Official Desktop Penryn Discussion Thread

[Shintai]

Hehe, tread is going rampant fast. Anyway, lets relax abit. Its just mainly certain SSE stuff that gets boosted. The extra cache will add 0-3% I guess. And it would just be a series of reviews quite abit from launch I guess.
But we already seen some benchmarks, unless they were another PR spin.

Anyway, I wait and see for Nehalem.

So...alot of hot air mainly until some time later.

The only thing I hope is that they keep lowering the TDP...

[savantu]

Hehe, tread is going rampant fast. Anyway, lets relax abit. Its just mainly certain SSE stuff that gets boosted. The extra cache will add 0-3% I guess. And it would just be a series of reviews quite abit from launch I guess.
.....

Even without SSE4 , Wolfdale will bring tangible perf improvements , they lowered the latency for a lot of instructions and this will help.

[BitpowerPM]

Only the radix-16 divider and SSE4 instructions (including super shuffle engine) coming with Penryn will boost some multimedia/math applications by 40 - 100%.

So - if necessary - Intel could offer 4 GHz parts of Wolfdale/Yorkfield and thats a large gap compared to 2,5-2,7 GHz K10...

cu, BitpowerPM

[GoThr3k]

Only the radix-16 divider and SSE4 instructions (including super shuffle engine) coming with Penryn will boost some multimedia/math applications by 40 - 100%.

So - if necessary - Intel could offer 4 GHz parts of Wolfdale/Yorkfield and thats a large gap compared to 2,5-2,7 GHz K10...

cu, BitpowerPM

4GHz in a 65w TDP
keep on dreaming

AMD B0 stepping is doing very well,so expect a 2.9 ghz K10 QC

[onewingedangel]

4GHz in a 65w TDP
keep on dreaming

AMD B0 stepping is doing very well,so expect a 2.9 ghz K10 QC

Higher end conroes, and kentsfields already have higher tdp's than the mainstream parts.

K10 parts too will consume more than 65w at the high end.

At least compare like for like.

[GoThr3k]

Higher end conroes, and kentsfields already have higher tdp's than the mainstream parts.

K10 parts too will consume more than 65w at the high end.

At least compare like for like.

i was talking dualcore
intel has a 65W TDP (in theory ) for dualcores
i dont see a 4GHz DC possible at that TDP...

i dont think Kuma will consume more than 65W,possible speeds of ~ 3ghz should be possible in a 65W TDP for amd
Wolfdale may squeeze around 3.3Ghz or a bit more in a 65W (intel) TDP
so we will end up with a 3GHz Kuma vs a 3.3/3.5ghz Wolfdale
i don't think there will be much of performance difference

[Shintai]

intel has a 65W TDP (in theory ) for dualcores

So true, they are so much below their spec. So its only in theory they will ever reach 65W.

Note its measured before the VRM, so its actually lower than on the graph.

[BitpowerPM]

4GHz in a 65w TDP
keep on dreaming

Does a XS-User really think about TDP?

cu, BitpowerPM

[nn_step]

Does a XS-User really think about TDP?

cu, BitpowerPM

one word "Prescott"

[Shintai]

one word "Prescott"

Two words, Athlon FX-7x

[GoThr3k]

Does a XS-User really think about TDP?

cu, BitpowerPM

i dont care about TDP
it's just the TDP that intel uses for their dualcores.
i don't think 4ghz is doable in a 65W TDP,so dont expect 4GHz Wolfdales (on stock that is...)
that was my point

[Shintai]

i dont care about TDP
it's just the TDP that intel uses for their dualcores.

How many times do you want to be proven wrong?

The actual TDP for Intels dualcores is WAY below their official announced TDP.

[BitpowerPM]

i dont care about TDP
it's just the TDP that intel uses for their dualcores.
i don't think 4ghz is doable in a 65W TDP,so dont expect 4GHz Wolfdales (on stock that is...)
that was my point

Core 2 Extreme X6800 Dual-Core and Xeon 5160 have a TDP of 75/80 watts and not 65.

The target frequency of Penryn core is around 3,6-3,7 GHz - so the way to 4 GHz is not far.

cu, Bitpower

[ted3]

i don't think 4ghz is doable in a 65W TDP,so dont expect 4GHz Wolfdales (on stock that is...)
that was my point

Just thought more about this and decided to calculate a little. Keep your guns in the holster if i calculated wrong along the way, im unarmed and had half a bottle of wine

Using the Xbitlabs numbers on page 2 of this thread i came up with the following:

D820=145w, D915=94w, same clockspeed, ~35% reduction from 90nm to 65nm

D915=94w, EE965=126w, increase in clockspeed is 33%, TDP increase is 34%

E6700 is 2.66GHz and 65w TDP, -35% for process shrink gives TDP of ~42.5w

Now, to go from 42.5w to the desired TDP of 65w, we take 65 and divide by 42.5 and get 1.5294, that means we have to increase 42.5w by ~53% to reach a TDP of 65w.

53% still, and we had a TDP increase of 34% to get a 33% increase in clockspeed. 53 multiplied with 33 divided by 34 gives a clockspeed increase of 51.44%, lets say ~51%.

So we take E6700, 2.66GHZ + 51% and we get? 4.016 Ghz

-------------

Ok, these are numbers based on only one test, for all i know the EE965 used here was xtremely good and the D820 was extremely bad (which i doubt, i had both D830 and D930, very big difference to say it the least)

On the other hand, what i did NOT take into consideration is that 90 to 65nm was a shrink, while 65 to 45nm is a shrink + the addition of High-K. Also, i used the TDP of E6700 here instead of the 59w power consumption meassured by Xbitlabs.

Also the EE965 got hyperthreading which adds to its power consumption.

Its just a bunch of theory anyway, doesnt mean in reality, the point is that i cant totally exclude the posibility of 4GHz/65w, and because the X6800 got a TDP of 75w theres still some slack.

....And i still dont know if my calculations are any good, thats up to you guys to check Im surprised myself here so some numbers could be a bit off.