The Zambezi CPU Performance Estimate... - Page 25

That graph isn't even possible.

A Phenom II x6 @ 4.2ish gets 22k in that test.

You guys really believe the 4 core bulldozer chips is going to be 50% faster with 50% less cores @ stock?

lol.....

Thanks for clearing that up, but actually, this is what you said, which is exactly what I posted:



So, how is there any discrepancy in my post in reference to the turkish slide, and what JF-AMD wrote?



Maybe I have Mad Photoshop skills, but for those interested, it is in this thread, Page 3, 9th post, at the time of this writing, that post has not been edited, and it has even been quoted by others:
http://www.tomshardware.com/forum/pa...83_28_100.html

If anyone can find what is being said now vs what was said in that POST, label me a troll with good reason. I merely posted what WAS said. Here's one such post with the QUOTE in place:



I'm not going to bother to reply to the rest of the posts, because clearly it has gone way over your heads, and all you will do is find anything to criticize and label someone as a troll.

I made my decisions to choose Nvidia perfectly clear, funny how no one has replied to this post:
http://www.overclock.net/amd-cpus/93...l#post12431154

It's not my fault Adobe chose to build Premiere with CUDA's architecture, to optimize its use with the Mercury Playback Engine, my PRIMARY use for my rig is video editing WITH Adobe Premiere, NOT gaming, so yea, this type of stuff tends to matter to me.

In case you all missed it, here it is again, but perhaps I made this up too, right? It is straight from the article I linked:
http://www.brightsideofnews.com/news...uda-only!.aspx

I'll say this one last time, I sure hope that BD spanks Intel's offering, that means lower prices for all of us, it will force Intel to innovate, and if BD is THAT good, I will gladly upgrade to it, and or build a 2nd rig based off BD. Competition is GOOD, we all benefit from it.

As of this moment what we know about BD's actual performance is Zip, Zilch, Nada, until something reliable gets released by AMD themselves, or something with AMD's confirmation, without leaving any room for speculation as seen ITT.
Edited by 2010rig - 2/18/11 at 6:30pm

Ok, ignore anandtech then. Now explain the dozens of other reviews that showed the exact same results. As I already said complaining about a site being biased is such a cop out it's not even funny. I can guarantee if anandtech showed bulldozer beating SB you would completely change your tune but because it doesn't fit into your current preconceptions about performance you call it biased. Just like for years AMD people would complain about cinebench being biased. Than the 1090t came out and beat the i7's and suddenly it was a totally legit bench, then sandybridge came out and its biased again. It's so ridiculous and you don't even realize it.
Edited by scyy - 2/18/11 at 3:24pm

Sutor, ne ultra crepidam

Eh... it's 32NM
And a brand new architecture with brand new instruction set support such as AVX
Nothing's impossible with the benefits

Please show me where it says that is a four core bulldozer? Saying that seems like another attempt to over estimate the performance speculations. As far as we know from official sources the first bulldozer cpu is going to be an 8 core, then a 6 core and 4 core. Im not saying that those benchmarks are for an 8 or 4 or 6 core im just saying we have no positive confirmation but given the chronological release order it would be more sensible to assume (should we want to make an unfounded assumption about a possibly fake benchmark) it would be the first released 8 core model.

I think we all need to take a step back. Im not an amd or nvidia or intel fan. I simply buy whatever hardware shows the best price/performance ratio based on actual real world benchmarks. Do I want AMD to do well with bulldozer? Of course, better products mean better competition and lower prices for the end user. In about two weeks time we'l start getting some real benchmarks popping up and we'l all look back on this and laugh at how much we were freaking out over things we knew nothing about but were religiously and in alot of posts offensively defending regardless.

So do your self a favour, sit back, relax and wait till at least after cebet around the 5th of March. Then once we have those real benchmark we can have a real factual discussion free from bias and enjoyably productive.

Wroooooong, you misunderstood
Intel was "invited" to court
1- not because : intel did not optimized their compiler for AMD cpus (thats not their business) ...

2-BUT BECAUSE : intel compiler takes the worst code path if AMD (or other non Intel) cpu is detected
==> to maximize harm / performance penalty on these processors..
Shady as sh_t, ugly Intel ..

... and of course ,also because of nasty coercing and bribing IT industry (OEMs)..

----------------

You misunderstood again, AMD does not use intel libs - but SW vendors do..
John will tell - AMD supports many opensource and microsoft compilers, AMD has not own compiler.

But at the end, software producer picks the tools (compiler)..
And that piece of software shouldn´t generate buggy code ..

-------------------

About nvidia part : i dont care if nvidia goes bankrupt or not - its not my interest
1 my idea was - with proper SW , ati HW may outperform CUDA..
2 opensource vs proprietary

It has already been tested by changing cpuid to intel from amd, at worst its 20%(in one or two things) On average for benchs that are effected its 5-10% and on a majority of benchs it made no difference. Yes its shady, I completely agree. But it isn't what is causing intel to lead amd right now. It causes the gap to widen in a couple benchs but it is hardly the main factor in intels high end desktop lead.

AVX has nothing to do with 3D Mark Vantage.