Intel Shows Off 8-Core 45nm Penryn Benchmarks

[perkam]

Wait a minute, that's not too impressive for Penryn... Considering....


Core 2 Extreme QX6800 runs at 2.93Ghz

and the Penryn(Quad) is running at 3.33Ghz

If the Penryn was running at the same speed as the QX6800 or vice versa
and they got the same scores as currently posted, then yeah I'd get real excited, but..c'mon it's running at a clock speed advantage already!

Quad will clock higher and run cooler at the same clocks...which is reason enough for majority of Kents/Clovertown owners to switch to this.

Perkam

[Shintai]

Best picture ever!

^^

[turbox997]

Quad will clock higher and run cooler at the same clocks...which is reason enough for majority of Kents/Clovertown owners to switch to this.

Perkam

Yes, true, and also all the other benefits from the die shrink. However I was speaking on Clock per Clock advantages over Conroe, I was expecting a little
more.

As in, yes the Penryn Quard core did get a higher benchmark score then the Quad core Conroe, but that's because it was already clocked higher to
begin with, I'd like to see a clock per clock comparison...I should work the numbers but I'm about to leave somewhere so maybe someone will beat
me to it or I'll do it when I come back.

2.93ghz = 10408
3.33ghz= 12881

[nemrod]

Wait a minute, that's not too impressive for Penryn... Considering....


Core 2 Extreme QX6800 runs at 2.93Ghz

and the Penryn(Quad) is running at 3.33Ghz

If the Penryn was running at the same speed as the QX6800 or vice versa
and they got the same scores as currently posted, then yeah I'd get real excited, but..c'mon it's running at a clock speed advantage already!

If, I don't make a mistake this bench isn't optimised for sse4
12881*2.93/3.33 = 11333. It's about 9% better than qx6800 on an even not sse4 bench at same clock.

[iterations]

If, I don't make a mistake this bench isn't optimised for sse4
12881*2.93/3.33 = 11333. It's about 9% better than qx6800 on an even not sse4 bench at same clock.

Exactly, even on a non SSE4 workset it is demonstrating %8-9 higher IPC. And on top of that, it will have a sizeable clockspeed advantage due to much better thermals allowing Intel to clock them higher at lower voltages.

What about that isn't impressive?

[perkam]

We've known since Intel's IDF 2006 slides that Penryn was just a die shrink...nehalem will be the architecture revision.

Perkam

[turbox997]

We've known since Intel's IDF 2006 slides that Penryn was just a die shrink...nehalem will be the architecture revision.

Perkam

Agreed, but there was also all this hype and fluff that got me excited about it performing 15% or so per clock, oh well, now that the numbers were worked out, 8-9% does it for me.

Exactly, even on a non SSE4 workset it is demonstrating %8-9 higher IPC. And on top of that, it will have a sizeable clockspeed advantage due to much better thermals allowing Intel to clock them higher at lower voltages.

What about that isn't impressive?

Alrite, alrite, I spoke too soon, now that with the numbers worked and considering that it is in fact a non SSE4 optimized benchmark, then yes, I'm satisfied.

[nemrod]

We've known since Intel's IDF 2006 slides that Penryn was just a die shrink...nehalem will be the architecture revision.

Perkam

You 've probably miss some infos:
http://www.realworldtech.com/page.cf...03-28-2007#370

[terrace215]

We've known since Intel's IDF 2006 slides that Penryn was just a die shrink...nehalem will be the architecture revision.

Perkam

That's false, as Intel's April 2007 IDF slides make quite clear.

Nehalem is a new architecture, but Penryn is more than a die shrink.

SSE4, super-shuffle engine, larger caches, better load/store reordering, faster division, faster official FSB support, etc.

A die shrink does not give you increased IPC.

Obviously we'll reserve final judgments on Penryn for our official review of the CPU, but these initial results look very promising. We would expect to see clock for clock Penryn vs. Conroe improvements to be in the 5 - 10% range at minimum depending on the application.

http://www.anandtech.com/cpuchipsets...spx?i=2972&p=3

[eXceeded]

Why is it that Intel release their results of unreleased processors and people still firmly buy their current CPUs but AMD won't show a thing except meaningless information with the apparent reason being that it would kill sales of current lineup.... Really hoping K10 doesn't suck against Penryn...

[perkam]

My point was on expectations.

June 20th, 2006:



Perkam

[nemrod]

My point was on expectations.

June 20th, 2006:

Since, they have done more than a die shrink as said march 28 2007
http://www.realworldtech.com/page.cf...03-28-2007#370

But even in 2006 slide I dont understand shrink/derivative as only shrink.

[Movieman]

Sick stuff, not a power point slide with graphs on how its "going to own"

Having a blast at Computex

(Looks at picture, drools, shorts out keyboard, pants explode out the front, and that ain't easy at 55!)

Hi Charles, How you doing?

Ahh, am I being too obvious?

Hey guys? Where the hell do you get Cinebench 10? I just see 9.5.
I want to see how the clovers compare to these new monsters.

[perkam]

Actually MM, two E5355s in a V8 system would be a monster...this is just plain insanity in terms of leaps ahead.

Perkam

[[XC] hipno650]

this is only one benchmark as well. who knows how good this thing will do in gaming? but the fact that it will clock higher is reason enough to be happy.

[Movieman]

Actually MM, two E5355s in a V8 system would be a monster...this is just plain insanity in terms of leaps ahead.

Perkam

Yes, just want to see how much it blows away my 2-X5350's at 3200mhz..
Can't find Cinebench 10 that they used for that demo..Just 9.5..
Any leads anyone?

[duploxxx]

Francois stressed the chip run much cooler than the previous generation.

well I hope he didn't touch those fbdimm's to check how cool the cpu's are...

16GB of fbdimm, that's + 100W powerconsumption....

nice system though, but my bucks will go for the new RD790 with dual 1207 for sure. price/performance/power consumption ratio will be much better.

@movieman isn't cinebench2003 the same as 10?

[perkam]

Gaming is fine too, but there's a reason I invited MM here ... I don't want to be telling my friends "Dude !! I'm playing Alan Wake with two Quad Core 3ghz processors !!! It's so smooth"



Perkam

[Vapor]

AMD needs to fire back and do the same benchmark to prove Intel wrong.

And if they can't?

Running benchmarks to show Intel is superior is something Intel WOULD LOVE!!! At this point...Intel should just run and publish every benchmark and make AMD put up or shut up. If AMD responds and wins a few, Intel will still make plenty of $$$$, or start a price war. If AMD doesn't, free advertisement and just more publicity for the better chip (but, it might cannibalize CNR/KFD sales)

[nemrod]

Any leads anyone?

Perhaps you could try info_de@maxon.net ?

[alucasa]

Yep.., it's hard not to like Intel lately. They've been so straightforward.

[Face]

Can't find Cinebench 10 that they used for that demo..Just 9.5..
Any leads anyone?

Closed beta.
"The new MAXON CINEBENCH R10 will not become publicaly available as a beta. You will have to wait for the release of the final version.
Shouldn't take to long though.
Cheers
Björn"

They changed the rendering scene though:

http://www.gamestar.de/_misc/img/det...849629060976##

isn't cinebench2003 the same as 10?

Cinebench 2003 is Cinebench 8 AFAIK.

[Nedjo]

AMD needs to fire back and do the same benchmark to prove Intel wrong.

That is the last thing AMD should do!!!

In a time before K7 AMD used sandbagging strategy that made Intele beleve that K7 won't go beyond 600 MHz

In a time before K8 same aproach was used (some of us still remember some preliminary tests of K8 couple of months before finall version. It looked like K8 sudenlly overnight gone form 800 MHz to 2 GHz!).

So far sandbagging proved good for AMD. Thee's no reason to think diferent in a case of K10.

And this intel strategy is so expected. You know guys this thing that these companies are doing is written in the management school books, and it's not hot water!

Only thing different from the past times and now is the pressure form the vastly expanded public on the Net, and Intel knows that and its' using it's army of fanboys to hit up atmosphere!

It's just like in a sports one team is using its position in a game, and public energy in effort of not allowing opposing team counteroffensive.

All this marketing gimmicks is irrelevant. In Q3 when K10 is out we'll se the reall state of things!

[billdavis]

beer

[Zytek_Fan]

Makes me want a Penryn bad