K10 demo video
2.0GHZ K10 30% faster than 2.33GHZ Clovertown (78/60).
The 2GHZ K10 is faster enough to frag a 3GHZ Intel quad.
But performance is not the only story, K10 has so many advanced features, it will take Intel years to even understand them.
Someone says that Intel engineers and scientists lack creativity.
Indeed, Core 2 looks so silly when compared to the K10. Intel dudes get a C- on CPU design from their own CTO. Who was that Israeli dude bragging about 40% lead over K8? I told you they were just patching up Bob Colwell's P6.
posted by Sharikou, Ph. D. @ 9/02/2007 10:57:00 AM
27 Comments:
Sharikou you useless tool. This is an old video that you already regurgitated on this site a couple of months ago. And by the way the only 'facts' in this video are the assurance of some marketing bimbo that can barely pronounce the syllables she was given to read out. You can't see a damn thing on the screens of any value. I'm sure this makes you feel better inside your own head but I've got some bad news:
An official SPEC result is not from some AMD infoslut, it must be validated via the SPEC organization. And guess what else? AMD ITSELF IS NOT RELEASING ANY SPEC INFORMATION UNTIL AT LEAST SEPTEMBER 10!! Therefore, according to AMD (you know, that company you blindly worship like a bunch of mind-numbed zombies) this video is nothing but a pile of bullshit.
Even AMD can't coordinate it's own propaganda, it's no wonder Sharikou sounds more like a drooling retard with every post.
The video isn't BS. It's probably a fairly accurate demonstration of K10 performance in Spec_FP. But that's not saying much. Spec_FP tests are mainly a memory bandwidth test. It's sensitive to sheer bandwidth and also the latency. We know that AMD will easily win these tests because of an on-die memory controller.
If you run Spec_FP on a 4x4 system and a Core 2 Quad system you'll see the 4x4 system easily win. But in real workloads the C2Q system will easily defeat the 4x4 system.
I belive we'll see the same thing in most workloads with Clovertown vs. Barcelona. We'll see the real results from sites like Anandtech on September 10. (that is, unless Sharikou dismisses Anandtech as a paid Intel pumper again!)
To pezal, obviosuly Barcelona will be faster than K8 in multithreaded applications because it's quad core vs. dual core. But in single threaded applications you're looking at 3.2Ghz K8 vs. 2Ghz K10. That's why AMD isn't launching K10 for desktops in any real hurry. They need faster clockspeeds as many desktop applications are still single threaded. In servers the vast majority of workloads will be mutli-threaded, so a slower clockspeed is a non-issue. Quad K10 will be clearly faster than dual K8 in server workloads.
You can't even quote your FUD right.
They are claiming a 30% Performance PER WATT advantage, not a 30% performance advantage.
Fail1: Used fud source
Fail2: Misquoted fud source
Fail3: No independent benchmarks yet
So if AMD's product is so superior then why aren't they pumping it into the hands of reviewers for independent, non-green powerpoint benchmarks?
Kind of scary, huh?
NDA NDA NDA NDA NDA NDA NDA NDA
Sharikou,
You are one of the most brilliant technical minds in the universe. Why you would subject to posting your wisdom on this blog for free is beyond me.
Please accept our invitation to join our family of universally gifted savants
Link
Phenom 3ghz not coming close to 30K in 3Dmark06: http://www.fudzilla.com/index.php?option=com_content&task=view&id=2808&Itemid=35
Sharikou keeps making stupid claims that "Intel said Core 2 was 40% faster than K8". What Intel did state was that Core 2 was faster than Pentium D by 40% and used 40% less power. They succeeded on both of those claims.
It's only FUD(zilla) to a die hard Inteler ;)
The emperor wears no clothes!
Follow the money!!!
Last fall, after Putin spoke about the need for the country to achieve scientific and technological superiority, a Veremeenko company agreed to buy the equipment at an Advanced Micro Devices (nyse: AMD - news - people ) microchip factory in Germany and plans to move it to Russia. The transplanted factory should begin operations in 2009.
only_amd: I'm not sure why I'm even dignifying your trollish stupidity with a comment, but I've got 3 minutes free so why not.
AMD sold off obsolete 130 nm fab equipment to the Ruskies because:
1. It cannot make a profit on any product at that feature size anymore. (Bear in mind that 130 nm is by no means obsolete for a very wide range of embedded IC's used in the real world every day, but for high-end CPUs it is obsolete at this point).
Interestingly, this means that other companies are more efficient than AMD in production... otherwise it would not have been economically wise for AMD to sell the equipment but to instead continue to make products with it and make further profits.
2. AMD desparately needs $$$ and selling equipment is a good way to get that $$$.
Hey Sharikou: Since you aren't that bright, and are also pretty lazy on a good day, let me do your propagandizing for you. You can use this line in about a week when we finally get real K10 numbers and they aren't that impressive.
This is in Today's Fudzilla and bear in mind that even the generally pro-AMD Fudzilla guys find this line to be amusing:
Sources close to AMD claim that its server customers actually want 2.0 GHz parts more than they want the 3.0 GHz ones.
Well they don’t have any other choice than to claim that and we know that AMD would love to have 3.0 GHz parts soon.
That's right Sharikou, next week when the K10 comes out and it sucks, you can claim that nobody even wants a fast chip from AMD which is why they never made one. Then, at some point in the indeterminate future AMD finally manages to get the chips to 3Ghz where they should have been 6 months ago, you can claim that overnight some miracle occurred and all of the sudden the customers need the fast chips! All praise to the AMD Gods, rip your brains out an worship Hector blindly!
What's sad is not just that you are an idiot, but that you are a predictable idiot.
Someone says that Intel engineers and scientists lack creativity.
By the way.. that link does not even go to a fudzilla article, it goes to a dead page.'
I say that Sharikou was in with Michael Vick in his dogfighting ring! The only difference between your statement and mine is that mine might actually be true.
HA HA HA HA HA
Very well written article. Right on the money. Must read.
http://hubpages.com/hub/How_AMDs_Failures_Are_Triggering_An_Intel_Monopoly
@chucky
i wont even dignify a comment on your latest comment & i have lots of time.
This comment has been removed by the author.
This comment has been removed by the author.
That's right Sharikou, next week when the K10 comes out and it sucks, you can claim that nobody even wants a fast chip from AMD which is why they never made one. Then, at some point in the indeterminate future AMD finally manages to get the chips to 3Ghz where they should have been 6 months ago, you can claim that overnight some miracle occurred and all of the sudden the customers need the fast chips! All praise to the AMD Gods, rip your brains out an worship Hector blindly!
This is hilarious! I almost had Pepsi coming out my nose when I read that!
Hail Hector! AMD only builds what customers want. No one wanted a high end video card to compete with the 8800 Ultra. Not a single person. No one wants a 3Ghz Barcelona CPU,
No one wanted a high end video card to compete with the 8800 Ultra. Not a single person. No one wants a 3Ghz Barcelona CPU,
No one is exaggerated but very, very few that’s for sure.
Update:
Gary Key, AnandTech:
Throughout the entire prototype and pre-production (as stated in my last message) process, certain features on the CPU, in the BIOS, or on the chipsets have been turned off/on, latencies have changed, etc, etc. This is a normal part of the engineering process as the design is fleshed out and finalized. It does not represent final silicon capabilities and performance.
As I said earlier, I used a poor example as it was not meant to be taken literally spec for spec when comparing engines and CPUs. Regardless of the example, the point was that the platform performance improved significantly as the core speeds improved and this included performance per watt among other indicators. There is a myriad of reasons as to why this occured but considering the early silicon, BIOS, and chipset designs, we could only speculate as to why and I tried to present a few reasons that we honed in on.
If you compare a B00 chip from May to a B02 today, there is a significant difference in performance in all areas (26 seconds in SuperPI 1m for one) and my comments represent observations of what has occurred over this time period. We have final silicon now and results will be posted in the near future. My observations today are different than they were two weeks ago and as the platform matures they will change again.
Once we see the HT 3.0 capable chipsets and Phenom cores mature then we will have an even better indication of the performance of this core design in the consumer market but for now the initial release is Barcelona in the enterprise market.
39s (B0) vs. 26s (B2)
or
39s (B0) vs. 39-26 = 13s (B2) ???
Cheers
intel sucks!!!
go amd!!!!!!!!
ah and I thought terry had an iq over 60... Guess it wasn't meant to be.
Perhaps that is why he couldn't get his former computer to work properly.
This comment has been removed by the author.
This comment has been removed by the author.
intel is still trying to get out of semiconductor cpu business with solar cell buy outs.
Yep. We know that Intel is so unsuccessful at making CPUs. $26 share price and $150bn market cap, $5bn in profit each year.
Compared to AMD's godly $7bn market cap, $13 share price and losing over $1.2bn already this year.
Tigerton results in: http://h71028.www7.hp.com/ERC/downloads/4AA1-4037ENW.pdf
AMD is finished. BK by Q2'08.
"The video isn't BS. It's probably a fairly accurate demonstration of K10 performance in Spec_FP."
The video is not BS but what you said after above are. SPECfp are real workloads for real problems that people need to solve. So what if they depend on the memory subsystem? That only mean Core 2's memory system is too ancient.
The problems in SPECfp are much more useful than SuperPi and the SSE4-enhanced games.
intelers..talk whatever u wanna say
coz i build and worked with pc based on my experience
i've been using pc from both proc and knows the difference between them
many of you just start assembling pc since core 2 arrive and feel complacent of what you have
Post a Comment
<< Home