ARM or x86 with FPGA emulator

[TeamBlackFox]

OlafS3,

Tekmote.NL sells some for €200-400, mostly due to import tariffs. If there was more demand I'm sure the cost would drop.

[biggun]

Yes, I'm anti-x86. I'm against a backwards architecture that is poorly engineered,.

Big words ...
I would not look down on x86 as this "poor" architecture is a  super performer.

x86  also has some big advantages over MIPS and SPARC.
* x86 has good address modes
* x86 can use immediates in instructions directly
  This is a big plus
* x86 can directly operate on memory.

Your x86 CPU can with 2 instructions often do about the same work as your MIPS does with 4.

[Kremlar]

The Lemote computers are readily available from resellers, they sell them on Amazon and other online retailers.

I've never heard of them.  There's ONE vendor on Amazon named "Revolutionary Books" with a 33% rating (3 reviews in the past 12 months) selling a Lemote netbook for $1500, and also for $2500?  This is the architecture you think they should port to??  I seriously doubt you'd ever get one if you ordered from that Amazon vendor.

BeOS failed to right it's ship even after porting to x86 because their sales were atrocious and Apple did not save them.  AmigaOS sales are atrocious now, so what's the difference?  Hyperion somehow seems to survive by selling a handful of licenses (if that) per month, which Be could not do.  

I'm not saying AmigaOS will survive long term by porting to x86, but it certainly won't survive on the path it's on now, and certainly would not survive if ported to ANOTHER obscure platform like you are suggesting.

I'm not a fan of the NG systems in general - I don't see the point, unless something unique can be brought to the table.  But, if you're going to do SOMETHING, don't spend incredible resources to just move sideways like you are suggesting.

Amiga was different because it was better.  There's nothing better about current NG systems, hardware or software - they are worse.  Porting to an obscure platform does not change that.  Porting to x86 could at least put them in the ballpark hardware wise, and resources could then be devoted to software instead.

Look what the move to x86 did for the Mac?  Saved the platform.  Of course the Amiga market doesn't have Apple-like resources, but with WinUAE a sandbox already exists to run classic apps on x86 - and that's half the battle.

AROS isn't successful because:
 - It's not "blessed" with the Amiga name
 - It tries to support generic x86 hardware and does not have "official" hardware behind it.
 - There are not enough resources devoted to it.

Personally, I think the biggest Amiga market is the classic market.  A Natami-like product would sell FAR more than a NG product.  It's far more interesting.

[TeamBlackFox]

Sure biggun, but it takes longer to have those instructions processed. The small amount of registers, combined with the amount of wasted silicon to useless backwards compatibility, and the overly complicated instruction set is just terrible. It makes a definitely orthogonal architecture like m68k seem RISC by comparison.

It takes about 40 cycles for the average x86/x64 CPU to access memory due to the size of the pipeline, a MIPS R16000 can do it in 11. In addition a benchmark compared a contemporary AMD Phenom to a R16000A, and it found they take about the same amount of time using a single thread to do a task. The AMD edges out as the number of threads increase till you hit the limit of CPUs a single computer can hold, then the R16000A takes the lead again with its ultra fast craylink clustering ability. Craylinked x86 computers are very uncommon whereas the R16000 is deployed with it almost exclusively. The reason why the R16000 can hold out so well has to do with its massive L2 cache in the 1GHz version it is 8MB, and it has a very streamlined instruction set.

Mikhail Kalashnikov, the late designer of the AK47 once said " All that is too complex is unnecessary and it is simple that is needed. " there is much to be said about this in the computing field.

[biggun]

It takes about 40 cycles for the average x86/x64 CPU to access memory due to the size of the pipeline, a MIPS R16000 can do it in 11.

??
Where did you get these numbers from?
These are not memory access times.

[TeamBlackFox]

I've never heard of them.  There's ONE vendor on Amazon named "Revolutionary Books" with a 33% rating (3 reviews in the past 12 months) selling a Lemote netbook for $1500, and also for $2500?  This is the architecture you think they should port to??  I seriously doubt you'd ever get one if you ordered from that Amazon vendor.

BeOS failed to right it's ship even after porting to x86 because their sales were atrocious and Apple did not save them.  AmigaOS sales are atrocious now, so what's the difference?  Hyperion somehow seems to survive by selling a handful of licenses (if that) per month, which Be could not do.  

I'm not saying AmigaOS will survive long term by porting to x86, but it certainly won't survive on the path it's on now, and certainly would not survive if ported to ANOTHER obscure platform like you are suggesting.

I'm not a fan of the NG systems in general - I don't see the point, unless something unique can be brought to the table.  But, if you're going to do SOMETHING, don't spend incredible resources to just move sideways like you are suggesting.

Amiga was different because it was better.  There's nothing better about current NG systems, hardware or software - they are worse.  Porting to an obscure platform does not change that.  Porting to x86 could at least put them in the ballpark hardware wise, and resources could then be devoted to software instead.

Look what the move to x86 did for the Mac?  Saved the platform.  Of course the Amiga market doesn't have Apple-like resources, but with WinUAE a sandbox already exists to run classic apps on x86 - and that's half the battle.

AROS isn't successful because:
 - It's not "blessed" with the Amiga name
 - It tries to support generic x86 hardware and does not have "official" hardware behind it.
 - There are not enough resources devoted to it.

Just an FYI, Amiga and BeOS objectively are two approaches to the same question " How simple can an OS be and still be useful? " neither is objectively better than the other. If you yourself aren't interested in NG Amiga hardware then you're doing nothing more than trolling this topic. Don't put out ideas that will potentially ruin what's left of the community if you have no intention of taking responsibility for your ideas, which your lack of interest clearly indicates.

Furthermore, you don't understand that putting a proprietary OS that lacks most features new users are familiar with on the same ballgame as Windows, OS X and GNU/Linux will result in them being trampled.

The reason the BSD communities are still around are that they mutually assist each other, are ported to several architectures which diversify the risk, and they aren't money driven.

Going after an idea with a gamble such as the entire OS and company at stake is an unacceptable risk, even if the supposed pay off is big. You wouldn't gamble your house in Las Vegas or Cancun Mexico if you had a wife and kids living there was the no second dwelling. As such, the Amiga community is spread too thin for diversifying to work. Instead there needs to be an affordable, high performance niche piece of kit which both NG solutions can agree to support.

There is just too much risk.

[biggun]

Sure biggun, but it takes longer to have those instructions processed.

No actually not.

Thats the point.

The same is true of 68k/Phoenix.

Phoenix for example can do this instruction in a single cycle:
ADD.L #$123456,($40,A0,D0*

How many instrutions does your typical RiSK need for this?
Exactly what the 68K does in a single Cycle the RISC needs generally  5-6 instructions to do the same.

[TeamBlackFox]

??
Where did you get these numbers from?
These are not memory access times.

Sorry, I phrased that poorly:

To read/write 64 bits of data from or to the main memory:

AMD Phenom: 33-40 cycles on average
MIPS R16000A: 11-15 cycles on average.

I apologise for the confusion.

[Kremlar]

If you yourself aren't interested in NG Amiga hardware then you're doing nothing more than trolling this topic. Don't put out ideas that will potentially ruin what's left of the community if you have no intention of taking responsibility for your ideas, which your lack of interest clearly indicates.

LOL, responsibility for my ideas?  If I wanted responsibility for my ideas I'd put my money where my mouth is and fund a project.

I'm not interested in current NG products, but of course if NG becomes more accessible and practical then I may be interested.

Furthermore, you don't understand that putting a proprietary OS that lacks most features new users are familiar with on the same ballgame as Windows, OS X and GNU/Linux will result in them being trampled.

They are being trampled now.  The only difference would be the cost of entry would be far lower and future development costs would be less - after, of course, the cost to port to x86.

Be tried to be another x86 operating system.  I'm not suggesting that - don't bring your OS to x86.  I'm saying pick an inexpensive x86 board and bring it to your OS - more like what Apple did than what Be did.

Going after an idea with a gamble such as the entire OS and company at stake is an unacceptable risk

OK, so why are you suggesting a port to an obscure, obsolete platform?

[TeamBlackFox]

No actually not.

Thats the point.

The same is true of 68k/Phoenix.

Phoenix for example can do this instruction in a single cycle:
ADD.L #$123456,($40,A0,D0*

How many instrutions does your typical RiSK need for this?
Exactly what the 68K does in a single Cycle the RISC needs generally  5-6 instructions to do the same.

So? The fact is that while you can feed those into the processor all at once, it takes multiple cycles to do those instructions. The other thing is with larger amounts of registers RISC CPUs can push more data at once. Sure you're correct these instructions have to be done one at a time, but RISC can do those instructions with minimal overhead.

Also let me remind you: memory is cheap now. We don't need a CPU that works direct from memory - working load/store is fine now especially with the norm of NUMA technology and decentralised DMA.

[biggun]

So? The fact is that while you can feed those into the processor all at once, it takes multiple cycles to do those instructions.

No.
PHOENIX can do this instrution example in 1 single cycle.
PHOENIX can do every cycle such an instruction.

Also let me remind you: memory is cheap now. We don't need a CPU that works direct from memory - working load/store is fine.

The problem is the instruction throughput.
Lets say you have a super scalar 68K.
Which does just 3 instrutions per cycle.

Do get the same amount of work done you need much much more RISC instructions decoded per cycle.
 And this is what kills you. You can not decode 10 instructions per cycle with your RISC chips.
Simply because your Icache is unable to feed so many bytes to you per cycle.
CISC instruction are a form of "compressed" instruction encoding.
This is a big advantage today - as today the cache bandwidth as a limiting factor.

[bloodline]

BeOS failed on the x86 for the same reason it failed on the PPC, because it had no software legacy... Apple have been able to migrate through two CPU architecture changes and an entire Operating system change, simply because the have a software legacy that people wanted to run and they made sure would run.

Microsoft only survived as a near monopoly for so long only because they had a software legacy, and they stayed compatible with it through their OS architecture changes.

[TeamBlackFox]

LOL, responsibility for my ideas?  If I wanted responsibility for my ideas I'd put my money where my mouth is and fund a project.

I'm not interested in current NG products, but of course if NG becomes more accessible and practical then I may be interested.

Then you just supported my point that you're here to troll and nothing more.

They are being trampled now.  The only difference would be the cost of entry would be far lower and future development costs would be less - after, of course, the cost to port to x86.

All that needs to be done is increase the cost/performance ratio of the hardware, I have lost faith in POWER considering the cost of an IBM POWER server, and the lack of top of the line designs from POWER6+ and up.

Be tried to be another x86 operating system.  I'm not suggesting that - don't bring your OS to x86.  I'm saying pick an inexpensive x86 board and bring it to your OS - more like what Apple did than what Be did.

Yeah, because everyone should be like Apple. Bunch of garbage they produce since Leopard. No, just no. That will fail just as hard.

OK, so why are you suggesting a port to an obscure, obsolete platform?

MIPS and SPARC aren't obsolete.

[matthey]

I prefer working with an architecture at a low level. The reason I give two %&$#?@!%&$#?@!%&$#?@!%&$#?@!s is because I actually would like to code some for Amiga down the line. Reason I don't now is simple: I am learning 68k assembler and that is one of the most tedious and pedantic languages I've learned because all the current compilers for C are too old and broken for OS 3.9 for me to use. I have been coding on a UNIX style C compiler such as Clang and that's how I intend to do this. GCC is a load of junk though so I may be forced to build my own compiler >_>. Anyways, back to my point: If the Amiga were to become x86 based I'd probably say screw it and not code for it because I have long given up optimising programs on x86 properly. Nothing about the tools I use exposes anything, rather, it is how I treat C as more flexible assembler. I like to be aware of the underlying hardware. With that said I'd probably stick to RISC boxes running BSD or some other UNIX if Amiga moved to x86.

There is a new version of vbcc in the works with much better C99 support. The complete source is available and I compile it with itself on my Amiga (although it can cross compile) along with Frank Wille's vasm and vlink. Only vclib is not publicly available because parts of it use copyrighted code with restrictions (but it's still available for programmers working on vclib). There are no dependencies or too complicated of build tool chains as the original target was embedded systems. It still has sophisticated optimizations (where fully implemented and not buggy) and a working instruction scheduler (for limited targets). It supports simple and easy inline assembler (including many system functions) although it's not as powerful as GCC and CLANG/LLVM assembler inlines (I would like to see support for this but it would be a lot of work). Vasm blows away GAS in ease of use and 68k peephole optimizations. The Amiga support is good and it's easy to install on the Amiga. Before you write your own compiler, maybe you could try it out and consider helping?

http://sun.hasenbraten.de/vbcc/
http://sun.hasenbraten.de/vasm/
http://sun.hasenbraten.de/vlink/

The binaries at the above vbcc link are old. You should e-mail Frank to get the latest sources (my sources may be old). Vbcc does need about 100MB of memory to compile so you would have to either upgrade your Amiga 3000 memory or cross compile. Vasm and vlink can probably be compiled with less than half the memory and the latest sources are available at the links above. You would probably want to install Frank's Posix.Lib for vbcc and my improved C99 68k math libs and support also:

http://aminet.net/dev/c/vbcc_PosixLib.lha http://aminet.net/dev/c/vbcc_PosixLib.lha
http://eab.abime.net/showthread.php?t=74692

The math libs are in 100% 68k assembler by the way. It's almost as easy as a high level language. I wouldn't try that in x86/x86_64 (not much love here from anyone) but your RISC processors wouldn't be much, if any easier. What we really need is a super compact enhanced 68k 32 bit CPU and a new properly designed Super-CISC 64 bit ISA big brother. CISC has real advantages but there hasn't been a new design in years despite the possibility to easily beat the x86_64 in encoding efficiency, code density and ease of programming.

As previously explained I could give a flying freak whether or not it would break binary compatibility. Sure other users care, but I care more about having a 64-bit OS with a CPU that can perform well today.

Don't feed anymore bull, you can look up the dhrystone measurements and other benchmarks yourself, but do keep in mind all of these systems are 64-bit and SMP capable so they're going to beat any slow uniprocessor 32-bit mode OS

64 bit processors can actually be slower in more than a few cases and they are more expensive in terms of resources and therefore cost. They generally do perform better because they are higher end with the expensive and extensive caches needed to make them fast. 64 bit is an advantage for servers and workstations but 90% of Amiga users would be more than happy with a 32 bit 68k Amiga with 300Mips and 1GB of memory.

Please show use where we could buy new Laptops or new Desktop with these for < $500. If you can do this - then your would have a reasonable point.

ARMv8 may be a better future RISC target than PPC, MIPS and SPARC because it's the most likely to have a CPU in portable computers sold to the masses. Performance shouldn't be any more of a limitation than these other RISC processors as the design is not that much different. The first devices may require jail breaking and Android will probably be the logical replacement unless AROS gets an ARMv8 target and is improved very quickly.

[TeamBlackFox]

BeOS failed on the x86 for the same reason it failed on the PPC, because it had no software legacy... Apple have been able to migrate through two CPU architecture changes and an entire Operating system change, simply because the have a software legacy that people wanted to run and they made sure would run.

Microsoft only survived as a near monopoly for so long only because they had a software legacy, and they stayed compatible with it through their OS architecture changes.

Yeah but both drop compatibility relatively quick. Stuff from the 2000/XP era won't always run due to ABI changes, and since its closed, recompiling against the new ABI isn't possible. Likewise with Apple Rosetta is dead. Apple is a status symbol, it is a symbol of eliteness and that's why stupid people buy it. People with brains like me use Android and cheaper alternatives that work just as well.

[Kremlar]

Then you just supported my point that you're here to troll and nothing more.

No, I'm here to discuss a topic on a public message board.

Yeah, because everyone should be like Apple. Bunch of garbage they produce since Leopard. No, just no. That will fail just as hard.

So... Apple produces garbage, and Lemote systems are fantastic?  Just trying to set a baseline here.

MIPS and SPARC aren't obsolete.

They are both obsolete and irrelevant on the desktop.