K10 Scores starting to surface

Printable View

Show 100 post(s) from this thread on one page

08-31-2007, 10:08 AM
zakelwe

All this talk of K10 needing MHz to really fly as such is really baloney.

No cpu in history has managed to achieve better than linear scaling. All have shown linear scaling low down and then drop off from this when other system bottlenecks start to appear. True, a good CPU will not drop off as much but it will never improve with speed. To say it scales better than linear you are sort of getting a perpetual motion machine scenario here, or more power out than in.

Gary is no mug but a K10 at 3GHz will be 50% or less quicker than one at 2Ghz, not 60% or 100% or 100000000%.

Maybe he is saying it has a high IPC and so any increase in speed gives a good rate of return on total cpu power due to the IPC level. That is a reasonable arguement. Non-linear scaling is definitely not.

As for the actual scores, you get this all the time with video card releases, somebody posts some high score and somebody posts some low score and it is only when the proper reviews come out with "relevant" cpu's to what you and I can buy, should you form your opinion.

We just have to be patient and see.

Regards

Andy
08-31-2007, 10:16 AM
JumpingJack

Quote:

Originally Posted by zakelwe

All this talk of K10 needing MHz to really fly as such is really baloney.

No cpu in history has managed to achieve better than linear scaling. All have shown linear scaling low down and then drop off from this when other system bottlenecks start to appear. True, a good CPU will not drop off as much but it will never improve with speed. To say it scales better than linear you are sort of getting a perpetual motion machine scenario here, or more power out than in.

Makes one wonder doesn't it :) ... how they come up with this logic :)
08-31-2007, 10:25 AM
JumpingJack

Quote:

Originally Posted by informal

And to the one dude who said that HT3.0 was pushed to 2009,he is wrong.All Phenoms are HT3.0 ready,the boards (RD790) support HT3.0(16 bit link width,5.2GT/s).The chips CAN and will work(100%) on AM2 motherboards and the HT scales back to HT1.0(What this does to performance is not clear ,yet).

I am just going by what was in AMD's latest roadmap:
http://pc.watch.impress.co.jp/docs/2.../kaigai_02.pdf
(Pg 42)
http://www.amd.com/us-en/assets/cont...ck_Bergman.pdf
(Pg 19)

Two different presenters, same conlcusion.... Phenom X2/X4 will have HT1.0 specification. It is speculation as to why, if AMD is indeed accurate, perhaps they do not understand their own plans.... I could guess, purely guessing, that HT3.0 is having issues and holding back clocks, so they may drop to 1.0 specs in order to get higher CPU clockspeed.

Some seem to think budapest will transistion to HT3.0.... but, unless AMD botched their presentation, it appears that it has been pushed.
08-31-2007, 10:37 AM
informal

Quote:

Originally Posted by JumpingJack

I am just going by what was in AMD's latest roadmap:
http://pc.watch.impress.co.jp/docs/2.../kaigai_02.pdf
(Pg 42)
http://www.amd.com/us-en/assets/cont...ck_Bergman.pdf
(Pg 19)

Two different presenters, same conlcusion.... Phenom X2/X4 will have HT1.0 specification. It is speculation as to why, if AMD is indeed accurate, perhaps they do not understand their own plans.... I could guess, purely guessing, that HT3.0 is having issues and holding back clocks, so they may drop to 1.0 specs in order to get higher CPU clockspeed.

Some seem to think budapest will transistion to HT3.0.... but, unless AMD botched their presentation, it appears that it has been pushed.

It's botched,Phenom is HT3.0
08-31-2007, 10:40 AM
terrace215

Quote:

Originally Posted by cpuz

At least that shows that all cache levels are enabled.
(latency gets the size by measuring the access time, unlike cpuz that relies on the cpuid outputs)

Why do people question those results any longer? The anand guy later confirmed that these results are like the results they are seeing... and that people were likely to be disappointed until AMD can get the clock speeds up.
08-31-2007, 10:44 AM
Lightman

2 Attachment(s)

Lets compare latencies!

My X2 5600+ at 1938MHz/784MHz 4-4-4-12-15 (I'm too lazy to do exact same settings at the moment)
Attachment 63782

Barcelona 2GHz/Reg. 667MHz 5-5-5??
Attachment 63783

What strikes is a lot higher access latencies to memory which is expected due to slower memory modules and dual socket nature of system. Now everybody know how well K8 scales in SuperPi with memory speed!

For sure C2D will still be king in that bench but at least Phenom is looking much better than K8! :)

Edit:
We also can see here much better L1 cache implementation in K10 (first two columns).
08-31-2007, 11:00 AM
cpuz

Quote:

Originally Posted by Lightman

What strikes is a lot higher access latencies to memory which is expected due to slower memory modules and dual socket nature of system. Now everybody know how well K8 scales in SuperPi with memory speed!

Don't forget that latencies are cumulated (memory = L3 miss + L2 miss + L1 miss) ;)
Keeps being high anyway.
08-31-2007, 11:08 AM
xlink

don't see why they can't just search all memory levels at once...

anyone care to inform me a to what prevents this?
08-31-2007, 11:47 AM
JumpingJack

Quote:

Originally Posted by xlink

don't see why they can't just search all memory levels at once...

anyone care to inform me a to what prevents this?

Technically, they do.... on almost every cache access, it is called snooping. It also depends if it is inclusive or exclusive cache, if inclusive then there is no need to search lower memory as it is guaranteed to be in lower cache... also since AMD uses an exclusive cache, the L1 and L2 are pooled together, more or less i.e. the data in L1 does not need to be in L2, but the search for data is still top down.

http://www.ece.mtu.edu/faculty/btdav...s/ispass04.pdf

Nice explanation and comparision of inclusive vs exclusive cache. Skim through their conclusions, exclusive caches benefit most when caches are small and dimishes when caches grow larger -- exclusive caches are also more complex and require more control/complexed logic.
08-31-2007, 12:18 PM
BrowncoatGR

Quote:

Originally Posted by JumpingJack

I am just going by what was in AMD's latest roadmap:
http://pc.watch.impress.co.jp/docs/2.../kaigai_02.pdf
(Pg 42)
http://www.amd.com/us-en/assets/cont...ck_Bergman.pdf
(Pg 19)

Two different presenters, same conlcusion.... Phenom X2/X4 will have HT1.0 specification. It is speculation as to why, if AMD is indeed accurate, perhaps they do not understand their own plans.... I could guess, purely guessing, that HT3.0 is having issues and holding back clocks, so they may drop to 1.0 specs in order to get higher CPU clockspeed.

Some seem to think budapest will transistion to HT3.0.... but, unless AMD botched their presentation, it appears that it has been pushed.

No im quite sure HT3 was pushed back only for multisocket servers, not for the desktop.(basically socket F+ got delayed or canceled). Take a look at slide 13 in the pdf you posted
08-31-2007, 02:30 PM
JumpingJack

Quote:

Originally Posted by BrowncoatGR

No im quite sure HT3 was pushed back only for multisocket servers, not for the desktop.(basically socket F+ got delayed or canceled). Take a look at slide 13 in the pdf you posted

Interesting.... but Socket F+ cannot be delayed, if it were then the split power plane will not be functional...
08-31-2007, 03:16 PM
EvlUndrWareNome

retail day is coming up :)
08-31-2007, 03:49 PM
adamsleath

k10>k8; it's that simple.
i just want to see fps for games with oc'ed phenom X4 (et al.) :yawn:
i really want that +5%: :yawn2:

& as i havent seen any amd quad results (ie re heat&oc) - i'm interested to see scaling/heat problems aswell.

Surely someone will have a rig setup in September?
08-31-2007, 05:15 PM
arisythila

Quote:

Originally Posted by savantu

Core totally owns it in wPrime.

Let's wait for some Penryn scores.

your on crack....

My Q6600 @ 3.3GHz memory clock at 1200MHz 5-5-5 doesn't even score that low....

There is something faulty about that benchy.
08-31-2007, 05:20 PM
arisythila

Quote:

Originally Posted by EvlUndrWareNome

retail day is coming up :)

For Barcy... Not Phenom...
08-31-2007, 05:27 PM
nn_step

Quote:

Originally Posted by arisythila

For Barcy... Not Phenom...

Barcy works in Socket F and you have many Socket F boards to choose from, so what is your point :rolleyes:
08-31-2007, 05:29 PM
red

oh no you didn't just eyeroll him!

phenom box looks better ok that's why
08-31-2007, 05:42 PM
mAJORD

Quote:

Originally Posted by arisythila

your on crack....

My Q6600 @ 3.3GHz memory clock at 1200MHz 5-5-5 doesn't even score that low....

There is something faulty about that benchy.

They're both 8core systems Aristhila, that's why.

But no, it doesn't own it, as the xeon was @ 2.6ghz
08-31-2007, 05:53 PM
KTE

1 Attachment(s)

Quote:

Originally Posted by informal

It's botched,Phenom is HT3.0

Quote:

Originally Posted by informal

And to the one dude who said that HT3.0 was pushed to 2009,he is wrong.All Phenoms are HT3.0 ready,the boards (RD790) support HT3.0(16 bit link width,5.2GT/s).The chips CAN and will work(100%) on AM2 motherboards and the HT scales back to HT1.0(What this does to performance is not clear ,yet).

For everyones information, look very carefully at the latest AMD roadmap.

Attachment 63799

I would say Phenom (only Agena) has HT 3.0 capability but disabled to work at HT 1.0 until the clocks are ramped up sometime late Q4. Clocks of approximately 2.4GHz I'm guessing which I expect around Xmas holiday period. I still expect Agena FX to have HT 3.0 fully working.
08-31-2007, 06:16 PM
Donnie27

Quote:

Originally Posted by red

oh no you didn't just eyeroll him!

phenom box looks better ok that's why

Good one :rofl: :rofl:
08-31-2007, 06:42 PM
gundamit

Quote:

Originally Posted by zakelwe

We just have to be patient and see.

Given the nature of overclockers patience is always going to be in short supply around here. :D
09-01-2007, 12:58 AM
savantu

Quote:

Originally Posted by cpuz

At least that shows that all cache levels are enabled.
(latency gets the size by measuring the access time, unlike cpuz that relies on the cpuid outputs)

Did you really expect otherwise ?
09-01-2007, 01:38 AM
NapalmV5

any benchs on female cycles? :D
09-01-2007, 01:43 AM
Nedjo

Quote:

Originally Posted by KTE

For everyones information, look very carefully at the latest AMD roadmap.

http://www.iian.ibeam.com/events/tho...e/Slide133.JPG

Show 100 post(s) from this thread on one page