Amiga.org
Amiga computer related discussion => General chat about Amiga topics => Topic started by: orb85750 on October 13, 2010, 12:49:31 AM
-
Tough question?
-
x86 is the commonest platform so it should be on it. Go full 64-bit SMP/SMT while your at it.
I would also like to see it on ARM because it is perfect for light lean OS and unlike other ARM OS you would be free to tinker with it.
PowerPC died when Apple dumped it, if people didn't see it was time to move then... they must interpret the world funny.
68k on FPGA will be satisfactory, but it is not for a serious alternative main OS.
If nothing happens I hope Haiku or AROS will be fully functional alternative OSes.
-
As long as hardware is available, why not? The CPU is just a tool, like any other. ARM might be more cost-effective long-term, but if by "Amiga" you mean "AmigaOS 4.x," then we have to live with what Hyperion supports.
-
PPC isn't a "future". It's a dead-end.
-
Yes, as long as it is something that it is not pittyfull, like current SAM and X-1000 processors. I mean something really powerfull that actually has a future, like some kind of licensed IBM POWER7 chip.
If not, hell no!!!
PS: Just as an example, the IBM POWER7 795 server features 128 cores and a whooping 4.25 GHZ clock frequency! And it is a PowerPC system ;)
But reallistically speaking, you should get over it, and acknowledge the Amiga as we knew it, is long dead. Today, we are just the witnesses, some indeed victims, of marketing BS.
-
Even though only a few people have voted, I'm not surprised to see the preference for x86.
I selected 'Other' because the CPU should be one of the things that is decided last. First I would devlop a product strategy, then as part of the product development I would define my market, design the product in terms of features to cater to that market, assess the budget and estimate the product per unit maximum cost and target profit margin, then I'd look at the component requirements for the production of the product and I would choose the CPU that best delivers the target market features at the appropriate per unit cost. There's a whole bunch of CPUs that fit that criteria, but given the unit cost of PPC MC/IC parts, I doubt they would be at the top of the list.
Unfortunate for Hyperion, PPC was part of a strategy laid down over ten years ago and they've already expended many resources moving AmigaOS to the PPC and they are keen to get some return on their investment. The path of least resistance is to bundle AmigaOS 4 with relatively expensive PPC systems.
As a technology strategist, I would not recommend they ever port AmigaOS to x86 or any other architecture. It would be easier an more beneficial to start from scratch.
-
No,
If we had gone to intel in the first place we wouldn't be in the mess we are in now. The only way the platform can survive now is as a hobby, and most of us can't afford new PPC hardware. In a few years the PPC Macs will all be antiques so that's not an option for the future.
-
For me, Amiga on Intel is WinAUE.
Amiga (hardware + OS) is 68K.
I don't disagree with other people doing other fun/interesting stuff tho..
desiv
-
We have the problem of endianess http://en.wikipedia.org/wiki/Endianness it is unlikely that amigaos will ever be ported to x86 and boot natively.That thing wont be an amiga.PPC can change the endianess http://en.wikipedia.org/wiki/PowerPC#Endian_modes but i dont think it would be easy to port it to x86.So x86 is definitely out of the question for me.
Also from the same page Endianness and operating systems on architectures
Little-endian operating systems:
* Linux on x86, x64, Alpha and Itanium
* Mac OS X on x86, x64
* OpenVMS on VAX, Alpha and Itanium
* Solaris on x86, x64, PowerPC
* Tru64 UNIX on Alpha
* Windows on x86, x64 and Itanium
Big-endian operating systems:
* AIX on POWER
* AmigaOS on PowerPC and 680x0
* HP-UX on Itanium and PA-RISC
* Linux on MIPS, SPARC, PA-RISC, POWER, PowerPC, 680x0, ESA/390, and z/Architecture
* Mac OS on PowerPC and 680x0
* Mac OS X on PowerPC
* MVS and DOS/VSE on ESA/390, and z/VSE and z/OS on z/Architecture
* Solaris on SPARC
Amiga in both 680x0 and PowerPC is big endian while any x64 and x86 above is Little-endian
-
I'm having a difficult time answering my own poll, but I'm wondering -- where are all the MOS and OS4 champions? Don't they support PPC for Amiga?
-
For me i think AmigaOS should be ported to x86/x64
PPC is slow, outdated and very expensive.
-
For me i think AmigaOS should be ported to x86/x64
PPC is slow, outdated and very expensive.
From http://obligement.free.fr/articles_traduction/itwbarthel_en.php
"The high price of the AmigaOne X1000 seems to be an argument, for lots of amigans, to not buy the machine. A solution to sell lot more copies of AmigaOS could be an x86 version. What is your opinion about that?
In this small market price is always an issue. The kind of power the X1000 provides, for such a small customer base, naturally results in a high price. As things stand today, you cannot make this kind of gear in sufficiently large enough volume to bring down the cost and consequently the price.
I consider the x86 path a pipe dream. AmigaOS has no platform/porting layer: it is hardwired to a big-endian host platform, not just the fundamentals but also its data structures. I would say that the chances to see AmigaOS run on an ARM are much higher than to see it run on an x86 family processor. If you wanted to make it work on an x86 host, you would have to throw out all existing Amiga software designed to run on the 68k platform, much of which is still useful today (I would go so far as saying that it is not just useful, it is necessary). You would have to throw away much of the operating system and replace it.
Even if you were to make all of that happen as part of an x86 port, you would have to make significant sacrifices. I doubt that any of these would result in a viable product."
-
I dont think it matters. Simple fact is that Amiga OS (capital A) is ppc. With hindsight it makes things difficult to even come close to competeing in terms of price and/or performance, but that wouldve been hard to predict 8 years ago when OS4.x was being instigated, let alone 15 or so years ago when the original ppc card became available. An x86 version is the only way to gain mass acceptance (I mean really, who other than the most dedicated enthusiasts are willing to pay 1500+ euro for a machine whos equivalent you can get for about 200 euro?), but even then it'd be an uphill battle (in the face of the competition that's out there). Amithlon style big endian byte ordering on x86 might've been the best way to go initially (so as to maintain the same style 68k emulation), leading the way to a "normal" x86 version by the time things reach 4.3 (or therabouts (ie. once there's software available)..... even with the performance hit suffered through big endian x86 you'd still be getting hugely improved bang-per-buck (and faster systems) than what is available now/in the forseeable future. This is all in regards to the branded "Amiga" of course. An alternative response could be that Im pretty content with AROS on x86 anyway ("amiga" vs "Amiga").
-
I vote for the 680x0. Since the heart of the Amiga is its unique graphics chipset, that limits the future to FPGA and similar technologies. As long as FPGAs are affordable, we should stick with 680x0 softcores to make them a compact SoC. Viva MiniMig, NatAmi, and CloneAA!
-
Voted yes since it's what we currently have, it's quite clear that the x86 route will never happen (let aros aside)... probably the "better than nothing" approach...
Cheers,
D.
-
A real Amiga is 680x0 only, plain & simple everything else is just a fraud... :)
-
where are all the MOS and OS4 champions? Don't they support PPC for Amiga?
Or maybe they just don't care about another useless poll. There is an Amiga route for x86 fans for 15 years. It is called AROS. It has all the advantages lack of which is pictured as drawbacks of MorphOS and AmigaOS 4. It runs on cheap and broadly available x86 hardware, it is free, it is opensourced. It should dominate the Amiga future, shouldn't it? Guess why it has not happened for 15 years.
-
and most of us can't afford new PPC hardware.
BS.
Most of us CAN afford new hardware - but there's a difference between value and reality. Choosing to overpay for re-used, abused and re-manufactured (if you're lucky) technology does NOT represent sensible computing value. Show us something of value, worthwhile, long lasting, currently supported and we will spring for it. En masse.
-
ARM A9 and A15.
-
This is all pretty theoretical, but I always figured ARM would be a good option for amiga OS
-
I don't care too much about the cpu. PPC has some practical advantages and the port is just there, s why not? When supply of maschines dreis out and someone does a port to a different API I would use that of course, too.
But currently I am quite satisfied with the ppc route in teh incarnation of MorphOS on my Mac mini. Couldn't be much better.
-
Amithlon was as close as we ever had to an x86 Amiga and that was killed by stupidity.
If it had support and a few revisions, it could have gotten somewhere.
So did Phase5 push us into PPC all by themselves? Why are we still there?
-
Explain future
-
Explain future
in amiga terms ? 2001 :)
-
It's all rather irrelevant IMHO.
Approval or not, your choices are dictated by those developing it. OS4 and MOS are written for PPC hardware. I don't expect either of them to jump ship to x86, or even ARM any time soon. If you are disappointed with this, then you can take the AROS route.
There are pros and cons to each platform, but the point is, if you think PPC was a bad idea, you aren't actually stuck with it.
-
Other. I know I'm dreaming but I love to see some kind of multi GPU based system running OS4.1. Something like the Nvidia Tesla of a couple of years ago. I use an intel but I know the basis of these machines hobbles their capabilities. Something wild and wicked to spark the imagination....BTW its 50:50 for and against Intel...
-
Other. I know I'm dreaming but I love to see some kind of multi GPU based system running OS4.1. Something like the Nvidia Tesla of a couple of years ago.
Trust me, you wouldn't want this. GPUs are not a simple replacement for CPUs. They have very specific programming requirements. Beyond the obvious, they aren't multithread friendly in the way a multicore CPU with SMP is in which several totally unrelated threads of execution can be running away concurrently. nVidia GPUs run very large numbers of threads through the same code using in-step execution. A multiprocessor will execute a warp of such threads completely in parallel. The moment you hit a conditional branch and some threads take conflicting paths, execution is serialized until the code paths merge again (the hardware scheduler is nice though; whenever any of the threads hit a slow memory access, it will switch it out for another warp of threads that are executable).
Furthermore, prior to the fermi architecture, the GPU could only be executing a single kernel (a block of code to be ran over a dataset, not OS core sense) at a time. This is at least one major improvement of the latest generation, but again, even with several kernels running concurrently, each one needs to be some massively parallel task to get any benefit from GPU execution.
-
Reading through a few comments on here. As far as I understood it PPC has a smaller instruction set than x86 and like for like will run much faster than an x86.
I don't know what the current maximum Ghz maximum is for both PPC and x86 technology, but I do know that a 1.8 Ghz processor (as per Amiga X1000) whether its little-endian or big-endian is more than suitable for the vast majority of computer uses as is required in 2010 for the vast majority of users on this planet.
Although CPU technology does get quickly all the time it is far from being a priority as much as it is has in the past and therefore there is less and less reason to upgrade as time goes on.
-
Reading through a few comments on here. As far as I understood it PPC has a smaller instruction set than x86 and like for like will run much faster than an x86.
You realise a smaller instruction set means more instructions are required to implement any given bit of code, right? Like for like, once you hit the baseline minimum of one instruction per clock, the CPU with less code to execute will win.
Also, the PPC isn't really that RISC as far as the number of supported operations goes, it has plenty of instruction/variants. It's classification as RISC is rather more architectural (consistent instruction word encoding, load store design etc).
Anyway, I'm afraid that the observation of PPC versus x86 is far out of date. Certainly not since the AMD64 architecture at any road and all new "x86" destktop processors tend to be AMD64.
-
I vote for the 680x0. Since the heart of the Amiga is its unique graphics chipset, that limits the future to FPGA and similar technologies. As long as FPGAs are affordable, we should stick with 680x0 softcores to make them a compact SoC. Viva MiniMig, NatAmi, and CloneAA!
Actually it was the the whole FPGA thing that made me pick "other"... Hmm!
BS.
Most of us CAN afford new hardware.
Whilst I get what you're trying to say, I think you're ignoring what he said - which was that they couldn't afford PPC hardware.
And given the cost even of a new Sam, much less the projected price of the X1000, is perfectly valid, even to the point of your own comment being true at the same time.
-
x86, eventhough its long past CPU choice being an improtant issue with the Amiga's "future".
Even if OS4 or 5 (or whatever) arrived tommorrow for x86 archetecture the Amiga's future would be much the same; still struggling for relevance in the 2010 computing world. Harsh but true unfortunately, the magic died the day Commodore went belly up.
-
Tough question?
Not a tough question at all. PPC in a shape and form that would be interesting to us is dead. X86 would be the best way to go, if desktop is the future of Amiga. But it's also the most difficult, as I have been told (something to do with endians ;)).
Easier would perhaps be ARM, and lots of things are happening in the ARM world now. The Cortex A8 is being established, the Cortex A9 is growing, and...
"The launch of the Cortex-A15 MPCore processor marks the beginning of an entirely new era for the ARM Partnership."
Well, that's no understatement!
Its simplest/lowest performance version (for next-generation smartphones) offers "5x performance improvement over today’s advanced smartphone processors, within a comparable energy footprint", and it scales up to quad-core configurations and speeds of up to 2.5Ghz, clearly breaking the boundaries of traditional applications where ARM has been used, and well into x86 territory.
Some companies are already using ARM in server configurations, something that probably will increase with Cortex-A15. Virtualisation is built right into the server variants of these chips, and they can support up to one terabyte of memory.
http://www.arm.com/about/newsroom/arm-unveils-cortex-a15-mpcore-processor-to-dramatically-accelerate-capabilities.php
The road map suggests that 2012 will be when it gets released.
(http://www.arm.com/images/Roadmap_for_Eagle_web_300dpi.jpg)
I'd like to see MorphOS ported to ARM!
:)
-
Just remember that the boat is sailing. If it's going to be ported to ARM start soon. How about on one of those Android tablets?
-
Architecturally can the PPC ever reach the performance of the x86!?
-
Architecturally can the PPC ever reach the performance of the x86!?
All that and cheaper too. Only problem is you would only expect a thousand sales compare to 200million for an Xbox360.
-
If this is reference to AmigaOS from Hyperion, it should remain PPC. I see no financial reason for Hyperion to under take such a man power intensive project to port a OS that can never generate a profit. I don't think they have the number of Devs to do a port if they wanted to.
I don't see a reason for MOS to go x86 either for basically the same reasons.
If you want x86/PPC Amiga-like OS, it's called AROS which is being ported to Genesi's EFIKA-MX. You want to support it financially, go pick a bounty of your fancy and spend some meaningful money or buy a iMica or AresOne.
If someone developes a true next generation AmigaOS that isn't hobbled by 3.1 API, I may be interested in supporting that myself if there is some intelligent road map for it.
-
Architecturally can the PPC ever reach the performance of the x86!?
The problem is not in getting PPC to match x86 on a given day, IBM have proven repeatedly that they are more than capable of doing so.
The problem is in maintaining parity between x86 and PPC once they meet.
Telecoms don't tend to need ultra fast PPC's as they use SOCs with the grunt work being passed onto specialised bits of silicon rather than a general purpose cpu so as to save power and reduce heat output.
Even the chips in the current games consoles really aren't all that, not that they were that competitive to begin with in raw performance terms.
-
Architecturally can the PPC ever reach the performance of the x86!?
As far as desktop CPUs? Unless IBM is going to release new PPC cores, not happening. Only thing Freescale is doing is repackaging the old cores. IBM's cells are for consoles and not suited for desktops. That leaves you basically with x86_64 or ARM as CPU choices that are in constant development.
-
We have the problem of endianess http://en.wikipedia.org/wiki/Endianness it is unlikely that amigaos will ever be ported to x86 and boot natively.That thing wont be an amiga.PPC can change the endianess http://en.wikipedia.org/wiki/PowerPC#Endian_modes but i dont think it would be easy to port it to x86.So x86 is definitely out of the question for me.
Also from the same page Endianness and operating systems on architectures
(SNIP)
Read http://emumiga.com/about/
Another reason is, we want Amiga applications to be run as native applications in AROS, or first class citizens, if you like. An Amiga application should be able to talk to the AREXX port of an AROS application, and the other way around. When the Amiga application calls a library, it will automatically be a native AROS library, running some Amiga applications at close to AROS speeds, for instance when using datatypes.
-
From http://obligement.free.fr/articles_traduction/itwbarthel_en.php
"The high price of the AmigaOne X1000 seems to be an argument, for lots of amigans, to not buy the machine. A solution to sell lot more copies of AmigaOS could be an x86 version. What is your opinion about that?
In this small market price is always an issue. The kind of power the X1000 provides, for such a small customer base, naturally results in a high price. As things stand today, you cannot make this kind of gear in sufficiently large enough volume to bring down the cost and consequently the price.
I consider the x86 path a pipe dream. AmigaOS has no platform/porting layer: it is hardwired to a big-endian host platform, not just the fundamentals but also its data structures. I would say that the chances to see AmigaOS run on an ARM are much higher than to see it run on an x86 family processor. If you wanted to make it work on an x86 host, you would have to throw out all existing Amiga software designed to run on the 68k platform, much of which is still useful today (I would go so far as saying that it is not just useful, it is necessary). You would have to throw away much of the operating system and replace it.
Even if you were to make all of that happen as part of an x86 port, you would have to make significant sacrifices. I doubt that any of these would result in a viable product."
Read http://emumiga.com/about/
-
Architecturally can the PPC ever reach the performance of the x86!?
What about the ppc in PS3 ?
-
ARM might be the way to go. Write multi-touch support into the OS and develop a tablet.
-
Reading through a few comments on here. As far as I understood it PPC has a smaller instruction set than x86 and like for like will run much faster than an x86.
PowerPC G3 has more instructions than Pentium II i.e. refer to http://arstechnica.com/cpu/4q99/risc-cisc/rvc-5.html
---
From http://en.wikipedia.org/wiki/Reduced_instruction_set_computing
A common misunderstanding of the phrase "reduced instruction set computer" is the mistaken idea that instructions are simply eliminated, resulting in a smaller set of instructions. In fact, over the years, RISC instruction sets have grown in size, and today many of them have a larger set of instructions than many CISC CPUs.[6][7] Some RISC processors such as the INMOS Transputer have instruction sets as large as, say, the CISC IBM System/370; and conversely, the DEC PDP-8 – clearly a CISC CPU because many of its instructions involve multiple memory accesses – has only 8 basic instructions, plus a few extended instructions.
The term "reduced" in that phrase was intended to describe the fact that the amount of work any single instruction accomplishes is reduced – at most a single data memory cycle – compared to the "complex instructions" of CISC CPUs that may require dozens of data memory cycles in order to execute a single instruction.[8] In particular, RISC processors typically have separate instructions for I/O and data processing; as a consequence, industry observers have started using the terms "register-register" or "load-store" to describe RISC processors.
Some CPUs have been retroactively dubbed RISC — a Byte magazine article once referred to the 6502 as "the original RISC processor" due to its simplistic and nearly orthogonal instruction set (most instructions work with most addressing modes) as well as its 256 zero-page "registers". The 6502 is no load/store design however: arithmetic operations may read memory, and instructions like INC and ROL even modify memory. Furthermore, orthogonality is equally often associated with "CISC". However, the 6502 may be regarded as similar to RISC (and early machines) in the fact that it uses no microcode sequencing. However, the well known fact that it employed longer but fewer clock cycles compared to many contemporary microprocessors was due to a more asynchronous design with less subdivision of internal machine cycles. This is similar to early machines, but not to RISC.
----------------------------------------------------
The Concept of the Instruction Set Architecture from http://arstechnica.com/cpu/2q00/x86future/isa-future-2.html
RISC vs. CISC: the Post-RISC Era from http://arstechnica.com/cpu/4q99/risc-cisc/rvc-1.html
RISC and CISC, Side by Side from http://arstechnica.com/cpu/4q99/risc-cisc/rvc-5.html
RISC vs. CISC Conclusion from http://arstechnica.com/cpu/4q99/risc-cisc/rvc-6.html
Both the Athlon and the P6 run the CISC x86 ISA in what amounts to hardware emulation, but they translate the x86 instructions into smaller, RISC-like operations that fed into a fully post-RISC core. Their cores have a number of RISC features (LOAD/STORE memory access, pipelined execution, reduced instructions, expanded register count via register renaming), to which are added all of the post-RISC features we've discussed. The Athlon muddies the waters even further in that it uses both direct execution and a microcode engine for instruction decoding. A crucial difference between the Athlon (and P6) and the G4 is that, as already noted, the Athlon must translate x86 instructions into smaller RISC ops.
-
I'm not against PPC in terms of architecture, and I understand tht going x86 is a different kind of step than the move from 68k to PPC, as that doesn't just change instruction sets, but also has the change in endianness to tackle, and is thus a lot of work. We know it took a very long time to get to PPC. It'll take another very long time to see x86 if that's chosen. Yes, Apple shows us it is possible, though they did have a bit more money to throw at the problem. AROS also shows us some things.
But, while I'm not against PPC, I do find it very frusrating that I cannot get a portable AmigaOS solution, even though PPC laptops do exist.
-
MorphOS 3.0 on Apple PowerBook G4. http://www.youtube.com/watch?v=V89YwHFoXyw
-
What about the ppc in PS3 ?
It's not a good desktop CPU, it's designed for consoles. Then I do not think Toshiba (since they bought Sony's share of cell production) is selling it to anyone else but Sony. So unless IBM is producing new cores to keep up with x86_64 multi cores, Freescale and others are going to keep repackaging the cores they have licenses for. Freescale is pushing ARM for a reason. ;-)
-
What about the ppc in PS3 ?
On normal linux apps, the CELL's PPE at 3.2Ghz was benchmarked to be around PowerPC 970 at 1.6Ghz. The PPE vs PowerPC 970 relationship is like Intel Atom vs Intel Core 2.
CELL's PPE is closer to Intel Atom i.e. in-order-processing and dual instruction issue per cycle design.
-
On normal linux apps, the CELL's PPE at 3.2Ghz was benchmarked to be around PowerPC 970 at 1.6Ghz.
Really? My experience was that the PS3 with Linux was alot slower for "normal linux apps" than my 1.33GHz G4 iBook, also when not using swap at all.
-
Really? My experience was that the PS3 with Linux was alot slower for "normal linux apps" than my 1.33GHz G4 iBook, also when not using swap at all.
http://www.xtremesystems.org/forums/archive/index.php/t-125219.html
Lack of direct access to NVIDIA RSX and 256MB ram for PPE didn't help PS3's linux situation.
-
http://www.xtremesystems.org/forums/archive/index.php/t-125219.html
Lack of direct access to NVIDIA RSX and 256MB ram for PPE didn't help PS3's linux situation.
Yes, but I was not using any graphics, all in CLI through ssh, and I specifically ran without swap, all well within the 256MB of RAM - and even then it was alot slower than my iBook.
-
Amiga OS must runs in PPC but neither will be very bad that it runs on X86 but with PPC and 68k compatibility, well, AROS for example.
-
Amiga OS must runs in PPC but neither will be very bad that it runs on X86 but with PPC and 68k compatibility, well, AROS for example.
You lost me on this one.
-
It's not a good desktop CPU, it's designed for consoles. Then I do not think Toshiba (since they bought Sony's share of cell production) is selling it to anyone else but Sony. So unless IBM is producing new cores to keep up with x86_64 multi cores, Freescale and others are going to keep repackaging the cores they have licenses for. Freescale is pushing ARM for a reason. ;-)
Freescale just recently released the brand new e5500 core.
Nobody is pushing ARM for anything other than mobile devices.
-
why cant they bass os5 or mos 3X for that matter on aros and add Proprietary software on
top? and have it run on x86 with ppc emu mybe
it may be that they just do not want to and i am cool with that!
I also may be way off the mark!
but i have allways wanted to ask this question
-
My comment about Amithlon was due to the fact that it had a transparent way to use 68k code at hyper speed for an immediate improvement, while also offering a way to use native x86 code.
Had this approach matured, we could have shifted towards the OS being x86 code similar to how OS4 and Morphos have shifted to PPC.
My biggest problem with Aros as it stands is lack of 68k software support. As it is, Aros is pretty much like any Linux distribution minus stability, drivers and memory protection. They both have UAE and the majority of Aros apps are on Linux too.
Seamless 68k integration could change my outlook dramatically, but I'm not sure what the status is beyond launching UAE when you click on an adf.
PPC is just an expensive dead-end and FPGAs can't get us to even current hand-held device speeds.
-
Pretty much, not the best of all worlds to be PPC since Apple, Motorola, IBM et al squandered their lead over x86. But its what we have and I dont see anyone wanting to do the work to port Amiga to x86. I cant see anyone believing theyd ever see a return on their invesement to do that.
-
I think my answer here is "No, not now, not any more"
PPC would have been a perfectly viable 'future' for the Amiga 10-15 years ago. Nowadays the architecture has all but been abandoned for computers. I believe it still exists in embedded devices, but that's not what an Amiga is :-)
Given the choice of CPUs at the moment, much as I hate to say it, x86 seems to be the only real choice for a high-performance CPU.
Of course, the CPU isn't what makes the Amiga, it's the custom chipsets and ingenuity in the design. I don't care what CPU architecture it uses, so long as it's got some flair that makes it more than just a rebranded PC motherboard.
-
Freescale just recently released the brand new e5500 core.
From what I see, it's a follow on e500 core for embedded systems that Freescale has been talking about since 2004. Not really applicable for desktop CPUs which we are discussing when comparing the multi core desktop beasts of Intel and AMD.
Nobody is pushing ARM for anything other than mobile devices.
Tell that to M$ and Google efforts for ARM based server farms. The recently announced ARM-15 can be a winner in none mobile device CPU market as well as mobile.
-
Of course, the CPU isn't what makes the Amiga, it's the custom chipsets and ingenuity in the design. I don't care what CPU architecture it uses, so long as it's got some flair that makes it more than just a rebranded PC motherboard.
With the computer case closed and out of sight, how can you tell the difference? It's the user's experience that counts.
-
I dont see anyone wanting to do the work to port Amiga to x86. I cant see anyone believing theyd ever see a return on their invesement to do that.
Aros is doing a pretty good job of that, but I agree there is no money in it.
It would have to be a labor of love, that's for sure.
-
Everyone is thinking 1 dimensional. Why not make use of all those excellent virtual machines and set them up to run the legacy software. I guess that is for AROS to do... eventually.
My new dream OS is directory Opus and a web browser (instant on) which can boot into any OS I want (mostly OS 3.1, AROS, Windows, and maybe Haiku.)
-
Everyone is thinking 1 dimensional. Why not make use of all those excellent virtual machines and set them up to run the legacy software.
Hi, that sounds like an emulator, and is why UAE is about everywhere.
-
I believe PPC was the past future of amiga. I think they should think about rewriting the os for x86 and cheap up to date hardware. I do not believe amiga was ever about the hardware, 68000 was just the most practical at the time amiga was introduced. I think if Jay Miner had a pentium or xeon available at the time he would have used it.
-
http://news.cnet.com/Intel-shows-off-80-core-processor/2100-1006_3-6158181.html
I would vote for this, intels newest, an 80 core cpu. :)
Say what you want about intel, they have a future, they are not stuck in place like the ppc is.
PPC fans, can you match an 80 core processor that will become available for
early adopters in 5 years from now? 12 years ago moving amiga to ppc was a good idea. Today, there is no future in ppc.
Steven
-
http://news.cnet.com/Intel-shows-off-80-core-processor/2100-1006_3-6158181.html
I would vote for this, intels newest, an 80 core cpu. :)
Say what you want about intel, they have a future, they are not stuck in place like the ppc is.
PPC fans, can you match an 80 core processor that will become available for
early adopters in 5 years from now? 12 years ago moving amiga to ppc was a good idea. Today, there is no future in ppc.
Steven
Intel's newest is 4 years old, and it was a research project.
An 80 core CPU is useless for the desktop.
-
my opinion, as an aros user, is amiga os should go x86.
does this mean that you have to rewrite it totally?
i think it's better eat 100 apples (100, not 1000 or 1000000 just 100) tomorrow than eating 1 apple today.
one day without eating doesn't kill anyone.
68k software compatibility? An emulator isn't enough? We're in 2010.
Just let die 80s software.
Let's imagine what sw could be created by passionate, motivate developers.
Let's imagine new worlds!
I'm a little hobbyist developer.
I write something for aros, something for windows, i like to do it.
How many of us would like to develop for aos? The majority of us.
As someone wrote, it's not the price, but what they give you for that price.
I understand that this market is little, very little.
But this market will always remain so little: prices are too high and products are not viable to common man. Let's see the truth: who buys an amiga (one) today? Only amiga lovers. Who is so insane to buy an old apple ppc to make work morphos? Only morphos lovers! Please forgive me if i'm rude and not polite in what i write, but i think morphos has a great potential and so aos4.
There'll be no "human sentient being from the planet earth" that'd buy such systems!
I recognize that without acube, aeon, hyperion and morphos team today we wouldn't talk about amiga!!
It's such their work, it's great work!
But let's look reality: Only if ppcs cpu, mboard and so on prices drop there'll be a greater market.
Why does this thing should be changed by selling x1000?
If even aeon would produce the phantomatic x500 (an underpowered version of x1000) at, let's say, half the price, be honest, would you like to buy an intel atom based machine for 1000 eur?
In all these years sam prices have halved? Why a new product should cost less if there's no profit by sellings? Research cost. It costs very much.
I think the only way is x86.
And I also know this will never be.
I'll repeat forever the same sentence: amiga was brute power at low prices.
Today amiga ones are low power at brute prices.
-
"Its a research project" - So was the pentium before it went into mass
production.
" An 80 core CPU is useless for the desktop. "
Spoken like a true visionary. Right now perhaps, but we're talking about the future. In time, content creation on the desktop will use
all that horsepower AND MORE... 3d movies, ultra realistic 3d enviorments and animation. New types of virtual reality,completely realistic animation of people which will mean real actors no longer needed to create movies, and more.
Think about the incredible things created on a quad core. Who wouldn't want a computer with 80 cores instead of 4?
Useless for a desktop? Are you on drugs? Can I have some of them?
Steven
-
Why keep going towards old technology? It would be great to see something ground breaking on the Amiga front.
-
As far as desktop CPUs? Unless IBM is going to release new PPC cores, not happening. Only thing Freescale is doing is repackaging the old cores. IBM's cells are for consoles and not suited for desktops. That leaves you basically with x86_64 or ARM as CPU choices that are in constant development.
And Power series? (power6, Power7 andfuture Power8)
-
http://news.cnet.com/Intel-shows-off-80-core-processor/2100-1006_3-6158181.html
I would vote for this, intels newest, an 80 core cpu. :)
Say what you want about intel, they have a future, they are not stuck in place like the ppc is.
PPC fans, can you match an 80 core processor that will become available for
early adopters in 5 years from now? 12 years ago moving amiga to ppc was a good idea. Today, there is no future in ppc.
Steven
I see your 80 core and raise you another 945
http://en.wikipedia.org/wiki/Kilocore
-
And Power series? (power6, Power7 andfuture Power8)
Are where they've always been: Big iron.
-
X86 makers:
-Intel
-Amd
-Via?
PowerPC makers
-IBM
-Freescale
-Amcc
-Toshiba
-Rapport inc
-Agnilux/google?
PowerPC wins
-
Think about the incredible things created on a quad core. Who wouldn't want a computer with 80 cores instead of 4?
And look at how much of the time 3 of those 4 cores are sat idling away because the processes required by the user can't be done efficiently as anything other than serial operations? Answer: With few exceptions, quite a bit of the time. There are issues inherent in multi processing in that quite a few of our day to day tasks cannot be broken up easily in a multi-threaded manner.
BeOS solved them by forcing everything to be multi-threaded. It meant that things like unpacking a zip archive was slower under BeOS than it was under Win98/2k on the same hardware because of the overheads in trying to break up single threaded operations. OSX does ok but even it's solution is no magic bullet, Dragonfly BSD's proposed solution is to turn multi core chips effectively into a Beowulf cluster.
Useless for a desktop?
For the forseable future, yes. 80 cores has no place on the desktop. You'd be damned hard pressed to justify 8 outside of a server...
-
X86 makers:
-Intel
-Amd
-Via?
PowerPC makers
-IBM
-Freescale
-Amcc
-Toshiba
-Agnilux/google?
PowerPC wins
You cannot possibly be this dumb.
-
You cannot possibly be this dumb.
It was half-jokingly. The problem with Amiga.org is that you can not embed images
-
It was half-jokingly. The problem with Amiga.org is that you can not embed images
[img]url to your image[/img]
You'll find that works just fine.
-
Anyway they must concentrate on software, no matter on which CPU it run (even if itś alien technology and is cheaper than X86) if there is not applications or certain features in the OS they will get the same result
-
I dont think the number of cores really have much of an impact on how fast final writer 97 and Dpaint IV runs.
-
x86 all the way. Think of all the people we've lost over the years because they never could run AmigaOS on their Windows boxes.
-
Discussing the future of Amiga is like arguing over who should be the next Roman emperor. Amiga is dead, it died with Escom. Sure, we can talk about current and future Amiga-inspired platforms, but they aren't Amigas. Amiga is and should be entirely in the realm of retro computing, as much as we would've all liked things to have gone differently in the early 1990s.
-
X86, but it's the OS'es that must be completely ported to X86.
The goal should be that 3.1/3.5/3.9/4.1 run entirely on X86, if we accomplish that, then Amiga as an OS has a future again.
It shouldn't matter which hardware would be in it, but modern drivers should be devolved of course.
I expect the OS to fully run on a X86 on a SATA SSD with whatever video car, audio card/onboard, network and everything else.
-
X86, but it's the OS'es that must be completely ported to X86.
The goal should be that 3.1/3.5/3.9/4.1 run entirely on X86, if we accomplish that, then Amiga as an OS has a future again.
Problem is of course, your still chained to 3.1 API even if you go x86. Keep OS4 on PPC only, neither are going any where.
-
Porting 3.1 3.5 or 3.9 to x86 would be awesome. I'm amazed that no one ever leaked the source code to any of them.
The files and sources had to have gone through many people's hard drives over the years. I wish someone would leak it. A bounty could be started to port it to whatever people wanted.
Steven
-
Other: in my distorted universe the future of Amiga is AROS running on x86, AMD64, ARM, PPC or m68k. It's up to the user to choose.
greets,
Staf.
-
Porting 3.1 3.5 or 3.9 to x86 would be awesome. I'm amazed that no one ever leaked the source code to any of them.
At one time it was available from an AT ftp server, an "oversight". IIRC it was this that allowed Olaf Barthel to get his copy.
A bounty could be started to port it to whatever people wanted.
Yes, because once you've gone so far as to commit copyright infringement, the next stage is to monetize it and potentially put other people in the spotlight along with you...
-
Porting 3.1 3.5 or 3.9 to x86 would be awesome. I'm amazed that no one ever leaked the source code to any of them.
The files and sources had to have gone through many people's hard drives over the years. I wish someone would leak it. A bounty could be started to port it to whatever people wanted.
Steven
What an odd statement, actually a few odd statements.
Anyhow, I guess you never heard of AROS?
-
i am not against any proposed solution nor against any other imaginable (including quantum processor), yet as long as it looks like just panickly trying to catch up with modern pcs i might as well stay with 68k.
-
I voted x86 as it's the only logical choice. Actually the only choice period. Aros is the future.
-
At one time it was available from an AT ftp server, an "oversight". IIRC it was this that allowed Olaf Barthel to get his copy.
Olaf Barthel was hired by Amiga Technologies GmbH to organize the source code from the Commodore backup tapes.
-
Since we already have AOS4 and MorphOS, I'm not sure about the point of this question. PPC has been a part of our future for quite a while.
Everyone needs to get over the Amiga name. "Amiga" is just a trademark. Soon we're likely to have X86 "Amigas" that won't be able to run AmigaOS (just AROS, Windows, or Linux). That's the future whether we like it or not.
As to future platforms for those of us still hanging on, since they're already available what are we debating here?
-
Who wouldn't want a computer with 80 cores instead of 4?
Anyone who's heard of Amdahl's law.
Useless for a desktop? Are you on drugs? Can I have some of them?
Actually that processor is useless for pretty much anything aside running linpack benchmarks.
It's an experimental chip used to see how they could get something like that to work. The cores are simple VLIW things that run no existing software. There is a newer 50 core version with Atom like cores but even it's a bit of an oddity, it's not SMP so you have to run an OS per core - unless you are using a specialist cluster based OS.
-
x86 is the commonest platform so it should be on it. Go full 64-bit SMP/SMT while your at it.
I would also like to see it on ARM because it is perfect for light lean OS and unlike other ARM OS you would be free to tinker with it.
PowerPC died when Apple dumped it, if people didn't see it was time to move then... they must interpret the world funny.
68k on FPGA will be satisfactory, but it is not for a serious alternative main OS.
If nothing happens I hope Haiku or AROS will be fully functional alternative OSes.
Sorry to pick on you, just quoting to address a general misconception, but PPC compatible cores are in Wii/PS3/360....and you can thank IBM not those twats at Apple ;)
Last Amiga died with A4000/A1200. All the others are just Amiga by name, no custom chips and no style just a box for running OS4 (which needs a LOT of work to catch up)
(CELL PPU is more or less 1 Xenon core)
-
Anyway they must concentrate on software, no matter on which CPU it run (even if itś alien technology and is cheaper than X86) if there is not applications or certain features in the OS they will get the same result
Exactly! You need a modern 100% compatible browser and all extensions like Flash/Jquery/PHP/JAVA/HTML5 etc and then all the codecs for SD and HD video and every flavour of audio and a nice media player. A torrent client. MSN/Yahoo/Skype client. A good professional paint program and office suite. An API for 3D acceleration. Oh and multicore/multithreading/64bit ALU support.
Actually that's about it really. doesn't sound like much....but it's all essential.
-
I've never seen PPC as being an important part of the Amiga platform. As far as I'm concerned, it's an architecture that was used in some third party accelerator cards and nothing more. That doesn't mean PPC support is a bad thing or a hindrance in any way, but there's no getting around the fact that x86 is the only viable option for powerful and affordable hardware.
I think having MorphOS and AmigaOS exclusive to PPC has actually worked out for the best. If those operating systems were available for x86, we probably wouldn't have AROS today, and it would be a shame not to have an actively developed FOSS member of the Amiga family.
-
X86 makers:
-Intel
-Amd
-Via?
PowerPC makers
-IBM
-Freescale
-Amcc
-Toshiba
-Rapport inc
-Agnilux/google?
PowerPC wins
X86 makers:
AMD
Advantech (e.g X86 SoC)
D&MP (e.g Vortex86 Series SoC )
Intel
NVIDIA (e.g. ULI M6117C)
RDC (e.g R8610 )
VIA
ZF Micro (e.g. ZFx86 SoC)
Intel has licensed Intel Atom to TSMC.
http://en.wikipedia.org/wiki/List_of_x86_manufacturers
-
Since we already have AOS4 and MorphOS, I'm not sure about the point of this question. PPC has been a part of our future for quite a while.?
I think he was getting a judge of how the users feel about PPC and is it still the way of future, or should we consider other CPUs for future development.
I'm firmly in the x86 camp. Nothing will ever be as fast per dollar again.
-
It is called AROS... It runs on cheap and broadly available x86 hardware, it is free, it is opensourced. It should dominate the Amiga future, shouldn't it? Guess why it has not happened for 15 years.
Because of people like you? :hammer:
AROS was never taken seriously among the "true" Amiga developers, it's just quite recently it has gotten to the point where it is even mentioned in the types of discussions like this one. And why has it taken so long? Because the said "true" Amiga developers have not really been interested in participating.
Oh, and btw - in my view, AROS is already dominating. :)
-
I voted PPC because to me some form does not leave out the possibility of other platforms.
Outside of Freescale using lawyers to hinder 680x0 dev. is there any technical reason why 680x0 could not be developed to compete with with todays quad cores?
Thanks. (Sorry if this question was asked a 100 times before )
-
Outside of Freescale using lawyers to hinder 680x0 dev. is there any technical reason why 680x0 could not be developed to compete with with todays quad cores?
Only the earth shattering costs of reworking an arch that hasn't seen development in what, 16 years?
That's even assuming that what you ended up with would remotely resemble or be compatible with what you used as a starting point.
Consider the differences between 68k and Coldfire and that is only one step away, what you're proposing is several steps away.
-
I voted x86 as it's the only logical choice. Actually the only choice period. Aros is the future.
AROS on brand new Commodore Amiga x86 machines!
:)
-
Only the earth shattering costs of reworking an arch that hasn't seen development in what, 16 years?
At least the 68010+ already meets the Popek & Goldberg virtualisation requirements :)
-
I'm with those who say there's nothing evil about a type of CPU. Well, unless Intel are assassinating pet kittens and using the corpses for their cores but I don't think so ;)
To me it seems senseless, especially in the current economic climate, to pick a minority platform that costs 4x as much for the same power (or less). There are a lot of hardcore Amiga fans on here, yet only an even more hardcore subset would bother paying that kind of money to play with what is basically an experimental OS.
AROS was never taken seriously among the "true" Amiga developers, it's just quite recently it has gotten to the point where it is even mentioned in the types of discussions like this one. And why has it taken so long? Because the said "true" Amiga developers have not really been interested in participating.
It suffered from chicken-and-egg syndrome I think. Nobody was interested in getting involved because it was taking so long (15 years!) to get into a state that can be considered "interesting" (reasonably usable). It didn't seem like it was getting anywhere, and therefore difficult to take seriously. Yet it probably took so long because nobody was interested in getting involved.
Now that it's in an interesting state, that's probably why it's being taken a bit more seriously as an option.
-
PPC is like the Amiga..people said it was dead but it is still ALIVE:afro:
-
PPC is like the Amiga..people said it was dead but it is still ALIVE:afro:
Why does it have to be one or the other? For example, viruses (the ones with the protein casings not the computer ones) aren't considered alive although in many respects they appear alive.
-
I don't really care for the move towards homogenization in the computer market, and that goes double for computers I like because of their hardware, so x86 is right out. But I'm not really fond of the PowerPC move, either. Don't get me wrong, it's not a bad processor, but why does everything 68k-based have to move to it? The 68000 architecture is a fundamental part of what the Amiga is, and taking that away makes it less of an Amiga.
Besides, the 68k is about the most assembler-friendly architecture you'll ever find. Don't want to give that up.
-
Besides, the 68k is about the most assembler-friendly architecture you'll ever find. Don't want to give that up.
That's true, but then you are sentenced to stay below 100 MHz forever. Some may accept it, some not.
-
That's true, but then you are sentenced to stay below 100 MHz forever. Some may accept it, some not.
Wrong! A medium sized and priced fpga should allow an enhanced 68k processor to achieve around 150MHz. That is what the Natami team is expecting and that is what similar complexity and sized processors are running in fpga. That should compare nicely to a single core PPC at more than 2x the clock speed and possibly approaching 3x the clock speed. FPGA's are getting cheaper faster than PPC processors are getting faster. The 68k is easier to program and much more tolerant of poorly optimized code like Hyperion is famous for. It's also much easier to debug than PPC or x86.
Disclosure: I love 68k, like PPC and hate x86. I only own classic Amigas but I am supportive of all Amiga users.
-
What is the likely hood of an Amiga OS4.1 port to X86 bounty?
How many would contribute to it if Hyperion would allow it?
-
Wrong! A medium sized and priced fpga should allow an enhanced 68k processor to achieve around 150MHz. That is what the Natami team is expecting and that is what similar complexity and sized processors are running in fpga.
Well now I'm really going to have to get one :)
It is a pity, though, that Motorola has given up on the line (microcontrollers and ColdFire excepted.) It'd be nice to be able to purchase a much faster 68k CPU, especially with modern execution features. It really is a beautiful architecture, with a lot of the nice features of RISC (a large array of general-purpose registers and sweet, sweet instruction-set orthogonality) but enough CISC features to keep things eminently usable for the assembly programmer. I wish I'd been using it back when I was first trying to understand assembly language; would've saved me a lot of time and trouble...
-
I'm happy with calling PPC a virus...
Why does it have to be one or the other? For example, viruses (the ones with the protein casings not the computer ones) aren't considered alive although in many respects they appear alive.
-
That's true, but then you are sentenced to stay below 100 MHz forever. Some may accept it, some not.
It's definately concern but until we have software where that makes a difference, I'm not sure its a practical concern.
-
Wrong! A medium sized and priced fpga should allow an enhanced 68k processor to achieve around 150MHz.
Wow, a whole 150Mhz?
I know MIPS aren't everything, but it's one indicator with numbers that were readily available on Wikipedia.
Assuming 060 performance, not 020/030 as most fpgas currently are:
68060@66 MHz = 88 MIPS
68060@75 MHz = 110 MIPS
68060@110 would be roughly 220 MIPS
Intel Pentium III @ 500 Mhz = 1,354 MIPS
ARM Cortex A8 @ 1.0 GHz = 2,000 MIPS
PS3 Cell BE @3.2 Ghz = 10,240 MIPS
XBox Xenon PPC @3.2 GHz = 19,200 MIPS
Intel Core 2 QX6700 @ 2.66 GHz = 49,161 MIPS
Intel Core i7 i980EE @ 3.2 GHz = 147,600 MIPS
x86 is clearly fastest per dollar now and will be for the foreseeable future.
Even the cheap embedded x86 chips are faster than the PIII 500MHz.
You can buy an off the shelf x86 that is 1677 TIMES FASTER than the fastest 060 available (66Mhz) for less than the cost of the 060 card.
I'm not sure why anyone would want to hobble Amiga with slow CPUs, they used the 68000 because it was the fastest for the money at the time.
Before Amiga went under they were already looking for alternative CPUs, so I'm not sure why there is such a strong attachment to a basic component that was near end of life already.
-
Anyhow, I guess you never heard of AROS?
I've heard of it an read up on it, but I don't think this is the answer.
What is the likely hood of an Amiga OS4.1 port to X86 bounty?
How many would contribute to it if Hyperion would allow it?
If it would go open source, I think you would be surprised.
-
Personally, I voted yes more because my Amiga ego gets the better of me. Logically, though I should have voted for the x86 way since it is way too dominant and cheap.
But then again, what truly makes an Amiga?? Is it the hardware or the OS? If the answer is the hardware then I go the ppc blind sighted. If it is the software then I have to concede that x86 is the way to go!!!
-
x86 is the cheapest for the money. What would be cool is if someone did a radical type of motherboard redisign and included multiple gpus, incredible sound card components and and multiple upgrade slots for adding MANY x86 processors, maybe additional coprocessing components and so on.
16 core chips will soon be very common... Imagine 4 phyical 16 core chips on one motherboard, or more, with great gpu, sound, ect, all on one slick mb that you can upgrade for many years.
Steven
-
I'm not sure why anyone would want to hobble Amiga with slow CPUs [...]
Seamless compatibility with existing software? How useful will a lightening-fast system be without much software to run on it?
-
Seamless compatibility with existing software? How useful will a lightening-fast system be without much software to run on it?
Our games catalogue fits on 4 DVDs which run on WinUAE on P3 PCs, no streaming video format of our own we use Mac/PC, broken browser and TCP/IP stack. What's to keep? What's unique? Fix UAE for OS/4 too and get that loser coding WinUAE to grow a penis and say f&#k off to scum like Cloanto who invest nothing back to Amiga.......then we can talk properly.
Amiga is a mess right now, don't tolerate lame over priced unimaginative rubbish either like SAM or x1000 either. No brains in R&D=NO SALE :)
-
What is the likely hood of an Amiga OS4.1 port to X86 bounty?
How many would contribute to it if Hyperion would allow it?
I'd happily contribute in the form of final purchase price.
-
Our games catalogue fits on 4 DVDs which run on WinUAE on P3 PCs, no streaming video format of our own we use Mac/PC, broken browser and TCP/IP stack.
If you're just going to do Amiga stuff in emulation, what's the point of even having an Amiga? Just get a PC and stop fooling yourself.
-
On the other hand hobbling a system to run 16 year old software is silly. Run classic software in UAE and abandon the constraints that are killing the Amiga. Either you develop new software to do new things or the whole point of faster more modern systems is moot.
Dpaint IV will run faster on my Mac Pro than an X1000, but it still isn't going to replace photoshop as my daily image editor...
Take OS4, throw out the outdated concepts and bring it into 2011. Move to X86 and be done with it. The CPU has zero relevance on how "different" an operating system is.
Seamless compatibility with existing software? How useful will a lightening-fast system be without much software to run on it?
-
someone here hate the idea amiga to be a pc. the amiga of 25 years ago wasn't because had its peculiarities.
the amiga (one) of today is already a pc.
it's a simple pc nor more nor less than an x86 one.
it has its cpu, ram, bus, hdd and so on.
it hasn't a x86 cpu but in the rest it's about to be the same.
i think if aos would go x86 it'll be only faster faster faster.
and surely for a pirated copy hyperion would gain by 2 original ones.
How many original copies of aos4 (how many amiga one) have been sold? 10000? i think less.
in x86 world this number has at least to grow double in short time.
really again i don't understand: Do you seriously hate so much the idea of fresh blood that you prefer to stay in your ivory towers? Do you seriously hate the idea that we're not an elite but instead today we're only fossils of a long ago past time to condemn amiga to die?
-
Given the choice of CPUs at the moment, much as I hate to say it, x86 seems to be the only real choice for a high-performance CPU.
I guess it's because you don't need the x86 instructions anymore, or it's the multi core that makes the 'immediate' feeling possible.
I recently bought an i5 pc and for the first time since I swapped DOS for windows 95 I got the feeling the GUI isn't a buggering resource hog anymore, considering both Linux and Windows (I never was happy with the performance of X11 either until now).
-
Seamless compatibility with existing software? How useful will a lightening-fast system be without much software to run on it?
At 1000+ times the speed, I'm sure you could handle a compatibility mode ala MacOS or MorphOS.
-
someone here hate the idea amiga to be a pc. the amiga of 25 years ago wasn't because had its peculiarities.
the amiga (one) of today is already a pc.
it's a simple pc nor more nor less than an x86 one.
it has its cpu, ram, bus, hdd and so on.
it hasn't a x86 cpu but in the rest it's about to be the same.
i think if aos would go x86 it'll be only faster faster faster.
The principles of north- and southbridge are in principle still inferior to a theretical modern day custom chipset design.
More flexible, yes, but also bottlenecks. Pumping up the bitrates still to overcome its deficiencies. Not something a tech head can be enthusiastic about.
-
I'd say port it to the dual core ARM..... Pretty soon your phone will be your desktop.
-
Wow, a whole 150Mhz?
You have to start some where. Creating a CPU in fpga is not trivial. This will ramp up quite quickly if there is a market. Fpga's will become faster and if a CPU could be burned then a very powerful for CISC 500MHz-1GHz would be possible. If the N68k could become a popular processor again, then more is possible. There is nothing besides money that keeps the 68k from x86 performance. The 68k has several advantages over x86 as far as making a chip. It's simpler, has smaller code (translates to less caches needed) and has less baggage that needs to be supported because it has a good design to start with.
Assuming 060 performance, not 020/030 as most fpgas currently are:
x86 is clearly fastest per dollar now and will be for the foreseeable future.
I agree. No contest. Games push the high end desktop market and the x86 duopoly is able to crush any and all competition. The mobile multimedia market, laptop/netbook and enbedded markets are huge and growing. This is more becoming ARM territory but an enhanced 68k has advantages over ARM. It is easier to program and has smaller code. ARM's advantage was simplicity but it lost most of that with enhancements.
The first Natami fpga CPU, the N68050, should be more powerful than the 68060 at the same clock speed. The superscaler N68070 should be able to average several complex instructions per clock. The N68k will have fairly modern enhancements like larger caches and DDR2 memory. The 68060 performs very well for it's day. It was probably the best processor of the day but was never clocked up and killed for marketing reasons. Motorola had decided to go PPC and was selling everyone that it was the future. The 68060 outperformed the PPC processors for the first couple of years. It did more with less.
I'm not sure why anyone would want to hobble Amiga with slow CPUs, they used the 68000 because it was the fastest for the money at the time.
The 68000 was a good fit. It was powerful but also flexible. I don't think the AmigaOS would be as efficient or as good if x86 had been used. The Amiga was never about having the fastest CPU. It was about having several processors working in parallel. It was ahead of it's time because that is where processors are headed today, integrating processors like SIMD and GPU to the CPU (faster & saves power). That is also what Natami is trying to do.
Before Amiga went under they were already looking for alternative CPUs, so I'm not sure why there is such a strong attachment to a basic component that was near end of life already.
That was because Motorola decided to kill the 68k in favor of the PPC. Motorola wasn't going to produce any new 68k processors.
-
someone here hate the idea amiga to be a pc. the amiga of 25 years ago wasn't because had its peculiarities.
the amiga (one) of today is already a pc.
it's a simple pc nor more nor less than an x86 one.
it has its cpu, ram, bus, hdd and so on.
it hasn't a x86 cpu but in the rest it's about to be the same.
i think if aos would go x86 it'll be only faster faster faster.
and surely for a pirated copy hyperion would gain by 2 original ones.
How many original copies of aos4 (how many amiga one) have been sold? 10000? i think less.
in x86 world this number has at least to grow double in short time.
really again i don't understand: Do you seriously hate so much the idea of fresh blood that you prefer to stay in your ivory towers? Do you seriously hate the idea that we're not an elite but instead today we're only fossils of a long ago past time to condemn amiga to die?
While I'm not into PCs, new processors or the need for speed at all, I don't and never have considered owning an Amiga as being elitist. I have been using the Amiga since the very start, way back in 86.
The Amiga to me was simply the natural progression from the Vic20 and C64. My main reason for it still being my favorite computer today is quite simply I'm more than happy with what it can do & the speed at which it does it.
This is in no way being elitist, it just my own personal choice and I have no objection to all the other types of processors that other folk would like to see being used. If a new Amiga of some description ever does appear, of course I would have a look at it, but it would have to be something special indeed to change me from being an old fossil... :)
-
Wrong! A medium sized and priced fpga should allow an enhanced 68k processor to achieve around 150MHz. That is what the Natami team is expecting and that is what similar complexity and sized processors are running in fpga. That should compare nicely to a single core PPC at more than 2x the clock speed and possibly approaching 3x the clock speed.
Assuming they can actually get it to 150MHz, I expect it'll have trouble matching a PPC at the same clock speed never mind exceeding it.
-
@Speelgoedmannetje
custom chipset is simply superior to all but that amiga is no more. To redesign a revolutionary vision you need money, money, money and meanwhile on facebook today i wrote amiga. at the first place there was a picture with two blond women...
@Franko:
I'm the first fossil. Because i never went ppc. Amiga to me is still that 68k machine that made me think there was no other computer superior to it. But that was 25 years ago. The son of amiga today is its spirit: the os. I regularly use aros on x86 and i've seen aos4 and morphos videos. This os has so many many many things to say to the whole world!! It's fast, it's efficient, it's easy. IT'S NOT UNIX OR NT!!!
Don't let it die...
-
Assuming they can actually get it to 150MHz, I expect it'll have trouble matching a PPC at the same clock speed never mind exceeding it.
If they don't get 150MHz this year, they probably will next as the speed of fpgas increase and the price drops. There are fpgas that are fast enough now but they cost a lot of money. The 68k did often outperform the early PPC processors. Even the 68040 outperformed the early PPC processors on the early MACs. Amiga users with 68060 and Shapeshifter or Fusion had the fastest MAC for about a year. Apple made the later MAC OS incompatible with the 68060 because of it. MAC OS 7 worked great with the 68060 and then MAC OS 8 didn't for some odd reason. An fpga N68k isn't going to wow people or steal x86 market share but it will probably be fast enough to impress Amiga users still using the classic and fast enough for general computer needs. That's enough for me. I'm not opposed to PPC Amigas. I would like to see 68k for the low end and laptops and PPC for the high end and desktops. The attitude of Hyperion has turned me off though. I prefer the openness of Natami and AROS (but don't care for the x86 focus of AROS).
Here's what an IBM engineer has to say about the 68060 and PPC...
"With 2 instructions per clock and excellent multiplication and branch performance, the 68060 performs very good. Depending on the workload the 68060 can even outperform similar clocked 60x/G2/G3 PowerPC CPU."
"Actually the 68060 is faster in multiplication than many PowerPC.
The PPC G2 (603) and G3 CPU need 5 cycles for a multiplication.
Which means a 100 Mhz 68060 achieves the same multiplication performance as an 250 Mhz G3."
http://www.natami.net/knowledge.php?b=4¬e=2418
Let's look at some 68k code to see what is so great about the 68k. Let's take a simple 68k memory copy with size (longwords) in d0...
.loop:
move.l (a0)+,(a1)+
subq.l #1,d0
bcc.b .loop
Let's say we don't know the alignment of the data either. This copies 1 longword/cycle with data aligned and is 6 bytes. If data is unaligned this is still pretty good. Now write that on PPC with anywhere near the performance. Don't let the old outdated 68060 with tiny little cache and only 4 bytes of instruction fetch/cycle DESTROY. I'll even give you a few hints. You better align the data first or the performance is really bad. You will need twice as many instructions to duplicate what's above. You will need to use an unrolled loop (wasting more code) and preload the cache. If you do all that optimally, you are still likely slower than the 68060 ;). No wonder PPC needs all those GHz.
-
If they don't get 150MHz this year, they probably will next as the speed of fpgas increase and the price drops. There are fpgas that are fast enough now but they cost a lot of money. The 68k did often outperform the early PPC processors. Even the 68040 outperformed the early PPC processors on the early MACs. Amiga users with 68060 and Shapeshifter or Fusion had the fastest MAC for about a year. Apple made the later MAC OS incompatible with the 68060 because of it. MAC OS 7 worked great with the 68060 and then MAC OS 8 didn't for some odd reason. An fpga N68k isn't going to wow people or steal x86 market share but it will probably be fast enough to impress Amiga users still using the classic and fast enough for general computer needs. That's enough for me. I'm not opposed to PPC Amigas. I would like to see 68k for the low end and laptops and PPC for the high end and desktops. The attitude of Hyperion has turned me off though. I prefer the openness of Natami and AROS (but don't care for the x86 focus of AROS).
Here's what an IBM engineer has to say about the 68060 and PPC...
"With 2 instructions per clock and excellent multiplication and branch performance, the 68060 performs very good. Depending on the workload the 68060 can even outperform similar clocked 60x/G2/G3 PowerPC CPU."
"Actually the 68060 is faster in multiplication than many PowerPC.
The PPC G2 (603) and G3 CPU need 5 cycles for a multiplication.
Which means a 100 Mhz 68060 achieves the same multiplication performance as an 250 Mhz G3."
http://www.natami.net/knowledge.php?b=4¬e=2418
Let's look at some 68k code to see what is so great about the 68k. Let's take a simple 68k memory copy with size (longwords) in d0...
.loop:
move.l (a0)+,(a1)+
subq.l #1,d0
bcc.b .loop
Let's say we don't know the alignment of the data either. This copies 1 longword/cycle with data aligned and is 6 bytes. If data is unaligned this is still pretty good. Now write that on PPC with anywhere near the performance. Don't let the old outdated 68060 with tiny little cache and only 4 bytes of instruction fetch/cycle DESTROY. I'll even give you a few hints. You better align the data first or the performance is really bad. You will need twice as many instructions to duplicate what's above. You will need to use an unrolled loop (wasting more code) and preload the cache. If you do all that optimally, you are still likely slower than the 68060 ;). No wonder PPC needs all those GHz.
K8/K10 and Core 2/i3/i5/i7 can process IMUL(32bit) at every cycle(1 cycle througput) with 3 cycle latency.
Core i3/i5/i7 can process IMUL (64bit) at every cycle (1 cycle througput) with 3 cycle latency. K8/K10 and Core 2 has can process IMUL (64bit) in 2 cycles (2 cycle througput) with 4 cycle latency. To hide the latency, factor in the pipeline and it's spectualive execution design.
Per instruction benchmarks doesn't show the whole picture in regards to overall performance i.e. use some proper application benchmarks.
....
This means that on the x86 you need to work constantly with variables on the stack. This limits the overall performance of the x86 quite a lot. All INTEL chips can at best do 1 stack operation per clock. This means as they often have to work on the stack your average instructions per clock goes down to 1.x.
That the x86 has to work with the stack constantly makes it very hard for the x86 to effective use more ALUs to increase performance
As for X86's stack arch issue, AMD K10 includes Sideband Stack Optimizer hardware while Intel Core includes Stack Pointer Tracker hardware.
From http://www.xbitlabs.com/articles/cpu/display/amd-k10_5.html
"Sideband Stack Optimizer unit tracks the stack status changes and modifies the instructions chain into an independent one by adjusting the stack offset for each instruction and placing sync-MOP operations (top of the stack synchronization) in front of the instructions that work directly with the stack register. This way instructions working directly with the stack can be reordered without any limitations"
--
This amounts to JIT(Just-In-Time) optimizer on hardware.
On Intel Core i3/i5/i7
Stack Pointer Tracking (SPT) implements the Stack Pointer Register (RSP) update logic of instructions which manipulate the program stack (PUSH, POP, CALL, LEAVE and RET) within the IDU. These macro-instructions were implemented by several micro-ops in previous architectures.
The benefits with SPT include using
+ a single micro-op for these instructions improves decoder bandwidth,
+ execution resources are conserved since RSP updates do not compete for them,
+ parallelism in the execution engine is improved since the implicit serial dependencies have already been taken care of,
+ power efficiency improves since RSP updates are carried out by a small hardware unit
---
http://www.chip-architect.com/news/2001_10_02_Hammer_microarchitecture.html
"This is for instance the case in the ESP Look Ahead Unit that allows among other things that consecutive PUSHes and POPs to and from the stack can be executed simultaneously"
PS; 2001 block diagram resembles AMD Bulldozer block diagram.
-
Let's look at some 68k code to see what is so great about the 68k. Let's take a simple 68k memory copy with size (longwords) in d0...
.loop:
move.l (a0)+,(a1)+
subq.l #1,d0
bcc.b .loop
Let's say we don't know the alignment of the data either. This copies 1 longword/cycle with data aligned and is 6 bytes. If data is unaligned this is still pretty good. Now write that on PPC with anywhere near the performance. Don't let the old outdated 68060 with tiny little cache and only 4 bytes of instruction fetch/cycle DESTROY. I'll even give you a few hints. You better align the data first or the performance is really bad. You will need twice as many instructions to duplicate what's above. You will need to use an unrolled loop (wasting more code) and preload the cache. If you do all that optimally, you are still likely slower than the 68060 . No wonder PPC needs all those GHz.
This example isn't really good at anything other than demonstrating the 68K is forgiving of lazy programmers. The alignment is never an unknown property; all you need to do is test the least significant bit(s) of the source and destination operands. You can also test the count and build a nice duff's device loop in assembler and only handle the trailing bytes before and after. On the 060, you might even be able to use move16, under the right circumstances; even when source and destination is not 16-byte aligned, you can often read (or write) via a temporary cache line in an appropriately aligned bit of stack.
In short, when implemented properly on the 68K or PPC, this will almost always be significantly faster than the lazy code above.
-
They should be able to hit 150 MHz about the time dual core 2 GHz tablets start appearing....
Sometimes the tortoise loses.
(http://west-festival.ioimprov.com/images/schedule/rigor_tortoise.jpg)
-
I don't understand people that say Amiga is about custom processors working together. That is what the amiga was but, that is the only way they could do it much like the c64, atari. They did that because they did not have off the shelf components that could achieve the performance they desired. Now you can get a processor with fpu, mmu, gpu, integrated that would blow them away. I think amiga if ported to x86 on modern hardware much like windows, Mac, Linux may not take over the marketplace it could certainly be successful. People, especially younger users are always looking for new stuff. Apple changed to x86 because ppc was no longer a viable option. Hardware does not make you money anymore, Software sales drive hardware sales, and generate profits. Look at the console market, Microsoft, sony, nintendo, make most of there money on software and basically give the consoles away. Amiga should really concentrate on developing some software applications, games, etc for there OS if they want to be successfull.
-
I'm happy with MorphOS on the mac and for x86 there's AROS, so I don't care either way. Next Amiga purchase will be a power mac and another MOS license. I'll use the machine until the wheels fall off and from having a bunch of mac PPC machines experience tells me that will be at least 10 years. I still have a working B&W G3 from '99 that's still kicking along. PPC Mac gear was built to last. I'm sure the MOS team will find a way to keep the ball rolling before the mac gear becomes useless.
-
A little OT, but a major patch was released for World of Warcraft earlier this week. Support for PPC Macs has been dropped.
Here's the official notice warning up the change:
http://forums.worldofwarcraft.com/thread.html?topicId=26560499428&postId=265579704371&sid=1#0
-
This example isn't really good at anything other than demonstrating the 68K is forgiving of lazy programmers.
It's not just lazy programmers. Good programmers mess up simple loops too. The above code is excellent for aligned data on the 68060 and small unaligned copies. This will also be the case for the N68050+. This code can be inlined because it's so small saving even more. Most processors require the unrolled loop and are very particular about alignment. Get it wrong and performance is a fraction of what it could be. The 68060 and N68050+ are just as fast if you use the unrolled loop and in some cases will be a little bit faster if you align the data. Use a movem.l copy loop and there is very little slow down too. Code optimized for any 68k processor will run very well on the 68060 and N68k. Is forgiving, easy to program, and small code bad?
The alignment is never an unknown property;
Check out exec.library/CopyMem(). It will copy memory of any alignment. This function is used way more than exec.library/CopyMemQuick() which does longword aligned copies. Never say never :P.
all you need to do is test the least significant bit(s) of the source and destination operands. You can also test the count and build a nice duff's device loop in assembler and only handle the trailing bytes before and after. On the 060, you might even be able to use move16, under the right circumstances; even when source and destination is not 16-byte aligned, you can often read (or write) via a temporary cache line in an appropriately aligned bit of stack.
Duff's device loop is slower on the 68060. Modern processors don't like the unpredictable jmp statement this generates and the 68060 doesn't need an unrolled loop. This is what the old SAS/C copy routine uses though. Does it perform poorly on the 68060? Not too bad. Are you a lazy programmer because you chose a slower copy routine that is ten times bigger? Nope. You're covered because the 68k is forgiving :).
You are right about testing the least significant bits to align the data except you only need to align the destination. Reading unaligned data is not as bad as writing unaligned data. Move16 is barely worth it on the Amiga at all. You have to copy several thousand bytes to make it worthwhile. Copies this large are rare on 68k Amigas. Here is a patch I wrote for CopyMem() and CopyMemQuick() on the 68060 and 68040...
http://aminet.net/util/boot/CopyMem.readme (readme)
http://aminet.net/util/boot/CopyMem.lha
It has assembler sources, timings, a Snoopy script that will show you the sizes and alignments of CopyMem() and CopyMemQuick() copies and more info. The 68060 optimized code is only 35% faster than the AmigaOS 3.9 functions which use a poorly implemented movem.l loop. They should have used an unrolled loop for the best performance on 68020-68060 and considering most copies are small. More lazy programmers?.
-
While I agree that the 68060 was a great CPU, there is a point where brute force and momentum overcome elegance.
I like the idea of using 680x0 code as a sort of bytecode JIT like Java or .net does.
It would give the ease of programming and backwards compatibility but wouldn't be run inside a complete sandbox like UAE.
The 68k code would seem to run far faster than on a real 68060.
If you wanted to use the native faster CPU you could and the 68k could call x86 libraries seamlessly.
-
@matthey
You rather missed my point: Only a lazy programmer writes the smallest possible loop to do a job and then blames the architecture if performance sucks. The 68060 is forgiving, PPC is not, but the PPC will deliver far better perfomance when it's rules are respected.
Regarding move16, it also depends on how much you want your cache polluting. If you are copying large amounts of data it has many advantages. You should never assume that because most copies are small, they all will be; well written code ought to be prepared for any reasonable eventuality.
The alignment is never an unknown property
Check out exec.library/CopyMem(). It will copy memory of any alignment. This function is used way more than exec.library/CopyMemQuick() which does longword aligned copies. Never say never :P.
No, "never" is perfectly accurate. The fact that any given function may not make use of the information does not mean the information is not there to be made use of. At a machine level, you will never have a transfer of data between addresses where at least the logical alignment is not known, since you have the addresses themselves.
Failing to use that information where it is useful a bit lazy IMHO.
-
Current version of Microsoft Office for Mac is intel only....
-
PPC isn't a "future". It's a dead-end.
your correct mister i couldnt said it any better myself.......
-
From 1994, everything looks like the future
-
My AmigaOne is slow! DOWN WITH PPC!
..and don't get me started on the BPPC!
-
I'm trying to figure out what I'm doing these days that simply could never be done on a 68060 -- seeing that it's fine for nonlinear video, etc.
-
To answer the OP, yes I do approve, in the form of MOS, but by now we must see that such discussions are fruitless, start flame wars and lead to ignorant comments like when Kolla called me a dumbass because of my opinion of the iMica.
Reasons why MOS, OS4 and Classic will probably never be x86.
Bye Bye to all your favorite apps native support, they all need big endian for native support of any kind
Making it x86 would involve twice the work, as its assembly code is a mess, and all our API, ABI and system calls taht have bits of ASM would all be bye bye, useless
Even if x86 was the main platform, do you know theres over 20 N/S bridge combinations currently produced?
Your average Linux or Mac geek (the market we probably would be attracting) would be pissed at:
lack of memory protection
Lack of security and privacy systems.
Unfamiliar controls, needing to learn whole new syntax (AmiDOS and derivatives)
Also, realize a 1.5 Ghz G4 beats a 3.2 GHz Pentium 4 in general performance, a PPC will give you twice (or more) performance per cycle due to its RISC and ability to execute instructions faster and more efficiently
Therefore, an x86 switch by any of those listed is HIGHLY unlikely. Before these happen, Ronald Reagan would come back from the dead, or Kennedy.
-
Also, realize a 1.5 Ghz G4 beats a 3.2 GHz Pentium 4 in general performance, a PPC will give you twice (or more) performance per cycle due to its RISC and ability to execute instructions faster and more efficiently
Tell me, what colour is the sky on the planet upon which you spend most of your time?
A 3.2Ghz P4 is in a whole other league of performance (http://www.systemshootouts.org/processors.html).
Inb4claimsofbias
-
To answer the OP, yes I do approve, in the form of MOS, but by now we must see that such discussions are fruitless, start flame wars and lead to ignorant comments like when Kolla called me a dumbass because of my opinion of the iMica.
Reasons why MOS, OS4 and Classic will probably never be x86.
Bye Bye to all your favorite apps native support, they all need big endian for native support of any kind
Making it x86 would involve twice the work, as its assembly code is a mess, and all our API, ABI and system calls taht have bits of ASM would all be bye bye, useless
Even if x86 was the main platform, do you know theres over 20 N/S bridge combinations currently produced?
Your average Linux or Mac geek (the market we probably would be attracting) would be pissed at:
lack of memory protection
Lack of security and privacy systems.
Unfamiliar controls, needing to learn whole new syntax (AmiDOS and derivatives)
Also, realize a 1.5 Ghz G4 beats a 3.2 GHz Pentium 4 in general performance, a PPC will give you twice (or more) performance per cycle due to its RISC and ability to execute instructions faster and more efficiently
Therefore, an x86 switch by any of those listed is HIGHLY unlikely. Before these happen, Ronald Reagan would come back from the dead, or Kennedy.
Have you ever heard of Aros?!?!
BTW dreamcast270mhz did you know that nothing on the dreamcast runs at 270mhz? the sh-4 cpu runs at 200mhz.
-
Tell me, what colour is the sky on the planet upon which you spend most of your time?
A 3.2Ghz P4 is in a whole other league of performance (http://www.systemshootouts.org/processors.html).
Inb4claimsofbias
So where does the dual core PA6T fall in that chart?
-
So where does the dual core PA6T fall in that chart?
I remember when the X1000 was first demoed and all the Amigans.net and AW regulars came here in droves to big it up that Karlos put up a link somewhere showing that the PA6T wasn't a huge amount quicker per clock than the G5. It's single biggest selling point was it's low power usage compared to the G5.
Either way, it'd be nomm'ed up by anything remotely recent.
-
I remember when the X1000 was first demoed and all the Amigans.net and AW regulars came here in droves to big it up that Karlos put up a link somewhere showing that the PA6T wasn't a huge amount quicker per clock than the G5. It's single biggest selling point was it's low power usage compared to the G5.
Either way, it'd be nomm'ed up by anything remotely recent.
Floating point performance of the PA6T was significantly higher than the G5 as I recall, though. Also remember that the performance was for one core. Of course, until OS4 / MOS get some sort of support for more than one core, that's a moot point.
-
Floating point performance of the PA6T was significantly higher than the G5 as I recall, though. Also remember that the performance was for one core. Of course, until OS4 / MOS get some sort of support for more than one core, that's a moot point.
I seem to recall that the only time the floating point performance really took off for the mac was in a few very select and very highly optimised benchmarks using photoshop.
Either way you'd probably struggle to get a lower performing PC that wasn't an Atom powered lifestyle PC.
-
I dunno, I'm used to wielding hundreds of GFLOPS nowadays. All CPU's seem insignificant in comparison.
-
I dunno, I'm used to wielding hundreds of GFLOPS nowadays. All CPU's seem insignificant in comparison.
All hail the power of CUDA. :D
-
The principles of north- and southbridge are in principle still inferior to a theretical modern day custom chipset design.
More flexible, yes, but also bottlenecks. Pumping up the bitrates still to overcome its deficiencies. Not something a tech head can be enthusiastic about.
Why is it inferior? The old Amiga 500 has Paula, Angus, Denise, Gary to provide chipset services. http://en.wikipedia.org/wiki/Amiga_custom_chips
In terms of chipset services, what special about the old Amiga custom chipset?
Intel Core i3/i5/i7 doesn't have the standard PC northbridge chip i.e. PCI-Express 2.0 lanes for graphics is built into the CPU.
-
I'm trying to figure out what I'm doing these days that simply could never be done on a 68060 -- seeing that it's fine for nonlinear video, etc.
MPEG2/H264 encoding in HD would be slow on the 68060. Today it's SMP and GpGPU.
-
I seem to recall that the only time the floating point performance really took off for the mac was in a few very select and very highly optimised benchmarks using photoshop.
With G5, Apple didn't factor AMD's K8 Athlon 64 i.e. refer barefeat.com's benchmarks.
-
With G5, Apple didn't factor AMD's K8 Athlon 64 i.e. refer barefeat.com's benchmarks.
Actually I was thinking prior to the G5's release. The only thing that the Mac offered in terms of performance that was anywhere near close to PCs of the day were those highly focused photoshop benchmarks - on anything else the G4 got spanked badly by both intel and AMD.
-
@matthey
You rather missed my point: Only a lazy programmer writes the smallest possible loop to do a job and then blames the architecture if performance sucks. The 68060 is forgiving, PPC is not, but the PPC will deliver far better perfomance when it's rules are respected.
Regarding move16, it also depends on how much you want your cache polluting. If you are copying large amounts of data it has many advantages. You should never assume that because most copies are small, they all will be; well written code ought to be prepared for any reasonable eventuality.
And you missed MattHey's point that a small inlined loop that can execute at the same efficiency of the big optimized loop in a subroutine makes the latter technique obsolete. The N68050 can execute an iteration of the small loop at about 2 clock cycles per iteration at 130 MHz due to improved pipelining of the instruction cycles and opcode fusion. Using move16 is only suitable for use on cacheable memory also. If you need to use it on a source or destination in Chip RAM while the custom chips are still whirring away, you may be in trouble.
The PPC requires that the cache be locked onto the loop adding additional steps to the process making inlining a disaster and brings back all of the calling overhead. The fact that the PPC is unforgiving makes it entirely unsuitable for a hobby computer anyway. Leave POWER on the big iron machines and make the hobby machine fun to use.
-
And you missed MattHey's point that a small inlined loop that can execute at the same efficiency of the big optimized loop in a subroutine makes the latter technique obsolete.
No, it does not. The original comparison to which I was replying was one of alleged 68K superiority over PPC in being able to execute such a loop effectively. The critical miss in this argument is the implication that the PPC is a poorer architecture because of this. This is, of course, complete nonsense. It's simply a different architecture with different gains and trade-offs. A non-lazy programmer will learn these and write code accordingly, not complain that the simplest possible loop is not as fast as it could be on the basis of the behaviour of a completely different architecture. Being able to do this on 68060 does not obsolete the technique at all when talking about a different CPU (the PPC) or even an earlier m68k.
The PPC can do floating point multiply add. That requires 2 instructions on 6888x/68040/68060. How horridly inefficient. It can also do bounded rotates and shifts, which require several instructions on 680x0. The 486 had bswap. Does that mean the 68K was utter pants for requiring 3 instructions to accomplish the same?
For the last time, a non-lazy programmer concerned about performance writes the best possible code for the architecture. If that's a simple loop, then great, an easy win. If he has to unroll it and align operands, then that's what he does instead.
Many moons ago, I wrote a series of tests to gather information about memory performance and got a great deal of data back regarding this very type of operation over different types of memory (system ram, chip ram, RTG ram) and on different 680x0 / PPC. FWIW, despite suggestions to the contrary, I have always found that a suitably aligned, unrolled loop even on 68060 performs better (or at least no worse) than the naive case. I just don't presently have the data to hand in order to back that up.
-
To answer the OP, yes I do approve, in the form of MOS, but by now we must see that such discussions are fruitless, start flame wars and lead to ignorant comments like when Kolla called me a dumbass because of my opinion of the iMica.
Reasons why MOS, OS4 and Classic will probably never be x86.
Bye Bye to all your favorite apps native support, they all need big endian for native support of any kind
Making it x86 would involve twice the work, as its assembly code is a mess, and all our API, ABI and system calls taht have bits of ASM would all be bye bye, useless
Even if x86 was the main platform, do you know theres over 20 N/S bridge combinations currently produced?
Your average Linux or Mac geek (the market we probably would be attracting) would be pissed at:
lack of memory protection
Lack of security and privacy systems.
Unfamiliar controls, needing to learn whole new syntax (AmiDOS and derivatives)
Also, realize a 1.5 Ghz G4 beats a 3.2 GHz Pentium 4 in general performance, a PPC will give you twice (or more) performance per cycle due to its RISC and ability to execute instructions faster and more efficiently
Therefore, an x86 switch by any of those listed is HIGHLY unlikely. Before these happen, Ronald Reagan would come back from the dead, or Kennedy.
In normal desktop benchmarks, PPE at 3.2Ghz in PS3 performs like PowerPC 970 @1.6Ghz. PowerPC ISA vs X86 ISA irrelevant i.e. what matters is the hardware implementation.
Since you made a claim on PPC vs X86 I'm restarting PowerPC vs X86.
http://www.barefeats.com/pbcd.html
Apple MacBook Pro (2.0GHz Core 1 Duo)/Apple MacBook Solo (2.0GHz Core 1 Solo)
vs
Apple PowerBook (PowerPC 7447A 2.0GHz upgrade)
vs.
Apple Power Mac (Dual Core PowerPC 970 2.0Ghz)
(http://www.barefeats.com/image06/pbcd-cin.gif)
(http://www.barefeats.com/image06/pbcd-imo.gif)
(http://www.barefeats.com/image06/pbcd-imo.gif)
We are not factoring Intel Core 2, AMD Phenom II and Intel Core i3/i5/i7 based PCs. AMD Bulldozer is already in engineering release mode i.e. same state as X1000 beta test.
http://www.barefeats.com/imcd3.html
iMac C2D/2.33 = 24" iMac Core 2 Duo 2.33GHz
iMac C2D/2.16 = 20" iMac Core 2 Duo 2.16GHz
iMac CD/2.0 = Jan 2006 - 20" iMac Core Duo 2.0GHz
iMac G5/2.1 = Oct 2005 - 20" iMac G5/2.1GHz 'iSight'
iMac G5/2.0 = May 2005 - 20" iMac G5/2.0GHz 'ALS'
(All test systems had 2GB of memory)
(http://www.barefeats.com/image06/im3-imov.png)
(http://www.barefeats.com/image06/im3-itun.png)
(http://www.barefeats.com/image06/im3-cin.png)
http://www.barefeats.com/g4up2.html
MAXPower G4/7448 Upgrade versus similarly clocked Macs
PM G5 2.0 MP b = Power Mac G5/2.0GHz "June 2003" with Radeon X800 XT
PM G5 2.0 MP a = Power Mac G5/2.0GHz "June 2003" with Radeon 9800 Pro SE
iMac CD 2.0 = Intel iMac Core Duo 2.0GHz with Radeon X1600
iMac G5 2.1 = iMac (Solo) G5/2.1GHz "iSight" with Radeon X1600 XT
iMac G5 2.0 = iMac G5/2.0GHz "ALS" with X1600 XTz
7448 1.8 MP = MAXPower Dual G4/1.8GHz 7448 Upgrade in a "QuickSilver 2002" Power Mac with Radeon 9800 Pro
7448 2.0 SP = MAXPower Solo G4/2.0GHz 7448 Upgrade in a "QuickSilver 2002" Power Mac with Radeon 9800 Pro
7447A 2.0 SP = GigaDesigns Solo G4/2.0GHz 7447A Upgrade in a "QuickSilver" Power Mac with Radeon 9800 Pro
7455 1.42 MP = Dual G4/1.42GHz 7455 "FW800" Power Mac with Radeon 9800 Pro
Quick 1.0 MP = Power Mac Dual G4/1.0GHz "QuickSilver 2002" with Radeon 9800 Pro
Quiick 800 MP = Power Mac Dual G4/800MHz "QuickSilver" with Radeon 9800 Pro
The G4 Power Macs had 1.5GB of RAM; The other Macs had either 1.5 or 2GB of RAM.
All Macs were running OS X 10.4.9.
(http://www.barefeats.com/image07/g4u_imo.gif)
(http://www.barefeats.com/image07/g4u_cin.gif)
http://www.barefeats.com/harper.html
Mac Pro 3.2GHz 'Harpertown' versus other Mac towers
Harper = "early 2008" Mac Pro "Harpertown"
Clover = "apr 2007" Mac Pro "Clovertown"
Wood = "aug 2006" Mac Pro "Woodcrest"
PM = Power Mac (last version with PCIe slots)
(http://www.barefeats.com/image08/harp_mp1m.gif)
(http://www.barefeats.com/image08/harp_cin.gif)
64bit GEEKBENCH 2 benchmark test on all Macs
(http://www.barefeats.com/image08/harp_gee.gif)
-
I voted x86 just because I have plenty of those machines laying around.
PPC, well that would be ok if I could buy an old mac and it worked but without quality software at affordable prices why bother
-
Actually I was thinking prior to the G5's release. The only thing that the Mac offered in terms of performance that was anywhere near close to PCs of the day were those highly focused photoshop benchmarks - on anything else the G4 got spanked badly by both intel and AMD.
In responds to Apple's G5 claims
http://www.pcworld.com/article/112749-8/64bit_takes_off.html
Athlon 64 vs. Apple G5 Systems: Not Even Close (chart)
Apple Power Macs did well on Photoshop, but the 64-bit AMD-based systems won handily on most tests.
AMD K8 Opteron 246 @2.0Ghz vs Power Mac G5 (two IBM PowerPC 970 @ 2.0GHz).
Benchmark Chart from http://www.pcworld.com/zoom?id=112749&page=8&type=table&zoomIdx=1
The AMD64 boxes debunking Apple's G5 claims i.e. 1 CPU vs 1 CPU and 2 CPU vs 2 CPU.
Intel Pentium IV is an easy target.
-
tough qwestion yeah right !!!
not your descion
the amiga been PPC for last decade bit late to ask know where have you been dude
hyperion cant port to x86 there rights are for ppc and why whould they want too
be commercial disaster all there work whould be pirated to hell.
hmm thats tough call not???
-
In responds to Apple's G5 claims
http://www.pcworld.com/article/112749-8/64bit_takes_off.html
Athlon 64 vs. Apple G5 Systems: Not Even Close (chart)
Apple Power Macs did well on Photoshop, but the 64-bit AMD-based systems won handily on most tests.
AMD K8 Opteron 264 @2.0Ghz vs Power Mac G5 (two IBM PowerPC 970 @ 2.0GHz).
Benchmark Chart from http://www.pcworld.com/zoom?id=112749&page=8&type=table&zoomIdx=1
The AMD64 boxes debunking Apple's G5 claims i.e. 1 CPU vs 1 CPU and 2 CPU vs 2 CPU.
Intel Pentium IV is an easy target.
Tbh I didn't really follow the G5 much beyond it's launch. It's interesting to see that even afterwards, whilst some of the gap between PPC and x86 was gained, it was still on the trailing edge of performance, except, as before and as you noted: Photoshop.
RE the PIV, a power hungry, hard to cool beast it may have been, but it could still put the kosh to a G4 or a G5.
-
Tbh I didn't really follow the G5 much beyond it's launch. It's interesting to see that even afterwards, whilst some of the gap between PPC and x86 was gained, it was still on the trailing edge of performance, except, as before and as you noted: Photoshop.
RE the PIV, a power hungry, hard to cool beast it may have been, but it could still put the kosh to a G4 or a G5.
Especially a HT enabled one running BeOS. ;)
-
Tbh I didn't really follow the G5 much beyond it's launch. It's interesting to see that even afterwards, whilst some of the gap between PPC and x86 was gained, it was still on the trailing edge of performance, except, as before and as you noted: Photoshop.
RE the PIV, a power hungry, hard to cool beast it may have been, but it could still put the kosh to a G4 or a G5.
?? The chart shows AMD64 boxes beating G5 systems in photoshop...
PowerMac G5 (two PPC 970 @ 2Ghz, two cores)
18 sec for 50 MB test
51 sec for 150 MB test
Polywell Polystation Two (K8 Opteron 246 @2Ghz, two cores)
17 sec for 50 MB test
47 sec for 150 MB test
-
No, it does not. The original comparison to which I was replying was one of alleged 68K superiority over PPC in being able to execute such a loop effectively. The critical miss in this argument is the implication that the PPC is a poorer architecture because of this. This is, of course, complete nonsense. It's simply a different architecture with different gains and trade-offs. A non-lazy programmer will learn these and write code accordingly, not complain that the simplest possible loop is not as fast as it could be on the basis of the behaviour of a completely different architecture. Being able to do this on 68060 does not obsolete the technique at all when talking about a different CPU (the PPC) or even an earlier m68k.
The PPC can do floating point multiply add. That requires 2 instructions on 6888x/68040/68060. How horridly inefficient. It can also do bounded rotates and shifts, which require several instructions on 680x0. The 486 had bswap. Does that mean the 68K was utter pants for requiring 3 instructions to accomplish the same?
For the last time, a non-lazy programmer concerned about performance writes the best possible code for the architecture. If that's a simple loop, then great, an easy win. If he has to unroll it and align operands, then that's what he does instead.
Many moons ago, I wrote a series of tests to gather information about memory performance and got a great deal of data back regarding this very type of operation over different types of memory (system ram, chip ram, RTG ram) and on different 680x0 / PPC. FWIW, despite suggestions to the contrary, I have always found that a suitably aligned, unrolled loop even on 68060 performs better (or at least no worse) than the naive case. I just don't presently have the data to hand in order to back that up.
I know it isn't 68k nor PPC but all this talk got me reminiscing about the old days and this wonderful article in particular. :)
http://nondot.org/~sabre/Mirrored/GraphicsProgrammingBlackBook/gpbb7.pdf
Enjoy! :D
-
The chart shows AMD64 boxes beating G5s systems in photoshop...
FFS... Yes, I know, I read it.
What I said was and I quote:
still on the trailing edge of performance, except, as before and as you noted: Photoshop.
I didn't say the G5 beat anything, just that in that particular test, it didn't perform like last years bargain bin part like it did on every other test. The numbers between the two things are in real terms only a gnats tadger apart.
That is all.
-
For any of the current "amiga" OS's, are there any practical difference between 1 and 3 ghz ?
Will an I7 run Deluxe Paint V faster than a 68060 ?
Will Quake run better on a G5 than a G3 ?
Does it make a difference for Final Writer 97 if I have 1 or 8 gigs of RAM ?
-
For any of the current "amiga" OS's, are there any practical difference between 1 and 3 ghz ?
Will an I7 run Deluxe Paint V faster than a 68060 ?
I would expect an i7 to be able to emulate AGA significantly faster than the actual hardware. Since that was the major bottleneck to performance for Deluxe Paint, not the processor then the answer is yes, obviously.
Will Quake run better on a G5 than a G3 ?
Faster, yes, better? Depends.
Does it make a difference for Final Writer 97 if I have 1 or 8 gigs of RAM ?
Obviously not, although at this point you're verging dangerously close to strawman territory.
-
Obviously not, although at this point you're verging dangerously close to strawman territory.
I'm being ridiculous on purpose.
When the software we have is between 10 and 15 years old in many cases, it becomes somewhat moot if the hardware is bleeding edge or not.
A while back, maybe a year ago, when asking some questions about Morph OS and what apps were available, I was directed to Final Writer 97.
-
I'm being ridiculous on purpose.
When the software we have is between 10 and 15 years old in many cases, it becomes somewhat moot if the hardware is bleeding edge or not.
A while back, maybe a year ago, when asking some questions about Morph OS and what apps were available, I was directed to Final Writer 97.
It's all about OWB 1.10 and Google Docs now! ;)
-
PPC seems dead in that there are no inexpensive machines with a descent bus speed that use PPC CPU's. Besides so many of my PPC games don't work in MorphOS anyhow, thus defeating one of the main purposes of my purchase. So I've little faith in the future of PPC in that respect also, though who knows, maybe these compatibility issues will some day be resolved.
The 680x0 line is great, I'd love to see the Natami succeed since running MorphOS and AROS are great and all, but not quite the same thing as a native environment.
As for AMD. Sure why not! Now a days it doesn't seem to matter what CPU you got, as they all seem very well rounded now a days. It's fast, it's cheap, go for it!
BOttom line, I want it all!!!
-
@Kthunder
What do you take me for? Of course I know that, my 270 means its OCed 70 mhz (I really don't have one OCed that high however) because thats teh highest stable speed i've seen w/o water cooling.
@Thread
I can see my arguements mean nothing, I am sorry to say that today I will not be joing you all in hell. Please send Intel my regards, that I'd rather stay outside their machines. Fate forbid the Amiga community suffers BeOs's fate, I will not be drawn.
Please, someone kill my account. For real, I'm tire of endless debates with fuck tards.
-
I can see my arguements mean nothing
A breakthrough!
Please, someone kill my account. For real, I'm tire of endless debates with fuck tards.
I believe the best way to prevent yourself from posting is to change your password to something you won't remember.
-
@Thread
I can see my arguements mean nothing, I am sorry to say that today I will not be joing you all in hell. Please send Intel my regards, that I'd rather stay outside their machines. Fate forbid the Amiga community suffers BeOs's fate, I will not be drawn.
Needs more ham and over dramatization.
Please, someone kill my account. For real, I'm tire of endless debates with fuck tards.
Moar dramallama..
-
When the software we have is between 10 and 15 years old in many cases, it becomes somewhat moot if the hardware is bleeding edge or not.
It's not an issue of being "bleeding edge", just not getting ripped off for 6+ years out of date hardware.
But there is a larger issue I think that really, really needs to be addressed.
Amiga is a retro hobby, treat it as such - see Minimig for how to do it right.
The whole AmigaNG thing is 10 years or more past being a realistic possibility and for everyone involved it's time to set it down as such.
I think the community really needs to come to terms with this.
-
It's not an issue of being "bleeding edge", just not getting ripped off for 6+ years out of date hardware.
But there is a larger issue I think that really, really needs to be addressed.
Amiga is a retro hobby, treat it as such - see Minimig for how to do it right.
The whole AmigaNG thing is 10 years or more past being a realistic possibility and for everyone involved it's time to set it down as such.
I think the community really needs to come to terms with this.
I absolutely agree. Minimig, natami if it ever materializes and at the promised cost, building some new accelerator boards or other nifty bits and pieces, thats what we got and how the community can be served.
-
Amiga is a retro hobby, treat it as such - see Minimig for how to do it right.
The whole AmigaNG thing is 10 years or more past being a realistic possibility and for everyone involved it's time to set it down as such.
What are you talking about? Ten years ago it wouldn't even have been a possibility, let alone a realistic one; now, we're finally starting to see some progress towards a more powerful Amiga-compatible (note the emphasis on "compatible," as in "not just a generic PPC/x86 system that's adopting the Amiga name?") The market doesn't have to be split binarily between "direct recreations of original hardware with no extra power or features" and "bog-standard x86 clone system running software that's somewhat modelled on an older OS people liked."
Assuming that the people behind projects like NatAmi do see them through to completion, and transition them to a business sanely (where "sane" is defined as "not charging $2300 for a 2GHz computer,") it can work. We live in a world where $50 will buy you a clone of a game console that used to cost $200-300; producing an affordable boosted-but-not-bleeding-edge clone of the Amiga is perfectly within the realm of possibility.
-
I just want a system that will run all of the classic games and apps natively, so a perfected 68k core is sufficiently powerful. For me, binary comapatibility with classic Amiga software is power.
-
Since you made a claim on PPC vs X86 I'm restarting PowerPC vs X86.
You're comparing 2003 machines to 2006 machine and are what - surprised?
There are plenty of benchmarks on this, but x86 are stronger in some areas (branchy integer stuff) while PPCs are better in different areas FP and especially Altivec.
Apple were very clever with the timing of their switch because it meant they went from lat year's PPCs to next years x86s and of course the x86s were faster.
Actually according to the benchmarks published at the time there wasn't that much of a difference between them, in fact the G4s could rip music faster than the first mac x86s.
It was only after the Core2Duos appeared that a clear gap emerged, but by then development of desktop PPCs had already stalled.
-
On the question of is PPC viable for the future, well I'm sure they'll do for now but after MOS supports the G5s and the X1000 eventually ships, where next?
PPCs are still moving forwards but their market is exclusively embedded these days.
If you want to stay on PPC you have to accept that you are going to pay a lot of money for machines that will be beat by x86 and also by even cheaper ARM machines.
The fastest Amiga this year is likely to be the Sam460 which with OS, memory etc will cost in the region of £800 or more*. Today I can get a Toshiba AC-100 10Z smartbook with a dual core 1GHz Cortex-A9 for £250**.
*based on an estimate from Amigans.net
**in stock at Amazon.co.uk
-
You're comparing 2003 machines to 2006 machine and are what - surprised?
There are plenty of benchmarks on this, but x86 are stronger in some areas (branchy integer stuff) while PPCs are better in different areas FP and especially Altivec.
Depends on the FP workload. Did you miss Cinebench benchmarks? SSE is missing some non-desktop application targeted SIMD instructions.
AMD K8 already has 128bit wide FADD SSE and built-in memory controllers. Each of K8's FADD, FMUL and FMISC has it's own instruction issue ports.
Apple were very clever with the timing of their switch because it meant they went from lat year's PPCs to next years x86s and of course the x86s were faster.
Actually according to the benchmarks published at the time there wasn't that much of a difference between them, in fact the G4s could rip music faster than the first mac x86s.
One problem with testing CD ripping speeds is the speed of the optical drives involved.
Did you factor in iMovie HD benchmarks?
Apple MacBook Pro (2.0GHz Core 1 Duo)/Apple MacBook Solo (2.0GHz Core 1 Solo)
vs
Apple PowerBook (PowerPC 7447A 2.0GHz upgrade)
(http://www.barefeats.com/image06/pbcd-imo.gif)
It was only after the Core2Duos appeared that a clear gap emerged, but by then development of desktop PPCs had already stalled.
Have you forgotten AMD64? The topic here is not about Apple's switch to Intel i.e. the topic is PowerPC vs X86(includes AMD64)
-
(http://30.media.tumblr.com/tumblr_lac9fqYX581qz4d4bo1_500.jpg)
-
What are you talking about? Ten years ago it wouldn't even have been a possibility, let alone a realistic one; now, we're finally starting to see some progress towards a more powerful Amiga-compatible (note the emphasis on "compatible," as in "not just a generic PPC/x86 system that's adopting the Amiga name?")
What am I talking about? 10 years ago PPC was still broadly speaking a contender. It had active development behind it for the desktop market. The Amiga community was ten times or more the size it is today, we still had large numbers of commercial grade apps being developed for.
By 2003 that was all gone. All of it.
The market doesn't have to be split binarily between "direct recreations of original hardware with no extra power or features" and "bog-standard x86 clone system running software that's somewhat modelled on an older OS people liked."
This is exactly the kind of nonsense that I'm talking about.
The desktop market is saturated. It is mature and unless you have a bank balance not unlike either Sony or IBM, you are not going to make a dent into it. There is no place for Amiga outside of the retro set.
Assuming that the people behind projects like NatAmi do see them through to completion, and transition them to a business sanely (where "sane" is defined as "not charging $2300 for a 2GHz computer,") it can work.
Within the hobbyist sense maybe, as a viable business, not so much. It is doubtful the developers will ever sell enough to recoup the development costs of the natami. That's not to say however that they won't make a few quid out of it.
We live in a world where $50 will buy you a clone of a game console that used to cost $200-300; producing an affordable boosted-but-not-bleeding-edge clone of the Amiga is perfectly within the realm of possibility.
Who the hell said otherwise dingus? But a Natami is in no way going to be a contender outside of the retro crowd. As a piece of technology it is interesting and will no doubt have some pull at the geek crowd. As a mainstream desktop? Hahahah. My Tocco Lite feature phone packs more of a punch.
-
One thing everyone seems to forget is availability of CPUs and innovation cycles. The x86 chips have very short innovation cycles and you can´t get the same kind of chip for more than a couple of years. A small platform however has to sell the same board for a much longer time to get back the costs of development. So unless you have the power to redesign your board every 2 years at least, you should probably choose a CPU that can be manufactured later in licence (ARM) or something that has longer cycles (maybe PPC).
If you continue on this thought, you will notice that drivers for other components suffer from the same problem, and that the main reason Linux is ahead of other alternative PC operating systems is that they get the drivers faster than anyone else.
-
I voted for x86.
Omega Space Protons