K10 Barcelona 50% faster than Kentsfield ?

[sm625]

Is there anyone who actually posted correct screenshots of benchmarks 1, 2, or 3 months before K10 launched?

 

[RoyG]

Is there anyone who actually posted correct screenshots of benchmarks 1, 2, or 3 months before K10 launched?

This one is from AMD official!

 

[piesquared]

Im guessing you were one of the people saddened that Fudo was incorrect on this a few years back?

This is a perfectly valid necro, and it is actually quite relevant...threads here don't vanish.

More flamebait. Was that guess supposed to be some kind of question? Let me try: i'm guessing you are somehow connected to this person, who is posting the same stuff on AMD finance message boards?

 

[videoclone]

K10 is an update of K8.1 and K8.1 is an update of K8 and K8 is an update of K7 ext ext

Bulldozer is a whole new redesign from the ground up.
I dont think this can relate to Bulldozer at all, and after all.. the Quad core K10 was almost a year late because they went native quadcore, giving intel a huge advantage.

Now we have intels 32nm Chip VS AMD's 32nm Chip .. its a little more balanced with the mature 32nm process going on intels side.

 

[RobertPters77]

Clear! *bzzt* Okay, you're good to go. Get back in there!

 

[Cogman]

K10 is an update of K8.1 and K8.1 is an update of K8 and K8 is an update of K7 ext ext

Bulldozer is a whole new redesign from the ground up.
I dont think this can relate to Bulldozer at all, and after all.. the Quad core K10 was almost a year late because they went native quadcore, giving intel a huge advantage.

Now we have intels 32nm Chip VS AMD's 32nm Chip .. its a little more balanced with the mature 32nm process going on intels side.

I think this thread is VERY relevant. It shows pretty much the exact path that hype takes. Who cares that bulldozer is a whole new design? Netburst was a whole new design as well, and look at how that panned out.

 

[podspi]

I think the big difference between then and now is that AMD has been pretty quiet about BD's performance (they weren't with Barcelona).

 

[drizek]

I think if AMD knew that Bulldozer would be as big a failure as Barcelona, they would have just packed up and gone home a long time ago.They can't survive another flop of that magnitude again, especially with 22nm still at least two years off. They need to beat SB, compete with IB and hold off IB+1 with BD at 32nm.

It better be really good.

 

[996GT2]

I think if AMD knew that Bulldozer would be as big a failure as Barcelona, they would have just packed up and gone home a long time ago.They can't survive another flop of that magnitude again, especially with 22nm still at least two years off. They need to beat SB, compete with IB and hold off IB+1 with BD at 32nm.

It better be really good.

Need to: yes.

Will it happen? most likely not.

 

[Tuna-Fish]

I think if AMD knew that Bulldozer would be as big a failure as Barcelona, they would have just packed up and gone home a long time ago.They can't survive another flop of that magnitude again, especially with 22nm still at least two years off. They need to beat SB, compete with IB and hold off IB+1 with BD at 32nm.

It better be really good.

Honestly?

I think they could survive off Llano and Bobcat if they needed to. Their GPU side is and will be such a huge advantage that it would be feasible for them to keep the company afloat for years on it alone.

 

[drizek]

That's kinda my point though, if they can't beat SB... why do they even bother existing?

Edit: to address Tuna-Fish, let me rephrase that, why do they even bother with Bulldozer if GPUs is all they're good for?

 

[OCGuy]

Honestly?

I think they could survive off Llano and Bobcat if they needed to. Their GPU side is and will be such a huge advantage that it would be feasible for them to keep the company afloat for years on it alone.

Not even close.....if BD is a flop, look for a buyout.


Their GPU and CPU divisions will already be at odds, as the APU becomes more powerful, it will be eating into the high-volume parts such as the 5770.

If BD doesnt deliver marketshare (performance without marketshare is worthless), then it is not going to be good for us enthusiasts...

 

[drizek]

The problem with a buyout though is that whoever buys them won't be albe to make x86 CPUs, right? The license is nontransferable.

 

[Idontcare]

The problem with a buyout though is that whoever buys them won't be albe to make x86 CPUs, right? The license is nontransferable.

License may not be transferable but the IP portfolio is. Intel needs access to that IP for their existing CPU's.

I'd be willing to bet that in light of the risk of receiving an injunction against the sale of their x86 cpu's that Intel would be quite ready and willing to negotiate a new x86 license for whatever business owns the IP portfolio.

 

[edplayer]

Their GPU and CPU divisions will already be at odds, as the APU becomes more powerful, it will be eating into the high-volume parts such as the 5770.

Their APUs will become more powerful. Beating the 5770 won't matter because by the time the APUs are that powerful, AMD will have a faster mid-range/high volume part

 

[RoyG]

That's kinda my point though, if they can't beat SB... why do they even bother existing?

Ask Phenom I/II.

 

[Jacky60]

this fall supposedly. as big a fan of amd as i am (my last intel was celeron 300a), i think it's going to be hard for me to buy a k10 knowing that 45nm penryn is right around the corner, probably with higher clock than k10. now if amd allows people to have a clear upgrade path from 65nm k10 to 45nm k10 on the same motherboard, and provided that k10 outperforms intel, then i might stick with amd. i dont wanna buy k10+mobo only to have to replace the mobo when 45nm k10 comes out.

You have an intel I5 7500 in your signature. Is that from the pre-celeron days?

 

[drizek]

Ask Phenom I/II.

Phenom II competes well against Core2Quad, particularly Thuban. At least with Phenom I they had Phenom II to come in and save them after a relatively short time. At the time, Nehalem was prohibitively expensive, with $250+ motherboards and requiring 3 sticks of expensive DDR3 RAM. That's why I got a Phenom II, it was a drop in replacement for my DDR2 Athlon X2.

Now they are competing against $350 for a Sandy Bridge quad core, 8GB ram and a motherboard(if you shop at microcenter). If they don't deliver a lot of performance for not a lot of money, they are going to get creamed, and they won't have a die shrink for another 2 years, at least.

 

[Nemesis 1]

I think the big difference between then and now is that AMD has been pretty quiet about BD's performance (they weren't with Barcelona).

Yes but it was differant times. AMD 64 x2 were hammering intel and the people who bought these CPus. The cheapest AMD x2 was $300+ After C2D release AMD stock sank to the bottom . Great Times for me. Intel brought C2D in at lower pricies than AMD and killed them with it . SO AMD was in panic mode and out and out lied about the PHI performance numbers and back than AMD fanbois were still foaming at the mouth and ate AMDs lies hook line and sinker . True Facts.

 

[Tuna-Fish]

AMD was in panic mode and out and out lied about the PHI performance numbers

The numbers they published were internal projections, and they believed them.

The big problems were a couple of bugs in the processor, and much more importantly, the AMD 65nm process dove head-first to the same swamp Intel 90nm had. Intel has steadily held the process tech advantage since then.

 

[Ferzerp]

I don't really think the necro is flamebait at all. It points out the folly in putting stock in rumors and such.