PC still playing Amiga catchup

[Karlos]

My A4000 6-7 years ago was a used as a server for 6 months straight without rebooting.

Running a basic OS3 or OS3.1 install on the base machine, possibly. Even then, you were lucky.

One minute?  We've been down that path with your souped-up, hardware hacked/overclocked, custom_OS running PC that you run 24/7.  You are in the infinitesimal minority of PC users.  Your experience doesn't count.

:roflmao:

Put your toys back in your pram and think about what you just wrote. My experience doesn't count simply because it is contrary to yours? A PC made entirely of off-the-shelf components, only one of which is overclocked (the graphics card) and running the most popular open source OS in the world counts as a hacked/overclocked custom OS PC? Do you have any idea how ridiculously petulant you sound?

I can name two other users right here on this very board that have PC's in the same hardware class as mine. 2GHz multicore is not a minority, it is pretty much the norm for current generation machines.

Further you've resorted to calling me and the millions of Windows users and MS itself, for whom boot times matter, "insane", and we are all "suffering from attention-deficit disorder". Name-calling is the last resort of those who simply can no longer defend their argument.

No, I've suggested that if having to wait 1 minute is too stressful for you then you probably have it. Not the millions of others for whom it is a minor inconvenience at best.

We've talked about your frankenstein A1200 before.  It doesn't count.

Bit hypocritical of you to slate my A1200 for having 2 CPU's and as much memory as I could throw into it. Why isn't it "souped up", like the PC instead? It's expanded with entirely legitimate expansions. There's nothing sat hanging upside down from one of the custom chips or dangling off the clockport. There aren't any low level hacks running in the OS.

By the sound of it, your definition of frankenstein is any amiga with a faster CPU fitted.

You have 4 CPU's running at 2,400 mhz. 4x2400 about 10,000.

One 14 mhz 020 boots faster than your 10,000 mhz of total CPU power machine.'  Nuff said.

Of course, if you knew the first thing about multicore computing you'd know that performance is not a simple linear scale up of clockspeed x cores. Also you'd know that only threaded applications or multiple concurrent instances of single threaded applications benefit.

[Karlos]

I have written software that can edit 600MB images using 16 MB of RAM.  It's nothing to do with the system.  It depends on the software.

This I'd be interested to see. Do you use a paging strategy for it, or do you limit it to the largest tile that can fit in 16MiB?

How do you give visual feedback on changes that affect the whole image, or do you allow modification only on a per tile basis?

I've written image processing code that operates on arbitrarily large images in a few kilobytes by basically streaming through it (for simple changes) or operating on tiny tiles (for image processing kernels). It worked but it certainly wasn't "visual". That didn't matter as it was for an automated process anyway.

This isn't a criticism, but I can't imagine such a system being a lot of use to people used to being able to operate at various levels of zoom as well as on the entire image at once. People buy big grunty PC boxes because they expect to be able to do stuff as quickly and readily as possible.

[Karlos]

Erm... can someone condense this whole thread into a nutshell please. It's been all around the universe and back and I'm  still confused. :crazy:

Is the PC still playing catchup? I mean really :lol:

I don't think so. Even if we accept the joyport example, external HID for PC's have all migrated pretty much to USB these days. Honestly, you can even get bloody USB graphics cards nowadays. Therefore the PC isn't actually in the race to have a high speed joyport, so it can't really be playing catch up. The same is true with other legacy expansion ports like good old centronic's parallel ports etc.Who uses a parallel port printer in a typical PC dominated office environment now? LAN printers have been standard for donkeys years.

I know I've contributed (as much as a flame fest can have contributions) to this thread but the reality is, we're all comparing oranges and apples here. 15-20 year old computers of any description, Amiga, Atari, PC, Mac, Sun are all in a completely different league to present day computers.

Hell, present day computers will be equally outclassed in raw processing power in a lot less than 15-20 years from now.

We all know the best computer platform from it's era was the Amiga, that's why we are here on this forum. However, like it or not, the platform is an extreme minority in the present day. There's no hardware to bridge the gap between then now. Cool as the A1, Sam and Pegasos are, they too are sliding further behind the relentless march in computer evolution. Unless AmigaOS and MorphOS take a leaf out of apple's book and jump the CPU architecture fence over to the x86/x64 side, they'll never really be able to take full advantage of that progress. However, as cool as that would be, it would also be quite sad IMO since variety is the spice of life. I actually like having systems with different CPU's and ways of working. It's fun. And since AROS at least is free to explore the x86/x64 avenue, well, you can have it all, really.

[Karlos]

Hi,

@Karlos,

Ok, enough, it takes you 30 seconds to reinit your computer from leaving it on, well guess what I left my Amiga on all night, all I did was turn off the LCD, turned back on my LCD and the Amiga was there ready and waiting, but darn I had to wait for my 24 inch LCD to turn on it took a total of 3 seconds, next time I won't turn if off hate waiting for this new stuff to work.

Now, lets talk about loading in a new fresh copy of your OS,

How long does it take windblows?

How long does it take Linux?

How long does it take Amiga OS 3.1?

How long does it take Amiga OS 3.1 with OS 3.9?

AMIGA WINS!!!

Windows SUCKS

Linux comes in 2nd

The PC is still trying to catch up to Amiga

smerf

My dear fellow, do try to keep up

http://www.amiga.org/forums/showpost.php?p=508702&postcount=168

I actually posted the boot times of my machines, completely from cold, earlier in the thread. Sadly, the A1200 lost the race between the two of them. Live with it.

However, I'll happily agree with you all that Vista isn't quick to start, despite whittling away all the unwanted gubbins.

PS:

OS4 on the G4 800 was fastest of all of them

[Karlos]

Hi,

@Karlos

NO, NO,NO

I don't mean boot times, I mean loading in a new copy of your OS on the computer, like starting with a new hard drive.

Amiga wins

smerf

That depends. You might have to replace your ROM chips before you begin. You know, small things like that

[Karlos]

My Abacus didn't even need to be booted.

Beat that! :laughing:

Sure it does, you have to push all the beads into their correct initial places before you use it, right?

[Karlos]

Talk about moving the goal post. :rolleyes:

Code: [Select]

while (argumentFails()) {
  mutateArgument();
}

[Karlos]

Sounds like what you did with the joystick argument.

Hardly. My argument was consistent all the way through. Modern computers have far exceeded 20 year old ones in performance and capability. You and a couple of other bitter diehards were the ones suggesting you need to use sampling rates of obsolete ports and boot times as significant metrics.

Frankly, I find your entire attempt to justify the premiership of long obsoleted hardware above hardware that what was once inferior but has since evolved beyond recognition hilarious.

Current machines have thousands of times the processing power, hundreds of times the memory and disk space available. You will find for the vast majority of all computer users, professional or otherwise, 20 year old hardware is of no practical use for their day to day needs nor live up to their expectations in terms of basic capability.

20 years is a long time. Simply playing an mp3 track or opening a large jpeg image from a digital camera will bring a classic amiga to its knees, unless a hardware or PPC decoder is used. A 68060 will manage either task more respectibly, but it uses a significant portion of the available CPU time to do so. Meanwhile, the rest of the world have grown used to the expectation that their mobile phone can do these things, let alone their computer.

I'm really sorry that you find yourself so opposed the notion that PC hardware has evolved far beyond the venerable miggy that you find things like emulation in UAE a total anathema. You are missing out on enjoying the using an amiga that has the raw horsepower of a modern machine for the sake of being true to hardware that even Jay Minor and Dave Haynie both expressed doubts about afterwards (As early as 1989, Jay mentioned in hindsight that he'd have opted for chunky rather than planar pixel formats and Dave wanted to use PCI instead of evolving the Zorro standard any further).

Still at the end of the day, your choice, your loss.

[Karlos]

It's a separate point regarding the buttons.  I never stated that sub ms is of prime importance but is required in some cases and that it's UNDOABLE on Gameport.  Even if you sample at 60Hz, Amiga wins but it is doable on PC gameports.  MOVE.W $DFF00A,D0 is faster than an entire algorithm using IN from 201h or serial protocol.

Under which specific cases is it required?

[Karlos]

When the Amiga catches up to multi-touch PCs and THIS on the XBOX-360, then I'll know it has a future..

Introducing Project Natal:

http://www.youtube.com/watch?v=g_txF7iETX0&feature=player_embedded
http://www.youtube.com/watch?v=SxU_T7C4Ils&feature=player_embedded

This is no joke, I saw this functional over a year ago..

I bet the execs at Nintendo aren't too happy with this, eh?

[Karlos]

If you want to be a purist, it can make a difference at any time.  If you sample at 60Hz, you could just miss that case of state change which could make a difference in the game.  As I stated, the recording I did was from a River-Raid game.

That hasn't quite answered the question. Does River Raid sample at 1kHz?

[Karlos]

Hi,

@everyone,

How many PC techs, or IT techs work for microsoft?
How many PC techs, or IT techs work for Linux?
How many PC techs, or IT techs work for Amiga?

Amiga has the least techs working for them, this means they have the most stable system that just works.

Amiga wins

smerf

Sinclair Reasearch Limited doesn't have any at all. Spectrum wins!

[Karlos]

Well said. Especially the boot times: it IS a joke on the PC, any PC.

My 800MHz G4 A1XE takes around half the time of my A1200T to boot. It has 32x the CPU speed, 5x the bus speed, 10x the sustainable hard disk transfer rate, yada etc.

It's running AmigaOS so on that hardware, surely it should boot in a flat second. Dear me, whatever could be wrong with it?

Boot times are not a metric for computer performance. Boot times are dominated by waiting, be it waiting for initialisation of hardware, software, synchronisation between processes or a myriad of other things. The more processes that are started, the more conflated this becomes.

All computers wait at exactly the same speed. Even a factor of a million CPU clockspeed difference cannot make a half second device initialisation go any faster. a 4GHz CPU cannot negotiate an IP address with your router any quicker than the router wants to talk to it.

The only valid indication of performance of a system is once it has booted up, not how long it takes to get there. My A1200* has a longish from cold boot time for an Amiga classic, but once up, it's pretty quick and capable, much moreso than a 7 second boot-from-cold bare OS3.1 install.

*FYI an accelerator card and graphics card as the sole internal expansion cards in a system do not make it a Frankenstein machine.

[Karlos]

Duly noted.  Even though you have transplanted an additional foreign brain from a totally different species and likewise a foreign display system, all communicating with the original carcass over transplanted foreign busses.

They share the same bus into memory. Logic on the board handles any differences between m68K and PPC's local buses.

Having both a PPC and 68k, would describing at as having a multiple-personality disorder be more appropriate? That might explain why it slows down every now and then: the two CPU's are fighting over who will be the dominant personality.

This is what caches are for. When you read from memory and you get a cache hit, no actual bus activity need occur. When you write to memory and you have copyback enabled, no actual bus activity need occur at that instant either. It'll get done some time later when the CPU decides it's the right time. When that happens, each CPU will spend most of it's time performing whole cache line transfers.

The worst performance hit in these systems are forced cache flushes on context switches. That is painfully slow. However, when you are performing a complex operation, such as decoding a datatype, one or  two of those is totally hidden in the speedup you get from doing the work on a 3-digit clockspeed CPU compared to a 2-digit one.

Now, talking about actual bus contention, you have to look no further than a 68K machine without fast ram.

The original 68000 can only access memory once in every two cycles. The custom chips get it every other cycle ideally. However, bump up the screen size, number of sprites etc and before long the DMA starts to eat into the bandwidth available for the CPU. And the custom chips will always win, slowing the CPU down. In fact, the CPU is forbidden alltogether from performing certain atomic operations on Chip RAM by the architecture.

On a 68020+, the situation is significantly worse since these CPU's can access memory every cycle. This is why a bare A1200 dies on it's arse compared to one with (pref zero wait state) fast ram fitted.

[Karlos]

I thought the PPC has no caches.

Nope, the 603e, for example has 16KiB instruction and 16KiB data. IIRC, the 604e doubles this.

What you are probably thinking of is L2 cache. There isn't any of that on the Blizzard/Cyberstorm. Then again, as far as I know, no amiga accelerator has L2 cache.

[Karlos]

Originally Posted by stefcep2  View Post
BTW does anyone know WHY Windows and linux need a swapfile even if they use so little available RAM? I know you can force the swap file size to zero in Windows, but I suspect it still uses a swap file. And AFAIK Linux won't install without a swap file partition.

First of all, they don't use a little amount of ram. They use as much of it as possible at any given instant since the paradigm they follow is that unused RAM is needlessly wasteful. Instead it's used for caches, buffers and so on:

The memory utilisation of my machine at work here a moment ago was as follows:

Code: [Select]

Mem:   1032208k total,   956012k used,    76196k free,   103616k buffers
Swap:  4610612k total,    31520k used,  4579092k free,   299596k cached


As you can see, most of the physical memory is in use. What you will also note is that most of the swap is not in use. It is possible to run without a swap file, but why would you want to? It's only used when you are trying to do more than can be reasonably accomplished within the confines of your physical memory. Think of it as a safety net. Better to run a  bit slower when paging kicks in than simply stop running and fail in some fashion.

Furthermore, modern memory allocation strategies don't actually have to allocate the memory all at once. Physical allocation need only occur when a page within that allocation space is accessed for the first time. It's not uncommon for large allocations at compile time to turn out to be oversized at runtime. This way, only the amount of memory actually required at runtime (as opposed to what the program thinks it required) gets allocated.

-edit-

My machine at home isn't using any swap:

Code: [Select]

Mem:   4053804k total,  3404668k used,   649136k free,   900776k buffers
Swap: 20000884k total,        0k used, 20000884k free,  1871376k cached