First bulldozer benches from AMD - surprising results (beats 980x)

[blackened23]

..Anyway, one of Dirt's development partner is AMD.

Uhh, what? Dirt 3 bears the "nvidia the way its meant to be played" monkier and supports nvidia 3d vision. I think the game is actually more optimized for nvidia hardware, I could be wrong. I don't think AMD did much of anything with it.

 

[Ferzerp]

Uhh, what? Dirt 3 bears the "nvidia the way its meant to be played" monkier and supports nvidia 3d vision. I think the game is actually more optimized for nvidia hardware, I could be wrong. I don't think AMD did much of anything with it.

Do you not see it as telling that the first benchmark they allow is a video card benchmark and not a processor benchmark?

 

[brybir]

It speaks to platform capability, which will be limited by the slowest components.

AMD is showing they've eliminated the platform limitation that was intrinsic to Phenom-based systems with the new bulldozer platform.

That's a good thing.

I think IDC is spot on here. We will not really know the "overall" picture of the CPUs abilities until release day when we get a wide range of benchmarks and game results. Until then, all we can say for sure is that in an equivalent set up, the Bulldozer CPU used in the demonstration relieved the bottleneck one would have gotten if using a Phenom II in the same situation.

Trying to jump in and analyze a few numbers on a few titles on systems where we hardly know any details about is not the right way to speculate if you are going to do it.

 

[Riek]

Whatever benchmark conditions and test data they used, it has to scale nicely with more cores/threads to show AMD FX 8-"cores" advantage. And that type of setup, would require all cores almost or fully loaded otherwise it will have similar fps or lower results (for the CPU with lesser IPC). Example of another borked result here (Core i7 980X loses to Core i5 2500K! )

Aaah yes scaling....

http://www.tomshardware.com/charts/...Transcode-Handbrake-MPEG-2-to-H.264,2421.html

i5 2c/4T 3.33GHz 270s

i7 990 6c/12T 3.33Ghz 113s

edit:
Thats a 200% core increase... for ... 60% thumbs up about scaling.

one should expect closer to 90 and not 20% higher. (which is accidently the scaling of 4-6cores)

 

[blackened23]

Do you not see it as telling that the first benchmark they allow is a video card benchmark and not a processor benchmark?

Like I said, we have more questions than answers. I was convinced that BD was going to be a dog but now i'm not so sure - i'm just going to be cautiously optimistic. I do believe that many of the early benchmarks were false-- and I think the rabid intel fanboys need to calm down for a second and stop proclaiming BD dead before we know for sure.

 

[Ferzerp]

Why? AMD seems to be demonstrating everything *except* the actual performance of their processor.

Staged overclocking. Great, but how much work can the thing actually do?

Video card benchmark. Great, but how many other processors will score the same exact score (within a range that is statistically insignificant) with those exact video cards?

 

[BlueBlazer]

Uhh, what? Dirt 3 bears the "nvidia the way its meant to be played" monkier and supports nvidia 3d vision. I think the game is actually more optimized for nvidia hardware, I could be wrong. I don't think AMD did much of anything with it.

Huh? Didn't you noticed AMD loves to showcase Dirt all the time, even the AMD Radeon logo is ever always present in its PR pages (such as this)?

 

[soccerballtux]

I'm pretty sure a Phenom 2 could pull off that FPS at that resolution too.

 

[Ferzerp]

That title really needs changed to something accurate. It isn't even a processor benchmark.


Let me guess, if they had done a file copy, and the results were slightly faster (not statistically significant) for their processor, you'd have used the same title?

 

[Zstream]

That title really needs changed to something accurate. It isn't even a processor benchmark.


Let me guess, if they had done a file copy, and the results were slightly faster (not statistically significant) for their processor, you'd have used the same title?

You guys need to calm down, I haven't come to this forum in a while because of a bunch of people getting all hot over a cpu. You have no insider information, you have no more information than anyone else. To try to put a negative or positive spin on things without having any knowledge is pathetic.

 

[Ferzerp]

You guys need to calm down, I haven't come to this forum in a while because of a bunch of people getting all hot over a cpu. You have no insider information, you have no more information than anyone else. To try to put a negative or positive spin on things without having any knowledge is pathetic.

Who isn't calm?

It's just a totally spurious title when the data is a single video card benchmark in a known GPU limited test case.

 

[Zstream]

Who isn't calm?

It's just a totally spurious title when the data is a single video card benchmark in a known GPU limited test case.

You posted four times with a bunch of useless babble. One time you made your point, the other times spent putting a negative spin on everything. Just calm down...

 

[BlueBlazer]

Aaah yes scaling....

http://www.tomshardware.com/charts/...Transcode-Handbrake-MPEG-2-to-H.264,2421.html

That one is based on time to complete, not on fps. I've also mentioned this earlier....

The other Handbrake results looks borked, IMHO (including the Toms Hardware one). :hmm:

 

[Ferzerp]

You posted four times with a bunch of useless babble. One time you made your point, the other times spent putting a negative spin on everything. Just calm down...

To be able to put a "spin" on things there has to actually be meaningful data. My point is there is absolutely no meaningful data available. This entire post is what you would call positive spin on something that gives no details, but when I point that out, in your eyes that is "negative spin".

Do we need to fill this post with links to to video card benchmarks showing extremely similar scores between processors when the benchmark is GPU limited? Or would that accuracy be "negative spin"?

 

[alexruiz]

just wait for the official release date reviews

Winner!
That is what I have done, just wait and see

 

[hooflung]

It seems these forums are riddled with conjecture these days.

 

[formulav8]

You Intel fannys just need to stay out of BD threads. I can't believe there are people here that does everything they can to show that BD is a failure. Its only a stinking cpu people, not your mother or anything. Intel doesn't even like you anyways.

 

[Riek]

That one is based on time to complete, not on fps. I've also mentioned this earlier....

Yes you are correct. You mentionned countless of times only Guru3D has correct results and everybody else flawed results. The fact you are comparing results which differ by factor 12 should ring a bell that they are not exchangable... like i already mentionned couple of times... this is closed for me now. Wether you accept that results differing by 1000% are not exchangeable or not is up to you.

 

[Abwx]

Or this could speak to a PCI-E Crossfire limitation somewhere, on the Intel platform. Perhaps they used a board with 16x/8x/8x on Intel, and used the two 8x slots, and on the AMD platform, they had two 16x/16x slots.

"If all you have is lemons - make lemonade!"

A 1366 plateform with tri mem channel and with only
second rate PCI-E..??...

Yet another fanboyz argumentation...

 

[notty22]

Dirt2 and Dirt3 were backed and promoted by AMD.
http://sites.amd.com/us/promo/processors/Pages/fx-processor.aspx
It's featured again in this promo video. Was shown at the Hocp event in eyefinity driven by BD etc

 

[BlueBlazer]

Winner!
That is what I have done, just wait and see

Just wished the release will be earlier (than expected/predicted) to lay all "conjectures" to rest. :thumbsup:

It seems these forums are riddled with conjecture these days.

That's the way start discussions, otherwise we all become boring robots/droids.

Yes you are correct. You mentionned countless of times only Guru3D has correct results and everybody else flawed results. The fact you are comparing results which differ by factor 12 should ring a bell that they are not exchangable... like i already mentionned couple of times... this is closed for me now. Wether you accept that results differing by 1000% are not exchangeable or not is up to you.

We have only those two (results) to go on, hopefully will see more soon. If only they also benchmarked Handbrake on that Core i7 980X system as well, then better information would be available. I wonder, why only against Core i5 and not against Core i7. :hmm:

 

[LOL_Wut_Axel]

Do you have something against AMD? Understand that all benchmarks floating around the web at the moment are probably early samples or falsified.

For me, these results leave more questions than answers. But I do know that a CPU getting 5 in cinebench probably *would not* get 83 fps in dirt 3 at 2560. But i'm eagerly awaiting official results

For me , i'm keeping an open mind. If bulldozer is a great product, that will be good for the community even if you stick with intel products.

The problem is that DiRT 3 is a completely multi-threaded game that favors AMD's architecture, hence why you see better results with their CPUs even if they're inferior. Look at the Phenom II X4 980 vs Core i5 2500(K) in the game and you'll see what I mean.

Not only does it favor AMD's inferior architecture, but it also takes advantage of six threads, hence why the Phenom II X6 and this do so well in it.

I'm just being realistic. DiRT 3 is not a good way to compare because it doesn't represent most games, which take advantage of two-four threads.

Even then, it's not a CPU benchmark. It's a CPU AND GPU benchmark, which skews the results. I personally want to see how they do in LAME single-threaded and MainConcept/x264 HD 2nd pass, 3dsMax, POV-Ray, Photoshop, etc.

Just no.

This. Just no. If you actually think this will match the i7-980X even in multi-threaded you need to go back and look at its price.

 

[Zstream]

The problem is that DiRT 3 is a completely multi-threaded game that favors AMD's architecture, hence why you see better results with their CPUs even if they're inferior. Look at the Phenom II X4 980 vs Core i5 2500(K) in the game and you'll see what I mean.

Not only does it favor AMD's inferior architecture, but it also takes advantage of six threads, hence why the Phenom II X6 and this do so well in it.

So AMD has an inferior architecture yet it performs better when an application is actually written for the future. So what you're really saying is that AMD is ahead of it's time and that poor programming results in favor of Intel CPU's?

 

[LOL_Wut_Axel]

Speaking of which:

DiRT 3 is an absolute mess when it comes to CPU scaling.

 

[Abwx]

So AMD has an inferior architecture yet it performs better when an application is actually written for the future. So what you're really saying is that AMD is ahead of it's time and that poor programming results in favor of Intel CPU's?

More accurately that generaly all softs and games are optimised
for intel uarchs with few or no special work done to optimize also
for AMD cpus...