Nehalem-EP......BLOOMFIELD

Printable View

Show 100 post(s) from this thread on one page

09-02-2008, 07:20 AM
Hornet331

im still waiting for benches from a not beta platform. :yepp:
09-02-2008, 07:40 AM
JCornell

Quote:

Originally Posted by Hornet331

im still waiting for benches from a not beta platform. :yepp:

Almost become Alpha platform :p:
Nehalem chips already released ES Rev. C0 & C1 :yepp:
09-02-2008, 07:45 AM
OBR

Yeah, my CPU has retail revision ... and mobo is last Rev. before Retail ... my platform become almost Retail ...
09-02-2008, 07:49 AM
Linchpin

Quote:

Originally Posted by OBR

Yeah, my CPU has retail revision ... and mobo is last Rev. before Retail ... my platform become almost Retail ...

Well that took away a fair bit of my enthusiasm for Nehalem, thanks for the info :up:
09-02-2008, 12:43 PM
Drwho?

Quote:

Originally Posted by Anemone

I don't think Nehalem will be another Prescott. But it seems strange to have crippled the L2 by such a large amount. L3 shared on all 4 cores is good, but certainly the value the L2 was playing was known. It's going to certainly be interesting to see where the i7 does well and where it does not before pushing the "buy" button...

Here is an interresting topic ...

Ronak and I argued for 4 years on this topics, we did extensive study on this, Ronak architect team vs the Performance team. I was very afraid that it will cause too much latency increase. After 2 years of arguying, I was forced to admit that I was wrong, and Ronak was right. The increase of latency in smaller than anything you can measure on real application. The multi-layer prefetcher does its job, as it did on Core 2 via the FSB.

The explanation is so simple that it is scary ... :rofl: The memory prefetcher from L2 to L3 is working almost 100% because the pattern from L2 to L3 is filtered by the L2, I mean, the L2 remove most of the unpredictable pattern.

Ronak was and is right, the L2 cache of Nehalem does not cause any issue.

I actually like when the architects are right, and I am wrong, it mean that we will have a kick a// product. :yepp:
And remember Andy's moto: "Only paranoid survive", it is my job to apply this to Intel's product :up:
09-02-2008, 01:09 PM
informal

Quote:

Originally Posted by Drwho?

Here is an interresting topic ...

Ronak and I argued for 4 years on this topics, we did extensive study on this, Ronak architect team vs the Performance team. I was very afraid that it will cause too much latency increase. After 2 years of arguying, I was forced to admit that I was wrong, and Ronak was right. The increase of latency in smaller than anything you can measure on real application. The multi-layer prefetcher does its job, as it did on Core 2 via the FSB.

The explanation is so simple that it is scary ... :rofl: The memory prefetcher from L2 to L3 is working almost 100% because the pattern from L2 to L3 is filtered by the L2, I mean, the L2 remove most of the unpredictable pattern.

Ronak was and is right, the L2 cache of Nehalem does not cause any issue.

I actually like when the architects are right, and I am wrong, it mean that we will have a kick a// product. :yepp:
And remember Andy's moto: "Only paranoid survive", it is my job to apply this to Intel's product :up:

Interesting post :),thanks.

Do you have any comments on OBR's post here,especially on power consumption in full load(supposedly a lot higher than on 45nm C2Q):

Quote:

Originally Posted by OBR

My first impressions with own Nehalem ...

1. BIOSes and whole platform is still very immature ...
2. Only little raised reference clock causes massive unstability ...
3. Ocing of locked-multi Nehalems will be a problem ... Reference clock of Bus is not like a FSB - my max stable clock is 140MHz from 133MHz
4. If you want great clocking, you need a Extreme chip with unlocked multi
5. With these early BIOSes is Memory performance poor (or Everest dont know how to measure it?)
6. Power consuption is in idle with all power savings great, but in fully load is far away from 45nm Quads ...
7. Max stable ocing was on my chip about 3500MHz ...
8. Performance is various, read my previous posts in this thread ...
9. We have two months to launch, and i believe Intel will do many improvements to that date. Will see next month, with new BIOSes and maybe different mobo ...
09-02-2008, 01:44 PM
bowman

Quote:

Originally Posted by Drwho?

Here is an interresting topic ...

Ronak and I argued for 4 years on this topics, we did extensive study on this, Ronak architect team vs the Performance team. I was very afraid that it will cause too much latency increase. After 2 years of arguying, I was forced to admit that I was wrong, and Ronak was right. The increase of latency in smaller than anything you can measure on real application. The multi-layer prefetcher does its job, as it did on Core 2 via the FSB.

The explanation is so simple that it is scary ... :rofl: The memory prefetcher from L2 to L3 is working almost 100% because the pattern from L2 to L3 is filtered by the L2, I mean, the L2 remove most of the unpredictable pattern.

Ronak was and is right, the L2 cache of Nehalem does not cause any issue.

I actually like when the architects are right, and I am wrong, it mean that we will have a kick a// product. :yepp:
And remember Andy's moto: "Only paranoid survive", it is my job to apply this to Intel's product :up:

Now that is interesting. I wonder what you said about static CMOS.. ;)
09-02-2008, 02:17 PM
Drwho?

Quote:

Originally Posted by informal

Interesting post :),thanks.

Do you have any comments on OBR's post here,especially on power consumption in full load(supposedly a lot higher than on 45nm C2Q):

I will let the journalists make the demos at launch time ... :yepp:
I believe OBR has a very early sample.
09-02-2008, 07:18 PM
npk

Quote:

Originally Posted by Drwho?

I will let the journalists make the demos at launch time ... :yepp:
I believe OBR has a very early sample.

and that would be.....? ;)
09-02-2008, 07:20 PM
Anemone

I'm not saying the L3 central isn't worthwhile and certainly to have a central pool and still have the individual cores fed properly you had to replicate to the L2. But seems to me there is no room left in the L2 to conduct a single core's chores (to keep the example simplified). You could have doubled or quadrupled the L2 with not a large hit on cost or really complexity since you've already designed the basic working format. Even then you'd still have room leftover in the L3 pool and each core would work faster, utilizing L2, and still have an excess of L3 to tap for the next tasks to assign to a core.

How I would have envisioned the layout:
1mb L2/Core
8mb of L3 shared

The cost reduction of the smaller L2 than in prior series would have covered the addition of the L3 and probably a mem controller of significant capability in the bargain.

Now I say this and I have to believe you gave this a shot. I honestly think you didn't draw up the current ratios without experimenting. So yes I'll wait for the tests, but it "feels" to me like Intel took the L2 down more for cost to benefit ratio than anything purely performance oriented. Meaning there was an advantage to the additional L2 (as surely there would be) but it was judged that the additional benefit didn't warrant the cost involved. I'm not baiting you to argue this, just explaing a "feeling" on this topic and any commentary you may feel is worthy is fine or none is fine too.

Given where the 9770 landed in cost, perhaps bringing things under control wasn't all bad. And perhaps what was sacrificed won't be all that noticeable. So I'll wait and see. But I do feel "some" additional L2 would have yielded a slightly better chip.
09-02-2008, 07:24 PM
Movieman

Dr.Who?:
What would be your guess as to the difference in performance of a 8 core Harpertown machine at 3200 and a 8 core gainstown at 3200 doing work that can take advantage of the HP in the new Nehalem based systems?
I'm talking about Distributed Computing work as we do for WCG where each core is assigned a work unit.
That's really what this comes down to me, how much more work can be done in the same timeframe..
Thank you.
09-02-2008, 07:58 PM
Ace-a-Rue

Quote:

Originally Posted by Anemone

You could have doubled or quadrupled the L2 with not a large hit on cost or really complexity since you've already designed the basic working format.

i DOUBT that because the transistor count on the die would probably quadruple just on doubling the size of L2.
09-02-2008, 08:45 PM
Drwho?

Quote:

Originally Posted by Ace-a-Rue

i DOUBT that because the transistor count on the die would probably quadruple just on doubling the size of L2.

you will see very little gain from increasing the size of the L2, its very short latency is a plus that you do not want lose.
09-02-2008, 08:48 PM
Drwho?

Quote:

Originally Posted by Movieman

Dr.Who?:
What would be your guess as to the difference in performance of a 8 core Harpertown machine at 3200 and a 8 core gainstown at 3200 doing work that can take advantage of the HP in the new Nehalem based systems?
I'm talking about Distributed Computing work as we do for WCG where each core is assigned a work unit.
That's really what this comes down to me, how much more work can be done in the same timeframe..
Thank you.

hehehe, I just can't answer this, I hope you understand ... :rofl::ROTF::rofl::ROTF::rofl::rofl::rofl::ROTF: :ROTF::clap::clap::D
09-02-2008, 09:10 PM
Movieman

Quote:

Originally Posted by Drwho?

hehehe, I just can't answer this, I hope you understand ... :rofl::ROTF::rofl::ROTF::rofl::rofl::rofl::ROTF: :ROTF::clap::clap::D

That's honest and yes, I do understand..
My guess is a 30% increase based on what I've seen and thats enough to push me to do one and if they will do 4000 like these Harpertowns then they will be winners.
My other concern is heat.
As to whether with the onchip IMC they will produce a higher heat dump than the harpertowns.
Currently I am able to run a pair of harpertowns at 100% load at 3758 on air at 47C in a 72F room..
Can you comment on the heat factor or is that still under NDA also?
Thank you..

Looks around, sees Dr.Who? is gone......
Damn, ran the poor guy right off the forum again!:rofl:
09-02-2008, 10:12 PM
qurious63ss

[QUOTE=OBR;3264423]Yeah, my CPU has retail revision ... and mobo is last Rev. before Retail ... my platform become almost Retail ...[/QUOT

You might have an earlier rev. The process (45nm HK) has already matured on penryn and now is ready for nehalem (BTW that is the beauty of tic toc). The chip that you have may still have some bugs in the arch design level for power mgmt that still hadn't been worked out yet. As long as the problem exist in the design level and not the process level then a single stepping can fix the issue.

BTW, I can tell you that it's fixed, but I can't provide sources.
09-03-2008, 12:55 AM
OBR

[QUOTE=qurious63ss;3266266]

Quote:

Originally Posted by OBR

Yeah, my CPU has retail revision ... and mobo is last Rev. before Retail ... my platform become almost Retail ...[/QUOT

You might have an earlier rev. The process (45nm HK) has already matured on penryn and now is ready for nehalem (BTW that is the beauty of tic toc). The chip that you have may still have some bugs in the arch design level for power mgmt that still hadn't been worked out yet. As long as the problem exist in the design level and not the process level then a single stepping can fix the issue.

BTW, I can tell you that it's fixed, but I can't provide sources.

yes it is possible, that was my EARLY suggestions of Nehalem ... we have to wait for retail mobos and CPU and will see ...
09-03-2008, 05:31 AM
Donnie27

[QUOTE=OBR;3266453]

Quote:

Originally Posted by qurious63ss

yes it is possible, that was my EARLY suggestions of Nehalem ... we have to wait for retail mobos and CPU and will see ...

Sure but you know some folks will jump on that and go negative for the sake of FUD to boost the other company's outlook. Kind of lame that they think this works.
09-03-2008, 05:46 AM
Mk

guys are we even gonna see Core i7 in September?
09-03-2008, 05:56 AM
Donnie27

Quote:

Originally Posted by C.Ron7aldo

guys are we even gonna see Core i7 in September?

Should see an announcement and maybe NDA's are lifted.
09-03-2008, 06:09 AM
GoldenTiger

So what's the latest on when we can buy Core i7 CPU's (say the $300ish model)? I've been looking around but most of the news I'm finding is older. Is it possible we'd see it in Oct/Nov. for purchase?
09-03-2008, 06:27 AM
@@@@

so if ES Rev. is already at C0 & C1

what would be the revision of the retail products?
09-03-2008, 06:45 AM
bowman

Quote:

Originally Posted by GoldenTiger

So what's the latest on when we can buy Core i7 CPU's (say the $300ish model)? I've been looking around but most of the news I'm finding is older. Is it possible we'd see it in Oct/Nov. for purchase?

I wouldn't expect anything earlier than November at this point.
09-03-2008, 08:42 AM
Anemone

Quote:

you will see very little gain from increasing the size of the L2, its very short latency is a plus that you do not want lose.

Fair enough - and I'm sure an honest answer. You've said several times in several ways that much of any slowness of comparing Yorktown to Nehalem and finding Nehalem slower is more due to early silicon/boards vs L2 issues. So I'll take that at face value.

Painful to realize that we've still got a couple more months till this chip is out :) But that is the zen of XS I think :)
09-05-2008, 05:34 PM
Sumanji

More benchies here
09-05-2008, 05:56 PM
vladimir

Hardspell is showing a Bloomfield Core i7 2.93GHz on air and overclocked to more than 4GHz and ran SuperPI 1M in slightly under 10 seconds.
09-05-2008, 06:01 PM
ap4lifetn

looks like the multi is unlocked on that 2.93?
09-05-2008, 07:36 PM
informal

Quote:

Originally Posted by Sumanji

More benchies here

Thanks.Can you confirm the Vantage CPU score is at default clock or the OCed 4Ghz clock?Also,is that version of CPUz not recognizing the number of threads properly?
09-05-2008, 09:11 PM
villa1n

Quote:

Originally Posted by vladimir

Hardspell is showing a Bloomfield Core i7 2.93GHz on air and overclocked to more than 4GHz and ran SuperPI 1M in slightly under 10 seconds.

That voltage doesn't look like its 24/7 though for 45nm ^^
09-05-2008, 09:39 PM
Cooper

Quote:

Originally Posted by informal

Thanks.Can you confirm the Vantage CPU score is at default clock or the OCed 4Ghz clock?Also,is that version of CPUz not recognizing the number of threads properly?

it's either 8 thread 3.0GHz or 4 thread <4.0GHz run
09-06-2008, 04:58 AM
Chri$ch

Now with higer Ref. Clock (~165Mhz) and memory clock

Quote:

What I can tell you:-
Stock Intel Cooler
2 x ATI HD 4870 X2 (Crossfire) (800MHz Core / 3800MHz RAM)
Seagate 160GB (Slow pants HDD but fine for benching)
Cellshock Blue Edition 1866MHz (8-8-8-16) (Clocked at 2000MHz 9-8-8-16) - Also on Weekend special at OcUK!!
Antec Signature 850W PSU

http://www.abload.de/img/preview4qa.jpg

http://www.abload.de/img/vantage1fe4.jpg

http://forums.overclockers.co.uk/sho...php?t=17916507
09-06-2008, 05:05 AM
Hornet331

damn why does he uses everest trail... i would like to see 2nd and 3rd levle cache latencies. :(

memory latencies on the other hand seem quite nice with CL9.
09-06-2008, 02:17 PM
ap4lifetn

Release seems scheduled for November.
http://www.nordichardware.com/news,8101.html

How long after the EE are the regular chips(2.66 & 2.93 variants) regularly released?
09-06-2008, 02:44 PM
Mad1723

Guys, one of the guys at VR-Zone who posted on the screen of the SuperPi topic says Anand and XS are unreliable sites :ROTF:

Anyway, those screens are damn impressive if true :D

1M under 6 anyone? :D
09-06-2008, 02:46 PM
Hornet331

hmm another november release means its available in europa somewhere bewteen christmas and new year. :D (same with XE yorkfield)
09-07-2008, 12:06 PM
terrace215

Quote:

Originally Posted by ap4lifetn

Release seems scheduled for November.
http://www.nordichardware.com/news,8101.html

How long after the EE are the regular chips(2.66 & 2.93 variants) regularly released?

All 3 of those Nehalems (3.2 2.93 2.66) are to be launched together.
09-07-2008, 06:18 PM
davewolfs

Quote:

Originally Posted by terrace215

All 3 of those Nehalems (3.2 2.93 2.66) are to be launched together.

Obviously too soon to tell, but between the 2.93 and 2.66, which should be more OC friendly?
09-07-2008, 06:31 PM
Sumanji

Both of those will be multi-locked? So I imagine the 2.93 will play nicer due to the higher multi.
09-07-2008, 06:45 PM
JumpingJack

Quote:

Originally Posted by Mad1723

Guys, one of the guys at VR-Zone who posted on the screen of the SuperPi topic says Anand and XS are unreliable sites :ROTF:

Anyway, those screens are damn impressive if true :D

1M under 6 anyone? :D

I really take exception to people who accuse a) Anandtech of malfarious benchmarking... I can reproduce most of his benches where I have like HW and SW readily and easily. b) Calling XS unreliable, most all the info I see here generated by people here who provide HW, screenshots, and such is just as reproducible and trustworthy from what I can gather (notable exceptions are the obvious spam from hit and runners)...
09-07-2008, 06:49 PM
ap4lifetn

Quote:

Originally Posted by vladimir

Hardspell is showing a Bloomfield Core i7 2.93GHz on air and overclocked to more than 4GHz and ran SuperPI 1M in slightly under 10 seconds.

Quote:

Originally Posted by Sumanji

Both of those will be multi-locked? So I imagine the 2.93 will play nicer due to the higher multi.

In the above post, there is an article describing an overclocked 2.93 Core i7, and it seems to have its multiplier adjusted...
09-07-2008, 07:00 PM
villa1n

Quote:

Originally Posted by ap4lifetn

In the above post, there is an article describing an overclocked 2.93 Core i7, and it seems to have its multiplier adjusted...

ES might have unlocked multi?
09-07-2008, 07:05 PM
Sumanji

Quote:

Originally Posted by ap4lifetn

In the above post, there is an article describing an overclocked 2.93 Core i7, and it seems to have its multiplier adjusted...

ES chip most probably.
09-08-2008, 04:06 AM
bowman

Either that or Turbo in effect.
09-08-2008, 05:54 AM
stevecs

Any word on a release date for the Gainestown version? Or was that pushed back to later next year?
09-08-2008, 08:00 AM
Drwho?

you will need this to go with your Nehalem : http://www.extremetech.com/article2/...2329593,00.asp
Nhm Extreme Bandwidth needs it!
09-08-2008, 08:03 AM
Gautam

Quote:

Originally Posted by Sumanji

ES chip most probably.

Really? I thought it was off the shelf at Fry's. :lol:
09-08-2008, 08:04 AM
Drwho?

Quote:

Originally Posted by Gautam

Really? I thought it was off the shelf at Fry's. :lol:

not yet :ROTF: The "entree" is ready, we are preparing the sauce.
09-08-2008, 08:21 AM
Oliver

Francois ya it really rocks

its so awesome
09-08-2008, 10:23 AM
@@@@

November is still far off I really want to see what Nehalem can do with its full potential at least reviewers and testers are getting a lot of testing and benching time, they can squeeze every last inch of potential out of it.
09-08-2008, 04:56 PM
Drwho?

got a 1 GB/s

:yepp:

Quote:

Originally Posted by Oliver

Francois ya it really rocks

its so awesome

I putted 4 of those little babies in RAID 0 ... 1 GB/s :yepp::yepp::yepp::yepp::yepp: with a seek time out of space

nice article here: http://www.anandtech.com/cpuchipsets...oc.aspx?i=3403
09-10-2008, 01:11 AM
RealTelstar

Now the question is, will intel SSD be faster than Micron new ones?
09-10-2008, 01:20 AM
Shintai

Quote:

Originally Posted by RealTelstar

Now the question is, will intel SSD be faster than Micron new ones?

Unless the micron uses the samsung or Intel controller it will. jmicron controller seems to make SSDs using it to...suck.
09-10-2008, 04:08 AM
Viss

Quote:

Originally Posted by Sumanji

More benchies here

Spi mod on XP would be nice. The one on Hardspell is fast.
09-10-2008, 04:44 AM
Charles Wirth

Bummer Gibbo doesnt come around anymore, I have some notes he could use.
09-10-2008, 10:58 AM
JCornell

Looks like SS provided by ocuk, the QPI is 7.2GHz ... :shrug:

From my Gainestown platform, the BIOS seems can set the multiplier, but now I'm with 2.93GHz QPI 5.86GHz, doesn't effect the frequency, Haven't test it with higher grade Nehalem yet ...
09-10-2008, 11:57 PM
Tommy L

hmm, what about the link between the vcore & vdimm? thought that was the problem to get high ram speed.
09-11-2008, 02:45 AM
Hornet331

lol i dont know where the people get the impression that vdimm and v(i)mc(h) has to coubled?

Now you can assign different voltages fo VDIMM and VMCH and i am sure same will be possible for nehalem.
09-11-2008, 03:20 AM
Tommy L

it is strange to do so, not to many ddr3 ram that hit 2000 @ 1.5-1.65v so i hope thats not why intel do not support more than 800 \ 1066 mhz ddr3 speed. on board memcontroller linked to vcore is bad if it was so.
09-11-2008, 03:42 AM
Hornet331

Quote:

Originally Posted by Tommy L

it is strange to do so, not to many ddr3 ram that hit 2000 @ 1.5-1.65v so i hope thats not why intel do not support more than 800 \ 1066 mhz ddr3 speed. on board memcontroller linked to vcore is bad if it was so.

for what do you want 2000mhz, with tripple channle thats 48GB/s, if you dont run apps that have a massive need for bandwidth it will get you nothing. I'd rather have 1600mhz with lower CAS latancy (cl6 maybe even lower :D )
09-11-2008, 03:52 AM
Movieman

Quote:

Originally Posted by Drwho?

you will need this to go with your Nehalem : http://www.extremetech.com/article2/...2329593,00.asp
Nhm Extreme Bandwidth needs it!

Damn, and here I was thinking a couple of 15K SAS drives would get me by.
Trying to keep up with you guys is like trying to win Formula one on a $5000.00 budget!:rofl:
Francois: Couple questions for you.
1) When is the official day the NDA is lifted?
2) If you can bring "your"system here we can set up a special section where no one will see it..
I promise, it will only be seen by a chosen few!:rofl:

Quote:

Originally Posted by Gautam

Really? I thought it was off the shelf at Fry's. :lol:

Damn, I got my 6 at the local flea market..$10.00 each!:p:
09-11-2008, 04:44 AM
Hornet331

Quote:

Originally Posted by Movieman

2) If you can bring "your"system here we can set up a special section where no one will see it..
I promise, it will only be seen by a chosen few!:rofl:

damit, dont be so selfish. :ROTF: ;)
09-11-2008, 05:23 AM
Tommy L

Quote:

Originally Posted by Hornet331

for what do you want 2000mhz, with tripple channle thats 48GB/s, if you dont run apps that have a massive need for bandwidth it will get you nothing. I'd rather have 1600mhz with lower CAS latancy (cl6 maybe even lower :D )

of course, but mem need more than 1.5-1.65 to run that to. but case closed! no need to worry about linked voltage...
09-11-2008, 06:35 AM
Drwho?

Quote:

Originally Posted by Movieman

Damn, and here I was thinking a couple of 15K SAS drives would get me by.
Trying to keep up with you guys is like trying to win Formula one on a $5000.00 budget!:rofl:
Francois: Couple questions for you.
1) When is the official day the NDA is lifted?
2) If you can bring "your"system here we can set up a special section where no one will see it..
I promise, it will only be seen by a chosen few!:rofl:

Damn, I got my 6 at the local flea market..$10.00 each!:p:

the NDA lift date is under NDA :rofl::rofl::rofl::rofl:
09-11-2008, 06:45 AM
Macadamia

Quote:

Originally Posted by Drwho?

the NDA lift date is under NDA :rofl::rofl::rofl::rofl:

:rofl:

We could use hypnosis :rofl:
09-11-2008, 07:26 AM
Donnie27

Quote:

Originally Posted by Drwho?

the NDA lift date is under NDA :rofl::rofl::rofl::rofl:

:rofl::rofl::rofl::rofl: Don't know if I'll still care by then:shrug:
09-11-2008, 07:29 AM
Movieman

Quote:

Originally Posted by Drwho?

the NDA lift date is under NDA :rofl::rofl::rofl::rofl:

Ok, thats an honest answer I can live with..
And I think I'll sig it also!:rofl:
09-11-2008, 07:50 AM
Drwho?

Quote:

Originally Posted by Movieman

Ok, thats an honest answer I can live with..
And I think I'll sig it also!:rofl:

since we are in the Jokes, we have some interesting french fries in France:

http://lafritedunord.mccain.fr/images/mc_paquet.jpg

try his campain support web site in France : http://www.mccain.fr :rofl::rofl::rofl::rofl::rofl::rofl::rofl:

He keeps telling us, it is Freedom Fries!!!!! :ROTF::ROTF:
09-11-2008, 07:51 AM
Drwho?

deleted repost
09-12-2008, 03:54 AM
Tommy L

well.... not so closed after all? http://www.nordichardware.com/news,8118.html
09-12-2008, 04:04 AM
Movieman

Quote:

Originally Posted by Tommy L

well.... not so closed after all? http://www.nordichardware.com/news,8118.html

Interesting read on the voltages to the memory.
Seems to me that the answer is in finding a way to send 2+v to the memory and not to the chip itself.
Either that or as it says in the article to get memory that will run at high speeds with lower voltage.
09-12-2008, 09:24 AM
XS Janus

I DON'T want 2v+ memory, please...
:(
09-12-2008, 10:08 AM
Sumanji

Haha, so Fudo wasn't full of sh1t as most people said ;)
09-12-2008, 10:16 AM
Hornet331

Quote:

Originally Posted by Sumanji

Haha, so Fudo wasn't full of sh1t as most people said ;)

i dont see any proof in here, so fudo is still full of it. :p:
09-13-2008, 01:13 PM
Drwho?

Fudo is a nice guy, don t be so mean.

Francois
09-13-2008, 01:37 PM
Movieman

Quote:

Originally Posted by Drwho?

Fudo is a nice guy, don t be so mean.

Francois

Question for you;
Will you be at CES in Las Vegas in January?
09-13-2008, 01:43 PM
Drwho?

Quote:

Originally Posted by Movieman

Question for you;
Will you be at CES in Las Vegas in January?

I am always there. :yepp:
09-13-2008, 01:50 PM
Movieman

Quote:

Originally Posted by Drwho?

I am always there. :yepp:

Then hopefully I will get the opportunity to say hello and shake hands.

(then kidnap, lock you in a closet for 3 days and pick your brains)
09-13-2008, 02:03 PM
JumpingJack

Quote:

Originally Posted by Drwho?

Fudo is a nice guy, don t be so mean.

Francois

I am sure he is a nice guy... Forrest Gump was a nice guy, but an idiot nonetheless. For a techno journalist, he is usually wrong on the technical stuff... terribly wrong. It fuels the flames of ignorance that winds up in the back alley forums all the time.
09-13-2008, 02:49 PM
Hornet331

Quote:

Originally Posted by JumpingJack

I am sure he is a nice guy... Forrest Gump was a nice guy, but an idiot nonetheless. For a techno journalist, he is usually wrong on the technical stuff... terribly wrong. It fuels the flames of ignorance that winds up in the back alley forums all the time.

i didn't expected such harsh words from you. :p:
09-13-2008, 11:05 PM
AuDioFreaK39

Quote:

Originally Posted by JumpingJack

I am sure he is a nice guy... Forrest Gump was a nice guy, but an idiot nonetheless. For a techno journalist, he is usually wrong on the technical stuff... terribly wrong. It fuels the flames of ignorance that winds up in the back alley forums all the time.

I met him at NVISION. Really nice guy...with a really high voice :D

Sorry, I just had to say it. Awesome though.
09-13-2008, 11:42 PM
JumpingJack

Quote:

Originally Posted by Hornet331

i didn't expected such harsh words from you. :p:

Yeah, well .... it was bit mean, I apologize to Fudo ...

However, Fudo (if you read), please try to learn something about your analysis of technical detail.
09-14-2008, 12:03 PM
Anemone

Quote:

the NDA lift date is under NDA

Ok that was damn funny :)
09-17-2008, 09:01 AM
Mad1723

http://www.hardware.fr/articles/733-...l-nehalem.html

This article contains a pic of the "stock cooler", don't know if it's final though.. probably not...

http://www.hardware.fr/articles/733-...l-nehalem.html

Link to the begining of the article, pretty interesting if you understand french :P
09-22-2008, 12:27 AM
Chri$ch

http://www.abload.de/img/64d88302-a123-4828-9fa9izz.jpg
http://en.hardspell.com/doc/showcont.asp?news_id=4096
09-22-2008, 12:38 AM
Shintai

Nice numbers :)
09-22-2008, 01:37 AM
Scog

I wish I could make out the CPU type, multiplier and memory type. :(
I hate secrets.
09-22-2008, 02:15 AM
WC Annihilus

Quote:

Originally Posted by Scog

I wish I could make out the CPU type, multiplier and memory type. :(
I hate secrets.

Blurred out part of CPU type is "Bloomfield (Bloomfield/Gainestown, LGA1366)," multiplier is 24x, blurred out part of memory type is "Triple"
09-22-2008, 02:26 AM
Sumanji

Why has Nehalem been shot down as a gaming chip because the cache isn't fast enough? L1+L2+L3 latency there looks approx the same as L1+L2 latency for C2D...
09-22-2008, 03:23 AM
Hornet331

Wow, that 3rd level cache is damn fast, nearly as fast as the 2nd level cache.

So much for the rumor "3rd level cache on nehalem is solw" :p:
09-22-2008, 03:35 AM
adamsleath

so who's getting a bloomfield?
teehee.
09-22-2008, 03:50 AM
Hornet331

me for sure, but if the launch is the same as with yorkfield, i wont be available before dez here in europa. :p:
09-22-2008, 04:37 AM
Boschwanza

Quote:

Originally Posted by Sumanji

Why has Nehalem been shot down as a gaming chip because the cache isn't fast enough? L1+L2+L3 latency there looks approx the same as L1+L2 latency for C2D...

I think everest reads l3 cache with working prefetchers and just "read" mode, same with the K10. To get correct Data of l3 cache latency you have to use right mark memory analyser.
09-22-2008, 12:02 PM
Scog

Quote:

Originally Posted by WC Annihilus

Blurred out part of CPU type is "Bloomfield (Bloomfield/Gainestown, LGA1366)," multiplier is 24x, blurred out part of memory type is "Triple"

It seems you didn't see my sarcasm. Please be carefull not to trip on it next time. :D
09-22-2008, 03:23 PM
terrace215

Quote:

Originally Posted by Sumanji

Why has Nehalem been shot down as a gaming chip because the cache isn't fast enough? L1+L2+L3 latency there looks approx the same as L1+L2 latency for C2D...

It's only been "shot down as a gaming chip" by people who don't know what they're talking about. :D
09-22-2008, 03:40 PM
karl_eller

Quote:

Originally Posted by adamsleath

so who's getting a bloomfield?
teehee.

Already saving up for one of the 2.66 Ghz chips. Here's hoping that they don't have the same sort of supply issues as the Yorkfield release.

Eller
09-22-2008, 04:54 PM
JumpingJack

Quote:

Originally Posted by Chri$ch

http://www.abload.de/img/64d88302-a123-4828-9fa9izz.jpg
http://en.hardspell.com/doc/showcont.asp?news_id=4096

First sign I have seen of a C0/C1, I wonder if everest is accurate?
09-22-2008, 05:52 PM
terrace215

Quote:

Originally Posted by JumpingJack

First sign I have seen of a C0/C1, I wonder if everest is accurate?

Blauhung said they're up to D stepping:

http://www.xtremesystems.org/Forums/...9&postcount=19

Maybe D is the launch step?
09-22-2008, 06:02 PM
JumpingJack

Quote:

Originally Posted by terrace215

Blauhung said they're up to D stepping:

http://www.xtremesystems.org/Forums/...9&postcount=19

Maybe D is the launch step?

Again, interesting ... if D is launch stepping and C is showing these kind of numbers.... hmmmmmm.
09-22-2008, 10:58 PM
sxs112

Nehalem White Box

http://farm4.static.flickr.com/3178/...612a7319_o.jpg

http://farm4.static.flickr.com/3175/...efcfa509_o.jpg
1366-775-478

Mobile01
09-22-2008, 11:23 PM
Vozer

I tried to restore this Core i7 965 Extreme Edition CPU-Z screenshot. :D

http://i279.photobucket.com/albums/k...ition_copy.jpg

Show 100 post(s) from this thread on one page

All times are GMT -8. The time now is 10:58 AM.

XtremeSystems