The Reg on future G4 roadmap
this from theregister.co.uk today. mileage may vary....
"Exclusive:
While Apple watchers look for first sightings of the G5 chip, Motorola is taking the G4 into fertile territory. By this time next year three as yet unannounced versions of the G4 will dramatically boost internal bandwidth, support switched fabric interconnects, and will see the processor talk to memory at full bus speed, according to disclosures from Motorola sources.
One caveat: as far as we know Apple hasn't committed to adopt these new G4 variants. Now it's got a portable operating system, it can choose something really weird and exotic if it desires, but common sense and recent precedent suggest that these two processors will form the mainstay of Apple?s iMac2 and low-end professional lines.
According to Motorola sources, a tweaked version of the Apollo 7450 G4, the 7470, will be ready for volume production shortly after the end of Q2, in time for a summer ramp. The 7470 will be manufactured on a 0.13 micron process, allowing for a smaller die size with room for 512K of L2 cache, and support up to 4MB of DDR-SDRAM L3 cache.
The 7470 supports a modified bus protocol, MPX+, which supports double data transfer and which should effectively run at 266Mhz according to sources.
The MPX+ bus retains MPX's 36-bit addressing lines, and is described as interim measure. Don't expect dramatic leaps in SMP scaling - two will remain the sweet spot. The 7470 should scale to 1.5MHz. In parallel development, Motorola is priming a cut-down 7470 labelled the 7460, which doesn't support L3 cache.
But the third addition to the G4 family, the 7500 - slated for volume production by this time next year, should steal some headlines. Like the 7470, the 7500 will be built to a .13 micron process, and will feature a 14 stage pipeline (11 integer).
Having boasted one of the shortest (and most efficient) pipelines in the business, with the G4's original four-stage unit, Motorola has been increasing the pipeline depth, which allows it to deploy higher clock frequencies. There's a whole science to optimizing processors to minimize the branch jump table penalty, which shouldn't detain us for too long. But a crude summary is that a deep pipeline allows the processor to second guess the subsequent instructions, at the cost of clearing the pipeline when it gets the wrong answer. If a processor has a higher clock frequency, it can clear the pipeline quicker when a mis-prediction is flagged).
More noteworthy is that the 7500 will be the first desktop processor to employ the RapidIO architecture to communicate with the system at 500Mhz.
RapidIO is a switched fabric interconnect that mirrors the parallel Infiniband initiative: the former is endorsed by the embedded industry, the latter by big iron system vendors, so the two don't really overlap. But the move to a standard switch architecture away has been a long time coming: high-end systems use their own proprietary switches (in mainframe terminology, a "crossbar switch") or a combination of a bus and a switch.
In practical terms it will permit the the memory controller to be housed on the die, communicating at full clock speed. So potentially, there's no need for L3 on-die cache. With DDR-SDRAM at 266Mhz and heading for 333Mhz, this should result in a comfortable improvement in throughput.
Our source suggests that Apple will have "little choice" but to adopt RapidIO, given that the bulk of Motorola and IBM PPC volume is in the embedded business. But there's much to be gained too, as RapidIO becomes the internal wiring for knitting together the various bus protocols a desktop PC needs to support: ATA, USB, FireWire and so on.
With Intel's latest Northwood systems employing a 400Mhz front side bus (up to 533Mhz by the end of the year), Apple loyalists should take some cheer from these developments. . System performance owes a great deal to the internal bandwidth, and running a high frequency processor on a slow frequency bus has never been considered optimal.
More importantly for Apple, it allows the company plenty of potential for system improvements to the consumer iMac range, and far more scope for differentiating between the pro and consumer lines...."
"Exclusive:
While Apple watchers look for first sightings of the G5 chip, Motorola is taking the G4 into fertile territory. By this time next year three as yet unannounced versions of the G4 will dramatically boost internal bandwidth, support switched fabric interconnects, and will see the processor talk to memory at full bus speed, according to disclosures from Motorola sources.
One caveat: as far as we know Apple hasn't committed to adopt these new G4 variants. Now it's got a portable operating system, it can choose something really weird and exotic if it desires, but common sense and recent precedent suggest that these two processors will form the mainstay of Apple?s iMac2 and low-end professional lines.
According to Motorola sources, a tweaked version of the Apollo 7450 G4, the 7470, will be ready for volume production shortly after the end of Q2, in time for a summer ramp. The 7470 will be manufactured on a 0.13 micron process, allowing for a smaller die size with room for 512K of L2 cache, and support up to 4MB of DDR-SDRAM L3 cache.
The 7470 supports a modified bus protocol, MPX+, which supports double data transfer and which should effectively run at 266Mhz according to sources.
The MPX+ bus retains MPX's 36-bit addressing lines, and is described as interim measure. Don't expect dramatic leaps in SMP scaling - two will remain the sweet spot. The 7470 should scale to 1.5MHz. In parallel development, Motorola is priming a cut-down 7470 labelled the 7460, which doesn't support L3 cache.
But the third addition to the G4 family, the 7500 - slated for volume production by this time next year, should steal some headlines. Like the 7470, the 7500 will be built to a .13 micron process, and will feature a 14 stage pipeline (11 integer).
Having boasted one of the shortest (and most efficient) pipelines in the business, with the G4's original four-stage unit, Motorola has been increasing the pipeline depth, which allows it to deploy higher clock frequencies. There's a whole science to optimizing processors to minimize the branch jump table penalty, which shouldn't detain us for too long. But a crude summary is that a deep pipeline allows the processor to second guess the subsequent instructions, at the cost of clearing the pipeline when it gets the wrong answer. If a processor has a higher clock frequency, it can clear the pipeline quicker when a mis-prediction is flagged).
More noteworthy is that the 7500 will be the first desktop processor to employ the RapidIO architecture to communicate with the system at 500Mhz.
RapidIO is a switched fabric interconnect that mirrors the parallel Infiniband initiative: the former is endorsed by the embedded industry, the latter by big iron system vendors, so the two don't really overlap. But the move to a standard switch architecture away has been a long time coming: high-end systems use their own proprietary switches (in mainframe terminology, a "crossbar switch") or a combination of a bus and a switch.
In practical terms it will permit the the memory controller to be housed on the die, communicating at full clock speed. So potentially, there's no need for L3 on-die cache. With DDR-SDRAM at 266Mhz and heading for 333Mhz, this should result in a comfortable improvement in throughput.
Our source suggests that Apple will have "little choice" but to adopt RapidIO, given that the bulk of Motorola and IBM PPC volume is in the embedded business. But there's much to be gained too, as RapidIO becomes the internal wiring for knitting together the various bus protocols a desktop PC needs to support: ATA, USB, FireWire and so on.
With Intel's latest Northwood systems employing a 400Mhz front side bus (up to 533Mhz by the end of the year), Apple loyalists should take some cheer from these developments. . System performance owes a great deal to the internal bandwidth, and running a high frequency processor on a slow frequency bus has never been considered optimal.
More importantly for Apple, it allows the company plenty of potential for system improvements to the consumer iMac range, and far more scope for differentiating between the pro and consumer lines...."
Comments
"More noteworthy is that the 7500 will be the first desktop processor to employ the RapidIO architecture to communicate with the system at
500Mhz."
This is totaly different from what they were saying back in december .
if this is true, i won't be buying any new mac for 2 year's and this sucks big time
I still think something is coming to the pro line by late summer / fall.....
Betting Seybold in September.....
Anyway, if they happen to be right (I seriously doubt it) I think the 7500 would be labeled as the G5 since it apparently shares many characteristics such as controller on-die, RIO, etc.
I give this report about a 20% chance of being right. I want to know what Rothenburg has to say about Apple's latest comments, given how "sure" all of his sources were (sources who apparently were testers themselves) new PM's were on the way in short order.
<img src="graemlins/hmmm.gif" border="0" alt="[Hmmm]" />
[ 02-11-2002: Message edited by: Moogs ? ]</p>
<strong>This clearly says no G5 till next year .
"More noteworthy is that the 7500 will be the first desktop processor to employ the RapidIO architecture to communicate with the system at
500Mhz."
if this is true, i won't be buying any new mac for 2 year's and this sucks big time</strong><hr></blockquote>
Why are you holding out for a processor you know nothing about?
Let's look at some of the features predicted for the "G5":
1) switched fabric motherboard (RapidIO)
2) on die memory controller
3) 14 stage pipeline
4) 1.2 to 1.6 GHz
5) .13 micron process
6) single core design
7) miraculously low price and reasonable energy consumption.
Now, add in the rumors about the G5 actually being a G4. And the insistence of some people that there were boxes sampling, and it's almost ready.
I hereby submit that the 7500 is the so-called "G5".
[ 02-11-2002: Message edited by: Amorph ]</p>
<strong>I hereby submit that the 7500 is the so-called "G5".
</strong><hr></blockquote>
7500 != 64 bit
<strong>
7500 != 64 bit</strong><hr></blockquote>
That's the one difference. But the rest of the features line up uncannily, no?
[edit: To clarify, I wouldn't be surprised if there is a real, honest-to-goodness 64-bit G5 in the works somewhere. But based on this article the 7500 sounds like the source of a lot of the "G5" rumors floating around; especially the ones that predicted a G5 sometime soon.]
[ 02-11-2002: Message edited by: Amorph ]</p>
What I care the most is peformance. If the processor can blow P4 and Athlon I don't really care if it's called G1
Why is everyone holding out for a processor they know NOTHING about?
What SPECIFICALLY will the G5 do for you in the areas of performance that a speedier G4 cannot do?
icom, saying that you won't be buying a Mac for the next two years because there won't be a G5 doesn't make any sense, unless you know something about the G5 that we do not.
The term "G5" is clearly a strong marketing term, as seen on these boards. Would it be smart for Apple to release a G5 from a marketing standpoint? Sure. Would it be smart for people to keep from buying a Mac just to wait for a so-called G5? I don't think so.
G4, G5 or GWhiz, I don't care what it's called as long as it shows me some serious real-world performance.
---------
RosettaStoned
<strong>
That's the one difference. But the rest of the features line up uncannily, no?
</strong><hr></blockquote>
True true. Plus IMO 64 bit is not that important and more of a pain than it's worth right now.
<strong> If the processor can blow P4 and Athlon I don't really care... </strong><hr></blockquote>
If the new PPC can indeed fellate other procs then it certainly won't be in any of Apple's family friendly consumer products. They'll probably drop the current product structure altogether and go with 'Family' and 'Adult' lines in place of consumer and professional.
<strong>More noteworthy is that the 7500 will be the first desktop processor to employ the RapidIO architecture to communicate with the system at 500Mhz. </strong><hr></blockquote>
but that was supposed to be the geeeeeefiiiiiive
<strong>The Register blew it on the G5 news. Why listen to them now?</strong><hr></blockquote>
because they nailed the ... oh, wait <img src="graemlins/bugeye.gif" border="0" alt="[Skeptical]" />
[ 02-11-2002: Message edited by: apple.otaku ]</p>
I don't think apple would call the 7500 a g5, because its not their 5th generation processor, however there ARE alot of revisions and additions, so it is like a whole new processor, but basic g4 arch.
however the original g4 was not much more than a g3 with altivec...perhaps the first model g5 will be not much more than a g4 with rapid I/O and one die memory controller(two things that will speed it up greatly at many tasks) then a little while down the line(read sometime next year) the REAL g5 will be released(the 85xx series) this will feature, faster clock speeds all around, 64-bit design, and support for all sorts of cool things(whatever is cool in a year)
I'm all for this 7500 being the 'g5' but more that it was always a g4, but some insider leaked it as a 'g5' or maybe as just 'next generation procssor' impying the next gen of g4, but the people he leaked it on extrapolated 'g5'
ya know?
its all perfectly in the realm of possiblity...I think that the 7500 looks pretty sweet, and I would be satisfied with it(especailly if it was at 1.5 ghz
As for the threat of the Hammer series to Apple's video and graphics market, its minimal I believe. The video guys don't really need 64-bit, database guys do, at least for the moment. However, if the Hammer generates significant performance increases in 32-bit application, then *maybe* its something to worry about, but only maybe. I am thoroughly convinced we will see the G5 now later than MWSF '03, which will be just a couple of months after Hammer starts shipping. A couple of months gap is NOT enough to get apple's core customers to switch.
what are we talking about again?
<strong>Unfortunately, this roadmap sounds reasonable.</strong><hr></blockquote>
Unfortunately?
Damn, an article appears that speculates that Motorola is really delivering (which, given the rapid progression from the 7410 to the 7450 to the 7455, is not all that surprising), and still nobody's happy.
If the article's right, we get 266MHz DDR this summer, attached to the next iteration of a chip that manages to squeeze out impressive performance while sharing a bus clocked 8 times slower.
Next year, we say goodbye to the bus altogether and go to a type of architecture that is currently the exclusive province of real high-end hardware, and which will, finally, make it sensible to include more than two processors.
[quote]<strong>I hope it's not true, because there's one puppy looming on the horizon that's going to kill everything else: Hammer. Intel's reportedly planning on scrapping/scaling back it's Itanium efforts in order to plan a 64/32 (not emulated 32 like Itanium) proc in order to compete with AMD. Apple better do the same. Because that video market they covet so much will dry up damn quick if they don't.</strong><hr></blockquote>
Apple is currently offering the video market a 5 pound, (comparatively) inexpensive laptop that does real-time effects in software. And that's with last year's processor and a motherboard that dates back to the Pismo. They have, hands down, the best video editing platform you can get without taking out a second mortgage. The towers have the bandwidth and the expansion to handle live video streams, and a motherboard that doesn't let the onboard FireWire and Ethernet ports take up its ample PCI bandwidth.
Hammer will do nothing to change that. Premiere at blazing speeds is still Premiere. The bottleneck is still the editor herself, not the computer. The 64-bit architecture will buy nothing.
Besides, if the Hammer is going to be a fire-breathing, 64-bit monster, it'll probably cost a hell of a lot more than a 7500 will. (Intel scaling back Itanic is no real surprise - they should have shed that albatross years ago - but if it's indeed a reaction to Hammer, that should tell you that Hammer is not aimed at the PC market.)
[ 02-11-2002: Message edited by: Amorph ]</p>