Power Mac 'Quadra' G5 quad processor coming soon?

Well I for one would like to see such a machine, but I doubt that it is coming. Quad G5s would just suck your bus dry.

It seems odd that Apple would revive the quadra name since they have done nothing else along these lines with the G4's or G5. More likely, Quadra would be a tongue in cheek codename (kinda obvious what it is) and they would just call such a beast the "PowerMac G5 Workstation/small office heater".

Wouldn't it be more plausible to see a dual processor - dual core g5
instead of an actual 4-processor ubersystem? And with that new
hyperthreading technology (not sure if this is the correct name), it
would act like 8 processors.

Dual Cores won't make it into the 970 line for at least one more revision. I think that most of the 980 romour s(now 975?) stated it would still be a single core chip. However they could build Quads Apple could build quad processor systems with the current line of chips from IBM.

The thought of it is sucking my 'bus' dry right now.

No it wouldn't, actually. Each 970 has its own point-to-point FSB connection to the system controller. The tough part would be building a system controller with 4 FSB ports, and a memory subsystem that has a hope of keeping up.

Much more likely, in my opinion, is a dual core 9xx variant replacing each of the chips in the current machine. I don't put any stake in any of the processor rumours so far, but I don't think a dual core chip is impossible this year. Whether it shows up depends mainly on where IBM and Apple's priorities are.

...and what would be the cost of FOUR processors ? Price points are right out the window with four chips. How much does a 970 cost (90nm) just for the processor....? Dual core sounds more plausible.

Goooo so expensive!

We don't know, but there have been several rumors that they're not much more than G4s. Even if a quad G5 cost $5000, it would sell.

I don't believe this rumor, but I don't think processor price is the obstacle.

Well, I might get one for myself after begging my accountant, but my employees would just have to cope with dual 2ghz machines. Five grand is moving toward pro-only, and then only the prosperous pros. I don't think sales numbers would stay where they are if we saw PMs at more than $3499... the current price points are steep for most, but doable. I don't think there is much left to add and keep people buying top-end PowerMacs.

Don't give Fred any ideas.

Try $10,000 and up...most likely.

HIghly unlikely.

My guess is portables.

The 970FX is probably cheaper than the G4 -- it is roughly the same transistor count, but on a 90 nm process instead of Moto's poorly yielding 130-150 nm process. $250-500 x 2 added to the price of the current high end Mac. I suspect a lot of pros would jump on it. Biggest problem would likely be getting enough processors to make all those machines!

On 300mm wafers vs. 200mm.


I remember a thread where we hashed out how Apple could go from 2 to 4 to "8" processors without going into expensive NUMA architectures: First two CPUs. Then two dual-core CPUs (or two SMT CPUs). Then two dual-core SMT CPUs. And the basic design of the motherboard never has to change significantly. It's still two chips and two busses to the controller ASIC.

We can get to the "4 CPU" stage this year, I think, and the "8 CPU" stage when IBM moves to 65nm in 12 months or so...

sure, you could...but what would feed these beasts? the current implementation of the elastic bus is stuck at 1.1GHz (according to IBM). so how do you keep 4 logical processors, each running at 2+GHz fed on a single 1.1GHz bus? and beyond the bus, RAM, and most significantly, HD?! I seriously think the biggest advances made in "consumer" computing in the next couple of years will revolve around storage performance. the PC-DIY crowd has already seen the light of RAID. far better performance payoffs than OC'ing a P4. add to that advances in SATA command queueing, etc. i just think the industry is starting to realize the growing bottleneck created by mass storage. either mass storage needs to become significantly faster, or the systems-model we've been using for years needs to be revamped to better address the limitations of mass storage.

I'm not so sure that feeding the beast will be all that difficult. The extra processor mean more cahce and chae that is used more effectively as you maintian a greater chance of previous code being in the cahces after a context switch. Now obviously not all programs are chewing through that much code but the same goes for data. Add a little intelligence to your scheduling algorithms and it may be possible to keep a process on a processor undestrubed by any context switches.

In the case of logical CPU's that are the result of SMT you do realize that the secondary thread may only see 30% or 40% of the performance of the primary thread so there is less demand on band width than may be first implied. The threads are not equal. It is interesting to see what the linux world has done with their kernel to make use of SMT. When SMT first came out SMT was a fairly negative feature, now after a bit of work on the kernel we are starting to see real benefits. While not wanting to go into a great deal of details part of the problem was somewhat bandwidth related due to cache issues. Just having a scheduler that maintains processes on a specific processor greatly reduced the need for cach refills do to processes moving around the machine.

So while I don't disagree that feeding the beasts could be a problem, it is not a problem that can not be dealt with. AS to advances for consumer computing I really believe that pervasive multi processing is the wave of the future. For some applicaitons it is the only way to grow future performance. For the very consumerish games market, SMP or similar multiprocessing arraingements are the only way for developers to extend their franchise in new directions.

There isn't a single processor implementation from anybody (IBM, AMD, Intel or xyz), that will be available in the near future, that can have a significant impact on certian markets such as Games, medical research, science research, FEM and othe engineering applications. It will be a long time before the vast majority of the people are satisfied with the computer that sits on their desk. The reality is that software quickly out strips the capability of a machine, thus requiring faster processors. The only good thing is that the transisition to 64 bits gives us some breathing room.

Dave

Feeding the beasts will be an issue, but I don't think the FSB is the problem. In the current PowerMacs the combined FSB throughput is somewhere around 14 GB/sec, but the dual channel DDR400 memory system only achieves around 6 GB/sec (on a good day). That is a lot of improvement required in the memory subsystem before the FSB is again the bottleneck.

IBM claims that their SMT implementation for the POWER5, on their test suite, runs 2 threads at full speed. Depending on the nature of the code, this is completely believable. Given how many threads are running on a typical MacOS X box you might find that SMT is quite a win. A few things don't SMT well (carefully coded AltiVec algorithms, for example), but IBM's SMT implementation has features to help ensure that this code gets a processor to itself.

Apparently Darwin's kernel already does processor/thread affinity, so future SMT and shard cache dual cores will benefit from that.

It won't be the first quad processor Mac however, DayStar came out with one years ago using four 604 processors:


From Low End Mac, this description

In more recent news Architosh had a Pro 3D user survey that found they "overwhelmingly want Quad Macs".

With Apple's high end software ambitions (Shake, Logic, FCP) a quad workstation would be a logical extension of their line.

But that's daystar not Apple.


What would the point be of having a Quad processor Mac without a Pro 3D graphics card?
I was one of the voters who voted yes to that survey, and I think it's safe to assume that the point I (and everybody else) was making when the votes were made was they (PowerMacs) still need to be faster. They are still overpowered by x86's built to be workstations. We need to be at least equal, or close in some areas, and faster in rendering, or something to have at least a semi competitive setup.
Another thing is historically speaking the actual purpose of a quad processor computer is questionable as a workstation at best. Most Quad CPU systems are mainly for the server market, and how much performance increase can be expected from such a machine anyway? If Apple intended to build a workstation that was a superior 3D, and Rendering machine there would likely be a major motherboard revision to accomplish this, and it would still need the one thing it truly lacks the most. A pro 3D graphics card. I've already been talking my own ear off in another thread about this, but it's totally the missing link of an increase in future Macintosh sales. Where was the graphics card survey. If you want to do 3D that is what's truly needed because without it a quad processor system is pretty useless.

Well, how about these then:

OMFG... those concepts ROCK.

You're hired.

The only difference between the "pro" cards and the "gamer" cards at this point is different drivers, slightly different firmware, and several hundred dollars. The drivers for consumer cards are more geared toward games.

But the Apple situation is different. You get a full OpenGL implementation regardless, and (as far as anyone can discern) unrestricted firmware. So your Radeon is a FireGL, and your nVIDIA is a Wildcat, for all that it matters. There used to be a real difference, but at this point it's mostly artificial, or restricted to software.

There are other things that will need to be sorted out to get the Mac up to full par in 3D, like someone throwing a lot of money at Omni to do a proper port of Maya. The hardware's pretty much already there.

Unless you want to spend several hundred dollars more on the same thing with a different name just to say that you have a "Wildcat".

#1) you are really over estimating what OpenGL will do compared to the correct firmware, and drivers. Secondly that's a bad example using Nvidia, and wildcat. Wildcats are sh*t. Unless that's what you were getting at. And 3rd. Refer to #1.

Amorph's point is perfectly valid. everyone in the PC gaming/DIY community knows that the only differences between the "Pro" and "Gamer" cards are the driver, firmware, and to a small extent, clockspeed. but it's the "Extreme Gamer" cards that have the higher clockspeeds, at the risk of slightly lower stability/image quality.

Basically, ATI spends some time "qualifying" a consumer gaming card with rock-solid firmware and drivers on specific 3D and high-end graphics/CAD/etc. programs.

Now, there is a valid complaint that there is sometimes a later release for the "Mac version" of the newest video cards, and that there are never as many flavors of cards to choose from. But this is far from Macs not having 'pro' graphics cards.

That said, let's all hope that ATI (and even nVidia, I guess...) start hiring a couple more people to develope the Mac drivers and firmware. Maybe Apple can (has been?) help out, offering up some of their firmware/driver specialists in exchange for a bigger commitment from ATI et al.

Or, maybe the growing darwin/opensource community will devote some personal days to porting/writing good drivers? not gonna hold my breath.

Where do the AGP/PCI cards go?

#1) ATI sucks, #2) refer to #1), and #3) That may be how ATI's cards work with CAD (woo hoo) but as 3D as CAD is it's not the same as having full Maya compatibility which ATI has never had AFAIK. Which is why I keep saying refer to #1. For the most part ATI is just making gaming card's, and Nvidia's Gaming cards are still out performing them. If you haven't noticed DOOM3, and UT2K4, are both recommending the GeForce FX to get the best possible performance. So why do you say "let's all hope that ATI (and even nVidia, I guess...)"?
Do you not want a better performing graphics option available in your Mac?

As a Googler? I can't take any credit for those designs, I should have posted this LINK to theapplecollection.com to give proper credit and allow browsing that cool site.

And Onlooker, from your postings in the Mac video card thread what you need (by WWDC) is a high end pro card with complete Maya compatability. (or is that Maya complete?).

It would seem to me, that if Apple did decide to offer a high end quad workstation (build it and they will come), they would also assure that it came with just such a card. Even if they had to build, and support it, themselves.

Surely such a pro-level graphics card would be useful for more than Maya. I'm sure Shake and FCP could use it, even if Logic would not. Basically, if the premise of this thread comes to be (ie a quad Mac), then the graphics card for pro 3D applications will come with it, at least as a BTO option.

Whit that attitude I suspect that your one of those people whom are completely satisfied with the level of performance you are currently getting from your Performa. I mean really why would anyone need more memory, faster processor or a bigger harddisk!

You seem to mis one importatn point here, there are whole classes of applications that need more CPU power but don't give a rats behind about the GPU. To sum it up your assertion is extremely self centered and at best questionable.

If there is any truth to the above statement then why did you make the one previous about the quad Macs?

Yep no doubt here at all, so agian what would be the point of quad processors?

Complete and utter ignorance. Multiprocessing is the wave of the future. Sure there are specific applications that don't make good use of SMP, but with OS/X the system always will. On the other hand a workstation will often be executing applications that can be coded for parallel execution and would benefit from extra processors. The optimal number of threads will vary from application to application but that is really no big deal, it does today even for applications running on single processors.

Your statement holds no water and flies in the face of the direction of the industry. SMT and dual core processors are in our future. I would not be surprised to find that in a year or two all PowerMacs will have at least 4 logical CPU's with possibly as many as 8. There is no other choice with respect to scalling performance and making use of resources.

Just what do you mean by the server market? Some of those machines may be the heart of a compute server. Some a database server and who knows what the rest will be doing.

In any event performance of such machines will be determined by the problem domain and not the benchmark posse. As always it is a question of software, if you have a problem that like processors and processor time then you will have a winner in a quad machine. Of course that is a simplification, given two differrent quad processors, application performance could vary greatly depending on the hardware implementation. To put it mildly without a context your question has no value. It can not be answered without hardware and software to take advantage of the hardware.

One has to realize that at this point everybody benefits from a dual SMP configuration. If it wasn't for intels marketing just about everybody would be selling SMP for the desktop on the i86 side of the fence. The reality of Apples sales figures with respect ot the SMP G5's pretty much pinpoints the opinion of Apples pro users. My suspicion is that we would see a rather fast up take with Quad processor PowerMacs and a rather quick adjustment of the software base to make use of them.

First of all; Apple builds general purpose computers, some of which have been adopted by the graphics industry. The longer it takes for the rev B G5's to come out the more I believe that we will see a major rev of the machine. It might be 3GHz or it might be PCI-Express to the GPu. Or if we are really lucky both.

It is the nature of the business to be continually reving the hardware. This should be no surprise to you or anybody else.

So why did you pollute this thread? Not to be unkind but everybody wants to see a faster Mac. The GPU is just a small part of the issue. I mean really Apple has been able toincrease the real performance of the G5 with every rev of the OS. They have a lot of work to do yet, the GPU and its associated drivers is just part of the issue.

Besides are you really that sure that Apple isn't currently shipping pro level drivers for its cards?

Again very self centered thinking. There are many people who would love to have a affordable quad processor anything on their desk. Yes MAC or not, reasonably priced hardware would sell without consideration for the graphics card.

Sure there is a subset that would love faster GPU's but I suspect that Apple is working on this right now. The world is abotu to change with repsect to GPU's, Apple could very well lead the pack soon.

Gee Wizard69, I wish you would get thye hang of quotes and bolding in your posts. Your post was very hard to read at all bold. Seems like you were SHOUTING at Onlooker. And I guess you were, but lighten up on him, he has a specific use for a high end graphics workstation and to accomplish his needs it must have a high end graphics card.

If Apple were to release such a beast, why would they leave out a major segment's (3D & Maya) needs? He has a valid point and in the context of this discussion it is relevant.

Since this is all speculation anyway, why not speculate that SGI's willingness to sell Alias, and with it Maya, as evidenced by recent statements about a mysterious "Investor group" coming from SGI itself may lead to Apple's acquisition of Alias.

Should this happen, Apple will definitely want to offer a complete solution for a graphics workstation. Even if they don't buy Alias, they would want one (graphics workstation) for Shake anyway.

Sure there are many uses for a quad machine that wouldn't require much of a graphics card, but there are many uses that would.

The Mac version of Maya is a complete disaster.

* It is not a Mach-o app.
* Because of that plugin development is a nightmare
* It is so slow even on a dual 2gig machine that mere incompetence can't possibly explain it
* It is not just buggy, but filled with numerous simple and easily fixed in five minutes type UI bugs

I can only hope that the reason for the sorry state of the current Mac version is they are working on a proper Mach-o app and the current version is no longer being worked on.

Instead of quad G5s, I would love to see something like mini-xservers for artists. None of the heavy stuff needed for a real server. Just enough for rendering jobs - CPU(s),memory, and darwin. Have your own mini-renderfarm 'just work' when you buy one and connect it up to your current Mac and Maya or other packages. Need more power, just pickup another node and plug it in to your current stack.

Sorry to hear that, but its not a big surprise. Maya is a huge package and to do it justice on a new platform would require a big engineering team... and Alias is not in particularly good shape so funding a big team for a platform with a small market percentage just doesn't make a lot of sense. The best hope for a quality version of Maya would be for Apple to buy Alias, but that would put the future of Maya on the PC into serious question and they might find a lot of users bailing. The best option might be for Apple to fund the Mac port of Maya directly.

Or perhaps buy Alias through a proxy investment firm, and have it a wholly owned subsidiary like FileMaker is. This might keep the Windows user base from bailing until a quality port of the code could be made. After that a pricing structure that favors the Macintosh could be rolled in.

The Mac version of Maya is a complete disaster.

* It is not a Mach-o app.
* Because of that plugin development is a nightmare

I can't tell you there are not a shortage of Maya plugins that are noted as Mac compatible. But, every Linux plugin, and Mel script from Highend3D that I have used works with Maya for Mac OS X. And I have plenty. I guess not many people tried it. I figured it couldn't hurt. You can even use the assistant_brushes_complete from Alias that are now noted as windows only, but used to say IRIX from Alias.com from the downloads section. They all work fine... I have not gone through and Guinea pigged every plugin in existence for Linux, and IRIX. I only tried what I needed, and they all work. There is a Sub Surface Scattering Linux plugin that works quite nicely with Mental-Ray.


Here it is: I'll reply to wizard69's post, or some of it. Otherwise it would take all day, and start a huge flame battle, or something. I'm just going to blow off singling out his comments one by one, and let that go. But to sum it up simply. In my mind it all comes down to what Apple has entered, what companies they bought, and how they are positioning themselves. My statements were not meant as selfish thoughts as you made it out to be. I was making a realistic assumptions based upon facts as to where Apple needs the most help in performance. I'm not worried about the performance of IBM's processors catching up with the x86'. I know they will very soon. But back to what I was saying: The Mac has always been tailored towards graphics oriented users, and a High Performance 3D graphics card option just was not a completely self centered thought. We know Pixar is working on RenderMan, and it's still on it's way. Actually It's probably been done for a while, but when RenderMan for Mac is fully unleashed you know Steve Jobs will have it rendering some of the coolest stuff imaginable for us, and he knows the whole Pro graphics community, and 3D production houses will be watching very closely. I can't imagine him using anything without using Maya Unlimited. RenderMan is the tool to have. There are no contenders, and there is no second place behind RenderMan. Second place is just who the first looser is. Seriously... With all the great companies Apple has acquired with all the fantastic pro level software they have, and what I assume is soon to be available from others close to Apple. I just don't see them lagging that far behind in anything other than a Pro 3D card. It just seems like a natural thing to biatch about because they should have gotten to it sooner.

I was reading about Microsoft's development kit for their Xbox 2.

The current version of the Microsoft Xbox 2 SDK is an Apple POWER Macintosh G5 computer based on two IBM POWER PC 64-bit microprocessors. Just like the latest Macs, the Xbox 2 SDK is equipped with ATI RADEON 9800 PRO graphics card. Microsoft decided not to wait for ATI Technologies to supply the next-generation R420 VPUs that resemble Xbox 2 graphics fairly more than the R350 chips.

Wouldn't mac users benefit with better ATI drivers because of this new SDK?

But are the supposed drivers not written for a version of Windows NT? I say supposed because all of this information comes from the Inquirer. Their track record is worse than Mac OS Rumors.

The problem with writing plugins for Maya on OS X is that they require an exact version and build number of CodeWarrior. And then once you have the exact CW version you have to then manually patch the CodeWarrior libraries and rebuild them.

The number of people who are running OS X and still have a copy of CodeWarrior, and the specific version, is pretty small.

Which codewarrior version is needed? I might have it. I have 8.2, or close to that. It's been a while sense I've tried my hand at coding It would be nice if we could use xcode though. That would freaking blow people away.

Which version of Maya you have determines which version of CodeWarrior you need. Maya 5 requires CodeWarrior 8.3.

Mach-o and gcc would solve the mess.

I have Maya 5.0.1, and CodeWarrior 8.3 LOL. I had no idea!