the frequency of processor speed isn't some exact 90.00000Mhz.

>Quit your moaning about 850ns resolution hardware clocks. If you are a low level coder then the above tick timer should prove no problem. It should work on pretty much anything since the pentium.

Sorry, even if I use RDTSC and somehow avoid the above-mentioned problems, it's accuracy is the accuracy of the timer used to calibrate it-- 840ns for PIT.  So problem remains.

>Or, if all that is too much of a PITA, you could, assuming you have a reasonably recent PC, just use HPET[/QUOTE]

The fact that they introduced the HPET which runs at lower frequency than RDTSC should tell you that RDTSC proved to be not that reliable.  HPET is not present on my latest 2.8Ghz machine so not worth using it since that means it won't be present on majority of PCs.  There are other issues that affect it's accuracy as well.