50 - I don't think you realize how cost-inneffective it is to create a completely new process flow or sort flow just to turn off a feature. Creating a different chip costs many hundreds of thousands of dollars PER LAYER that's changed. The mask changes alone would cost about half of a million dollars per reticle. Forget about the engineering initiative necessary to design the changes. It would be retarded of Intel to make a move like that. 45 hit the nail right on the head. The same products will be made, and then filtered out by working/non-working parts at end of line sorting.
You don't really think your graphics / non-graphics chipsets are MADE differently, do you? (PSST, they're not). Simply put, they're all tested at the end of production. Some have working graphics sub-systems, some don't. They're distributed accordingly.
I'm not sure how much Intel paid AnandTech for this article, but it must be a grundle to shovel it like this...
"As a dual core solution, Yonah is the most advanced (other than perhaps Itanium 2 Monticeto) solution that we have seen out of either AMD or Intel."
Wow, so they have some cool new integrated memory controller in place to leap frog AMD. NO, well then what about the new Intel branded Hyper-transport knock off they are working on? Oh well, at least we can look forward to some big Intel adds on AnandTech in the coming months!
Perhaps when AnandTech talks about how advanced a platform is, they should wait until they can compare the performance with others as they did recently in their article...
What matters is how fast Corporates embrace 64-bit outside the Enterprise app level (since most are still mainframe or at least Unix based). Generally technology and software updates are slow to rollout due to costs, contracts, stability, etc. If, somehow, 64-bit was to become part of the mainstream corporate app profile - THEN it will matter if Intel has a 64-bit mobile (laptop) processor.
I would add at least one year past when Longhorn finally debuts before you see a major shift towards 64-bit. Until then it won't be a big deal IMO.
52:
Add 1 for EM64T support on 5xx and 3xx CPUs.
Add 2 for VT support on 6xx CPUs.
Add 3 for 65nm 6xx CPUs that overlap 90nm parts (and have VT).
Otherwise, it's basically higher numbers within the same family gives better performance/features. It's a way to de-emphasize MHz/GHz, since we may be plateauing on clock speeds for a while. Intel spent so long convincing people to upgrade PCs for an extra 400 MHz that they now need to change tactics. Smart marketing, really.
Another point with Yonah is that it is intended to be a low-power consuming Mobile design, not desktop. Most laptop users have no need of a faster CPU but do want longer battery life / smaller lighter battery etc.
Given that the whole design of the Pentium M chips (Banias -> Dothan -> Yonah) is about saving power by artificially limiting the maximum intended clock speed, it makes sense for Intel to make Yonah no faster than Dothan so that they can further reduce the power consumption of the processor at any given speed compared to what it would draw if the design could reach, say 2.5GHz.
It doesn't seem at all surprising to me that Yonah will be little or no higher clocked than Dothan as there is little demand for the extra speed but plenty of demand for reduced power consumption.
45 - Possibly, but as we indicated in the article, it's just a guess. As I understand it, Vanderpool (VT) isn't adding a lot to the die size - actually, it's been present since the Prescott 2M/Irwindale cores, but deactivated. I'm more inclined to believe that Intel is just trying to separate the market: charge more for VT enabled chips, as they will go to server/workstation systems which tend to cost more.
-----------
Regarding clock speed, while it's true that clockspeed isn't everything, we're essentially looking at a process shrink that isn't improving the top speed of CPUs at all. Yonah is pretty much Dothan (maybe) with dual cores. Banias topped out at 1.7 GHz, Dothan topped out at 2.26 (or will in a while), and Yonah is launching at 2.13 GHz max. It's surprising, that's all.
While MHz/GHz are not everything, the basic fact remains that similar architectures running at the same clock speed will perform similarly. Dothan 2.13 GHz will match a single core Yonah 2.13 GHz barring any drastic changes to the underlying architecture. Merom is the next major change in the underlying architecture, so we'll have a CPU that may be as much as 50% faster at the same clock speed.
Taking a more pragmatic look at the CPU environment, it's sort of interesting that the fastest (official) Northwood cores were 3.4 GHz and Prescott with 90nm and a longer pipeline only bumped that up 400 MHz. Willamette topped out at 2.4 GHz, so the 180nm to 130nm transition increased top CPU spped by 1000 MHz - 42% instead of only 12%!
Think AMD's done much better? The fastest 130nm chips from AMD were the FX-55 (2.6 GHz) and right now it doesn't look like they'll release anything above 2.8 GHz with 90nm SOI! Even if we throw out the FX-55 (which is a bit of a special case, since it's the only 130nm AMD chip with strained silicon), AMD still only went up 400 MHz with the transition - 17%.
The best we saw out of AMD/Intel for the transition to 90nm was a 33% speed bump from Banias to Dothan, but it sounds like that was also accompanies by a slightly longer pipeline.
If we got as much as a 50% speed increase going from 180nm to 130nm, and only a 33% going from 130nm to 90nm (even with adding copper, SOI, and strained silicon), what will 65nm bring? A maximum of a 20% speed increase for the same design? Maybe even less? Time will tell, but I find it an interesting trend to say the least!
People keep shouting about 64-bits, but 64-bits won't make a difference to the vast majority of users. Most of the people I know who use computers surf the web, write email, print pictures, and other very basic tasks. In the corporate space, the transition to 64-bit will be glacial. The place I'm working at has used Windows 2000 for almost four years now and has no plans to change. They aren't the only ones:
The only ones 64-bit will make a difference to are the very small percentage of people who actually need it, and the fanbois who buy the biggest for the sake of having the biggest.
Although it still sounds vague in explanation, if VT tech lets you run two *different* operating systems at the *same time*, similar to using VMWare in full screen mode... that would be pretty nice.
The savings of having to buy extra hardware (or VMWare itself) for another OS without dual booting would help those on a budget.
A geforce 6600GT runs at 500Mhz GPU..a 7800GTX runs at 430Mhz..does the 7800GTX suck compared to the 6600GT?
Sometimes you just don´t need huge CPU power, but you need low powerusage for either batterytime and/or how compact you can make it.
The 1.06Ghz Yonah most likely uses a few watts only. And with few we are talking a low single digit number. Or the same as having 30 1.06Ghz for 1 2.4Ghz AMDx2. Or having 45 1.06Ghz instead of 1 3.2Ghz P4D.
"All of the Cedar Mill cores clearly have VT support (as do the Prescott 2M cores), so why Intel would want to deactivate it in one model is anyone's guess."
Binning!
Intel is expecting noticeable issues getting high yields out of the VT portions of the silicon, or at least are expecting a noticeable failure rate(30% or so higher than the average failure rate for the rest of the chip?), so they are planning something to do with all the chips that fail VT qualification, but pass everything else.
"Presler will in fact be nothing but two Cedar Mill cores sharing the same core, just as Smithfield is only two Prescotts sharing the same core."
Wouldn't it make more sense to say Presler is two Cedar Mill cores sharing the same *die* or sharing the same package? Two cores sharing the same core doesn't make any sense.
Eug - "But it doesn't HAVE to be 2006. If it's out by 2007 for laptops that's fine"
Fair enough...but remember that the important factor here is the PERCEPTION of release.
By that I mean that the imminent release of 64 bit apps would be a big deterrent (IMHO) to anyone thinking of buying a Yonah based laptop next year. If true, then Yonah would be the only chip unable to run the apps. Software in 2006 will most likely be both 32 and 64 bit...but if people believe that any of the apps they use will be released in 2007 as a 64 bit only, then they have to accept that their new laptop will only have a 1 year lifespan (something that businesses would probably avoid, and they buy the most laptops).
This is especially true as AMD should have a very competitive product (both in power and low power usage) that is already 64 bit and will probably cost a few dollars less...
I disagree. 64-bit on laptops can be important, if only because it allows you to do 64-bit development and testing on a laptop.
But it doesn't HAVE to be 2006. If it's out by 2007 for laptops that's fine. By that time both Windows Longhorn and OS X 10.5 Leopard should be out, perfect timing for Merom.
Viditor:
I wasn't completely sure(maybe next Yamhill:).
That's it. For now 64bits on mobile doesn't make sense(except *nix). Howerever in '06 it's gone be pretty much a mainstream feature on desktop(not to mention server).
Also in the big picture this makes sense since it will put SOME(just on niche markets) pressure on AMD with minimal resources amd will also limit P-M into low-power space so it will not interferewith next-ge chips.
But here come BIG BUT! it seams that only single possible serious contender in performance race from intel camp is out of the game!
So it seems AMD has free ground to play for another at least 1.5yrs ! (That makes it 3.5 in total!!!). Anyway i like smart moves by AMD this is NOT gona be GOOD FOR US. (customers)
little sorry for my screams, not slept for too long ;)
mino - no, Yonah will not be 64bit (as Shintai explained)...but I disagree that it will not be important. For software in 2006, it won't be important but for software in 2007 it will be (IMHO).
There you have 2 differing OPINIONS...we shall see! :-)
No..and it´s not really important. Meron(mobile) and Conroe(desktop/server) will be 64bit and with characteristics of pentium M. They are an 8th genration core tho. And not based on the 6th(p-M) or 7th(p4)
Finally intel execs came to their senses. people should applaud them all at once! They are evidently going to get rid of those super-trooper power drainers they are producing for last 2 yrs.
BTW you all seeing performance parity arise just remember tah if AMD needs it even wouldn't need K9 to compete with Merom(unless it will be some miracle chip). They could yust release quad-core server chips plus some 3.2-3.4 desktop K8+ dualies and be done with it !
It's becomming so funny that first chips able to really axploit potential of DDR2(666+),technology som much tooted and pushed by Intel, will be 65nm X2's.
Ironic, isn't it?
Merom Merom Merom Kris! is the only thing Intel has I'm waiting for since I dont use notebooks. Does'nt quite sound as nice does it.:P
I just can't see the extra cache doing much for the 9xx series, much like the 6xx did'nt do squat.. So the only thing that remains to be seen and potentially exciting is power draw and overclockabilty of the 65nm desktop chips.
But on a much more serious note, I think VT would be good if it would work with very little or no OS support. I remember horror stories with Windows and Linux partitions, and I really don't want to find out how much Windows on VT can destabilize the rest of operating systems running on virtual partitions
Hmm..I think people have too high expertations after the few last years of gigahurtz.
I think 65nm will give us affordable AMD64 X2s maybe a speedbump to 5000 and 5200. But I think it will be more focused on quad cores, cheaper manufactoring and lower power consumption.
P4 65nm. I think we might see the 4Ghz now. But else the same thing as with AMD, cheaper dualcores, lower power usage.
Yonah is abit different, size the manufactoring cost of Yonah wont increase that much compared to a P4/X2 dualcore. But yonah sports SSE3, some 20-30% faster speed at the same frequency. So Yonah will be desktop and server attractive. More than Dothan is now. Plus it keeps its low powerusage. Also a speedbump is likely here.
But remember people, building an X2 or P4D is alot more expensive than a singlecore. So 65nm is not the "Yiiihah" speedbumpage. But more like the 1100$ AMD 4800 X2 down to 3-500$ thing.
So I wouldn´t really expect much other than more cores and alittle tweak here and there until K9 and Meron/Conroe.
If I ran two operating systems at once, I'd basically idle on one while working on the other one. So my overhead for running to OSes would mostly be memory. It'd be like dualbooting without the booting, you just switch your active OS whenever you wish to. It'd be great for those of us who prefer *nix OSes but NEED windows for specific tasks *cough*games*cough*.
The problem, of course, will end up being how much additional software will be needed to do this (not to mention how much it will cost ^^), I'm guessing it wont be just installing both OSes and then booting them.
Seriously why are you guys concerned about clock speed, as everyone has reported clock speed does not equate to a significant increase in performance. BTW who in the hell needs to run four operating systems at once?? I mean it reallY?? Glad to see intel in finally going to stop making two of the same chipset and giving them different names. I almost fell asleep looking at all the different cpu's seems like the same stuff just a different day. I dont run a multi billion dollar company but Intel should seriously simplify and stop getting there teeth kicked in by AMD.
I'll be upgrading to the P4-633 then. Yeah it's strange thye are even going to both with the 6x2 series unless they want to make a tier of products, but that sucks.
DRM, at least in the beginning, will be an enabling technology. The problem is not the technology itself but rather the ability to ENFORCE license agreements it gives content providers.
I personally dont think everyone following license agreements is the problem, but rather the fact that the content providers will be able to achieve THEIR aims using MY hardware. This will, in turn, make it easier for content providers to force users into insane license agreements, like being able to play a song only on a single pc, for example (at least, that's what my limited understanding of DRM--and trusted computing as a whole--leads me to believe).
One thing we probably should have pointed out is that this roadmap ends right before the time when we should start seeing the Conroe/Merom CPU cores show up (2H'06). Part of that is probably because not even Intel known what they'll call those processors, but I think that's the biggest event currently on the Intel CPU horizon. :)
PrinceGaz: Two things; "just about every tech site" was really ONE website that understood something poorly, reported on it, and then about 30 other websites reporting the same thing or reclarifying the original statement. DTCP is surprisingly similar to HDCP in many ways but mainly differs in the fact that it only works for DTCP-ready content. How much DTCP content are you viewing right now that you need to worry about whether or not it will hamper your multimedia experience? I'm kinda approaching this like a scenario for Macrovision without DVDs.
OK point 2; it can be disabled. The first reaction many people claim is "oh it can be disabled, it's only a matter of time before you cannot!". Maybe. On the other hand, if you want IPTV without any DRM you might want to start your own broadcast studio.
I don't like unnecissary DRM as much as the next person, but I do want to watch four different angles of the Yankees @ 1080p over FIOS. Maybe I'll write something exploring some of the non-knee jerk details of DTCP.
VT is interesting and has major advantages over using something like VMWare which only implements partial hardware support for a host OS. Of course the vast majority of people, even most AT readers, are unlikely to use it seriously.
Personally I'm far more interested/concerned about the progress of Intel's LaGrande and AMD's Presidio security (aka hardware DRM) in forthcoming chips. Why is it that this topic seems to be completely ignored by AT articles when it is potentially the most important aspect of new processors, given the implications it has on who will really control our computer (assuming you are foolish enough to install the DRM-riddled Longhorn when it is released)?
Just about every other tech site has reported about the recent Pentium D DRM story in depth (both the initial story, and the follow up with their analysis of what that really meant), but it hasn't had a single mention on AT.
VT/Pacifica is a niche technology, that much is for certain. It will definatly help the server segment(imagine 4 'machine' clusters that are all running on the same hardware) and some enthusiasts may like it(although I bet most won't use it often to maximize performance), but its not going to take the world by storm or anything.
As for Yonah and power savings, remember that the entire platform must be compared to comparable AMD solutions, not just the CPU. AMD builds most northbridge functions(memory controller being the obvious one) into thier CPU which saves a considerable amount of power, and allows single chip chipset solutions like nForce to be practical. Measuring power consumption of just the CPU's without the supporting platform is apples to oranges.
And in order to be 100% precise :-) Dual OS natively is brought to x86 for the first time through these two technologies. The current solutions require emulation/software layer and thus exhibit higher overheads.
The problem though lies in the fact that even dual cores under the same OS can not cope with heavy multitasking (eg two heavy applications) without a significant perf. penalty for both. So as correctly pointed in this site, its another thing to increase heavy multitasking performance and another to actually use those scenarios since the hit will be noticeable. The same logic applies even more exaggerated in the case of two OSes and their apps running concurrently... (and by that I do not mean Solitaire XP together with Opera for Linux; this is something even Vanderpool can do :-)
StriderGT: Well dual OSes can be done right now with overhead; thats what VMware, UML and such are for. Part of the goal is to minimize overhead. VT nor Pacifica are limited to dual core CPUs by the way.
I do not think that anyone besides administrators would need VT, let alone use such a thing. DualBoot seems bulky but its way faster and more robust. A real usage scenario would require you to boot in XP to play games reboot in Linux to surf or whatever, otherwise two OSes running together will impose a real overhead. So you only gain the few mins or secs between each boot and lose performacewise. Its more like look what dual cores can do feature than what most peole will do...
Interesting, but I would like to have a chart of AMD to the side. Is this coming tomorrow?
Of all the chips Yonah looks the most promising and yet as I was glancing through it would be confined to certain applications. The energy requirements are stellar! I would love to see how AMD is going to compete.
StriderGT: Actually I think VT is pretty neat. I run Linux on one machine and Windows for work. Putting both on the same computer would be really awesome.
hope so 2 #9 :-) because otherwise we will stick to "virtualized" performance gains... Can u say Vanderpooled?!? A real show stopper for desktop users!
BTW I forgot to give a thumbs up to intel engineers for their latest innovation. The dual core superglue.
PS I think that marketing dep of intel devoured their last real engineers long ago. So now they meet apple and we get platformization en extremis... I love this buzzzzzzzzzzwordzzzzzzzz
Instead of this really pathetic roadmap they can just throw in the towel in technology terms...
The real roadmap reads:
1. Price cuts and Price undercuts till AMD suffocates...
2. Marketing Nonsense Flooding (even rivers?!?) aka Vanderpool, EMT64=AMD 64bit etc etc
3. Company bullying. Either u stick with us or we send the Borg 4s to heat u to death...
4. They've got the furniture company 2. Apple anybody?
Nice article Kris. I have one comment in the grammar department. The following sentence fragment at the end of the article "... four core Yonah blades would certainly peak out attention." Should be "... four core Yonah blades would certainly pique our attention."
This seems underwhelming other than Yonah for some reason. Only one speedbump for dualcore by Q1 '06? AMD seems to have the server space to themselves for 6-8 more months on dualcore. That could cause problems for Intel and marketshare/perception. AMD had 28% of the 4P server shipments in Q1 according to IDC. L=http://www.xbitlabs.com
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
57 Comments
Back to Article
cssmicro - Friday, July 22, 2005 - link
50 - I don't think you realize how cost-inneffective it is to create a completely new process flow or sort flow just to turn off a feature. Creating a different chip costs many hundreds of thousands of dollars PER LAYER that's changed. The mask changes alone would cost about half of a million dollars per reticle. Forget about the engineering initiative necessary to design the changes. It would be retarded of Intel to make a move like that. 45 hit the nail right on the head. The same products will be made, and then filtered out by working/non-working parts at end of line sorting.You don't really think your graphics / non-graphics chipsets are MADE differently, do you? (PSST, they're not). Simply put, they're all tested at the end of production. Some have working graphics sub-systems, some don't. They're distributed accordingly.
cornflake - Monday, June 20, 2005 - link
I'm not sure how much Intel paid AnandTech for this article, but it must be a grundle to shovel it like this..."As a dual core solution, Yonah is the most advanced (other than perhaps Itanium 2 Monticeto) solution that we have seen out of either AMD or Intel."
Wow, so they have some cool new integrated memory controller in place to leap frog AMD. NO, well then what about the new Intel branded Hyper-transport knock off they are working on? Oh well, at least we can look forward to some big Intel adds on AnandTech in the coming months!
Perhaps when AnandTech talks about how advanced a platform is, they should wait until they can compare the performance with others as they did recently in their article...
http://www.anandtech.com/IT/showdoc.aspx?i=2447
AMD is a full generation ahead in technology and a generation behind in fluff.
Icehawk - Friday, June 17, 2005 - link
What matters is how fast Corporates embrace 64-bit outside the Enterprise app level (since most are still mainframe or at least Unix based). Generally technology and software updates are slow to rollout due to costs, contracts, stability, etc. If, somehow, 64-bit was to become part of the mainstream corporate app profile - THEN it will matter if Intel has a 64-bit mobile (laptop) processor.I would add at least one year past when Longhorn finally debuts before you see a major shift towards 64-bit. Until then it won't be a big deal IMO.
apriest - Wednesday, June 15, 2005 - link
Dual Dempsey's sounds intriguing... and dang expensive I'll wager...JarredWalton - Wednesday, June 15, 2005 - link
52:Add 1 for EM64T support on 5xx and 3xx CPUs.
Add 2 for VT support on 6xx CPUs.
Add 3 for 65nm 6xx CPUs that overlap 90nm parts (and have VT).
Otherwise, it's basically higher numbers within the same family gives better performance/features. It's a way to de-emphasize MHz/GHz, since we may be plateauing on clock speeds for a while. Intel spent so long convincing people to upgrade PCs for an extra 400 MHz that they now need to change tactics. Smart marketing, really.
cryptonomicon - Wednesday, June 15, 2005 - link
for the love of god, can someone explain INTELs not so new naming scheme? I cant make 1 bit of sense from it, it just leaves me mystified.I mean come on!! at least with AMD we knew the 3000+ meant somewhat-roughly-equivalent to a pentium of 3000mhz. gah!
PrinceGaz - Wednesday, June 15, 2005 - link
Another point with Yonah is that it is intended to be a low-power consuming Mobile design, not desktop. Most laptop users have no need of a faster CPU but do want longer battery life / smaller lighter battery etc.Given that the whole design of the Pentium M chips (Banias -> Dothan -> Yonah) is about saving power by artificially limiting the maximum intended clock speed, it makes sense for Intel to make Yonah no faster than Dothan so that they can further reduce the power consumption of the processor at any given speed compared to what it would draw if the design could reach, say 2.5GHz.
It doesn't seem at all surprising to me that Yonah will be little or no higher clocked than Dothan as there is little demand for the extra speed but plenty of demand for reduced power consumption.
JarredWalton - Wednesday, June 15, 2005 - link
45 - Possibly, but as we indicated in the article, it's just a guess. As I understand it, Vanderpool (VT) isn't adding a lot to the die size - actually, it's been present since the Prescott 2M/Irwindale cores, but deactivated. I'm more inclined to believe that Intel is just trying to separate the market: charge more for VT enabled chips, as they will go to server/workstation systems which tend to cost more.-----------
Regarding clock speed, while it's true that clockspeed isn't everything, we're essentially looking at a process shrink that isn't improving the top speed of CPUs at all. Yonah is pretty much Dothan (maybe) with dual cores. Banias topped out at 1.7 GHz, Dothan topped out at 2.26 (or will in a while), and Yonah is launching at 2.13 GHz max. It's surprising, that's all.
While MHz/GHz are not everything, the basic fact remains that similar architectures running at the same clock speed will perform similarly. Dothan 2.13 GHz will match a single core Yonah 2.13 GHz barring any drastic changes to the underlying architecture. Merom is the next major change in the underlying architecture, so we'll have a CPU that may be as much as 50% faster at the same clock speed.
Taking a more pragmatic look at the CPU environment, it's sort of interesting that the fastest (official) Northwood cores were 3.4 GHz and Prescott with 90nm and a longer pipeline only bumped that up 400 MHz. Willamette topped out at 2.4 GHz, so the 180nm to 130nm transition increased top CPU spped by 1000 MHz - 42% instead of only 12%!
Think AMD's done much better? The fastest 130nm chips from AMD were the FX-55 (2.6 GHz) and right now it doesn't look like they'll release anything above 2.8 GHz with 90nm SOI! Even if we throw out the FX-55 (which is a bit of a special case, since it's the only 130nm AMD chip with strained silicon), AMD still only went up 400 MHz with the transition - 17%.
The best we saw out of AMD/Intel for the transition to 90nm was a 33% speed bump from Banias to Dothan, but it sounds like that was also accompanies by a slightly longer pipeline.
If we got as much as a 50% speed increase going from 180nm to 130nm, and only a 33% going from 130nm to 90nm (even with adding copper, SOI, and strained silicon), what will 65nm bring? A maximum of a 20% speed increase for the same design? Maybe even less? Time will tell, but I find it an interesting trend to say the least!
piroroadkill - Wednesday, June 15, 2005 - link
Yonah was the only thing worth looking at. This is certainly no 'offensive' by Intel.Pandaren - Wednesday, June 15, 2005 - link
People keep shouting about 64-bits, but 64-bits won't make a difference to the vast majority of users. Most of the people I know who use computers surf the web, write email, print pictures, and other very basic tasks. In the corporate space, the transition to 64-bit will be glacial. The place I'm working at has used Windows 2000 for almost four years now and has no plans to change. They aren't the only ones:http://news.com.com/The+slow+road+to+Windows+XP/21...
The only ones 64-bit will make a difference to are the very small percentage of people who actually need it, and the fanbois who buy the biggest for the sake of having the biggest.
segagenesis - Wednesday, June 15, 2005 - link
Although it still sounds vague in explanation, if VT tech lets you run two *different* operating systems at the *same time*, similar to using VMWare in full screen mode... that would be pretty nice.The savings of having to buy extra hardware (or VMWare itself) for another OS without dual booting would help those on a budget.
Shintai - Wednesday, June 15, 2005 - link
#42A geforce 6600GT runs at 500Mhz GPU..a 7800GTX runs at 430Mhz..does the 7800GTX suck compared to the 6600GT?
Sometimes you just don´t need huge CPU power, but you need low powerusage for either batterytime and/or how compact you can make it.
The 1.06Ghz Yonah most likely uses a few watts only. And with few we are talking a low single digit number. Or the same as having 30 1.06Ghz for 1 2.4Ghz AMDx2. Or having 45 1.06Ghz instead of 1 3.2Ghz P4D.
Araemo - Wednesday, June 15, 2005 - link
"All of the Cedar Mill cores clearly have VT support (as do the Prescott 2M cores), so why Intel would want to deactivate it in one model is anyone's guess."Binning!
Intel is expecting noticeable issues getting high yields out of the VT portions of the silicon, or at least are expecting a noticeable failure rate(30% or so higher than the average failure rate for the rest of the chip?), so they are planning something to do with all the chips that fail VT qualification, but pass everything else.
(At least, that's my guess.)
sgtroyer - Wednesday, June 15, 2005 - link
your wording in paragraph 4 is a little wierd:"Presler will in fact be nothing but two Cedar Mill cores sharing the same core, just as Smithfield is only two Prescotts sharing the same core."
Wouldn't it make more sense to say Presler is two Cedar Mill cores sharing the same *die* or sharing the same package? Two cores sharing the same core doesn't make any sense.
Viditor - Wednesday, June 15, 2005 - link
Eug - "But it doesn't HAVE to be 2006. If it's out by 2007 for laptops that's fine"Fair enough...but remember that the important factor here is the PERCEPTION of release.
By that I mean that the imminent release of 64 bit apps would be a big deterrent (IMHO) to anyone thinking of buying a Yonah based laptop next year. If true, then Yonah would be the only chip unable to run the apps. Software in 2006 will most likely be both 32 and 64 bit...but if people believe that any of the apps they use will be released in 2007 as a 64 bit only, then they have to accept that their new laptop will only have a 1 year lifespan (something that businesses would probably avoid, and they buy the most laptops).
This is especially true as AMD should have a very competitive product (both in power and low power usage) that is already 64 bit and will probably cost a few dollars less...
blwest - Wednesday, June 15, 2005 - link
Ok. 1.06ghz... that was soooo 5 years ago.Eug - Wednesday, June 15, 2005 - link
I disagree. 64-bit on laptops can be important, if only because it allows you to do 64-bit development and testing on a laptop.But it doesn't HAVE to be 2006. If it's out by 2007 for laptops that's fine. By that time both Windows Longhorn and OS X 10.5 Leopard should be out, perfect timing for Merom.
mino - Wednesday, June 15, 2005 - link
Viditor:I wasn't completely sure(maybe next Yamhill:).
That's it. For now 64bits on mobile doesn't make sense(except *nix). Howerever in '06 it's gone be pretty much a mainstream feature on desktop(not to mention server).
Also in the big picture this makes sense since it will put SOME(just on niche markets) pressure on AMD with minimal resources amd will also limit P-M into low-power space so it will not interferewith next-ge chips.
But here come BIG BUT! it seams that only single possible serious contender in performance race from intel camp is out of the game!
So it seems AMD has free ground to play for another at least 1.5yrs ! (That makes it 3.5 in total!!!). Anyway i like smart moves by AMD this is NOT gona be GOOD FOR US. (customers)
little sorry for my screams, not slept for too long ;)
Viditor - Wednesday, June 15, 2005 - link
mino - no, Yonah will not be 64bit (as Shintai explained)...but I disagree that it will not be important. For software in 2006, it won't be important but for software in 2007 it will be (IMHO).There you have 2 differing OPINIONS...we shall see! :-)
Shintai - Wednesday, June 15, 2005 - link
#37No..and it´s not really important. Meron(mobile) and Conroe(desktop/server) will be 64bit and with characteristics of pentium M. They are an 8th genration core tho. And not based on the 6th(p-M) or 7th(p4)
mino - Wednesday, June 15, 2005 - link
ONE IMPORTANT QUESTION:(mostly to autor)
WILL YONAH BE 64-bit ????
please tell us.
every glimpse appreciated;)
mino - Wednesday, June 15, 2005 - link
My "typing" is becomming even funnier sometimes, unfortunatelly ;)mino - Wednesday, June 15, 2005 - link
Finally intel execs came to their senses. people should applaud them all at once! They are evidently going to get rid of those super-trooper power drainers they are producing for last 2 yrs.BTW you all seeing performance parity arise just remember tah if AMD needs it even wouldn't need K9 to compete with Merom(unless it will be some miracle chip). They could yust release quad-core server chips plus some 3.2-3.4 desktop K8+ dualies and be done with it !
It's becomming so funny that first chips able to really axploit potential of DDR2(666+),technology som much tooted and pushed by Intel, will be 65nm X2's.
Ironic, isn't it?
Zebo - Wednesday, June 15, 2005 - link
Merom Merom Merom Kris! is the only thing Intel has I'm waiting for since I dont use notebooks. Does'nt quite sound as nice does it.:PI just can't see the extra cache doing much for the 9xx series, much like the 6xx did'nt do squat.. So the only thing that remains to be seen and potentially exciting is power draw and overclockabilty of the 65nm desktop chips.
Calin - Wednesday, June 15, 2005 - link
But on a much more serious note, I think VT would be good if it would work with very little or no OS support. I remember horror stories with Windows and Linux partitions, and I really don't want to find out how much Windows on VT can destabilize the rest of operating systems running on virtual partitionsCalin - Wednesday, June 15, 2005 - link
Executive series of mainboards probably have air conditioned as standardShintai - Wednesday, June 15, 2005 - link
Hmm..I think people have too high expertations after the few last years of gigahurtz.I think 65nm will give us affordable AMD64 X2s maybe a speedbump to 5000 and 5200. But I think it will be more focused on quad cores, cheaper manufactoring and lower power consumption.
P4 65nm. I think we might see the 4Ghz now. But else the same thing as with AMD, cheaper dualcores, lower power usage.
Yonah is abit different, size the manufactoring cost of Yonah wont increase that much compared to a P4/X2 dualcore. But yonah sports SSE3, some 20-30% faster speed at the same frequency. So Yonah will be desktop and server attractive. More than Dothan is now. Plus it keeps its low powerusage. Also a speedbump is likely here.
But remember people, building an X2 or P4D is alot more expensive than a singlecore. So 65nm is not the "Yiiihah" speedbumpage. But more like the 1100$ AMD 4800 X2 down to 3-500$ thing.
So I wouldn´t really expect much other than more cores and alittle tweak here and there until K9 and Meron/Conroe.
Furen - Wednesday, June 15, 2005 - link
If I ran two operating systems at once, I'd basically idle on one while working on the other one. So my overhead for running to OSes would mostly be memory. It'd be like dualbooting without the booting, you just switch your active OS whenever you wish to. It'd be great for those of us who prefer *nix OSes but NEED windows for specific tasks *cough*games*cough*.The problem, of course, will end up being how much additional software will be needed to do this (not to mention how much it will cost ^^), I'm guessing it wont be just installing both OSes and then booting them.
dotdotperiod - Wednesday, June 15, 2005 - link
Seriously why are you guys concerned about clock speed, as everyone has reported clock speed does not equate to a significant increase in performance. BTW who in the hell needs to run four operating systems at once?? I mean it reallY?? Glad to see intel in finally going to stop making two of the same chipset and giving them different names. I almost fell asleep looking at all the different cpu's seems like the same stuff just a different day. I dont run a multi billion dollar company but Intel should seriously simplify and stop getting there teeth kicked in by AMD.Eug - Tuesday, June 14, 2005 - link
I'm surprised that so many people are complaining about the 2.16 GHz Yonah when it's dual-core and so low power. It's only about 35 Watts people.porkster - Tuesday, June 14, 2005 - link
I'll be upgrading to the P4-633 then. Yeah it's strange thye are even going to both with the 6x2 series unless they want to make a tier of products, but that sucks..
Furen - Tuesday, June 14, 2005 - link
Well put.DRM, at least in the beginning, will be an enabling technology. The problem is not the technology itself but rather the ability to ENFORCE license agreements it gives content providers.
I personally dont think everyone following license agreements is the problem, but rather the fact that the content providers will be able to achieve THEIR aims using MY hardware. This will, in turn, make it easier for content providers to force users into insane license agreements, like being able to play a song only on a single pc, for example (at least, that's what my limited understanding of DRM--and trusted computing as a whole--leads me to believe).
JarredWalton - Tuesday, June 14, 2005 - link
One thing we probably should have pointed out is that this roadmap ends right before the time when we should start seeing the Conroe/Merom CPU cores show up (2H'06). Part of that is probably because not even Intel known what they'll call those processors, but I think that's the biggest event currently on the Intel CPU horizon. :)KristopherKubicki - Tuesday, June 14, 2005 - link
PrinceGaz: Two things; "just about every tech site" was really ONE website that understood something poorly, reported on it, and then about 30 other websites reporting the same thing or reclarifying the original statement. DTCP is surprisingly similar to HDCP in many ways but mainly differs in the fact that it only works for DTCP-ready content. How much DTCP content are you viewing right now that you need to worry about whether or not it will hamper your multimedia experience? I'm kinda approaching this like a scenario for Macrovision without DVDs.OK point 2; it can be disabled. The first reaction many people claim is "oh it can be disabled, it's only a matter of time before you cannot!". Maybe. On the other hand, if you want IPTV without any DRM you might want to start your own broadcast studio.
I don't like unnecissary DRM as much as the next person, but I do want to watch four different angles of the Yankees @ 1080p over FIOS. Maybe I'll write something exploring some of the non-knee jerk details of DTCP.
Kristopher
tfranzese - Tuesday, June 14, 2005 - link
A 2.5 GHz Yonah with all the trimmings and some of the poor performing areas addressed might impress me.None of this stuff in their roadmap does however.
PrinceGaz - Tuesday, June 14, 2005 - link
VT is interesting and has major advantages over using something like VMWare which only implements partial hardware support for a host OS. Of course the vast majority of people, even most AT readers, are unlikely to use it seriously.Personally I'm far more interested/concerned about the progress of Intel's LaGrande and AMD's Presidio security (aka hardware DRM) in forthcoming chips. Why is it that this topic seems to be completely ignored by AT articles when it is potentially the most important aspect of new processors, given the implications it has on who will really control our computer (assuming you are foolish enough to install the DRM-riddled Longhorn when it is released)?
Just about every other tech site has reported about the recent Pentium D DRM story in depth (both the initial story, and the follow up with their analysis of what that really meant), but it hasn't had a single mention on AT.
AlexWade - Tuesday, June 14, 2005 - link
And to think, if it wasn't for AMD's competition, we would still be using Pentium 1 at 100 MHz.HSuke - Tuesday, June 14, 2005 - link
I agree. 2.5+ GHz Yonahs with SSE3 would be nice.Doormat - Tuesday, June 14, 2005 - link
Yea I'm really disappointed in Yonah performance. I fully expected to see 2.5GHz Yonahs by Q1 2006.KayKay - Tuesday, June 14, 2005 - link
I like the Intel Chipset/Processor names, thats about it, as it is doubtful I will buy a desktop Intel CPU ever againReflex - Tuesday, June 14, 2005 - link
VT/Pacifica is a niche technology, that much is for certain. It will definatly help the server segment(imagine 4 'machine' clusters that are all running on the same hardware) and some enthusiasts may like it(although I bet most won't use it often to maximize performance), but its not going to take the world by storm or anything.As for Yonah and power savings, remember that the entire platform must be compared to comparable AMD solutions, not just the CPU. AMD builds most northbridge functions(memory controller being the obvious one) into thier CPU which saves a considerable amount of power, and allows single chip chipset solutions like nForce to be practical. Measuring power consumption of just the CPU's without the supporting platform is apples to oranges.
StriderGT - Tuesday, June 14, 2005 - link
And in order to be 100% precise :-) Dual OS natively is brought to x86 for the first time through these two technologies. The current solutions require emulation/software layer and thus exhibit higher overheads.The problem though lies in the fact that even dual cores under the same OS can not cope with heavy multitasking (eg two heavy applications) without a significant perf. penalty for both. So as correctly pointed in this site, its another thing to increase heavy multitasking performance and another to actually use those scenarios since the hit will be noticeable. The same logic applies even more exaggerated in the case of two OSes and their apps running concurrently... (and by that I do not mean Solitaire XP together with Opera for Linux; this is something even Vanderpool can do :-)
StriderGT - Tuesday, June 14, 2005 - link
#14 I totally agree with you, but that does not change the fact that VT/Pacifica is a niche feature at best (admins, testers etc)KristopherKubicki - Tuesday, June 14, 2005 - link
StriderGT: Well dual OSes can be done right now with overhead; thats what VMware, UML and such are for. Part of the goal is to minimize overhead. VT nor Pacifica are limited to dual core CPUs by the way.Kristopher
StriderGT - Tuesday, June 14, 2005 - link
I do not think that anyone besides administrators would need VT, let alone use such a thing. DualBoot seems bulky but its way faster and more robust. A real usage scenario would require you to boot in XP to play games reboot in Linux to surf or whatever, otherwise two OSes running together will impose a real overhead. So you only gain the few mins or secs between each boot and lose performacewise. Its more like look what dual cores can do feature than what most peole will do...cscpianoman - Tuesday, June 14, 2005 - link
Interesting, but I would like to have a chart of AMD to the side. Is this coming tomorrow?Of all the chips Yonah looks the most promising and yet as I was glancing through it would be confined to certain applications. The energy requirements are stellar! I would love to see how AMD is going to compete.
KristopherKubicki - Tuesday, June 14, 2005 - link
StriderGT: Actually I think VT is pretty neat. I run Linux on one machine and Windows for work. Putting both on the same computer would be really awesome.Kristopher
StriderGT - Tuesday, June 14, 2005 - link
hope so 2 #9 :-) because otherwise we will stick to "virtualized" performance gains... Can u say Vanderpooled?!? A real show stopper for desktop users!BTW I forgot to give a thumbs up to intel engineers for their latest innovation. The dual core superglue.
PS I think that marketing dep of intel devoured their last real engineers long ago. So now they meet apple and we get platformization en extremis... I love this buzzzzzzzzzzwordzzzzzzzz
flatblastard - Tuesday, June 14, 2005 - link
Sure hope AMD has their floatation devices handy.KristopherKubicki - Tuesday, June 14, 2005 - link
Kensei: Ooops - fixed.Kristopher
StriderGT - Tuesday, June 14, 2005 - link
Instead of this really pathetic roadmap they can just throw in the towel in technology terms...The real roadmap reads:
1. Price cuts and Price undercuts till AMD suffocates...
2. Marketing Nonsense Flooding (even rivers?!?) aka Vanderpool, EMT64=AMD 64bit etc etc
3. Company bullying. Either u stick with us or we send the Borg 4s to heat u to death...
4. They've got the furniture company 2. Apple anybody?
phaxmohdem - Tuesday, June 14, 2005 - link
Sorry to be a total dimwit, but what the hell is VT Technology? is it something like NX Bit?Kensei - Tuesday, June 14, 2005 - link
Nice article Kris. I have one comment in the grammar department. The following sentence fragment at the end of the article "... four core Yonah blades would certainly peak out attention." Should be "... four core Yonah blades would certainly pique our attention."michaelpatrick33 - Tuesday, June 14, 2005 - link
This seems underwhelming other than Yonah for some reason. Only one speedbump for dualcore by Q1 '06? AMD seems to have the server space to themselves for 6-8 more months on dualcore. That could cause problems for Intel and marketshare/perception. AMD had 28% of the 4P server shipments in Q1 according to IDC. L=http://www.xbitlabs.comQuestar - Tuesday, June 14, 2005 - link
Heh, a dual core cpu dissipating 15w of heat? Awsome.flatblastard - Tuesday, June 14, 2005 - link
Wow, Intel's roadmaps continue to bore me. I don't know why, they just do I guess.Eug - Tuesday, June 14, 2005 - link
Gimme my 13.3" widescreen 1152x768 Yonah PowerBook!