-
First Penryn (wolfdale) Numbers
-
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...
-
i dont really think that 1M run was at 2.66GHz
-
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.
-
thanks for the numbers :) it looks like a winner with 6MBs of L2
-
Look at the other shots from Everest.... they are actually lower than a E6700 at same speed? Hows that?
-
Quote:
Originally Posted by
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.
True but everest is on par with C2D, i just dont want to make false hopes, if it does that time great :)
-
Quote:
Originally Posted by
KiD0M4N
Look at the other shots from Everest.... they are actually lower than a E6700 at same speed? Hows that?
What I was thinking
-
Quote:
Originally Posted by
KiD0M4N
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.
-
Quote:
Originally Posted by
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.
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?
-
looks yammy.. cant wait until they are out.
-
Quote:
Originally Posted by
K404
SSE4 does...
...nothing for SuperPi Mod v1.5 ;)
-
Quote:
Originally Posted by
metro.cl
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?
-
The radix and shuffle engine can help on any version of SSE. But I dont see superpi as one.
-
Results with OC would be nice :).
-
Quote:
Originally Posted by
M3kk
Results with OC would be nice :).
My thought exactly :D
Great information metro, as always :up:
//Andreas
-
I'd like to see what yorkfield has to offer.
-
Remember those SSE2/SSE3 versions of SuperPi? Maybe thatīs the answer.
-
Quote:
Originally Posted by
NH|Delph1
My thought exactly :D
Great information metro, as always :up:
//Andreas
I hope the news about OC ability are just tales :P.
-
Quote:
Originally Posted by
safan80
I'd like to see what yorkfield has to offer.
is yorkfield supposed to be > wolfdale?
-
it's the quad-core version of wolfdale
-
Quote:
Originally Posted by
safan80
it's the quad-core version of wolfdale
Ahh, that makes sense, thanks
-
Quote:
Originally Posted by
Eastcoasthandle
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.
-
Quote:
Originally Posted by
M3kk
Results with OC would be nice :).
assuming it overclocks (well)
-
Quote:
Originally Posted by
nn_step
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!:D
Thanks for the info Metro!:toast:
-
Quote:
Originally Posted by
DoubleZero
Look at the second Everest benchmark.
Yeah, I see that but it's still a beta, that's why I asked.
-
Quote:
Originally Posted by
Movieman
(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!)
At least someone made me laugh on this extremely warm day! :rofl:
-
Quote:
Originally Posted by
Movieman
(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!:D
Thanks for the info Metro!:toast:
Super PI just isn't the type of video game that I am into, nor does it dictate how much work will be done in WCG... ;)
-
Quote:
Originally Posted by
nn_step
Super PI just isn't the type of video game that I am into, nor does it dictate how much work will be done in WCG... ;)
Just like specfp_rate ;)
-
yeah... i need CPU Power to emulate PS2 engine...
-
Quote:
Originally Posted by
nn_step
Super PI just isn't the type of video game that I am into, nor does it dictate how much work will be done in WCG... ;)
Agreed, but it is an indicator of what amount of computational power exists in that cpu..
My 8 core clovertown will only do 15.562s in SP1M but it will do almost 26,000 a day in WCG and I think thats the top single producing machine in the project....Why? 8 cores..
There are machines that produce more per core but not more total in a day..
If all the shown SS here are correct then this looks like a nice increase over the C2D's and makes me want a pair of Harpertowns all the more!:D
-
Now i know what happened in that super pi run, do you remember Core Multiplexing?
I know for a fact that Wolfdale has it and that it should be enabled in that run, now that super pi could be about 3GHz? not sure how much the increase of mhz will be if they disable 1 core.
-
It is looking like my upgrade path is becoming clearer. Still waiting on amd numbers.:rolleyes:
-
Quote:
Originally Posted by
metro.cl
Now i know what happened in that super pi run, do you remember Core Multiplexing?
I know for a fact that Wolfdale has it and that it should be enabled in that run, now that super pi could be about 3GHz? not sure how much the increase of mhz will be if they disable 1 core.
No ;)
Also the only thing Penryn got is the dynamic OC. And thats mobile only.
-
Could be that Wolfdale uses all of it's 6 MBs of L2 for Spi with CMT and maybe even OCs the one core in singlethreaded apps.
So far Everest doesn't impress me at all(even a bit slower in most cases clock 4 clock versus Conroe..)
-
Quote:
Originally Posted by
nn_step
assuming it overclocks (well)
Since when does an Intel chip not overclock well??? :D
-
Quote:
Originally Posted by
informal
Could be that Wolfdale uses all of it's 6 MBs of L2 for Spi with CMT and maybe even OCs the one core in singlethreaded apps.
So far Everest doesn't impress me at all(even a bit slower in most cases clock 4 clock versus Conroe..)
It uses all or close to all6Mb. Just like a Conroe would use close to 4MB.
There is no CMT in them. And no OC unless its a mobile.
-
The IDF numbers still seems to cover more than Everest and SuperPI ;)
http://shintai.ambition.cz/pics/penryn.png
So roughly remove 13.6% from those numbers (Cept 3Dmark overall due to GPU) and you got the IPC improvement in each category.
So for gaming, HL2 is about 25% faster clock for clock.
-
That's all in intel controlled environment ...I wouldn't hold my breath for 25% increase in gaming clock for clock.More like 6-10% in average..
With SSE4 it's all other game.This should bring evident advatage to Penryn versus Conroe,once the software hits the shelves(that might be soon or it might be in a few years...).
-
-
Ye, I'm sure the biggest part of the market buys CFUs only to run WCG. Hey, they gotta use the money somewhere :D
Quote:
Originally Posted by
nn_step
Super PI just isn't the type of video game that I am into, nor does it dictate how much work will be done in WCG... ;)
-
Quote:
Originally Posted by
alfaunits
Ye, I'm sure the biggest part of the market buys CFUs only to run WCG. Hey, they gotta use the money somewhere :D
Nah, nn_step was teasing me if you read it closely..:D
-
WOW this looks good. Thanks for the numbers.
-
-
All factors aside, BIOS, Everest update, etc.
THIS LOOKS GOOD! Even though the E6700 inches out some benches, it's still on par, and just think about it when the tweaks/updates hit.
I just want to know/see the limits of this thing overclocked. 4.5Ghz on air baby!!!
-
Quote:
Originally Posted by
informal
With SSE4 it's all other game.This should bring evident advatage to Penryn versus Conroe,once the software hits the shelves(that might be soon or it might be in a few years...).
Yeah right, only very few <good> programmers spend optimizing their algorithms by hand coding them in assembly using multimedia and sse instructions. Don't expect to see sse optimized programs or games, only in encoders and decoders (from smart programmers like divx devs). There is no compiler that I'm aware of that can optimize code very well by using any extended instructions, all of them do job very poorly.
-
Quote:
Originally Posted by
Shintai
No ;)
Also the only thing Penryn got is the dynamic OC. And thats mobile only.
Have you seen a bios shot? i have and i think Core multiplexing is what this is about.
-
wow... if those numbers are legit penryn will rock.
-
Quote:
Originally Posted by
MaxxxRacer
wow... if those numbers are legit penryn will rock.
We didn't need the numbers to confirm the latter ;)
-
Quote:
Originally Posted by
metro.cl
Have you seen a bios shot? i have and i think Core multiplexing is what this is about.
No. Core Multiplexing just disables/enables the cores, leaving just one enabled. For example, core multiplexing will disable 3 cores on a Kentsfield, 1 core on a Conroe/Penryn, etc.
Also, I really don't think 14.x seconds for SuperPI 1M is possible at 2.66GHz stock speed for a Penryn family processor.
-
new s-pi champion
expect 6 seconds (1M) for 5,5-6 GHz penryn
-
Quote:
Originally Posted by
Shadowmage
No. Core Multiplexing just disables/enables the cores, leaving just one enabled. For example, core multiplexing will disable 3 cores on a Kentsfield, 1 core on a Conroe/Penryn, etc.
Also, I really don't think 14.x seconds for SuperPI 1M is possible at 2.66GHz stock speed for a Penryn family processor.
SuperPi loves cache, and disabling a core means the used core can use all 6MB, and that is the reason - maybe - of that score.
-
Quote:
Originally Posted by
JuanFlaiter
SuperPi loves cache, and disabling a core means the used core can use all 6MB, and that is the reason - maybe - of that score.
you have a great point
-
Quote:
Originally Posted by
JuanFlaiter
SuperPi loves cache, and disabling a core means the used core can use all 6MB, and that is the reason - maybe - of that score.
One core would get all the cache anyway in a singletreaded application even when both cores are enabled. Thats the bonus of being shared and dynamicly allocated.
-
Just like with the AMD's, it looks to be an interesting year ahead.
Whether Penryn is 10% or 25% faster than C2D isn't an issue, 10% faster than an already great chip is a huge increase.
Look at what is going on with the new G0 stepping 65nm chips and now from the looks of things Penryn will be even better!
Enough to give an old guy wood!:D
-
Movieman, i see only 5-8 per cent penryn average advantage over conroe
where did you find 10-25 per cent he-he
-
Quote:
Originally Posted by
MAS
Movieman, i see only 5-8 per cent penryn average advantage over conroe
where did you find 10-25 per cent he-he
From the different comments I've seen. If it's 5-8%, I won't argue, I still feel the same, any increase over what is already a great cpu(C2D) is a plus..
I can't wait until someone on the site gets one in hand and sees what they can do in real world numbers.:up:
I grew up with slide rules and adding machines so that might explain why you see the excitement of a little kid in me when I see what these can do so please excuse my enthusiam.
When I stop to think that when I went to school there was no such thing as a PC, calculator, color TV, cable TV, internet, disc brakes, seatbelts,etc, it really boggles the mind to see the advances.
I was 9 years old when Alan Shepard made his 15 minute trip into space and watched it on a 19" B+W TV with rabbit ears for an antenna in a classrom with 30 others glued to the screen.
Like I said, amazing advances and now I sit here with not one, but 2- 8 core clovertown machines in my house and it really makes one sit back in awe at times.
To appreciate what we have today, one has to look back a generation and see what was.
-
I'd put some cash forward on that pi run being at 3.2GHz+.
-
wow, looks good :) hopefully get lower 11's in 1m s-pi @ 4.0ghz for daily use :D
-
Quote:
Originally Posted by
Gautam
I'd put some cash forward on that pi run being at 3.2GHz+.
Me too.
-
Quote:
Originally Posted by
Shadowmage
No. Core Multiplexing just disables/enables the cores, leaving just one enabled. For example, core multiplexing will disable 3 cores on a Kentsfield, 1 core on a Conroe/Penryn, etc.
Also, I really don't think 14.x seconds for SuperPI 1M is possible at 2.66GHz stock speed for a Penryn family processor.
http://img177.imageshack.us/img177/5364/intel10xm5.jpg
Shot with unknown at 1969-12-31
his is what im talking about
-
As for core multiplexing, Shintai is right for once.
Quote:
Originally Posted by
metro.cl
[URL=http://imageshack.us]
his is what im talking about
EDAT can't be it, since it's a laptop technology. The chip in question is a Wolfdale.
-
It has obviously lower multi comparing to c2d, thus it's not assured it will clock that high.
-
Quote:
Originally Posted by
MoTiG
It has obviously lower multi comparing to c2d, thus it's not assured it will clock that high.
depends on what clocks will Penryn start off. lets say there will be 333*6 Penryn, then it takes some mobo to overclock it to 3.5 GHz.
iīm also curious to see where low-multi Penryns hit fsb walls.
-
I know its not possible now but it would b cool if they could make it so you can overclock each core individually. Would bring a whole new level to overclocking. Well more like quad levels :D
-
-
Quote:
Originally Posted by
metro.cl
i dont really think that 1M run was at 2.66GHz
it wasn't ;)
Penryn is slower than that
-
Quote:
Originally Posted by
dinos22
it wasn't ;)
Penryn is slower than that
I did wonder if Intel would have to drop the 45nm clocks until their process matures- is that what you mean?
A question re the 65nm G0 stepping chips...are the improvements in the microcode or is the silicon tweaked? If its a silicon improvement, will they be able to use it in 45nm?
-
Quote:
Originally Posted by
Movieman
Just like with the AMD's, it looks to be an interesting year ahead.
Whether Penryn is 10% or 25% faster than C2D isn't an issue, 10% faster than an already great chip is a huge increase.
Look at what is going on with the new G0 stepping 65nm chips and now from the looks of things Penryn will be even better!
Enough to give an old guy wood!:D
Dave...You're Slaying me brother:D ....P.S....I still use a Stick Ruler in the Wood Shop as my preffered everyday Measuring Device ...Much more accurate than a Tape Measure ever will be!!!!
-
Quote:
Originally Posted by
K404
I did wonder if Intel would have to drop the 45nm clocks until their process matures- is that what you mean?
A question re the 65nm G0 stepping chips...are the improvements in the microcode or is the silicon tweaked? If its a silicon improvement, will they be able to use it in 45nm?
no that is not what i mean
the SuperPI time at those clocks should be slower :)
-
Who in the right mind posts SP time without clock speed? :p:
-
Quote:
Originally Posted by
Movieman
From the different comments I've seen. If it's 5-8%, I won't argue, I still feel the same, any increase over what is already a great cpu(C2D) is a plus..
Well comments are cool and all, but in everest wolfdale lags behind conroe in every bechmark but the one that uses sse4.
Thank good it's a Intel chip, if it was a AMD chip this thread would be useless by now thanks to the trolling.
-
Quote:
Originally Posted by
DoubleZero
Well comments are cool and all, but in everest wolfdale lags behind conroe in every bechmark but the one that uses sse4.
Thank good it's a Intel chip, if it was a AMD chip this thread would be useless by now thanks to the trolling.
Maybe because its tested in several real world applications on real chips. So not much to argue about.
Nobody here can run around headless and claim 50% overall performance here on an extrapolated estimate out from 1 synthetic bench :shrug:
Intel have proven superb with Conroe and Penryn how to kill hype before ti starts. Along with getting alot of free PR for basicly no effort.
-
I wouldn't rely too much on the Everest benches.
Results vary from version to version - as is pointed out by Everest itself.
-
Quote:
Originally Posted by
Shintai
The radix and shuffle engine can help on any version of SSE. But I dont see superpi as one.
They can help with x87 floating point as well so they can help with SuperPI.
Quote:
Originally Posted by need.for.mhz
There is no compiler that I'm aware of that can optimize code very well by using any extended instructions, all of them do job very poorly.
That means you are not aware of Intel C++ Compiler 10.0.025 which was out two weeks ago and which can already generate SSE4 optimized code for Penryn.
-
Quote:
Originally Posted by
Shintai
Maybe because its tested in several real world applications on real chips. So not much to argue about.
Nobody here can run around headless and claim 50% overall performance here on an extrapolated estimate out from 1 synthetic bench :shrug:
Intel have proven superb with Conroe and Penryn how to kill hype before ti starts. Along with getting alot of free PR for basicly no effort.
Very easy to be PR friendly when your already on top:YIPPIE:
Im just hoping that C2D lights a fire under AMDs ass the same way A64 lit one under Intels... Then we all win :D
-
Quote:
Originally Posted by
NH|Delph1
My thought exactly :D
Great information metro, as always :up:
//Andreas
exactly. Lets see the overclocking potential :D
-
When is the official date for the NDA release? I thought it was sometime in later July.
-
Quote:
Originally Posted by
Danger30Q
When is the official date for the NDA release? I thought it was sometime in later July.
Not really later July...
15 July is the date,on coming Sunday.:yepp:
-
Quote:
Originally Posted by
major_john
Not really later July...
15 July is the date,on coming Sunday.:yepp:
for real?
awsome:up:
-
-
there goes my Q6600 order. I'm gonna run with the wolf
-
Although I want to see some reliable benchmarks before going with Yorkfield, I'm sure I'll end up going with the cheaper Q6600. There is a reason why all these massive price cuts are coming July 22nd - to make room for the premium priced penryn chips. I don't know if it will be worth the big increase in cost.
-
-
^^if it means they'll expand as kia then why not. but no doubt Penryn is going to give them some headache unless they come with higher clocks for K10. i hope they're up to the challenge.
-
Quote:
Originally Posted by
dexman
^^if it means they'll expand as kia then why not. but no doubt Penryn is going to give them some headache unless they come with higher clocks for K10. i hope they're up to the challenge.
AMD needs to be a challenge? ... no not just a challenge, they need a penryn killer. unless they start making 1watt cpus AMD will be like they were when I had my last intel system. they need to come up with a good performance reason for people to buy their cpus and gpus again.
-
When is Penryn supposed to come out again?
I better start saving now!
-
Quote:
Originally Posted by
safan80
AMD needs to be a challenge? ... no not just a challenge, they need a penryn killer. unless they start making 1watt cpus AMD will be like they were when I had my last intel system. they need to come up with a good performance reason for people to buy their cpus and gpus again.
It would be nice if Barcelona was Penryn killer but what are the chances? They need to stay at least competitive in higher mainstream/highend otherwise AMD becomes a company selling low-end bang for the buck alternatives to Intel chips. Still lots of OEM builders would use them due to the price and efficiency.
People are not only about performance, most of them don't even know what are they buying. Kuma @1.9 GHz(45W) is still a luxury for people browsing web, listening to music, watching movies and ocasionally playing games. It's not just power users out there.
-
Quote:
Originally Posted by
dexman
It would be nice if Barcelona was Penryn killer but what are the chances? They need to stay at least competitive in higher mainstream/highend otherwise AMD becomes a company selling low-end bang for the buck alternatives to Intel chips. Still lots of OEM builders would use them due to the price and efficiency.
People are not only about performance, most of them don't even know what are they buying. Kuma @1.9 GHz(45W) is still a luxury for people browsing web, listening to music, watching movies and ocasionally playing games. It's not just power users out there.
Rather good considering that AMD had over 3 years to work on it :rolleyes:
-
^^it's not like Intel was sleeping over that time
-
Quote:
Originally Posted by
nn_step
Rather good considering that AMD had over 3 years to work on it :rolleyes:
Intel used how many years on Prescott? :rolleyes:
-
Quote:
Originally Posted by
Shintai
Intel used how many years on Prescott? :rolleyes:
Too many!
:D
-
Quote:
Originally Posted by
Shintai
Intel used how many years on Prescott? :rolleyes:
4 , the same as K10
-
Quote:
Originally Posted by
Jimmer411
Very easy to be PR friendly when your already on top:YIPPIE:
Im just hoping that C2D lights a fire under AMDs ass the same way A64 lit one under Intels... Then we all win :D
QFT! Both times:)
-
Quote:
Originally Posted by
Jimmer411
Very easy to be PR friendly when your already on top:YIPPIE:
Im just hoping that C2D lights a fire under AMDs ass the same way A64 lit one under Intels... Then we all win :D
:up: Someone who get's "it"..
Good competition between these companies benefits us the end user in both cpu advances and in pricing so even though I have a house full of Intel equipment I am praying for AMD to come out with a monster.
-
Quote:
Originally Posted by
Movieman
:up: Someone who get's "it"..
Good competition between these companies benefits us the end user in both cpu advances and in pricing so even though I have a house full of Intel equipment I am praying for AMD to come out with a monster.
:up: Someone else who get's "it".. :clap:
