The K10 stepping fiasco

[Carfax]

If anyone has been keeping up with the nightmare that has become the Barcelona launch, this article from DailyTech may help shed some light on some of the controversy surrounding the launch.

At first, Dave Graham over at AMD Zone stated that the B1 chips had issues concerning the North Bridge, and that the BA stepping would be used in the retail versions.

DailyTech confirms this, but then it becomes even more confusing.

In his article, Kubicki alludes that the chips used in Monday's launch were B1 stepping, but then also states in the same article that they used B2 stepping in the preview aswell.

Apparently, the 2.5ghz parts use the B2 stepping, and are supposedly errata free.

Yet, both the Anandtech and Tech-Report preview/review seemed to have some inconsistencies in the K10's performance.

So now, I'm left wondering whether Anandtech and Tech-Report really did have B2 stepping chips, or if the B2 stepping chips also have some weird issues that would also affect performance one way or another.

[Sparky]

Could be other factors in the inconsistencies maybe, such as bios and chipset?

Not saying there are but just throwing that out there for whatever it may be worth (probably not much).

Bugs to work out? Maybe. If not, fine.

[dinos22]

Could be other factors in the inconsistencies maybe, such as bios and chipset?

Not saying there are but just throwing that out there for whatever it may be worth (probably not much).

Bugs to work out? Maybe. If not, fine.

yeah probably bios related more than anything else

this is bad publicity for amd going out demoing crippled chips/platforms...it doesn't look good

just stick it out for the other few months since it's taken so long and do it right

[Kenetixx]

I would say BIOS issues

[SEA]

Carfax

The K10 stepping fiasco



.. If anyone has been keeping up with the nightmare that has become the Barcelona launch, ...


I really like the way you try to express your feeling!

[perkam]

It was a soft launch.

The Xeon fanboy part of DT should at least wait for the actual launch of retail chips before passing judgement on usability issues.

No it doesn`t start like clockwork but you can`t define it a fiasco based on ES chips.

Perkam

[lapdog]

Better late than never. Much better late then defective.

[Caparroz]

Better late than never. Much better late then defective.

Exactly what I was thinking. I'm no expert in the serverland but judging from the very cold reception I saw Barcelona getting from the interwebs it could be delayed another couple of months.

[n91htmare]

Well it's now apparent that Barcy needs another revision or two. So at 6 weeks per revision, we're looking at 1.5 months at the least.

There was no way AMD was going to delay the launch. So instead they did a soft/paper launch of the product.

Now they're getting heat for to.

I'd feel sorry for AMD if they're weren't so kocky about the K10.

[zakelwe]

So now, I'm left wondering whether Anandtech and Tech-Report really did have B2 stepping chips, or if the B2 stepping chips also have some weird issues that would also affect performance one way or another.

If Anandtech used BA cpu's and BA was the same as B2 then that would explain why B2 had similar performance or "weirdness" to what you and Kris K at Daily Tech suppose were B1's.

That's probably a more consistent argument than saying B1 is borked and B2 is also borked, I think that unlikely.

You could say, well why would BA/B2 have this weirdness? Well, I don't know but 65nm K8 had cache weirdness when the L2 cache latency went up over the 90nm K8. AMD's answer to that .. so we can put bigger L2 cache in future. Are they ever likely to put in more L2 cache for K8 when they are now yesterdays news and selling for very low $$ ..nope, why make them even more expensive by adding more cache? So that was just spin.

Regards

Andy

[Morais]

It was a soft launch.

The Xeon fanboy part of DT should at least wait for the actual launch of retail chips before passing judgement on usability issues.

No it doesn`t start like clockwork but you can`t define it a fiasco based on ES chips.

Perkam

I have to agree.They tested barcy on k8 chipset, that doesnt look fair for k10 results...The best is wait for phenom calmly and then make the conclusions.

And what tha hell? A fanboy in DT staff is

[Hornet331]

I have to agree.They tested barcy on k8 chipset, that doesnt look fair for k10 results...The best is wait for phenom calmly and then make the conclusions.

And what tha hell? A fanboy in DT staff is

then tell me pls why amd makes all the fuzz about super drop in upgradability of k10 into k8 boards when the chipsets "suck"...

[R101]

If it was February, I would have given AMD all the time in the world, but after this many months, these issues that are popping left and right seem inexcusable.

[alayashu]

then tell me pls why amd makes all the fuzz about super drop in upgradability of k10 into k8 boards when the chipsets "suck"...

that's on the server side, where 10-15% more performance doesn't
justify the costs of a new MB etc.

[Donnie27]

Did AMD sell any B1's?

[Jacky]

Did AMD sell any B1's?

I hope for them they didn't. Imo the BA stepping was released and sold...

[Donnie27]

I hope for them they didn't. Imo the BA stepping was released and sold...

I hope they didn't either with them being buggy as well as slower. Please note, I also said Intel shouldn't have launched the first Prescotts they shipped. I knew they were hot but I didn't believe just how hot they were until I saw two, that was a Joke.

[MaxxxRacer]

Apparently, the 2.5ghz parts use the B2 stepping, and are supposedly errata free.

No CPU is errata free... none.

[red]

I think fax means free of errata that can cause significant performance difference.

http://www.dailytech.com/Stumbling+i...rticle8804.htm
5% is pretty significant for an errata.

[informal]

I think fax means free of errata that can cause significant performance difference.

http://www.dailytech.com/Stumbling+i...rticle8804.htm
5% is pretty significant for an errata.

From the same article:

An AMD engineer, when confronted with the claim, stated that 5% gains when moving from B1 to BA processors "seem conservative."

[Carfax]

I think fax means free of errata that can cause significant performance difference.

http://www.dailytech.com/Stumbling+i...rticle8804.htm
5% is pretty significant for an errata.

Thats exactly what I meant..

[Shintai]

Today..a 3Ghz Opteron can compete with a 3Ghz Woodcrest.

On the desktop a 3Ghz X2 can compete with a 2.4Ghz Conroe.

So no more hypes please

I also dont have much faith in the stepping part. Because that has never been so in history either on such a late stage.

[Morais]

i just hope AMD fixes all bugs untill the official phenom launch

[DeepThought86]

Today..a 3Ghz Opteron can compete with a 3Ghz Woodcrest.

On the desktop a 3Ghz X2 can compete with a 2.4Ghz Conroe.

with the 2Ghz K10 buggy part performing like a woodcrest at 2.33 Ghz, and keeping in mind K10 scales better both in terms of frequency and core count I would say your server speculation .. kind of... sucks...

As much as I hate to agree with Shintai , I interpreted his original statement as referring to today's K8 i.e. currently in server K8 Opterons are already clock-to-clock equivalent to Core-based Xeons but in desktop they trail.

In the server space I think Barcelona will cause significant acid-indigestion for Intel. Already, their superior platform means even with K8 overall power consumption and performance is competitive and with K10 they can hit the 1S 4C market they're been locked out of for 1 year as well as take the allout performance crown in 2S or 4S.

As for the desktop, outside of the ultra-enthusiast market I'm pretty sure Phenom's performance will be "close enough" to land ever-increasing OEM business. It's basically a race against the clock to switch to the K10 line top to bottom before they run out of cash

[Shintai]

with the 2Ghz K10 buggy part performing like a woodcrest at 2.33 Ghz, and keeping in mind K10 scales better both in terms of frequency and core count I would say your server speculation .. kind of... sucks...

For the desktop it looks like K10 has a good chance of equaling the IPC of c2, it depends on how much improvement will a low latency high bandwidth memory subsystem result in. But I don't think 5% are out of reach, K10 is 4 data hungry cores. That plus the "at least 5%" from fixing bugs should bring K10 very close to penryn IPC wise. Penryn will still clock higher but the gap will be nowhere near the one that is between c2 and K8.

K10 has very good chances of wiping the floor with intel in server, and be competitive on the desktop front, it all depends on how will amd execute their manufacturing, so shintai you can spare yourself the fanboi stuff ... you know what, I actually don't think you're an intel fanboy, you just want amd to fail badly. I bet you will get nightmares and eventually lost your sleep, and your mind if amd fight back the performance crown

A 2Ghz K10 dont perform like a 2.33Ghz Clovertown.

The 5% is another bogus story. And I will gladly admit im wrong if not. But the already Core 2 killer with 2Ghz beating 3Ghz Core 2s and such is dead.

Talking about fanboy, how would you categorize yourself? I give a rats rear end about both AMD and Intel. But there is a reality we have to deal with.

Phenom will be 5% lower than current 65nm Core 2. For 45nm Core 2 its gonna be worse with 10-15% slower.

But again, we can just wait and see. And I can yet again for the nTh time tell the hypeboys: I told you so.