Nehalem Info from hkepc

[Donnie27]

You just replace it with a higher performing CSI link to the southbridge. So no. Also the FSB itself uses very very little power.

Wouldn't that be a DMI link to the south bridge? Intel has used DMI since at least i875/65. IIRC DMI is already a Serialized CSI like BUS/Link or whatever you like to call it. I only saw Higher end Bloomfield using CSI or Quick Path to a DT-IOH (Tylersberg), then DMI to the ICH-10 (South Bridge). That is unless PC Watch blew it and the first link here missed that too, I'll check.

http://pc.watch.impress.co.jp/docs/2.../kaigai397.htm

[Shintai]

Wouldn't that be a DMI link to the south bridge? Intel has used DMI since at least i875/65. IIRC DMI is already a Serialized CSI like BUS/Link or whatever you like to call it. I only saw Higher end Bloomfield using CSI or Quick Path to a DT-IOH (Tylersberg), then DMI to the ICH-10 (South Bridge). That is unless PC Watch blew it and the first link here missed that too, I'll check.

http://pc.watch.impress.co.jp/docs/2.../kaigai397.htm

For Bloomfield yes, since you still have the I/O hub. For the desktop and mobile versions no. ICH10 is the last ICH.

I also think HKEPC havent realized it yet. Also DMI is just another word really for a PCIe x4 link.

[Donnie27]

For Bloomfield yes, since you still have the I/O hub. For the desktop and mobile versions no. ICH10 is the last ICH.

I also think HKEPC havent realized it yet. Also DMI is just another word really for a PCIe x4 link.

OK, Cool, thanks!

[Helmore]

Also DMI is just another word really for a PCIe x4 link.

Oh....I didn't know that....just looked it up to be sure:

Direct Media Interface
To meet the device-to-memory bandwidth requirements of PCIe, SATA, USB 2.0, Intel HD Audio and others, a proprietary serial interface, based on PCIe, was developed, the DMI link. This link connects the ICH6-M and the GMCH. It offers 2 GB/s maximum bandwidth compared to 266 MB/savailable with the ICH4-M hub interface. The DMI integrates priority-based servicing to allow concurrent traffic and isochronous data transfer capabilities for Intel HD Audio.

Linky
That means that DMI isn't even close to CSI from a technical standpoint....isn't it.....
Well we learn something new every day....

[Shintai]

Oh....I didn't know that....just looked it up to be sure:

Linky
That means that DMI isn't even close to CSI from a technical standpoint....isn't it.....
Well we learn something new every day....

Precisely. And thats also why it has outserved its purpose. Specially with 6+ SATA ports now that is a peak of 1.8GB/sec in theory. Plus USB, turboflash etc etc.

And I´m sure its also easier and cheaper to just link the ibexpeak with CSI/Quickpath. Faster, less traces and most likely better electric properties.

When thinking about it. I would also make a quite real and possible statement that nVidia is out of the chipset business in 2010/2011. VIA knows this and already abandon Intel chipsets. Because look at the Ibexpeak. Its basicly the same AMD will have with their cores in 2010 or so. And the IGP market is also 100% AMD/Intel with on CPU IGPs. I think this is also why AMD puts less and less effort on highend discrete GFX. And another bold statement would be that around 2013-2015 everything the Ibexpeak and AMD equal will be on the CPUs. That can yield some seriously small corporate/parents desktops with a CPU+memory+SSD basicly

[Donnie27]

Oh....I didn't know that....just looked it up to be sure:

Linky
That means that DMI isn't even close to CSI from a technical standpoint....isn't it.....
Well we learn something new every day....

IIRC DMI is already a Serialized CSI like BUS/Link or whatever you like to call it.

DMI was one of the first fruits of the PCI Sig and that is where it came from. The DMI link is merely a different variation of a PCI-E Even the link you posted hints at that. This tech is the root of CSI and I believe if Intel felt it needed it sooner, they would have went with it.

[Donnie27]

http://www.pcisig.com/news_room/08_08_07/

[Hornet331]

Precisely. And thats also why it has outserved its purpose. Specially with 6+ SATA ports now that is a peak of 1.8GB/sec in theory. Plus USB, turboflash etc etc.

And I´m sure its also easier and cheaper to just link the ibexpeak with CSI/Quickpath. Faster, less traces and most likely better electric properties.

When thinking about it. I would also make a quite real and possible statement that nVidia is out of the chipset business in 2010/2011. VIA knows this and already abandon Intel chipsets. Because look at the Ibexpeak. Its basicly the same AMD will have with their cores in 2010 or so. And the IGP market is also 100% AMD/Intel with on CPU IGPs. I think this is also why AMD puts less and less effort on highend discrete GFX. And another bold statement would be that around 2013-2015 everything the Ibexpeak and AMD equal will be on the CPUs. That can yield some seriously small corporate/parents desktops with a CPU+memory+SSD basicly

i really hope that doesn't means the death of highend discrete cards, cause i doubt we see anythign compareable to a 8800 on a cpu soon.

[Helmore]

i really hope that doesn't means the death of highend discrete cards, cause i doubt we see anythign compareable to a 8800 on a cpu soon.

It won't, not for the next 10-15 years and the graphics chip inside the CPU can always be used for physics calculations.

[Donnie27]

i really hope that doesn't means the death of highend discrete cards, cause i doubt we see anythign compareable to a 8800 on a cpu soon.

As always even if Geeks tried to make it something it is not, the highly integrated CPU's have always been for Budget systems. That's what Timna was meant as right from the start. Look at the rest of the Layout of the platform for it and it even screams Budget.

[Shintai]

It won't, not for the next 10-15 years and the graphics chip inside the CPU can always be used for physics calculations.

I´m quite sure the CPU part will handle that...always...physics is and have always been a flop on GPUs

The only thing it will do is sit idle or do 2D.

[Shintai]

It won't, not for the next 10-15 years and the graphics chip inside the CPU can always be used for physics calculations.

I wouldnt say 10-15 years. Looking at how relatively close we are to true raytraycing and abundance of CPU power along with maximum useable resolution in comparision to the human eye. I would say 6-8 years.

nVidias biggest fear is this. Since their goldmine chipset business is already doomed.

However AMDs and Intels biggest fear is to end in the gadget segment sooner or later.

[MaxxxRacer]

If these slides are true, then Nehalem looks nothing short of amazing.

The only thing I pray that Intel really works hard on is the IMC. Having a robust 3 channel DDR3 controller would be amazing. By robust, I mean not finicky like that of beloved Athlons of years gone past, but easily overclockable and not requiring 900 bios options to get it stable.

[Helmore]

If these slides are true, then Nehalem looks nothing short of amazing.

The only thing I pray that Intel really works hard on is the IMC. Having a robust 3 channel DDR3 controller would be amazing. By robust, I mean not finicky like that of beloved Athlons of years gone past, but easily overclockable and not requiring 900 bios options to get it stable.

They know how to do it on their chipsets, so I have no worries there...

[Donnie27]

If these slides are true, then Nehalem looks nothing short of amazing.

The only thing I pray that Intel really works hard on is the IMC. Having a robust 3 channel DDR3 controller would be amazing. By robust, I mean not finicky like that of beloved Athlons of years gone past, but easily overclockable and not requiring 900 bios options to get it stable.

MOST of the time Intel shoots for stability first, at the cost of speed. But what good is fast if its crashing.

[Zytek_Fan]

MOST of the time Intel shoots for stability first, at the cost of speed. But what good is fast if its crashing.

They're probably well on their way to that by now since they demonstrated Nehalem booting Windows at IDF.

[Donnie27]

They're probably well on their way to that by now since they demonstrated Nehalem booting Windows at IDF.

True! But this still relates to that other thread that caused all of the fights. If AMD has nothing and Penryn is selling what gives Intel the Push to NOT delay Nehalem for at least the Desktop?

Link

Intel Unveils 16 Next-Generation Processors, Including First Notebook Chips Built on 45nm Technology ›INTERNATIONAL 2008 CONSUMER ELECTRONICS SHOW, Las Vegas, Jan. 7, 2008 – Intel Corporation unveiled 16 products today, including the company's first 45 nanometer (nm) processors for Intel® Centrino® Processor Technology based laptops.

See? That is Clearly the Reason most reasonable posters here wanted to see AMD do well with Phenom. That's really doing well and not merely pretending they're doing well. If they don't we'll more than likely see another delay caused by Obscure errata or some other lame excuse to milk more money from the Computer Public. This ain't bad since Penryn is Kick-A$$ but Nehalem will be even better. I know folks who're already waiting on it.

[Zytek_Fan]

True! But this still relates to that other thread that caused all of the fights. If AMD has nothing and Penryn is selling what gives Intel the Push to NOT delay Nehalem for at least the Desktop?

Link

Intel Unveils 16 Next-Generation Processors, Including First Notebook Chips Built on 45nm Technology ›INTERNATIONAL 2008 CONSUMER ELECTRONICS SHOW, Las Vegas, Jan. 7, 2008 – Intel Corporation unveiled 16 products today, including the company's first 45 nanometer (nm) processors for Intel® Centrino® Processor Technology based laptops.

See? That is Clearly the Reason most reasonable posters here wanted to see AMD do well with Phenom. That's really doing well and not merely pretending they're doing well. If they don't we'll more than likely see another delay caused by Obscure errata or some other lame excuse to milk more money from the Computer Public. This ain't bad since Penryn is Kick-A$$ but Nehalem will be even better. I know folks who're already waiting on it.

I hope AMD can put out a bug free K10 and get it up to speed. We need competition

[Helmore]

I hope AMD can put out a bug free K10 and get it up to speed. We need competition

I'm not sure if that will give enough competition for Intel to hurry up on Nehalem, maybe K10 on 45 nm. might do the trick....but that's still a year away and thus to late....

[Donnie27]

I hope AMD can put out a bug free K10 and get it up to speed. We need competition

Yet, if you don't lie for them, you have folks calling others FanBoys.

I'm not sure if that will give enough competition for Intel to hurry up on Nehalem, maybe K10 on 45 nm. might do the trick....but that's still a year away and thus to late....

Intel doesn't have to hurry Nehalem no matter what AMD does. I meant Intel would stick to schedule and ship it later.

[Zytek_Fan]

Yet, if you don't lie for them, you have folks calling others FanBoys.



Intel doesn't have to hurry Nehalem no matter what AMD does. I meant Intel would stick to schedule and ship it later.

I guess people just keep telling themselves it isn't as bad as it seems.



Yep, Nehalem will still launch late Q4 08 and Q1 09 (someone said Q2 09 now though... ) no matter what
Probably early server CPUs late this year, followed by limited desktop availability early next year...

[Shintai]

I guess people just keep telling themselves it isn't as bad as it seems.



Yep, Nehalem will still launch late Q4 08 and Q1 09 (someone said Q2 09 now though... ) no matter what
Probably early server CPUs late this year, followed by limited desktop availability early next year...

The 3 dates are for 3 segments. First server/Extreme in Q4 08. Then Performance/mainstream in Q1 09. And value in Q2 09.

So for those not buying extreme or server here. Nehalem comes in Q1 2009.

[Zytek_Fan]

The 3 dates are for 3 segments. First server/Extreme in Q4 08. Then Performance/mainstream in Q1 09. And value in Q2 09.

So for those not buying extreme or server here. Nehalem comes in Q1 2009.

I'm gonna try to grab Extreme

[adamsleath]

i'll probbly have a penryn for at least one year b4 going nehammel- ioften mistakenly typo nehamel. must be dislexic.

how many years b4 multicore cpu's are mainstream and super cheap.
q'2140' @ <100 bucks mmmm.
i reckon 2011 22nm sandybridge projected then... holy moly

...but nehamel...int graphics on core could be a v nice thing to have if it can be used in tandem with g card....yes: old news but a nice step forward for value adding to a cpu line.

AMD's Chief Technology Officer Phil Hester said in an interview that AMD's Fusion project will be in production only in late 2009. This means it won't be available until 2010, which is later than the company initially expected.

http://www.dvhardware.net/article16469.html

[Zytek_Fan]

I'm gonna go cheap as possible for high end stuff for my Penryn rig...so no SLI, CrossFire maybe...