Gold 2.7 release for the Vampire accelerators

[psxphill]

Aha. So if I built my 6502 as a silicon chip without looking at the 6502 die and by accident came up with the identical netlist as what you consider a 6502, what would it be? Emulation or the real thing? Seems to be some philosophical straw you are clutching at.

You're the one that is trying to break my argument by using stupid philosophical arguments. It's impossible that you will happen to create an identical mask without referencing the original.

Which "6502" is the real one that you need to decap to make your own one?

It depends which behaviour you want, it's often important to get the correct one for your application.

By your definition everything but the 1975 die ones are just pretending to be a 6502 AKA emulating one I suppose? :rofl:

No, that is by your definition. I don't consider someone speaking to be doing an impression of themselves, even though over time you have cells die and new ones grow & are no longer the exact same person with the exact same abilities.

Going back on topic. VHDL is a language, like any other programming language. It allows you to control the gates in an FPGA, like you can control the gates in a CPU. You can implement a 6502 in C running on an x86 or implement a 6520 in verilog running on an fpga. Both are emulating certain behaviours of a 6502.

BTW, nobody claims the 68080 was a Motorola 68000, 68010, 68020, 68030, 68040 or 68060, remember?

https://en.wikipedia.org/wiki/Ship_of_Theseus == strawman, got it?

[grond]

You're the one that is trying to break my argument by using stupid philosophical arguments, I didn't come here to discuss

 Yes, you came here to make statements:  

I know what an FPGA is & I know what emulation is.

Apollo is not a software emulator written for a general purpose computer, but that isn't all that "Emulation" is.

You can emulate a cpu with 74ls chips if you really wanted. http://www.baltissen.org/newhtm/ttl6502.htm

And you clearly want to remain ignorant about the subject you are commenting on. But I guess this is as close to admitting you were wrong and have no arguments left as your personality will ever allow you to get.

[psxphill]

And you clearly want to remain ignorant about the subject you are commenting on. But I guess this is as close to admitting you were wrong and have no arguments left as your personality will ever allow you to get.

The only thing I admit to is letting you troll me with your straw men.

My point is clear, your religious hatred of the word emulation is making you unable to see it. So much so that you apply magical qualities to the word implement.

But I guess you have your reasons. I'll let you get on with pretending that emulating a CPU in an FPGA isn't emulation, if it makes you happy.

If you ever are interested in a reasoned debate then I will consider it, but I very much doubt that your personality will ever let that happen.

[grond]

Going back on topic. VHDL is a language, like any other programming language. It allows you to control the gates in an FPGA, like you can control the gates in a CPU. You can implement a 6502 in C running on an x86 or implement a 6520 in verilog running on an fpga. Both are emulating certain behaviours of a 6502.

BTW, this clearly demonstrates that you don't know what you are talking about. VHDL is not a "language like any other programming language". It is a _hardware description_ language, not a _programming language_. It's like saying that you could write a true equivalence of Shakespeares body of work in Inuit because it is just another language like English is. Unfortunately you'll end up with lots of words to describe snow but none to describe a half of what Shakespeare described. And the differences between a hardware description language and a programming language are far bigger than that. One to start with is that there is no concept of parallelism in any of the programming languages I'm familiar with and certainly not in C. That is also why you need a high MHz CPU interpreting foreign CPU code of a 6502 or 68k while you only need an FPGA running at 80 MHz to exceed 68060 speed as demonstrated by the Apollo Core.

[grond]

But I guess you have your reasons.

My reason is that I have a PhD degree in microelectronics and as a scientist in this field like using correct terminology. And I don't like being taught about my art by somebody who doesn't know sh1t about it. If you want to discuss with the big boys, you'll have to make sure you are understood or shut up.

[Chucky]

As I told. word-picking.   even if VHDL is not a real "programminglanguage"  for the user it behaves somewhat similiar.     and that the 080 is bases on a reverseengineering. while when motorola did the 000,010 etc.  they for sure did not start from scratch everytime.   actually a potential bug could be moved from 68000 -> 68060  as it is a lot of "copy and paste"    so  all this emulation vs nonemulation is just picky with words.  the end result when it comes to how the final product behaves is pretty much the same.   emulator or fpga.  as both still is based on a reverseengineering perspective than what motorola could do as they actually have the real data. and I guess if motorla did a open version of a FPGA 68k (any), not much would be the same as TG68 OR the 080.

And that is my very point of this, you can call it emulation, simulation, implementation
 but it would still not be a exact copy of the real thing and in the end. it all narrows down to what you would get with a emulated product, close enough but not the real deal.  simple.     anyway. I agree.  this is off topic.  so.  stepping out of this thread.

[psxphill]

BTW, this clearly demonstrates that you don't know what you are talking about. VHDL is not a "language like any other programming language". It is a _hardware description_ language, not a _programming language_.

I don't get how you can argue that a Language used for Programming is not a programming language.

Field Programmable Logic Array. VHSIC Hardware Description Language

VHDL borrows heavily from the Ada programming language in both concepts and syntax.

It's like saying that you could write a true equivalence of Shakespeares body of work in Inuit because it is just another language like English is.

No, that would be a straw man. A common occurrence in your attempts to derail any discussion.

This particular one seems to be aimed at https://en.wikipedia.org/wiki/Turing_completeness

One to start with is that there is no concept of parallelism in any of the programming languages I'm familiar with

That is your ignorance showing. Not all programming languages are procedural.

With OpenCL you can:
 Leverage CPUs and GPUs to accelerate parallel computation
 Get dramatic speedups for computationally intensive applications

https://developer.amd.com/wordpress/media/2012/10/OpenCL_Parallel_Computing_for_CPUs_and_GPUs_201003.pdf

Over time it's likely we'll see more software switch to GPGPU https://en.wikipedia.org/wiki/General-purpose_computing_on_graphics_processing_units
To the point that WinUAE will have some of the same advantages as an FPGA emulation of a 68k amiga (eg generate the video on the graphics card to remove a layer of latency in the OS).

That is also why you need a high MHz CPU interpreting foreign CPU code of a 6502 or 68k while you only need an FPGA running at 80 MHz to exceed 68060 speed as demonstrated by the Apollo Core.

Sure. I understand that, but it doesn't solve any issue of whether that is emulation or not. We know that dedicating logic gates to a particular task has a greater efficiency than time sharing them. It's an implementation detail.

[guest11527]

And that is my very point of this, you can call it emulation, simulation, implementation but it would still not be a exact copy of the real thing and in the end. it all narrows down to what you would get with a emulated product, close enough but not the real deal.  simple.     anyway. I agree.  this is off topic.  so.  stepping out of this thread.

The 68060 is neither an exact copy of the 68000. Actually, it works entirely different. The latter is microcoded, the former is not. So, one could even say that the 68000 is a "bad software emulation" of a 68060 - to a certain degree, the 68000 does everyhing "step by step" in a microcoded CPU by some sort of software for which the 68060 has silicon gates. So which one is the real thing and which one is not?

In the end, it does not make a freaking difference. The chip is "real enough" for many users. Probably not for my use case, but that's a different story and not related how you call it what it does.

[psxphill]

The latter is microcoded, the former is not.

Whether it's microcoded or not is an implementation detail. Whether a 68060 was emulating a 68000 is up to Motorola to decide, like Ship of Theseus.

A 65816 can emulate a 6502. A NEC V30 can emulate an 8080.

The chip is "real enough" for many users. Probably not for my use case, but that's a different story and not related how you call it what it does.

As Winuae is real enough for many users, both have pros and cons in their implementation. Saying it's not emulation is an attempt to create a religious following that overlooks the downsides, because "it's always better because it's not emulation".

[guest11527]

Whether it's microcoded or not is an implementation detail. Whether a 68060 was emulating a 68000 is up to Motorola to decide, like Ship of Theseus.

Whether it is implemented on an FPGA and written in VHDL is an implementation detail as well.

As Winuae is real enough for many users, both have pros and cons in their implementation.

For me, it's not. WinUAE delivers inconsistent performance, and I require a windows system. Certainly, it's an achievement as far as software is concerned. But pay Microsoft for Amiga Software? I don't think so.

[kolla]

But pay Microsoft for Amiga Software? I don't think so.

WinUAE does not require Windows, just saying.

[OlafS3]

Whether it's microcoded or not is an implementation detail. Whether a 68060 was emulating a 68000 is up to Motorola to decide, like Ship of Theseus.

A 65816 can emulate a 6502. A NEC V30 can emulate an 8080.



As Winuae is real enough for many users, both have pros and cons in their implementation. Saying it's not emulation is an attempt to create a religious following that overlooks the downsides, because "it's always better because it's not emulation".

it is a rather weird discussion and not really related to Gold 2.7 Core. There are thousands of customers who are very happy with Vampire and do not give a %&$#?@!%&$#?@!%&$#?@!%&$#?@! if it is Asic or in this case implemented in a FPGA. It is nearest to real hardware but it can evolve (in opposite to a silicon chip). Also pressing silicon would cost a fortune and is only a option if the product is really finished (feature wise) and tested. Most users are happy with what they get, even with the direction, a couple of not but those could sell it without loosing money. Then there are people critisizing the direction while not owning it and with propably no intention to ever buy it what is a little strange. For some hardcore users it is not real enough so they prefer the old hardware. Others are happy with emulation and do not need hardware to be happy. Everybody can decide what he prefers. This whole "FPGA is emulation" discussion is really weird, if FPGA based solutions are not your interest then simply do not buy it.

[psxphill]

This whole "FPGA is emulation" discussion is really weird, if FPGA based solutions are not your interest then simply do not buy it.

You missed the point. Saying that the FPGA is being used to emulate various parts of an Amiga system, is not a criticism of the product. Only a criticism of the way in which people speak about it.

By their own admission the v2 is too limited for the full Apollo core, so unless Gunnar has an epiphany that allows him to shrink it then I'm at least waiting for a v4. Also the lack of source means that I'll wait until the features I want are done, in case he gets knocked over by a bus.

For me, it's not. WinUAE delivers inconsistent performance, and I require a windows system. Certainly, it's an achievement as far as software is concerned. But pay Microsoft for Amiga Software? I don't think so.

I used WinUAE as an example because it's most convenient for most people. I don't see requiring windows as a huge problem, if you do then there are other options. I'd still like to see a native 68k JIT for x64 hardware that allows you to run 68k AmigaOS as close to the metal as possible & with as little hardware emulation as possible. Then stage two would be to throw PowerPC into the mix. I've got too many porting projects keeping me busy at the moment to do it myself.

[Louis Dias]

Apparenntly...  The "Win" in "WinUAE" doesn't stand for "Windows"...  Now I've heard everything...

[kolla]

Apparenntly...  The "Win" in "WinUAE" doesn't stand for "Windows"...  Now I've heard everything...

Sure does, but Windows is not a requirement, for example it works also with WINE (and iirc also ReactOS).

[guibrush]

So, is WINE a Windows emulator or a Windows emulation ?