AMD Bulldozer Engineering Sample CPU Overclocked to 4.63GHz

[Abwx]

Seriously?

Bulldozer can execute instructions that haven't been created yet?

You re stretching my words purposely..

Was talking of course of instructions that are still not used
by current softwares , and as such are FUTURE instructions
for the sofware designers, such as FMA and AVX, not counting
the XOP subset wich is distinct to AMD.

 

[Abwx]

Strong troll

Strong troll, not sure , but weak answer, for sure..

 

[Abwx]

Seems that BD is rather late :

For the high-end Scorpius platform, AMD will announce the AM3+-based FX-8150, FX8100, FX6100 and FX4100 by the end of September with FX8170, FX8120, FX6120 and FX4140 set for the first quarter of 2012.

http://www.digitimes.com/NewsShow/NewsSearch.asp?DocID=PD000000000000000000000000020423&query=AMD

 

[Minerva]

Why? It's been long known that Bulldozer was designed with high clock speeds in mind rather than the high IPC of the Sandy Bridge processors.

Just about every single 2500K or 2600K out there can do 4.63 GHz with ease. Bulldozer needs to be able to overclock higher than that to be competitive.

Also, did you see the voltages used in the OP? That BD chip needed 1.5V to reach 4.63 GHz. My 2500K will do 5 GHz prime-stable at that voltage, and there are many 2500/2600Ks out there that will do 5 GHz stably at lower voltages.

And that's where the Achilles Heel lies. There is no guarantee in OC at all.

The userbase (all pc users not just AMD) of non overclockers is far, far greater than the other. Out of the box performance is what matters and (for AMD's sake) I hope they can deliver the goods this time around.

 

[ShadowVVL]

I thought bd was a strange idea in the first place and I still dont understand how its supposed to work, but atleast it doesnt have a igp that I will never use.

 

[Skurge]

Dude, haven't you been paying attention lately?

Bulldozer is the Chuck Norris of CPU's.

It is so awesome that it designed itself, traveled to the future to determine what instruction set it needed, then went back in time to kick the P4's ass just for sh!ts and giggles, then when it came back to the future it realized that with all its extra site-seeing (what kind of self-respecting Chuck Norris CPU wouldn't take the time to go back in time to see the original release of the K7 Athlon?) that it missed its own launch date by a few months. (but it is so awesome that it doesn't even care, it will kick ass all the same whenever we are graced with its presence, yeah, its simply that awesome...Chuck Norris awesome!)

Dude, awesome post, gonna use the 1st part for my sig. I would use the whole thing, but its too long

 

[Arzachel]

Considering the resources Intel has plowed into developing not only Sandy Bridge's architecture but also the 32nm process tech that enables it's clockspeeds and power-consumption...the only thing that we should expect to be able to beat Sandy Bridge is Ivy Bridge.

Miracles can happen, but Sandy Bridge is no Pentium 4 Netburst step-back situation. Miracle denied IMO.

Unless AMD has managed to pull a Netburst, I'll have to disagree. Correct me if I'm wrong, but wouldn't shrinking Thuban with slight tweaks net something close to/on par with SB performance? If AMD knows BD is going to be a lemon, then why pour all the cash into it?

 

[sangyup81]

Unless AMD has managed to pull a Netburst, I'll have to disagree. Correct me if I'm wrong, but wouldn't shrinking Thuban with slight tweaks net something close to/on par with SB performance? If AMD knows BD is going to be a lemon, then why pour all the cash into it?

Because they're gambling that the GPU can start doing some of the tasks that CPUs aren't good at such as things requiring parallelism like browser embedded graphics that up until a couple years ago used CPU power. Computing would have to become more graphical for such an architecture to have any advantage.

 

[Idontcare]

Unless AMD has managed to pull a Netburst, I'll have to disagree. Correct me if I'm wrong, but wouldn't shrinking Thuban with slight tweaks net something close to/on par with SB performance? If AMD knows BD is going to be a lemon, then why pour all the cash into it?

If that was all it took then they why didn't they do that with Phenom or Phenom II versus bringing to market the lackluster products they brought?

If all that thuban needs to be competitive with SB is "slight tweaks" then I suspect Llano would have been more of a tour de force.

If AMD knows BD is going to be a lemon, then why pour all the cash into it?

This is an obvious fallacy, right?

Companies pour cash into their future not knowing if it will be a lemon or a halo product. That's how we end up with products like Phenom and Prescott P4 in the first place.

Nobody intentionally sets about creating uncompetitive products, but no one is assured of creating a halo product simply because "their time is due" or "they have more heart in it".

 

[gramboh]

Unless AMD has managed to pull a Netburst, I'll have to disagree. Correct me if I'm wrong, but wouldn't shrinking Thuban with slight tweaks net something close to/on par with SB performance? If AMD knows BD is going to be a lemon, then why pour all the cash into it?

This is called risk, it's common to all businesses .

 

[bridito]

Got my reply on:

http://seekingalpha.com/article/276697-amd-s-fortunes-rise-with-llano-but-risk-remains

and it seems is was a DUH moment:

"Apologies, a correction request was submitted to the SA team making it clear the launch date for the FX flagship line of chips will be in the August - September time-frame while the channel bulk looks to ramp into beginning of 2012. Benchmarks and overclocking attempts have already hit the web, with relatively impressive results. Thank you very much for catching this."

"relatively impressive..." yeah, as I said... DUH!

(X6 1055 < 2500K < 2600K < SB-E Quad < SB-E Hexa < Cray < Skynet < BD < God): Yeah they said the same thing right before the delayed release of Phenom

IF and it's a big IF BD truly does underperform to the point of not being able to keep up overall with 2600K let alone SB-E do you think that the wild claims to AMD high end greatness and pwnrship over Intel will finally subside? Or will it just shift to Phenom... er... BD... er... TRINITY will rule!

It's saying with BD Opterons you won't have to be a giant customer and work directly with AMD to set your CPUs maximum TDP at something lower than the max rating from the factory. I'm not big into datacenter type operations but it seems reasonable that each facility and perhaps certain areas of the facility have a maximum amount of power they can deliver. I've read that the obsession with keeping everything as close to 16C-18C ambient has gone away for the most part and so power delivery and UPS capacity has become the primary concern in the dense computing world.

Edit: Oh, and that once they set their max TDP they can self experiment to find the frequencies they are comfortable with operating within the new TDP envelope.

OK, that makes more sense. Thanks!

I would read this blog article by JF. It explains it better than the eweek article.

http://blogs.amd.com/work/2011/06/28/tdp/

Yeah, thanks. I thought I was missing something but JF-AMD stated it succintly as "if your workload does not exceed the new modulated power limit, you can still get top speed because you aren&#8217;t locking out the top P-state just to reach a power level."

Dude, haven't you been paying attention lately?

Bulldozer is the Chuck Norris of CPU's.

It is so awesome that it designed itself, traveled to the future to determine what instruction set it needed, then went back in time to kick the P4's ass just for sh!ts and giggles, then when it came back to the future it realized that with all its extra site-seeing (what kind of self-respecting Chuck Norris CPU wouldn't take the time to go back in time to see the original release of the K7 Athlon?) that it missed its own launch date by a few months. (but it is so awesome that it doesn't even care, it will kick ass all the same whenever we are graced with its presence, yeah, its simply that awesome...Chuck Norris awesome!)

IDC is Chuck Norris Awesome. Word!

 

[Schmide]

Bulldozer is the Chuck Norris of CPU's.

...Chuck Norris is a Birther and Bulldozer has trouble being born???

 

[Arzachel]

If that was all it took then they why didn't they do that with Phenom or Phenom II versus bringing to market the lackluster products they brought?

If all that thuban needs to be competitive with SB is "slight tweaks" then I suspect Llano would have been more of a tour de force.

Llano has better IPC than Thuban at the same transitor count. It also has no L3 cache and has to share bandwidth with the on-die GPU.

This is an obvious fallacy, right?

Companies pour cash into their future not knowing if it will be a lemon or a halo product. That's how we end up with products like Phenom and Prescott P4 in the first place.

Nobody intentionally sets about creating uncompetitive products, but no one is assured of creating a halo product simply because "their time is due" or "they have more heart in it".

Thats why I said "Unless AMD has managed to pull a netburst".

 

[BLaber]

Strong troll

Dont think so , unless u can provide evidence to prove him wrong

 

[Khato]

Thats why I said "Unless AMD has managed to pull a netburst".

Who knows, they very well might. It is the first mainstream CPU since netburst to have the integer core clocked separately from the rest of the pipeline after all. Though netburst got its integer core up to 7.46GHz on the highest stock frequency - good thing Intel marketing didn't decide to report integer core frequency as the operating clock frequency like AMD is apparently intending to do.

 

[Concillian]

This thread is pretty funny with some people holding single thread performance as the yardstick and some people holding fully multithreaded as the yardstick. Of course the majority of the posts don't mention single or multithreaded performance and are drawing conclusions...

Umm, single threaded performance, unless there is a miracle, BD will not beat SB.

Multithreaded performance, however, is all about priceerformance and powererformance. Can't tell **** before release.

Enthusiast multithreaded decisions, in addition to priceerformance and power usageerformance are also about price: overclocked performance and power usage: overclocked performance. Can tell even less **** about that before release.

I think the 6 core Thuban vs. 2600k benchmarks bode well for 6 core BD vs. SB... I mean shrinking process, adding transistors, it would be really difficult to not gain 10-15&#37; perfomance. However, without pricing information you can make no conclusions that matter.

More food for thought is availability. Llano was in the press a couple weeks ago and you can't buy actual systems yet, let alone components. Is BD going to be any different? I'm not chomping at th bit to get anything, but release date is one thing. Being able to walk into Microcenter and buy something is likely to be significantly later than launch date.

 

[AtenRa]

Different micro architectures, different goals to reach, is not difficult to understand why either SB or BD will not rule over the other. One will have better single thread performance due to higher IPC and the other will have more cores and perform better in multithreaded applications.

Well, there will be only one processor to rule them all and that will be the 6-core SB-E but at $999 it will be out of reach for the 99,9999% of users.

 

[AtenRa]

ahh look at that, again the BD is an ES

AMD Bulldozer ES vs Intel Core i7-990X SLI results

 

[996GT2]

ahh look at that, again the BD is an ES

AMD Bulldozer ES vs Intel Core i7-990X SLI results

At 2560x1600 with 8x AA/16X AF, most of the work is being done by the GPUs so you can't really draw many conclusions from that...

 

[AtenRa]

I know, i just posted the link

 

[Abwx]

At 2560x1600 with 8x AA/16X AF, most of the work is being done by the GPUs so you can't really draw any conclusions from that...

Even with 4 way SLI ?...

An then, if only a few cores are at work, it s just more amazing
since BD make use of a single module for 2T and 2 modules for 3 or 4T
while a 990X make use of a full core for each thread in such case...

 

[sm625]

It makes me wonder... if the L2 cache really is disabled, yet it performs on par with an i7-990, that is very very good news for AMD. It makes me wonder if they did not disable it purposely, just to hide its awesomeness from intel.

 

[Arzachel]

It makes me wonder... if the L2 cache really is disabled, yet it performs on par with an i7-990, that is very very good news for AMD. It makes me wonder if they did not disable it purposely, just to hide its awesomeness from intel.

With OBR's track record, there is no reason to trust those benches, atleast on the BD side.

 

[996GT2]

It makes me wonder... if the L2 cache really is disabled, yet it performs on par with an i7-990, that is very very good news for AMD. It makes me wonder if they did not disable it purposely, just to hide its awesomeness from intel.

 

[OCGuy]

It makes me wonder... if the L2 cache really is disabled, yet it performs on par with an i7-990, that is very very good news for AMD. It makes me wonder if they did not disable it purposely, just to hide its awesomeness from intel.

Haha. I think some of you think waaaaay to much into super-secret tactics.

Odds are that Intel has a fully working BD ES.