AMD Zambezi news, info, fans !

[Dresdenboy]

Only 6.95 with 4.3ghz? Doesn't the 2600K pull 6.8 at 3.4ghz?

If there is any use for these results.. why don't you ask why the 3.6G FX is as fast as a 4.3G FX..

[TESKATLIPOKA]

Dresdenboy Why?

[Seth-01]

If there is any use for these results.. why don't you ask why the 3.6G FX is as fast as a 4.3G FX..

because Cinebench benched in normal mode (3.6 GHz) but recognize the frequency in turbo mode ???

[Pestilence]

If there is any use for these results.. why don't you ask why the 3.6G FX is as fast as a 4.3G FX..

Why?

[TESKATLIPOKA]

Seth-01 Not quite, this BD was run at 4.2Ghz with turbo OFF.

[Solus Corvus]

Great news guys, the noname blogger says his pal Peter sent him some tests comparing IPC between BD and Thuban at 4.2Ghz no turbo (1 thread)
SuperPI +22% for Thuban
Cinebench 10 +13% for Thuban
Cinebench 11.5 +23% for Thuban
wPrime 32M +42% for Thuban
Fritzchess (both 6 threads) +24% for Thuban
Seriously Its too unbelievable to be believable

I wouldn't trust those results for the simple fact that we have others with legit access to these cpus saying the opposite. Plus nothing we know about the architecture would suggest such a huge drop in IPC - it would come down to a failure in implementation, which could indicate the quality of particular chip he has.

However, with that said, don't rest your (Not you specifically TESKATLIPOKA, but everyone) sense of self and identity on those numbers not being true, you risk becoming the next reverse-fanboy if they are. Those of us with a long memory will remember that OBR is exactly that sort of individual. When he came here he was a pro-amd troll. He said that Conroe was "very big hype only" and then after release it wouldn't be faster for long (how did those predictions turn out, Mr "inside info" ). Then, disappointed with barcelona and R600 he turned into an anti-amd troll and said things like if the leaked R600 benches were true (they were, roughly) that we should say "Good Bye to AMD/ATi" (how did that one turn out? lol).

Everyone, if you don't want to become the next OBR please moderate your expectations. If not for yourself at least do it for the rest of us. Companies aren't perfect and even your favorite one will let you down someday.

[TESKATLIPOKA]

Solus Corvus Nicely said but my expectations aren't that high, in my opinion IPC can't be lower than K10 and why is that, because of module and integer size compared to Llano, considerably bigger yet lower IPC doesn't coexist in my book.

[Apokalipse]

Great news guys, the noname blogger says his pal Peter sent him some tests comparing IPC between BD and Thuban at 4.2Ghz no turbo (1 thread)
SuperPI +22% for Thuban
Cinebench 10 +13% for Thuban
Cinebench 11.5 +23% for Thuban
wPrime 32M +42% for Thuban
Fritzchess (both 6 threads) +24% for Thuban
Seriously Its too unbelievable to be believable

If he's talking about broken ES chips, maybe it's true.... and completely irrelevant
(I think I read somewhere that one reason for poor ES performance was no hardware prefetching)

[TESKATLIPOKA]

Apokalipse I heard it was enabled in AGESA 0.0.9.* and that should be in F5 bios for Gigabyte or wasn't yet enabled .

[rog]

I no understand this:

Attachment 120169

Same result with different frecuency?

The left result is his own Benchmark result and the other result is the one from Peter, he sold one of his B2 to him. That's why they are slightly different, nothing special I think.

[dess]

Hey guys, I wonder why nobody cared to reflect on my questions from yesterday (#2696)... Does it just vent unnoticed next to the newer OC results, or is it an indication I should drop them altogether?

[Oese]

it did not seem to be a question but more like a reflection

[Pestilence]

All i want is a review from Anandtech and i'll be happy.

[dess]

it did not seem to be a question but more like a reflection

Yes, the first part of it. Maybe I've packed to much into one message.

So, I mean these ones:

BTW, they're saying it brings +xx% with only 33% bigger area, right? Well, +33% over a single thread BD module. But, what about 10h cores? A 2-thread BD module is almost twice the size of a 10h core! I didn't counted about but it's roughly as much powerful (c2c) as much it's bigger, isn't it?

What's the rationale behind it, then, one could ask? I think these:
- It allows for higher clocks, and so higher performance. In theory, at least. I wonder how much...
- It allows for turning off the whole FPU, gaining even more frequency headroom. We will see, how much, as well.
- It allows for replacing the FPU with some GPU-like compute units. I don't know it it's the plan, but I think this one is the most encouraging.
- ...?

BTW 2, I was speculating on the possibility of clocking the integer clusters higher than the rest of the module. When they were to reveal some "BIG secrets" a few days back I was thinking is it perhaps about this...? More so that I've heard something like if they were trying to solve some issues, but failed, for now. I still wonder if it makes sense...? We know the prefetch and decode logics can handle 4 instructions per cycle, forwarding 4 macro-ops. Then, each integer unit can receive 4 micro-ops, which is essentially 2 macro-ops, so half of the amount the front-end forwards. And it's allways half of it. (In contrast to SMT...) But, what if there are 3 or even 4 independent instructions in a thread? I know it's rare, and so the average IPC is around 1.00 (many times even less), I was also playing with performance counters. But still, it's an average amount, with high and low borders...

Of course, I know about the importance of the front-end in achieved IPC, and I hope the Bulldozer is advanced in this respect, as well.

All in all, I still count on Bulldozer, and I know it can be a surprise (a positive one). Well, if not the current implementation, then the next one (Piledriver). (Unless should it turning out to be too weak, from the basics of it, but I don't think so.)

[Nintendork]

Btw someone sent me a PM here pointing out that "noname faker guy" says I post comments that he deletes on his blog?! I don't even visit his blog so how can I post comments? That guy is a real piece of work hehe.
I see some of you posted results of 4.2Ghz FX. Is this from him?

I think it's better not even mention as "the blabla guy". Forget that he exists, he laughs everytime someone gives somekind of a voice in the forum.


Last 2 pages dedicated to the "problem", you help the problem.

[JumpingJack]

All i want is a review from Anandtech and i'll be happy.

I listened to the PCPer podcast #170 this afternoon, they made brief mention that they haven't been briefed by AMD on BD as of yet, it looks like people hoping for an NDA lift on the 19th will be disappointed.

[JumpingJack]

Btw someone sent me a PM here pointing out that "noname faker guy" says I post comments that he deletes on his blog?! I don't even visit his blog so how can I post comments? That guy is a real piece of work hehe.
I see some of you posted results of 4.2Ghz FX. Is this from him?

Meh. His confrontational tone diminishes his credibility, pay it no mind.

[radaja]

i hate finding posts like this
smartidiot89 posted this at amdzone

I got some time alone with a Bulldozer system with a retail sample FX-8150 and what we've seen so far seems correct
and AMD aren't even sure internally(!) when Bulldozer will launch. I am well aware it still could be an old BIOS/AGESA code
so don't lecture me on that.
I'll be a tease as I'll write an article about it tomorrow specifically what I know about the when they think(!) launch will take place approximatelly

[Pestilence]

i hate finding posts like this
smartidiot89 posted this at amdzone

Its just someone's opinion. No reason to get upset about it.

[radaja]

Its just someone's opinion. No reason to get upset about it.

i think he is a hardware reviewer for a website

[Olivon]

i think he is a hardware reviewer for a website

smartidiot89 works for Nordic Hardware if I say no mistake.

[mAJORD]

22% slower than thuban at super pi , so slower than bobcat?

[metalazzo]

Curry > Cheeseburger

[Sparky]

Who cares about stupid super pi. It has zero bearing on anything.

*edit* hmm a little ironic post I guess given my current avatar.

[duron]

what's "super pi" again?