AMD Zambezi news, info, fans !

[Nintendork]

My guess still stands for 8150 @CB11.5 --> 8.75pts.

[2good4you]

And you, you're paid by AMD for sayin' such bullits or what ?

Why should you care? Feel hit by the post of mine? There are 2 people in last pages that I meant and one of them was you. Quite amazing. Bullsh1t? Oh no. The difference is that I don't buy all for a dollar and knows whats lie and not (yeah JF will confirm under my post). But yeah please continue with the facts of your and your "reliable" friend.

Are you aware that AMD has sent confidential datas to some press ? Do you really think that data directly from AMD are indeed faked data ?

Ohh thanks for the bright news! I don't think and I have the info to make me silent and not making fun of myself, especially with that attitude you have, but I understand why

[JF-AMD]

Well, if they don`t do marketing, who planned today`s surprise for them? On Intel`s day as well ;-).

Everyone here needs to understand that marketing =/= PR.

And you, you're paid by AMD for sayin' such bullits or what ?

Are you aware that AMD has sent confidential datas to some press ? Do you really think that data directly from AMD are indeed faked data ?

The room was full of press guys, I was there. Anything that came out of the room was shared with everyone in the press. It was all captured on film.

I found a few posts by JF which you might find interesting, I think he was commenting the sandra benchmarks:



These are from [H] and were posted in august, but there are quite a few hints there.

I think everyone should relax, there are so many fake benchmarks flying around no one can tell which one (if any) is true.

Yes, back in august there were all kinds of benchmarks on "final" silicon. I could not mention that we had not reached production silicon either.

The funniest thing is that I could give 2 people (an intel fanboy and an amd fanboy) the exact same piece of silicon and both could give you different benchmark results. Why would anyone assume that all of these fake benchmarks, if they were real, were actually on an optimized system? Couldn't you run a 4200RPM HD, 800MHz memory, and play all kinds of BIOS tricks? I know that I could probably get about 80% of the optimizations done to get the best performance out of a platform, but I know I could do 100% of the things that would sabotage performance. If you think about it, AMD is not releasing info, so the stuff that is floating around (if it is even real) is probably from people not friendly to AMD. And somehow everyone is trusting those results. Nobody ever questions the motives of the people supplying this info, but to be fair, because it is third or fourth hand (some guy I know who has a friend who has an uncle that knows a guy in...) how can anyone vouch for the results.

[undone]

The funniest thing is that I could give 2 people (an intel fanboy and an amd fanboy) the exact same piece of silicon and both could give you different benchmark results.

WTF AMD you're indeed EVIL

[informal]

I've forgot them.

BTW it seems, that you have something in common with those guys who satirized AMD running a platform with slides instead of a CPU.

Well you need to refresh your memory. Zambezi is launching soon.
And no,I don't have anything in common with those guys. I'm just being a realist now,not an optimist who based his expectations on power point bullets.

I found a few posts by JF which you might find interesting, I think he was commenting the sandra benchmarks:








These are from [H] and were posted in august, but there are quite a few hints there.

I think everyone should relax, there are so many fake benchmarks flying around no one can tell which one (if any) is true.

We do however know that IPC increases and clock is increased shouldn't that result in better performance?

Actually those sisoft numbers are quite good in SIMD department and not THAT bad in integer part,IF Turbo was off. If Turbo was on,then integer is abysmal (compared to Family 10h) and SIMD is still good. All this on "unoptimized" platform.And all this if the test is even real.

[PerryR]

He didn't give any results.
And you prepare review as far as I know.
So I can't see where is the problem.

Huh? He already said BD is much slower than its perceived competition.

[FlawleZ]

Until we have real numbers on relevant benchmarks with the final product, I don't think we should be drawing any conclusions.

To be honest, this was a BIG confidence booster for me.

I cheer good products. Blue,Green or pink, doesn't matter.
Now there are things I can't talk about yet but I can say I think they have a winner here.
I saw the benches...

[undone]

Well you need to refresh your memory.

No I needn't. Empiricism means nothing to me, history was history.

I'm just being a realist now,not an optimist who based his expectations on power point bullets.

There's a word that better than realist and optimist - neutral, and you could post less. And I will post less, everybody should post less.

These days I'd love to silent myself but often couldn't bear some weird comments flying around my ears and eyes. I'm tired.

[EniGmA1987]

still showing wrong info like TDP 174W but the core voltage is just 1.164V.

Maybe it likes to eat current for breakfast. Om nom nom

[radaja]

too bad we can't have everyone see the glass either half full or half empty
instead we get half screaming the glass is full and the other half screams the glass is empty!
where the hell is reality when you need it?

[freeloader]

Quoted by JF-AMD

Yes, back in august there were all kinds of benchmarks on "final" silicon. I could not mention that we had not reached production silicon either.

The funniest thing is that I could give 2 people (an intel fanboy and an amd fanboy) the exact same piece of silicon and both could give you different benchmark results. Why would anyone assume that all of these fake benchmarks, if they were real, were actually on an optimized system? Couldn't you run a 4200RPM HD, 800MHz memory, and play all kinds of BIOS tricks? I know that I could probably get about 80% of the optimizations done to get the best performance out of a platform, but I know I could do 100% of the things that would sabotage performance. If you think about it, AMD is not releasing info, so the stuff that is floating around (if it is even real) is probably from people not friendly to AMD. And somehow everyone is trusting those results. Nobody ever questions the motives of the people supplying this info, but to be fair, because it is third or fourth hand (some guy I know who has a friend who has an uncle that knows a guy in...) how can anyone vouch for the results.

I can't speak for anyone else around here, but I sure am upset that AMD can't even tell us when the NDA lifts. What financial damage is going to happen from releasing such a date? The NDA is under NDA, what a crock of . Share a little information with your "loyal" customers for once. I would understand if you had no idea when you were going to release the product, but you must have a concrete date by now for BD's release.

[repman]

Until we have real numbers on relevant benchmarks with the final product, I don't think we should be drawing any conclusions.

To be honest, this was a BIG confidence booster for me.

Agree on everything you said. Including the second line

[Solus Corvus]

too bad we can't have everyone see the glass either half full or half empty
instead we get half screaming the glass is full and the other half screams the glass is empty!
where the hell is reality when you need it?

The glass contains 50% fluid and 50% air. Hot air.

[rog]

I read somewhere that end of nda is not before end of September.

I read somewhere 12th October.

[Manicdan]

I can't speak for anyone else around here, but I sure am upset that AMD can't even tell us when the NDA lifts. What financial damage is going to happen from releasing such a date? The NDA is under NDA, what a crock of . Share a little information with your "loyal" customers for once. I would understand if you had no idea when you were going to release the product, but you must have a concrete date by now for BD's release.

because that date has probably changed as the release date has changed. the moment someone says the NDA is up, chances are it means the product is coming out in that next week. theres no need to feel hurt because they have a business to run. why not be happy they showed us what kind of air/water OC we can expect.

[maltrabob]

Everyone here needs to understand that marketing =/= PR.

Partially agree on that. Organizing that OC event was public relations (the action of a company in promoting goodwill between itself and the public / the community etc).
But then, setting a new world record and letting anybody know was marketing (the total of activities involved in the transfer of goods from the producer to the consumer, including advertising, shipping, storing, and selling). ;-)

[informal]

I read somewhere 12th October.

The FX giveaway contest has this date too in the rules section .

[LowRun]

because that date has probably changed as the release date has changed. the moment someone says the NDA is up, chances are it means the product is coming out in that next week. theres no need to feel hurt because they have a business to run. why not be happy they showed us what kind of air/water OC we can expect.

Maybe because you can't OC a CPU that's not available and even more because that CPU was supposed to be available somewhere between one month and a half ago and two weeks ago but instead it doesn't even have a launch date (not to mention availability ).

[Manicdan]

Maybe because you can't OC a CPU that's not available and even more because that CPU was supposed to be available somewhere between one month and a half ago and two weeks ago but instead it doesn't even have a launch date (not to mention availability ).

so we go look at concept cars because we want them, and the moment they say its not going to be anymore than a concept we call them horrible names and buy the competition, but all AMD is doing is trying to get things finished up, and theres so many things going on here. new arch, new node, new company building these chips, its ALOT of risk. the fact that opteron is shipping means they wont just make this product go away like larabee, it will be here, people just need some patience.

[metalazzo]

Huh? He already said BD is much slower than its perceived competition.

And do you know how much is "much slower" ?

[Andi64]

Some new info from OBR. This is something interesting to talk about, IMHO:

"Little secret: In Windows 8 (Development Release) is not Bulldozer chip as "8 Core - 8 Threads" but 4 Core - 8 Threads! AMD went out with the truth ! ! !"

IF Windows scheduler thinks this is an octo-core, and the threads go to whatever core is free, then you could have 4 threads running on 2 modules, which is far from optimal performance. Don't you think? It would be better to treat the CPU as a 4c/8t, the same way Intel HTT works.

[undone]

IF Windows scheduler thinks this is an octo-core, and the threads go to whatever core is free, then you could have 4 threads running on 2 modules, which is far from optimal performance. Don't you think? It would be better to treat the CPU as a 4c/8t, the same way Intel HTT works.

A core can be called a thread, but a thread might not be called a core. It depends on how 'big' the thread is. Some latest leak(despite the score) show that it only has 4.8x speedup in cinebench, if it's not a bug or crippled then the second integer core is much 'smaller' than expected, in this case I think it might be called a thread.

EDIT: I won't assert anything cuz something we can see now is weird, not only the crappy benchmark, but something,...

[repman]

Some new info from OBR.

It should read: Some crap/lies from *insert name here*

[Dirk Diggler]

Some new info from OBR. This is something interesting to talk about, IMHO:

"Little secret: In Windows 8 (Development Release) is not Bulldozer chip as "8 Core - 8 Threads" but 4 Core - 8 Threads! AMD went out with the truth ! ! !"

IF Windows scheduler thinks this is an octo-core, and the threads go to whatever core is free, then you could have 4 threads running on 2 modules, which is far from optimal performance. Don't you think? It would be better to treat the CPU as a 4c/8t, the same way Intel HTT works.

Maybe the driver being release has something to do with helping the scheduler with this issue and maybe the lack of a driver with all the other ES that have been benched are the reason for the low scores.

[Opteron146]

Some new info from OBR. This is something interesting to talk about, IMHO:

"Little secret: In Windows 8 (Development Release) is not Bulldozer chip as "8 Core - 8 Threads" but 4 Core - 8 Threads! AMD went out with the truth ! ! !"

IF Windows scheduler thinks this is an octo-core, and the threads go to whatever core is free, then you could have 4 threads running on 2 modules, which is far from optimal performance. Don't you think? It would be better to treat the CPU as a 4c/8t, the same way Intel HTT works.

Depends if you want to use Turbo mode or not. I.e. that feature might be interesting for OC, but not for the typical Joe Sixpack enduser.

@JF-AMD:
Just found that comment from the x264 lead developer, they are interested in hand-coding for XOP:

XOP: possibly, but I need SSH access to a Bulldozer to do such optimizations.

http://forum.doom9.org/showthread.ph...43#post1507243
Contacts: http://x264dev.multimedia.cx/about

It is an old message from June, but just in case if nobody @AMD knows him, still: Please help that guy.
I guess I do not need to tell you something about x264 and its importance ^^

Thanks

Opteron146