AMD's 3GHz K10 to break 30,000 3DMark06 (Inq)

argh... 7 more days...

i hope than all this unnecessary discussions will come to an end.

Quote:

---

Originally Posted by MR_SmartAss

All I can see in your sig are images of CPUz screens, which are not a clue that you really have a K10 or Harpertown. It is like I put pics of two naked sexy girls and I claim I am working on them. ;)

---

:rofl: :ROTF:

speculation

Quote:

---

Originally Posted by MR_SmartAss

If you have those systems, do some benches and publish the results here. It will be highly appreciated and will increase your credibility here.

---

I would not doubt about duploxx lol :)
and pushing him for breaking a nda is not nice eh ;)

Quote:

---

Originally Posted by MR_SmartAss

If you have those systems, do some benches and publish the results here. It will be highly appreciated and will increase your credibility here.

---

Would you take my word that he's credible?:D

I think he wouldn't MM :D.But nice you came forward and said it:D

Quote:

---

Originally Posted by informal

AMD Phenom X4 can do 3GHz and above

http://my.ocworkbench.com/bbs/showth...200#post420200

Bluetooth is one of those guys who is credible and who got the one of the 1st GA RD790 mobos to test.So this is very good news coming from them!

Note he says air cooling is used and it's a X4 ,so all of the cores must work at the same clock since something is wrong(bios?) and they can't use separate PLLs to clock the cores individually.

And a note to Donnie27 and others going OT in this thread ,for the Nth time:

"Please post something that has to do with Phenom or get out from this news thread!"

We don't need trolling about 4x4 here Donnie.You take your views to separate thread in general hardware and discuss till there is no tomorrow,ok?Or you are afraid it will go down the tubes like the one topic you tried to post recently:"4x4 vs V8"?That was a funny thread,with wrong title,wrong link and wrong posts :p:

---

The only troll here is YOU! It was an A & B conversation, why don't you C your AMD troll a$$ out of it LOL!? He keeps asking why I called you a Fanboy, sheesh the answer is plain enough.

When Victor, Fugger or Hell, even Movie Man gets a Barkie, I'll believe benchmarks, the rest I'll read but take with a Grain of Salt. Sorry, I can't take pics of the Servers, MACs or the brain-scan machines at work LOL!

Quote:

---

Originally Posted by Movieman

Would you take my word that he's credible?:D

---

[OT]
Yet, he still doesn't know what I do, what I've played with or built:) My personal stuff has little to nothing do with what servers I've seen, played with or fixed. I do believe he has those even before you spoke up. Yes, your word is more than good enough for me, thanks for backing him up. I'm not running a Server in my home. But I do have two AMD based rigs and two Intel based rigs.

I'm not always right and when proven wrong I'd rather see it as something as learned instead of digging a deeper hole like some others here. So maybe informal is still smarting from being shown the definition of a Paper Launch or the other guy about how much money AMD pays IBM, hell, I don't know. I don't hold grudes.[/OT]

If the 3GHz Barkie did break 30K on 3DBung-O-Marks, big deal since that doesn't translate or carry-over to any real-world Game/s or Apps. Most of the local IT geeks I know aren't excited about Barkie at all (or the next Intel Xeon). Most just say, we'll see and go from there. These men and women are saying sales will be tough/slow going for Intel and AMD. I asked why and each said "Glut". Now it is Funny as hell that I can say both and certain folks read that as AMD bashing:rofl:

Sure thing Donnie,lmao.I am a "troll" because i post relevant news in connection to the topic title,and you are a great dude who posts anything that is off topic in a news thread.News flash for you:this is a news thread!Get it!? Maybe not...Too hard to figure i guess.

And Donnie,I see you still use that bad mouth to label others("troll a$$" for instance).I wonder how much more will the mod on duty here keep his eyes shut or half open.After all we are in a news thread where people come to read news.Not off topic arguments about non related stuff.They can read that at other subforums(or that's the way it should be..)

Guys I'm going to say this once and if nobody listens or I see one more flame this thread is gone and warnings/bans will be handed out.

STOP FIGHTING!

A few more days, then we'll know what's what fellas. :slap:

New info from Gary@AnandTech:

Quote:

---

Throughout the entire prototype and pre-production (as stated in my last message) process, certain features on the CPU, in the BIOS, or on the chipsets have been turned off/on, latencies have changed, etc, etc. This is a normal part of the engineering process as the design is fleshed out and finalized. It does not represent final silicon capabilities and performance.


As I said earlier, I used a poor example as it was not meant to be taken literally spec for spec when comparing engines and CPUs. Regardless of the example, the point was that the platform performance improved significantly as the core speeds improved and this included performance per watt among other indicators. There is a myriad of reasons as to why this occured but considering the early silicon, BIOS, and chipset designs, we could only speculate as to why and I tried to present a few reasons that we honed in on.

If you compare a B00 chip from May to a B02 today, there is a significant difference in performance in all areas (26 seconds in SuperPI 1m for one) and my comments represent observations of what has occurred over this time period. We have final silicon now and results will be posted in the near future. My observations today are different than they were two weeks ago and as the platform matures they will change again.


Once we see the HT 3.0 capable chipsets and Phenom cores mature then we will have an even better indication of the performance of this core design in the consumer market but for now the initial release is Barcelona in the enterprise market.

---

So Gary said that the jump in performances between B00s from May to B02s is very large(he saw the time in SPi 1m test decreased by 26s from B00's score-quite a lot).This right there invalidates the coolaler's forum topic(which BTW is gone-at least the pictures of the K10 ES results)

Also he said he saw a visible improvement within the last two weeks ,so this means that a lot of beta silicon chips floats at Far East's mobo factories.
Like he said:"My observations today are different than they were two weeks ago and as the platform matures they will change again." Presumably he is talking about the Phenom and RD790 boards which will be a little late (not September but middle of October-due to low volume of K10 DVTs out there at the moment).
All of this still gives us a hint about a variety of chips,boards and support for them in form of functional bioses.6 days to go and no retail silicon leaked.Tells a lot about NDA and what AMD actually sends to others for testing.

Quote:

---

Originally Posted by duploxxx

and for the clueless and stay at you're desktop. just check my sig what i am working on. so i do have an idea what is going on in the cpu world.

---

B0 stepping eh.... :D
early sample? :yepp:

ROFL
26s improvement in 1M

something tells me it's still a dog if you can shave off 26seconds in beta :ROTF: :D

Quote:

---

Originally Posted by MR_SmartAss

For example Kentsfield/Woodcrest performance is scaling incredibly well, while being a MCM approach, while Pentium EE 840 scales poor, although it is a native dual core.

---

nay, the pentium d series is MCM, including the EE versions. native should definitely scale a little better, the early k10 benchmarks already show a scaling improvement in cinebench (~6x performance improvement going from 1-8 cores for xeon vs ~7x for k10)

Quote:

---

Originally Posted by dinos22

ROFL
26s improvement in 1M

something tells me it's still a dog if you can shave off 26seconds in beta :ROTF: :D

---

:D :yepp:

http://www.tcmagazine.com/comments.php?id=15914&catid=2

Quote:

---

AMD's cat, the K10-based Opteron is finally out of the bag as, on September 1st the company has announced that it has already begun shipping the new processors.

---

Quote:

---

Originally Posted by MR_SmartAss

Do a little research. Pentium 840EE is the first x86 dual core and it is a native(monolithic die) dual core.

That is due to the direct (CPU to CPU) HTT link VS the parallel indirect (CPU to northbridge to CPU) link. Not because of the native vs MCM approach. Try benching single K10 and single C2Q systems.

---

840ee is two prescotts on a piece of silicon. http://www.hardwareanalysis.com/content/article/1797/

Quote:

---

Originally Posted by informal

Sure thing Donnie,lmao.I am a "troll" because i post relevant news in connection to the topic title,and you are a great dude who posts anything that is off topic in a news thread.News flash for you:this is a news thread!Get it!? Maybe not...Too hard to figure i guess.

And Donnie,I see you still use that bad mouth to label others("troll a$$" for instance).I wonder how much more will the mod on duty here keep his eyes shut or half open.After all we are in a news thread where people come to read news.Not off topic arguments about non related stuff.They can read that at other subforums(or that's the way it should be..)

---

:rofl: :ROTF: So your constant Trolling directed at me is relevant and on Topic, right? Stop acting like a Troll and I'll stop calling you one;) If I bother you soooooo much there is such a thing as an ignore button.

Six more days to see what Barkie can do. I'll be happy for heart-broken AMD Fans everywhere who've had to put up with Conroe Spankings for how long now? Maybe the forums will be a little more peaceful if Barkie performed anywhere near the 30K rumored by these guys.

Quote:

---

Originally Posted by MR_SmartAss

Then K8 is not a native dual core. ;)

---

Don´t be a fool. Neither Smithfield or Presler are native dual cores, they are MCMs of Prescott and Cedar Mill.