or Connect
AppleInsider › Forums › Mac Hardware › Future Apple Hardware › Xbox 2 specs leak
New Posts  All Forums:Forum Nav:

Xbox 2 specs leak - Page 3

post #81 of 121
I could be wrong, but as I understand it, the cores themselves don't require the bulk of the transistors. So, 3 cores wouldn't in an of themselves drastically increase transistor counts. Maybe registers, cache etc. might balloon a bit though and those little itty bitty wires connecting stuff may increase somewhat(more layers of silicon?).

Someone with more knowledge please correct me, I sure am out on a limb here with my limited knowledge.

Quote:
G-News
I don't see that Xbox2 coming in at less than 400$ and that is a VERY steep pricetag for a console,..

maybe they'll add some surprise additional capabilities?
just waiting to be included in one of Apple's target markets.
Don't get me wrong, I like the flat panel iMac, actually own an iMac, and I like the Mac mini, but...........
Reply
just waiting to be included in one of Apple's target markets.
Don't get me wrong, I like the flat panel iMac, actually own an iMac, and I like the Mac mini, but...........
Reply
post #82 of 121
It also just occurred to me that the 970 uses the elastic bus @ 1/2 processor speed. Makes me wonder about high speed external ram with an on die memory controller alleviating some of the on die L1 / L2 cache. Then again I'm just guessing and tossing out ideas.
just waiting to be included in one of Apple's target markets.
Don't get me wrong, I like the flat panel iMac, actually own an iMac, and I like the Mac mini, but...........
Reply
just waiting to be included in one of Apple's target markets.
Don't get me wrong, I like the flat panel iMac, actually own an iMac, and I like the Mac mini, but...........
Reply
post #83 of 121
Quote:
Okay, but you might want to take into account that I'm the one under NDA.
(bad assumption that a 3 core chip would cost 3 times as much, by the way)

That a very easy claim to make without any way for us to prove or disprove it.
I could be equally under NDA and nobody could tell for sure if it was true or not. Either throw out bits you can and may, or leave it.

It's about an equally bad assumption as to thinking a single chip only costs 200$, that price decay will be 60% and that the move to 65nm won't involve additional heavy costs on IBMs side, which will be rolled off to the customers in one way or the other too.
Matyoroy!
Reply
Matyoroy!
Reply
post #84 of 121
Quote:
Originally posted by rickag
It also just occurred to me that the 970 uses the elastic bus @ 1/2 processor speed. Makes me wonder about high speed external ram with an on die memory controller alleviating some of the on die L1 / L2 cache. Then again I'm just guessing and tossing out ideas.

Like 3.2GHz XDR DRAM?
post #85 of 121
Well you can believe what you want and the referenced material is a rumor, but I think you have to ask your self how is MS going to compete agains the other game station makers. Sony is pursuing Cell for one very good reason, it needs options to deliver the processing power required for the next generation of games. Ms has to be able to compete in the enviroment it plays in, if the other players are going the high performance route then MS has no option but to pursue performance.

But I do wonder why people believe that the 970 is an inherently expensive processor. Just take a cruise over to price watch and look at the prices on the Athlons and similar processors. The 970 is a smale chip to begin with, its smaller agian at 90nm and will likely be even smaller at 65nm. Or maybe it will grow again as more features are add. The point is that it is a small chip. The prices you see on pricewatch are retail, I'd be very surprised to find Apple paying much more than a $100 for each of its 970's

Now I could be completely wrong about Apple and its arraingements with IBM, but the fact remains that the 970 has little reason to cost a great deal. It is realtively cool and prints to a reasonable chip size, if the price is much higher that $100 it is probally a result of recovering R&D expenses.

Yeah three chips sound a bit odd but it is MS competition that will be driving what is in the box. Remember this is a next generation device, it is not a platform for yesterdays gaming knowledge.

Dave


Quote:
Originally posted by G-News

That's about all we know for sure.
Now make of that whatever you want. Some will make it a 3 core, SMT enabled monster PPC 976 cluster with ATI R500 core and the option to bake bread while playing, luring millions of readers to their website, while others might take a more traditional (and imho sensible) approach and look more towards a mix of a PS1-Gamecube design with custom PPC chips working together with a custom ATI chip to provide excellent performance for specific uses (which is what games are all about). I'm sorry if I'm the only person not seeing a 3 core SMT PPC 976 solution as a "specific use solution". A brute force approach, rather, uneconomic by definition, expensive and overkill.

And everyone who thinks MS is going to spend an extra 1000$ on an Xbox2, just to satisfy the customer, hoping to make up for it in game sales, simply has no clue, really.
post #86 of 121
Quote:
Originally posted by G-News
That a very easy claim to make without any way for us to prove or disprove it.
I could be equally under NDA and nobody could tell for sure if it was true or not. Either throw out bits you can and may, or leave it.


Well I'm not under NDA and I'm not even involved in the industry. But I can tell you that the cost of a dual core processors will not double.

That would be under any situation but is even more of a truth if the information I have gleamed about the pending dual core processor is true. Apparently IBM has taken the approach of having the dual cores share the L2 cache. There are advantages and disadvantages here of course, but there would be a simplification of some of the logic and a smaller chip.

But take IBM out ot the equation for a moment and look around at pricing on high density logic. There is not enough electronics in the current 970 to justfy an extremely high price. If the current price is high it is directly the result of recovering development costs. Frankly I doubt that there is much there to recover as Apple probally paid up front for some of the development.
Quote:

It's about an equally bad assumption as to thinking a single chip only costs 200$, that price decay will be 60% and that the move to 65nm won't involve additional heavy costs on IBMs side, which will be rolled off to the customers in one way or the other too.

One only has to look at chips of equal physical size to get a rough estimate for pricing. Then realize that the retail prices aren't even close to what a manufacture pays for a CPU. After that if you're not convinced yet then look at price watches CPU list and the price spread for Athlons. It is not a mystery or even an unknown process, CPUs ramp up in speed and drop in price at a realtively quick pace. You can continue to believe that Apple is paying many hundreds of dollars for each CPU but I find that very doubtful based on the realities of the market and the product.

Dave

Quote:

post #87 of 121
Quote:
Originally posted by Programmer
No, the only people that will be doing XBox2 work right now are MS people. By the time 3rd party developers start MS will have a fully Windows-based solution which communicates with a dedicated developer box. No Macs involved.

No Macs need be involved if the assembly code the 3rd party developers are using runs on the G5. That's a leg up.

This may be far fetched, but I've heard no reason to believe it's out of the question. Actually, quite the opposite. Regardless of the developer box, if the chip in the Xbox2 is the same, there are definite possibilities.
"Hearing a corrupt CEO like Cheney denigrate Edwards for being a trial lawyer is like hearing a child molester complain how Larry Flint is a pervert." -johnq
Reply
"Hearing a corrupt CEO like Cheney denigrate Edwards for being a trial lawyer is like hearing a child molester complain how Larry Flint is a pervert." -johnq
Reply
post #88 of 121
Quote:
if the price is much higher that $100 it is probally a result of recovering R&D expenses.

The smaller the volume of chips sold, the higher the R&D cost-recovery per chip. Straight forward.

Triple core: If the chips are separate, ie 3 chips somehow connected over PCB, the price will be exactly threefold.
If it's a single piece of silicon, how would you arrange 3 cores? Either in a straight line, giving you serious pain connecting core 1 to core 3 (layers are expensive, result in bad yields and are difficult to engineer). Or over the edge, leaving the entire space of a 4th core empty. Fill that with cache or a memory controller or whatever and you have additional R&D, additional transistors, additional heat, additional cost, additional space used etc.
This is not going to be 3 times the price, but it's going to be at least 2 times the price of a single core.
Matyoroy!
Reply
Matyoroy!
Reply
post #89 of 121
Quote:
Originally posted by G-News
Let's also assume a 2GHz chip costs around 200 maybe 250$ in quantities of 1000.

Let's assume that Microsoft wants so sell 10-20 million Xbox Next the first year. The price they get will be considerably lower than the price for someone who buys just 1000.

Considering dual core processors, there's no one in the industry that have the ammount of experience contructing then as IBM do. They've been doing dual core processors for years, and the competitors have hardly begun yet. The POWER4 is a dual core procesor, and IBM have probably had dual core technology in mind when deriving the 900-family from it. The 400-family is dual core ready already, and the future 700-familiy will probably be also. The rumord 300 core as well. IBM and Motorola have made it a point of doing PowerPC cores very modular so their customers have the choice of designing highly customized SOC-processors. I think that the 900 family is constructed with this in mind. Joining the know how from doing Power4, and the 440-based SOC-processors. Designing and manufacturing presicely what we're talking about here shouldn't be too hard. When IBM did the 440 based nodes to BlueGene/L they said that 90% of the job was already done thanks to the modular nature of their PowerPC technology.

IBM's successful cooperation with Nintendo showed them that they could do processors for game consoles too. I think it's no surprise that IBM bagged Nintendo, Microsoft AND Sony.. They do rule, are selling their technology aggressively and they _can_ make excactly the processors their customer's want.
post #90 of 121
Quote:
Originally posted by bunge
No Macs need be involved if the assembly code the 3rd party developers are using runs on the G5. That's a leg up.

This may be far fetched, but I've heard no reason to believe it's out of the question. Actually, quite the opposite. Regardless of the developer box, if the chip in the Xbox2 is the same, there are definite possibilities.

But that is such a trivial part of the game development process that it just won't have a measureable effect on the number of Mac games. There are far greater hurdles than a bit of assembly code (99% of the code is already portable anyhow).
Providing grist for the rumour mill since 2001.
Reply
Providing grist for the rumour mill since 2001.
Reply
post #91 of 121
Quote:
Originally posted by G-News
The smaller the volume of chips sold, the higher the R&D cost-recovery per chip. Straight forward.

Triple core: If the chips are separate, ie 3 chips somehow connected over PCB, the price will be exactly threefold.
If it's a single piece of silicon, how would you arrange 3 cores? Either in a straight line, giving you serious pain connecting core 1 to core 3 (layers are expensive, result in bad yields and are difficult to engineer). Or over the edge, leaving the entire space of a 4th core empty. Fill that with cache or a memory controller or whatever and you have additional R&D, additional transistors, additional heat, additional cost, additional space used etc.
This is not going to be 3 times the price, but it's going to be at least 2 times the price of a single core.

The smaller the volume of chips? Uh... have you looked at the volumes in the game console business? MS is aiming to do a lot better than it did with XBox, and they almost at 20 million there. And for the R&D costs, consider that POWER4, POWER5, 970, etc. all share the same basic core technology. IBM has built a big hammer, and they are hitting everything in sight with it to spread their costs around. For the 65nm node they have Sony publicly helping out directly with funding, and who knows who else privately.

Triple core: first of all I don't think that anybody who gives this a few minutes thought thinks that they'd really put 3 processor chips into a console and expect it to be cheap. That means 3 cores on one chip. Given the other tid bits of info floating around, the 4th quadrant can obviously contain the shared elements of the three processors (more or less, and defining quadrant rather loosely since cores don't have to be rectangular)... i.e. shared FSB, shared cache, shared integrated system components. The individual cores are probably 50 million transistors or less since a whole 970 + 512K L2 cache is only 56 million. That's a total of about 200 million, well within the project targets for 65nm... heck, IBM was doing it on 180nm (at an outrageous price with server grade circuits).

Intuitively you'd think that such a beast would be more expensive than a simpler, smaller single core on the same process. What is bizarre about the semiconductor industry, however, is that there is sort of an ideal physical size where the price/performance/power curve has a knee (i.e. its not a linear function). My guess is that the transistor count of the supposed triple core design is closer to that knee that the single core design. We don't know the shape of that curve so we can't predict the relative costs of these alternatives. Microsoft and IBM have a lot of really smart people, however, and you can bet that their models are telling them where to aim. The rumours are saying that's the 3 core design, and I'm telling you not to scoff at those rumours so much.
Providing grist for the rumour mill since 2001.
Reply
Providing grist for the rumour mill since 2001.
Reply
post #92 of 121
Interesting insights Programmer...

Some questions I would have about all of this...

If these rumors are true it looks as if IBM has all 3 console makers in line for their chips.

Microsoft, Sony and Sega (that is the 3rd right?)

MS is rumored to be shooting for a 9xx derived CPU
Sony WAS rumored to be shooting for CELL but I've been hearing different as of late and a 9xx based CPU is what they seem to be set on
Sega ... I just know they too are in IBMs camp but have no idea as to the CPU but a 9xx based CPU would seem to make sense give everything else we've heard..

Questions I have:

- Could ALL THREE use the same basic chip core (cores) maybe with just some custom additions... Something IBM has been pushing.
- Does this 9xx core contain altivec?
- Does/Could this same 9xx core have a future inside an Apple branded box?

Thinking about the numbers... IBM will be churning out TONS more PPCs then ever before... IBMs R&D dollars spent on improving the CPU will rise quickly and given the much larger number of CPUs being sold will be much less 'per CPU' than every before... Thus lowering the price per CPU.

ALL REALLY GOOD THINGS! (tm)

As for bad things...

Apple will quickly fall from being the #1 PPC buying client and might start getting the short end of the stick when it comes to asking for specific things be added / changed (to future designs) and GOD FORBID maybe even being 'wait listed' when it comes to getting the latest and greatest CPUs off the line... Hey I wouldn't even blame IBM for doing it... The customer that buys the most gets premium attention... That's the way the word works. (unless Apple has some kind of contract that is)

You thoughts?

Dave
Apple Fanboy: Anyone who started liking Apple before I did!
Reply
Apple Fanboy: Anyone who started liking Apple before I did!
Reply
post #93 of 121
Quote:
Originally posted by DaveGee
Apple will quickly fall from being the #1 PPC buying client and might start getting the short end of the stick when it comes to asking for specific things be added / changed (to future designs) and GOD FORBID maybe even being 'wait listed' when it comes to getting the latest and greatest CPUs off the line... Hey I wouldn't even blame IBM for doing it... The customer that buys the most gets premium attention... That's the way the word works. (unless Apple has some kind of contract that is)

This is not something I'm especially worried about, actually, since IBM has focused so much on modularity. They're making PowerPC-based custom solutions for everyone, and that's not bad for Apple at all. If anything, it's something Apple can take advantage of as well.

Remember, IBM is finally realizing one of the goals of the AIM alliance!
"...within intervention's distance of the embassy." - CvB

Original music:
The Mayflies - Black earth Americana. Now on iTMS!
Becca Sutlive - Iowa Fried Rock 'n Roll - now on iTMS!
Reply
"...within intervention's distance of the embassy." - CvB

Original music:
The Mayflies - Black earth Americana. Now on iTMS!
Becca Sutlive - Iowa Fried Rock 'n Roll - now on iTMS!
Reply
post #94 of 121
Quote:
Originally posted by DaveGee

Microsoft, Sony and Sega (that is the 3rd right?)

Nintendo. Sega went software-only after the Dreamcast failure.


Quote:

Sony WAS rumored to be shooting for CELL but I've been hearing different as of late and a 9xx based CPU is what they seem to be set on

A lot of people say this, but I have seen no real evidence. The things which are pointed to as "evidence" are either 3rd/4th hand, or they don't actually imply that PS3 won't be Cell. Oddly enough, from the little we know about Cell it is not impossible that its PPC cores could be derived from the same POWER4 lineage.
Providing grist for the rumour mill since 2001.
Reply
Providing grist for the rumour mill since 2001.
Reply
post #95 of 121
It's amazing how people pick and believe the rumors they like and dispell the ones they don't.
I wouldn't believe any of it until I get official word about it. And that excludes "The Inquirer" per default.

Quote:
Considering dual core processors, there's no one in the industry that have the ammount of experience contructing then as IBM do.

We're talking about triple core, that's what's lifting eyebrows. Thanks for your educations about dual core systems, but we've known and seen them for years now, thanks a lot.

Quote:
MS is aiming to do a lot better than it did with XBox, and they almost at 20 million there

Over several years, which is nowhere near P4 sales in comparison.

Quote:
The rumours are saying that's the 3 core design, and I'm telling you not to scoff at those rumours so much.

We'll see. I'll keep my doubts as I please though, may you keep yours.

PS: The Gamecube is based on a 400 core derivate, last thing I knew. Why not assume a dual core version of that core family, maybe even a triple core version for some strange reason. That would make more sense in a lot of ways.
Matyoroy!
Reply
Matyoroy!
Reply
post #96 of 121
Quote:
Originally posted by DaveGee
[B]Apple will quickly fall from being the #1 PPC buying client and might start getting the short end of the stick when it comes to asking for specific things be added / changed (to future designs) and GOD FORBID maybe even being 'wait listed' when it comes to getting the latest and greatest CPUs off the line... Hey I wouldn't even blame IBM for doing it... The customer that buys the most gets premium attention... That's the way the word works. (unless Apple has some kind of contract that is)/B]

First.. Apple isn't IBM's largest customer for PPC processors, Nintendo is. IBM have produced approx 20 million Gekko-processors to them the last 3 years. That's more prosessors that Apple have used in all of their products in the same time frame, and most of them came from Motorola.

Microsoft will become a large customer, but an inflexible one. Like Nintendo's, all of their processors will be rated the same. To guarantee deliveries in volume, the Xbox processor probably won't be be the top of the line models. There migth be crumbs from that table for Apple to take, processors that are faster than the ones that Microsoft will use. Microsoft will have a harder time cooling their processors, Apple have more room for that inside their machines.

I'm not worried that Apple will be left with inferior processors, but they probably won't have access to exactly the same ones that Microsoft have bought. They are probably custom designs. Apple on their hand have room for custiomization too.
post #97 of 121
Quote:
Originally posted by G-News
Over several years, which is nowhere near P4 sales in comparison.

Yes, but its beyond Apple's sales by quite a bit. And I'm sure MS is gunning for PS2 territory (or better) with 70+ million units. That is surely enough to justify the R&D costs of the chip and bring its actual cost down to the cost of actually producing it.


Quote:
PS: The Gamecube is based on a 400 core derivate, last thing I knew. Why not assume a dual core version of that core family, maybe even a triple core version for some strange reason. That would make more sense in a lot of ways.

No, it is a 750 core derivative. Its only 32-bit, doesn't have vector processing units, and doesn't clock nearly as high.



I'm still trying to see what your objection is (and the following doesn't reflect anything I know from non-public sources)...

Do you just not believe that a near-200 million transistor chip can be a consumer commodity level part by the end of 2005? ATI and nVidia are shipping 130 nm and 150 nm 110-125 million transistor GPU parts right now at the add-in board level. 90 nm SOI is shipping from IBM right now, and they are spending very heavily to get to 65 nm quickly (so is everybody else). Naive arithmetic says that'll quadruple the transistor counts... meaning 400M+ transistors at the add-in board price point, and near-200M at a considerably lower price point. We already know they can ship a leading edge GPU in a game console (they did with XBox), so ATI can do it this time around. So why is it hard to believe in a customized CPU from IBM using the core technology from the established lineage POWER4, POWER4+, POWER5, 970, 970@90 (plus whatever we see between now and XBox2 launch)?

The 200M transistor figure might be too high. The 970 without its L2 cache and bus interface unit is probably only 30-40 transistors, so for 2 extra cores that's only 60 - 80M added to a 970 with a (presumably) boosted cache for a total of 120-150M. That's in the same ballpark as Intel's Prescott (125M at 90nm and shipping this week), and it may not clock as high. Power is not linear with clock rate so running at only 2-3 GHz the rumoured 3 core PPC would be much much cooler than Prescott (not to mention IBM's SOI technology which seems to limit power loss better than Intel has managed).

A couple of years ago I read a published paper from IBM (written circa 2000, IIRC) that predicted transistor counts in commodity level chips would hit 1 billion by 2010. So far things seem on track to hit that, and 2005/2006 is easily in the 200M range. The paper was about how to use this kind of transistor count, and the conclusion of the author was that massive multi-core processors ("Cells") were inevitable. Nobody has figured out how to effectively use more than about 50 million transistors in a core, that much cache is just silly, so the only direction to go is multiple cores.
Providing grist for the rumour mill since 2001.
Reply
Providing grist for the rumour mill since 2001.
Reply
post #98 of 121
Quote:
Originally posted by DaveGee

As for bad things...

Apple will quickly fall from being the #1 PPC buying client and might start getting the short end of the stick when it comes to asking for specific things be added / changed (to future designs) and GOD FORBID maybe even being 'wait listed' when it comes to getting the latest and greatest CPUs off the line... Hey I wouldn't even blame IBM for doing it... The customer that buys the most gets premium attention... That's the way the word works. (unless Apple has some kind of contract that is)

No. This is like saying that Power5 developemnt is going to be a lesser priority because Apple is shipping 200 times as many 970 chips. Apple will always be a customer for IBM who is pushing the limit and in a market where IBM can make more profit. MS will be a customer who wants a new chip every 4-5 years and wants it for as cheap as possible. Also, MS is reaping a benefit from all of IBM's PPC R&D, so MS will want IBM to keep PPC R&D going.


You have a tree of dependencies:

Power 4->970->MS PPC

The power 4 led to the successful 970 product and this leads to a successful bid for the XBox2 CPU. So actually, because the 970 and MS PPC are there to shore up the profits, what you will see is an increase of effort and money at the highest level. IBM thinks to itself "Hey, these PPC server chips can be modified to be good desktop chips, and those desktop chips can be modifed to be good console chips, and when we do that we make alot of extra money. Let's design better server chips to get even more people on this train!" This increase of R&D into PPC will be geared towards making chips that can be effectively converted to workstation CPUs and high end gaming consoles. In the end, the more people who get on the PPC bandwagon, the better everyone else does.
King Felix
Reply
King Felix
Reply
post #99 of 121
a main concern remains the price:
you compared it to ATI chips found on "add-in boards".
These are actively cooled, 500$ monsters.
What makes you think people are going to spend 700$ on a console in 2005, I ask?
Matyoroy!
Reply
Matyoroy!
Reply
post #100 of 121
Quote:
Originally posted by G-News
a main concern remains the price:
you compared it to ATI chips found on "add-in boards".
These are actively cooled, 500$ monsters.
What makes you think people are going to spend 700$ on a console in 2005, I ask?

Read my post again -- I said that the current add-in boards will scale to 400M transistors, whereas only 200M is required for the 3 core PPC... giving it a much lower price/power point. The price point will be lower than the current XBox, MS isn't going to make that mistake again.
Providing grist for the rumour mill since 2001.
Reply
Providing grist for the rumour mill since 2001.
Reply
post #101 of 121
We shall see.
Matyoroy!
Reply
Matyoroy!
Reply
post #102 of 121
Quote:
Originally posted by Programmer
What is bizarre about the semiconductor industry, however, is that there is sort of an ideal physical size where the price/performance/power curve has a knee (i.e. its not a linear function). My guess is that the transistor count of the supposed triple core design is closer to that knee that the single core design. We don't know the shape of that curve so we can't predict the relative costs of these alternatives.

Actually this is exactly what Moore's Law talks about. Generally the optimal size they aim for is around 120 mm^2 (this is just an observation for high performance consumer microprocessors) and with each generational improvement in process technology they can roughly double the transistors in that area. It's worth noting the PPC970 has roughly the same transistor count on the 90 nm process as the 130 nm and is quite substantially below that 120 mm^2 size.
"When I was a kid, my favourite relative was Uncle Caveman. After school, wed all go play in his cave, and every once and awhile, hed eat one of us. It wasnt until later that I discovered Uncle...
Reply
"When I was a kid, my favourite relative was Uncle Caveman. After school, wed all go play in his cave, and every once and awhile, hed eat one of us. It wasnt until later that I discovered Uncle...
Reply
post #103 of 121
Quote:
Originally posted by Telomar
Actually this is exactly what Moore's Law talks about. Generally the optimal size they aim for is around 120 mm^2 (this is just an observation for high performance consumer microprocessors) and with each generational improvement in process technology they can roughly double the transistors in that area. It's worth noting the PPC970 has roughly the same transistor count on the 90 nm process as the 130 nm and is quite substantially below that 120 mm^2 size.

Exactly. "Moore's Law" is so increadibly over-used I don't like to mention it explicitly.
Providing grist for the rumour mill since 2001.
Reply
Providing grist for the rumour mill since 2001.
Reply
post #104 of 121
Can't say I'm a great fan of Moore's Law either since it is more often than not misused but it is a general statement about the economics of IC manufacture tacked together with a rough observation of how often new processes are brought online.
"When I was a kid, my favourite relative was Uncle Caveman. After school, wed all go play in his cave, and every once and awhile, hed eat one of us. It wasnt until later that I discovered Uncle...
Reply
"When I was a kid, my favourite relative was Uncle Caveman. After school, wed all go play in his cave, and every once and awhile, hed eat one of us. It wasnt until later that I discovered Uncle...
Reply
post #105 of 121
Quote:
Originally posted by Telomar
Can't say I'm a great fan of Moore's Law either since it is more often than not misused but it is a general statement about the economics of IC manufacture tacked together with a rough observation of how often new processes are brought online.

Yes, I remember being quite surprised when I read the original statement Moore made (as opposed to the large number of interpretations). It was remarkably simple, which is probably why it has remained (approximately) true this long. I read recently even (especially?) Moore was surprised by how well it had held up.
Providing grist for the rumour mill since 2001.
Reply
Providing grist for the rumour mill since 2001.
Reply
post #106 of 121
Quote:
Originally posted by fieldor
http://theinquirer.org/?article=13928
http://theregister.co.uk/content/54/35265.html

see for your self, just read it. This maybe coming our way eventually.

its actually sounds like a half decent microsoft product\
"Cuz if you leave the world a better place than when you got here, we all win"
-MURS 316
Reply
"Cuz if you leave the world a better place than when you got here, we all win"
-MURS 316
Reply
post #107 of 121
Quote:
Originally posted by G-News
What makes you think people are going to spend 700$ on a console in 2005, I ask?

Inflation
post #108 of 121
better buy some reserves then, because if you're going to have an inflation that high, prepare yourself for another world economy crisis ala twenties.
Matyoroy!
Reply
Matyoroy!
Reply
post #109 of 121
Please pardon my igorance, but I have a question and may word it incorrectly.

With all this talk about multithreading and multicore cpu's, my question is,"Do the three cores have to be identical?" The reason I ask is, if different demands on the cpu could be directed during compiling more easily to separate cores. Since my ignorance of both hardware and software engineering is monumental, the lame examples I'll use will be graphics, physics and sound(other examples may be much more appropriate).

If each core is more or less designed to handle specific tasks, would this make programming multiple threads somewhat easier, or if proper compiler instructions added, even automatic? Possibly, then the space(#'s of transistors) could/may be designed much more efficiently.

Since we're talking about a cpu for xBox Next, which could be specifically designed for gaming, rather than general purpose desktop/workstation computing, does any of the above make any sense?
just waiting to be included in one of Apple's target markets.
Don't get me wrong, I like the flat panel iMac, actually own an iMac, and I like the Mac mini, but...........
Reply
just waiting to be included in one of Apple's target markets.
Don't get me wrong, I like the flat panel iMac, actually own an iMac, and I like the Mac mini, but...........
Reply
post #110 of 121
afaik, both could be possible.
However, how good the programs will be optimized, is mainly a matter of how good MS's development environment/compilers will be.
Matyoroy!
Reply
Matyoroy!
Reply
post #111 of 121
Quote:
Originally posted by G-News
afaik, both could be possible.
However, how good the programs will be optimized, is mainly a matter of how good MS's development environment/compilers will be.

Thank you for the reply.

Well, if Mac websites are to be believed, we know Microsoft is very good at designing compilers for high Spec scores.
just waiting to be included in one of Apple's target markets.
Don't get me wrong, I like the flat panel iMac, actually own an iMac, and I like the Mac mini, but...........
Reply
just waiting to be included in one of Apple's target markets.
Don't get me wrong, I like the flat panel iMac, actually own an iMac, and I like the Mac mini, but...........
Reply
post #112 of 121
Quote:
Originally posted by rickag
Please pardon my igorance, but I have a question and may word it incorrectly.

With all this talk about multithreading and multicore cpu's, my question is,"Do the three cores have to be identical?"

No, they don't. In fact, this sort of thing is common in consoles. And Amigas. And, actually, modern Macs - part of OS X now leans on the graphics chip to do work.
"...within intervention's distance of the embassy." - CvB

Original music:
The Mayflies - Black earth Americana. Now on iTMS!
Becca Sutlive - Iowa Fried Rock 'n Roll - now on iTMS!
Reply
"...within intervention's distance of the embassy." - CvB

Original music:
The Mayflies - Black earth Americana. Now on iTMS!
Becca Sutlive - Iowa Fried Rock 'n Roll - now on iTMS!
Reply
post #113 of 121
Quote:
Originally posted by rickag
Please pardon my igorance, but I have a question and may word it incorrectly.

With all this talk about multithreading and multicore cpu's, my question is,"Do the three cores have to be identical?" The reason I ask is, if different demands on the cpu could be directed during compiling more easily to separate cores. Since my ignorance of both hardware and software engineering is monumental, the lame examples I'll use will be graphics, physics and sound(other examples may be much more appropriate).

If each core is more or less designed to handle specific tasks, would this make programming multiple threads somewhat easier, or if proper compiler instructions added, even automatic? Possibly, then the space(#'s of transistors) could/may be designed much more efficiently.

Since we're talking about a cpu for xBox Next, which could be specifically designed for gaming, rather than general purpose desktop/workstation computing, does any of the above make any sense?

This is a very good question, actually. In general purpose computers there is a lot of benefit to having symmetric cores (hence the term SMP for symmetric multiprocessing) because the software can remain largely ignorant of the particular hardware it is run on, but in specialized hardware like game consoles this isn't as important because the software is custom designed for the hardware. The PS2 has several different kinds of processors -- a MIPS core (two, actually), a couple of vector processors, a DMA engine, and a couple of sound chips. The PS3's Cell architecture is rumoured to have conventional processors with a set of slave vector processors.

What is key in this kind of design is to provide processors which can be used for a wide variety of processors, rather than over-specializing them. GPUs and SPUs are an exception because all games have lots of graphics and sound, but even there the over-specialization can limit what game developers can do (for example, the current DirectX/OpenGL vertex program model means that you can't create/destroy vertices or do inter-vertex optimizations in the GPU itself, whereas PS2 does this quite well because it uses a more general vector processor).

Even if the cores are the same, there is no requirement that the software use them in the same way. Most people tend to assume that a symmetric multi-core processor will just divide up the running pre-emptive threads, but this isn't necessarily the best way to do things.
Providing grist for the rumour mill since 2001.
Reply
Providing grist for the rumour mill since 2001.
Reply
post #114 of 121
Thank you all for the responses. My next question concerns the examples I used for multithreading, graphics/physics/sound. Are there more basic ways to separate threads directed toward individual cores.

Taking my example of graphics, I would think this might not be a good example, because graphics cards are very sophisticated and comsume a lot of transistors and ram.

I guess what I'm saying is,"Is there a way in hardware to make programming multithreading easier or automatic? And if so is there any advantage to designing each core for specific purposes?

The only example I can think of at the momment is SIMD, and this still might be a bad example. If say only one core has Altivec/VMX(or maybe two), would it be easier to program, or automate during compiling, directing this thread toward the core with SIMD?

If this all sounds redundent, chalk it up to my lack of knowledge.
just waiting to be included in one of Apple's target markets.
Don't get me wrong, I like the flat panel iMac, actually own an iMac, and I like the Mac mini, but...........
Reply
just waiting to be included in one of Apple's target markets.
Don't get me wrong, I like the flat panel iMac, actually own an iMac, and I like the Mac mini, but...........
Reply
post #115 of 121
I don't know to what extent that could be done in hardware, but what you're talking about is done by the compiler and the OS.
Matyoroy!
Reply
Matyoroy!
Reply
post #116 of 121
G-News, thanks.

I guess I just don't know enough about how threads are generated and controlling multithreading so there aren't a ton of threads stepping on each other. It is an interesting topic though, even for the technologically challenged like me.
just waiting to be included in one of Apple's target markets.
Don't get me wrong, I like the flat panel iMac, actually own an iMac, and I like the Mac mini, but...........
Reply
just waiting to be included in one of Apple's target markets.
Don't get me wrong, I like the flat panel iMac, actually own an iMac, and I like the Mac mini, but...........
Reply
post #117 of 121
Quote:
Originally posted by rickag
I guess what I'm saying is,"Is there a way in hardware to make programming multithreading easier or automatic? And if so is there any advantage to designing each core for specific purposes?

Not really -- the software has to be setup to deal with multiple processors and the specific kinds of processors. The more automatic you make it, the less control developers have over it. Making hardware too specific limits what it can be used for.

GPUs are a good example: they are very specialized to rasterize 2D pixel maps from triangle vertex data and 2D textures. This makes it impossible (or really difficult anyhow) to use their massive floating point capabilities for anything other than the graphics they were designed to do. Curved surfaces, for example, don't do well through a triangle-based GPU. GPUs are getting more and more generalized all the time, first by the introduction of shaders, and now by the ever increasing expressive power of the shaders. Eventually they'll be useable for things which aren't even graphics.
Providing grist for the rumour mill since 2001.
Reply
Providing grist for the rumour mill since 2001.
Reply
post #118 of 121
Quote:
Originally posted by rickag
Thank you all for the responses. My next question concerns the examples I used for multithreading, graphics/physics/sound. Are there more basic ways to separate threads directed toward individual cores.


I'm not sure exactly what your asking here. One way to for a thread to be generated for a specific processor is through another thread issuing a call to a system function or library function. Consider your main program that has been built to wrk with a DSP card, it may issue a call that results in code running on the DSP. While I have a hard time describing this as multi threaded you would end up with code running on a specific processor.

Generally you don't want threads going to specific cores or processors, rather you would hope that the OS can manage the correct allocation of resources. Of course there are always cases where an OS would choose a poor allotment of processors.
Quote:

Taking my example of graphics, I would think this might not be a good example, because graphics cards are very sophisticated and comsume a lot of transistors and ram.

I guess what I'm saying is,"Is there a way in hardware to make programming multithreading easier or automatic? And if so is there any advantage to designing each core for specific purposes?

When you say programming automatic I'm not sure what you are asking. There are no limits to what may be added to a processor other than the limit space on the chip. So it is possible to add hardware to a processor to make it a better machine for a multithreaded environment. That won't make anything automatic, but you could make things easier. But that easinees is at a low level and probally not what you are inquiring about.
Quote:
The only example I can think of at the momment is SIMD, and this still might be a bad example. If say only one core has Altivec/VMX(or maybe two), would it be easier to program, or automate during compiling, directing this thread toward the core with SIMD?

If you really wanted to go to all the trouble you probally could get a machine to operate with a AMD and PPC chip on the same board. Beyond a whole bunch of issues you would still need to get the OS to handle sending the right code to the right processor. You could likewise build a PPC system with a processor with SIMD and one with out, still taking into account the required OS work that would need to be done.

I'm not sure why anyone would want to do this though. Such a mix of processors may very well work in a server environment where a large number of threads just need integer operations. But again it is a software issue and one would have to wonder why not implement SMP. Come to think of it some servers do implement intelligent I/O which execute requests from the OS. I have trouble describing that as threading though.
Quote:

If this all sounds redundent, chalk it up to my lack of knowledge.

Questions never hurt though my response above may hurt a bit.
Quote:

post #119 of 121
i think it's highly dependany on the APIs. Apparently DirectX10 will be used. DirectX is only on windows so, it could be possible to port the games to windows. But for MacOSX ull have to port DirectX whitch will be preety difficult. If on the other hand they choose to use OpenGl as well...it could theoretically be possible.
post #120 of 121
If they run it DirectX and run it on a PPC platform, they'll have to port it already anyway. So chances are, they could port DirectX to Mac OS X along with the games.
-IF- they want that.
Matyoroy!
Reply
Matyoroy!
Reply
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: Future Apple Hardware
AppleInsider › Forums › Mac Hardware › Future Apple Hardware › Xbox 2 specs leak