Collection of Conroe Data. (Core 2 Duo and Core 2 Extreme!)

[AlexanderTheGreat]

At least this time we were able to get a taste of raw truth. The more the merrier.

 

[jkflipflop98]

It's gonna be a great year. 😀

 

[AlexanderTheGreat]

Yes, awe yes indeed. I've been tangled in the comparison of the major brands. Is it not that the so different distant future or the not so distant future is what really has me in a hold for geting out to new things? After having read all the threads, I tend to want to get what I need. The uncertainty factor is still at large here. Why doesn't any one ever make it easier for us? The wait alone is a horifying process. On top of it all the big and the ugly wants to have us use trial and error to succeed. I think I'd rather not sort through all the 3'rd party mumbo, just get it straight from the source, the wish master, which is more stuborn than a dumb animal on a hot day that you're trying to drag to the water. We're far from the age where the manufacturer will tie the knot and grant you virtually anything you ask for. I'm so glad that we have this forum. don't want to think about what would happen otherwise. This leads to the question of what the future will and won't have for the favoring side in terms of perks and drawbacks in comparison to the flawed, the not so fortunate ones that are trying real hard to compete, but can't. there will be lots of multi cores, I'm thinking Conroe as a steping stone.

 

[lewis71980]

What is the die size of an extreme core 2 duo?

 

[iterations]

What is the die size of an extreme core 2 duo?

Core 2 Extreme has a 145mm^2 die size.

For reference, Dual core opterons and FX series are 199mm^2.

So even though it has a 4mb L2 cache, Conore uses 37% less silicon area, since it is produced using Intel's 65nm litho techniques.

 

[iterations]

New server solution info: http://www.anandtech.com/IT/showdoc.aspx?i=2772

Dual Woodcrest thouroughly stomps Dual Opteron. I'm actually quite amazed by this data. Intel had a long way to go to catch up with AMD in server apps, but they did that and more. It is very very dominant in Intel's traditional areas of weakness: MySQL, PHP, Apache, Java, SSL, RSA, etc....

 

[Artmic]

New server solution info: http://www.anandtech.com/IT/showdoc.aspx?i=2772

Dual Woodcrest thouroughly stomps Dual Opteron. I'm actually quite amazed by this data. Intel had a long way to go to catch up with AMD in server apps, but they did that and more. It is very very dominant in Intel's traditional areas of weakness: MySQL, PHP, Apache, Java, SSL, RSA, etc....

Wow, now that is amazing to see, i hope they run some Multithreading benchmarks on a windows XP system next, i'm dying to see how well it can handle the tasks against an AMD processor.

 

[ethernalite]

in Intel's traditional areas of weakness: MySQL, PHP, Apache, Java, SSL, RSA, etc....

In other words, every common server application? :roll:

 

[AlexanderTheGreat]

in Intel's traditional areas of weakness: MySQL, PHP, Apache, Java, SSL, RSA, etc....

In other words, every common server application? :roll:


just got better

 

[lewis71980]

What is the die size of an extreme core 2 duo?

Core 2 Extreme has a 145mm^2 die size.

For reference, Dual core opterons and FX series are 199mm^2.

So even though it has a 4mb L2 cache, Conore uses 37% less silicon area, since it is produced using Intel's 65nm litho techniques.

Thanks for the info.

So with a die shrink to 65nm the AMD will probably not be significantly smaller than the 4mb cache core 2 exterme.

 

[gOJDO]

http://www.intel.com/products/processor/core2/index.htm

Core 2 info on Intel site.

 

[zarooch]

well... Intel P965 Express Chipset info is now available here BTW this is info related to P965 Chipset i wonder why they didn't release info for G965... but anyways... also its not a Performace Desktop chipset its Mainstream Desktop chipset... i thought it would be Performance (P965).

 

[iterations]

New June 9, 2006:
Core 2 Duo E6700 based system has set new world records for 3DMark01SE (74353), 3DMark05 (23851), and Aquamark3 (201,602).

Links:
http://www.oohashi.jp/c-board/file/3DM01_74353_E6700_4308.87.png
http://www.oohashi.jp/c-board/file/3DM05_23851_E6700_4308.87.png
http://www.oohashi.jp/c-board/file/AM3_201602_E6700_4166.67.png

 

[BlueStone]

From Firingsquad, they compare 2.4GHz Conroe with a 2.8GHz AM2 system.

http://www.firingsquad.com/hardware/intel_core_conroe_benchmarks/

* Yawn * The lower clocked core 2 is at worst on par in some cases and at best blows away the competition in others....

 

[hacky_maximus]

dudes, thanks a lot for this topic ! I's a bless for me 😀

 

[iterations]

New June 10 2006:
Tarosa has set new World records in SuperPI 2M-32M:

M/B: Intel D975XBX Rev.303 mods BIOS 1181 2006.05.26
CPU: Conroe E6700 ES
Memory: Patriot PC2-8000 XBLK CL4 1GB ×2
HDD: Seagate ST318453LW 18GB ULTRA320/Adaptec 39320D 32Bit PCI
VGA: KUROUTO SHIKOU　FX5200 PCI 128MB
PSU: Zippy-600W the Gaming Edition 3.3V Rail mod →3.45V
OS: Windows Server 2003
Vcore:1.731V, Vdimm:2.91Ｖ(Actual), Vnb:1.725V(BIOS), Vfsb:1.395V(BIOS)

2M: 26.921s http://www.geocities.jp/gbxfs134/26_921.jpg
4M: 1m03.562s http://www.geocities.jp/gbxfs134/103562.jpg
8M: 2m28.329s http://www.geocities.jp/gbxfs134/228329.jpg
16M: 5m22.797s http://www.geocities.jp/gbxfs134/5_22_797.jpg
32M: 11m51.797s http://www.geocities.jp/gbxfs134/11_51_797.jpg

for reference, here are the AMD world records:

2M: 48.750s http://green.ap.teacup.com/fredyama/img/1137895193.gif
4M: 1m 47.781s http://premium1.uploadit.org/fredyam...3893.9MHzR.gif
8M: 3m 55.156s http://premium1.uploadit.org/fredyam...-3893.9MHz.gif
16M: 8m 47.218s http://premium1.uploadit.org/fredyam...3859.9MHzR.gif
32M: 18m 45.156s http://premium1.uploadit.org/fredyam...-3893.8MHz.gif

 

[ltcommander_data]

Intel D975XBX Rev.303 mods

Is this accurate? I thought Rev 304 was needed to support Conroe unless the "mods" means that "upgraded" the rev 303.

4.6GHz and a 1841MHz FSB is amazing. I'm curious as to why the L2 cache is being read as 2MB though since this is the E6700. I think CrystalCPUID divides the shared L2 cache in half though so that really isn't a problem. A Vcore of 1.731V seems very high though.

 

[iterations]

Intel D975XBX Rev.303 mods

Is this accurate? I thought Rev 304 was needed to support Conroe unless the "mods" means that "upgraded" the rev 303.

4.6GHz and a 1841MHz FSB is amazing. I'm curious as to why the L2 cache is being read as 2MB though since this is the E6700. I think CrystalCPUID divides the shared L2 cache in half though so that really isn't a problem. A Vcore of 1.731V seems very high though.
Yes it is a Rev. 303 board. There are Vmods out there (pretty easy if you are electrically inclined) to fix revision 302 and 303 boards to run Conroe.

Rev. 304+ will run conroe (and kentsfield, supposedly) out of box.

And yeah, CrystalCPUID is messing up on the cache size, it is indeed 4MB L2 on this chip. CPU-Z is reporting it correctly in all of the other screenshots.

Vcore of 1.731 is pretty high, but just keep in mind that these are world record runs, so the specs are gonna be crazy for the most part. We have yet to see a high Vcore damage a conroe chip, it appears that the mobos are the first to go, lol. Core 2 has been pretty bulletproof so far.

In fact, TAM had run a 1.8+ Vcore for his 5GHz runs and finally a VR on the bad axe mobo blew out, but the chip was still going strong when moved to another mobo.

Cheers!

 

[BlueStone]

http://www.hothardware.com/viewarticle.aspx?articleid=832&cid=1

More Conroe benchmarks...

 

[stusigpi]

Any Merom data out there yet?

 

[gOJDO]

http://www.hothardware.com/viewarticle.aspx?articleid=832&cid=1

More Conroe benchmarks...

This should be added to the main thread.
Also "NEW" should be removed before each date and thel list should be labeled "Records hronicle"

 

[iterations]

Good call gOJDO, I fixed the annoying formating of dates etc...

June 11 2006:
Some new Core 2 Duo E6700 and X6800 benchmarks:
http://www.hothardware.com/viewarticle.aspx?articleid=832&cid=1

Here we see Conroe besting an overclocked (2.8GHz) FX-60 system in benchmarks such as FutureMark PCMark05 and 3DMark06, as well as real life workloads such as Quake 4 single threaded and multithreaded, low and high resolutions, FEAR, Farcry, LAME Audio encoding, DIVX encoding, and Photoshop filtering. The 2.66GHz Core 2 consistantly wins by 15-30% and the Core 2 Extreme wins by larger margins, as expected.

 

[iterations]

Any Merom data out there yet?

Yes, if you look through the sticky you will notice there is some Merom data mixed in there. Merom is the same Core architechture as Conroe just with best power characteristics, and a TDP of 35W as opposed to Conroes 65W.

All in all, the data simply confirms Intel's claim of 20% increase over their Core Duo (Yonah) chips while using the same ammount of power.

It is due to be Released in August, so I suppose the focus will shift to Merom (and Kentsfield and Bloomfield and AMD's K8L/Deerhound, but that will likely be another thread) after Conroe is released July 23rd.

Cheers!

 

[gOJDO]

This looks like my next rig:
http://www.xtremesystems.org/forums...b51bcc871d367ea2ddea1c5&p=1505499&postcount=1
Intel BadAxe i975BX(or maybe 765) + Conroe E6600 2.4GHz + GeForce 7950 + DDR2-800 CL4

How it will handle with CPU overclocked at 3.3GHz(366x9), RAM at 837MHz(533MHz + 57% overclock), FSB at 1466MHz?

 

[ltcommander_data]

You forgot the Firing Squad review. I'm not a fan of this Hot Hardware one though since it really isn't that much better than the IDF one. Intel only allowed them to run game tests so that's less than ideal.

Anyways, I don't see the small SMP variations to be indicative of Conroe being bandwidth starved. Certainly the bandwidth should be sufficient for the 3.2GHz Extreme Edition. Conroe is still showing poor FSB utilization right now anyways, so it's not that a 1066MHz FSB can't provide enough bandwidth. Hopefully final revisions and successive BIOS updates will provide some bandwidth improvements. Bandwidth shouldn't be a problem for dual cores, but it'll certainly matter for Kentsfield so we'll have to see what Bad Axe 2 brings into play and what can still be done for current boards.