First Penryn (wolfdale) Numbers

[metro.cl]

Ok got this link by MSN,

Here you can see a lot of screenshots, the ones without a CPU-Z by the side, specially Super Pi 1M, take it with a huge grain of salt.
















Here is the source


Brought to you by CHW Lethal Squad

[LagunaX]

So a 2.7ghz dual core penryn does the same superpi time as a 3.7ghz e6600 or e6700! But there is a 2mb advantage so probably equal to a 3.5 ghz e6600 if the e6600 had another 2mb... P5k deluxe mobo is compatible...

[metro.cl]

i dont really think that 1M run was at 2.66GHz

[Kunaak]

why not? the difference between a E6400 and E6600 in the same overclock, same board, and same ram, even in 1M is pretty drastic.

another 2 megs to the cache, would be no different.
4 megs to 6 megs would be a nice jump for PI.

[[cTx] Nooc]

thanks for the numbers it looks like a winner with 6MBs of L2

[KiD0M4N]

Look at the other shots from Everest.... they are actually lower than a E6700 at same speed? Hows that?

[metro.cl]

why not? the difference between a E6400 and E6600 in the same overclock, same board, and same ram, even in 1M is pretty drastic.

another 2 megs to the cache, would be no different.
4 megs to 6 megs would be a nice jump for PI.

True but everest is on par with C2D, i just dont want to make false hopes, if it does that time great

[Jamesrt2004]

Look at the other shots from Everest.... they are actually lower than a E6700 at same speed? Hows that?

What I was thinking

[savantu]

Look at the other shots from Everest.... they are actually lower than a E6700 at same speed? Hows that?

Board , BIOS , etc...I wouldn't be worried about that.

[K404]

why not? the difference between a E6400 and E6600 in the same overclock, same board, and same ram, even in 1M is pretty drastic.

another 2 megs to the cache, would be no different.
4 megs to 6 megs would be a nice jump for PI.

I agree. Assuming the extra cache allows full performance scaling and isnt bottlenecked by something else, and SSE4 does its thing, it should take towards 2 secs off a Spi 1M time compared to a 4MB Conroe at the same clocks.

Penryn @ 3600MHz should be around....12-12.2 secs?

[Solarfall]

looks yammy.. cant wait until they are out.

[BenchZowner]

SSE4 does...

...nothing for SuperPi Mod v1.5

[Eastcoasthandle]

True but everest is on par with C2D, i just dont want to make false hopes, if it does that time great

SSE4 is fairly new. Is it not possible that his beta copy of Everest is not optimize to run SSE4?

[Shintai]

The radix and shuffle engine can help on any version of SSE. But I dont see superpi as one.

[M3kk]

Results with OC would be nice .

[NH|Delph1]

Results with OC would be nice .

My thought exactly

Great information metro, as always

//Andreas

[safan80]

I'd like to see what yorkfield has to offer.

[JuanFlaiter]

Remember those SSE2/SSE3 versions of SuperPi? Maybe that´s the answer.

[M3kk]

My thought exactly

Great information metro, as always

//Andreas

I hope the news about OC ability are just tales :P.

[Phlash]

I'd like to see what yorkfield has to offer.

is yorkfield supposed to be > wolfdale?

[safan80]

it's the quad-core version of wolfdale

[Phlash]

it's the quad-core version of wolfdale

Ahh, that makes sense, thanks

[DoubleZero]

SSE4 is fairly new. Is it not possible that his beta copy of Everest is not optimize to run SSE4?

Look at the second Everest benchmark.

[nn_step]

Results with OC would be nice .

assuming it overclocks (well)

[Movieman]

assuming it overclocks (well)

(nn_step cringes at the thought that the pic of super pi was done at 2666mhz,sells AMD stock, applies for job with Intel, shot at door as a suspected spy!)

If those SP1M times were at 2666mhz then Penryn is what it's claimed to be.
If at 3000 it's still a very nice increase.
Does make you want to get one and try for 8x500 though!

Thanks for the info Metro!