Tuesday, March 07, 2006

INTEL's self-defeating prophecy

INTEL announced that their Woodcrest server CPU will be 80% faster than the Paxville DP 2.8GHZ. However, currently, the Paxville 2P has a SpecFp_rate score of 40.3, and Opteron 280 2P has a score of 74.4, the Opteron 280 is already 85% faster than Paxville DP. Furthermore, AMD just released Opteron 285 yesterday, with another performance boost of up to 14%. Actually, Opteron 890 is already out there, and AMD readied hounds to blood Intel's next gen hares.

INTEL's bogus cliams of performance using vaporware no one has seen will definitely cause a massive Osborne effect, people will wait for the new wonder chips for sure, so expect the sales of Paxville to halt. INTEL execs see that.

What INTEL is trying to do here is not to help itself, but to hurt AMD, it is a feeble attempt, just like its Skype deal. INTEL hope that people will stop buying AMD but wait for INTEL.

It won't happen. As we have seen from the case of Google, businesses depend on computing won't wait for INTEL even if INTEL CEO sits on their board. Diehard INTEL fans will wait for INTEL, so they will stop buying current INTEL junkies.

So the situation will be this: INTEL revenue will drop sharply, some going for AMD, which promises an upgrade path, some wait for INTEL, then when INTEL comes out with something 6 months later, AMD already launched their newer generation. AMD will always be two steps ahead. For instance, the dual core Tuion 64 X2 will be released in May 2006, several months ahead of Merom, which is struggling with heat problems. Before INTEL releases Woodcrest to match Opteron 285, AMD will have Rev F opterons for sale. Not to mention that Woodcrest is only good for low end 2-way computing.

27 Comments:

Anonymous Anonymous said...

Better read this:
"Spring IDF 2006 Conroe Preview: Intel Regains the Performance Crown"
http://www.anandtech.com/tradeshows/showdoc.aspx?i=2713
Conroe 2.66 is faster than overclocked Athlon FX60 in all the tests, e.g. in media encoding test Conroe is 30% faster. Athlon 2.8GHz, Conroe 2.66MHz.....
And remember it was possible without integrated memory controller.....

1:15 PM, March 07, 2006  
Anonymous Anonymous said...

Lets wait and see, Intel ran the comparison, until we get results from an unbiased source it is hard to take the results seriously.

1:31 PM, March 07, 2006  
Blogger Sharikou, Ph. D said...

INTEL is trying to stop people from buying AMD, just like their dirty Skype deal, which use CPUID instruction to block AMD. In these INTEL tests, the same dishonesty may be employed, if CPUID matches AMD, then slow down. Cheating on Benchmark was INTEL's trick back in BAPCo times. Read the AMD lawsuit, one of the charges was that INTEL rigged benchmarks.

1:38 PM, March 07, 2006  
Blogger netrama said...

Hmmm .. Looks like even more vapourvare at the latest Intel IDF..who is Intel trying to fool ....even folks in the thirdworld see through this now !!

1:48 PM, March 07, 2006  
Anonymous Anonymous said...

Sharikou behave like a man......
Now everyone can verify your 'technical' analysis on superior AMD technology versus 3-rd world Intel technology.
LOL.... AMD is 5 generations ahead, lol.....

1:53 PM, March 07, 2006  
Blogger Sharikou, Ph. D said...

I warned that INTEL will use their old dirty trick again, but this time, it will only hurt itself. INTEL is still five generations behind, the Conroe/Merom/Woodcrest Pentium 3 stuff is outdated before arrival.

2:01 PM, March 07, 2006  
Anonymous Anonymous said...

wow! if Conroe based on P3 technology is on average 20-30% faster than the fastest/latest Athlon FX overclocked to 2.8MHZ than AMD has a problem...serious problem. Better sell your AMD shares now, next month will be too late....

2:04 PM, March 07, 2006  
Anonymous Anonymous said...

Copied from web:

> This was just INTEL scam like the Skype scam.
CPUID, and run slow on AMD.
INTEL's old trick. <

It could well be. From the Anandtech article:

------
Both systems had a pair of Radeon X1900 XTs running in CrossFire and as far as we could tell, the drivers and the rest of the system setup was identical. They had a handful of benchmarks preloaded that we ran ourselves, the results of those benchmarks are on the following pages.
------

So Intel supplied and configured the systems, and to a perfunctory inspection they appeared identically-configured. But

1. Were they really configured identically?

2. Even if they were, did Intel refrain from adding a program to both systems that selectively slowed down the AMD system? Recall that Intel has been caught doing this with its compilers (e.g., http://www.swallowtail.org/naughty-intel.html ).

3. What was really in the boxes Intel provided?

4. *** Why does the AMD system's BIOS screen say "AMD Processor Model Unknown", and what does that mean for how the BIOS and OS configured the processor and system? ***

2:14 PM, March 07, 2006  
Anonymous Anonymous said...

"Intel is very excited about their new Core architecture, especially with Conroe on the desktop. It's not really news to anyone that Intel hasn't had the desktop performance crown for years now; their Pentium 4 and Pentium D processors run hotter and offer competitive or lower performance than their AMD competitors. With Conroe, Intel hopes to change all of that."

INTEL is asking people to buy AMD?

2:15 PM, March 07, 2006  
Anonymous Anonymous said...

Be serious. As author of the article in anandtech.com writes:
"As far as I could tell, there was nothing fishy going on with the benchmarks or the install. Both systems were clean and used the latest versions of all of the drivers (the ATI graphics driver was modified to recognize the Conroe CPU but that driver was loaded on both AMD and Intel systems).

Intel told us to expect an average performance advantage of around 20% across all benchmarks, some will obviously be higher and some will be lower. Honestly it doesn't make sense for Intel to rig anything here since we'll be able to test it ourselves in a handful of months. I won't say it's impossible as anything can happen, but I couldn't find anything suspicious about the setups. "
You must accept that the days where AMD has the fastest CPUs are counted. Intel will regain performance lead again. What's funny according to Sharikou inferrior technology (P3 based) is on average 20-30% faster than the fastest Athlon FX available (yet overclocked to 2.8MHZ)...LOL

2:21 PM, March 07, 2006  
Anonymous Anonymous said...

AnandTech.com can't be trusted since INTEL is doing a lot of ads there. See Why did AnandTech handicap the Opteron?.

2:29 PM, March 07, 2006  
Anonymous Anonymous said...

sure - by following your logic - you cannot trust Sharikou because he owns a lot of AMD shares......

2:43 PM, March 07, 2006  
Blogger Sharikou, Ph. D said...

My work is to analyse reliable and independent results, for once I did a test on Athlon 64 socket 754 which showed it to be 40-50% faster than Xeon 3.6GHZ EM64T, that's all, every Athlon 64 user can repeat the test.

INTEL has a history of cheating on benchmarks.

2:51 PM, March 07, 2006  
Anonymous Anonymous said...

Sharikou, you make me laugh. First read your 'reliable' and independent analysys http://sharikou.blogspot.com/2006/01/amds-current-generation-is-more.html and compare it with the results on the anandtech.com site.... you are funny. better sell your AMD shares if you didn't sell them already.

3:06 PM, March 07, 2006  
Anonymous Anonymous said...

If Intel was so confident that it's cpu was superior, why didn't they give the cpu(with their mobo) to a few benchmarking sites, like for example, Tom's hardware guide, to test against AMD's cpu's? It has been done before. I really don't trust Intel to build and configure the AMD system for optimum speed, as they most assuredly did to their own. And, as was said, they have cheated in the past, even when they weren't so desperate to prove that they were faster.

4:00 PM, March 07, 2006  
Blogger Sharikou, Ph. D said...

Looking at the BIOS screen captured by AnandTech, it says "Main Processor: AMD Processor Model Unknown". It's apparent INTEL rigged the motherboard to use the ancient BIOS that can't recognize the AMD CPU, our gullible Anand was duped by INTEL folks.

7:20 PM, March 07, 2006  
Anonymous Anonymous said...

I really hope Intel has come up on performance and less heat output for the sake of all these Intel fans who should not buy any Intel
cpu's (I would stick to the Northwood for now) until the release of these super chips,
meanwhile the rest of us in the real world will be working with real 64 bit cpus doing real work saving real power
watching our share price really fly.

3:34 AM, March 08, 2006  
Anonymous Anonymous said...

I will repeat once again - Conroe 2.66 GHz is on average 20-30% faster than fastest yet overclocked Athlon FX (2.8MHz).....
Preliminary tests of AM2 (e.g. tomshardware.com) prove that AMD does not have anything that can match new Intel offering....
Bye, bye AMD

5:30 AM, March 08, 2006  
Blogger DBA said...

Not sure if I can trust on those benchmark at this point. Assume those are accurate, the impact will be pretty much on the desktop areas. Those benchmarks does not much impact to the corporate server world (particularly in multi-core and nulti-CPU environment). Without the proper bus architecture, I don't think Xeon(or whatever from Intel) can real perform, not until I see for myself.

5:47 AM, March 08, 2006  
Anonymous Anonymous said...

with Conroe and Merom Intel will beat AMD easily. The server market is another issue - on dual core front Intel probably will be better than AMD too - Woodcrest should be good enough to beat Opetron - however these two CPUs will be very similar in terms of the performance. It was a fun to read what Hector says now:
http://www.tgdaily.com/2006/03/06/amd_ceo_capacity_could_be_traded/
He already knows that AMD has nothing against Conroe and Merom - so he will try to at least not to loose on the server front.....

7:02 AM, March 08, 2006  
Anonymous Anonymous said...

Hexus.net has benchmarks too! http://www.hexus.net/content/item.php?item=4843&page=1

Lets keep in mind that Anandtech and Hexus are both respected technology websites. The Athlon 64 FX (even overclocked to 2.8Ghz!) just got demolished! We musn't forget that this is AMD's fastest desktop CPU, OVERCLOCKED vs a 2.66Ghz Conroe. Wait until the Extreme Edition (higher clockspeeds, 1333mhz FSB, more cache) is benchmarked. With such a low TDP It will overclock quite well also.

Long live Intel! Screw this crappy blog! Seems that Intel won't be reporting massive layoffs next year after all, with huge profit losses etc. Dell will have no reason to think about AMD... grovelling to AMD for processors, begging them? Get over yourself lol. You yack on about AMD as if they're some sort of deity.

I almost forgot the news about AMD's upcoming Turion dual core (X2), it seems they'll top out at 2GHz. They're also set to be released in May... Intel has nice price cuts also in May, along with a new 2.33Ghz Core Duo processor. Owned. Again.

Long live Intel! (July is looking like a superb day to update my 3.4Ghz Northwood P4 system to a new Conroe PCI-E based system!)

7:46 AM, March 08, 2006  
Anonymous Anonymous said...

I just noticed something more:

"For instance, the dual core Tuion 64 X2 will be released in May 2006, several months ahead of Merom, which is struggling with heat problem"

More total FUD from you sir. The Turion X2 is designed to compete against the Intel Core Duo - which was launched some time ago, you can go buy a laptop with these dual core processors in them now. Not the Merom processor, which is Intel's next generation mobile part. There's no need for Merom so quickly, since the Core Duo already is the fastest notebook processor around, and they have a 2.33Ghz version and price cuts on the 2.16ghz and lower models in May... same time as the dual core Turion.

Just something to think about.

(Yes, I am going out of my way to make these posts as biased as-is possible. Still I can't come close to the blog owner! He must have a degree in FUD!)

8:05 AM, March 08, 2006  
Anonymous Anonymous said...

Don't underestimate AMD because:

1. HT 2.0 can offer up to 22.4Gb/s transfer. The current limit can be changed using DDR3 memory which is scheduled for 2007. HT 3.0 is scheduled also for next year but only for Opteron line - I assume 20% performance boost.

2. Cache can be extended also for A64 giving another performance boost - this is not a big technical problem but requires a bit larger die...which costs more.
Let's say 10% performance increase?

3. Clock and voltage improvements will be achieved by shinking to 65nm.
So I think 3.2GHz can be achieved.

Summaring 20% HT gains, 10% from cache and clock increase by 20% gives - 40-50% overall performance increase WITHOUT 2005 X2 logic core changes.

Just wait a moment - AMD X2 core was completed in January 2005? Nothing new from this date except clock increase?
I expect most of improvements in Semptember/October timeframe to take over "Intel Killer". Or just clock 3.0GHz/3.2 GHz at last...

AMD will be ready to produce 30 million chips in Chatered, another 40 in Germany in 6 months...

8:51 AM, March 08, 2006  
Anonymous Anonymous said...

"More total FUD from you sir. The Turion X2 is designed to compete against the Intel Core Duo - which was launched some time ago, you can go buy a laptop with these dual core processors in them now. Not the Merom processor, which is Intel's next generation mobile part. There's no need for Merom so quickly, since the Core Duo already is the fastest notebook processor around, and they have a 2.33Ghz version and price cuts on the 2.16ghz and lower models in May... same time as the dual core Turion."

Are you aware that Turion is 64 bit and CoreDuo is only 32bit? What happens when Vista comes out? Are we all buying this new tech so that we can run old WinXP or Vista in 32bit compatibility mode? Anyone that purchases a system today has to think of Vista as their future. That is why Merom is coming out so soon after CoreDuo(current iteration), it has 64bit capability at last.

That said, the author here is being unreasonably dismissive of Intel's new technology. Yes they are playing games to capture "mindshare", and they are comparing apples to oranges, but on the face of it, they have made a huge step forward in cpu design. They have seemingly followed amd's lead, and thanks to their superior process execution, can be expected to gain a small performance lead over amd 5 months from now. Of course, amd also has advances coming, but due to their capacity and resource limitation, they are not as flexible in being able to front an immediate response. But I do expect that amd's reworked core will probably retake a slim lead, but probably not until mid 2007. A lot depends on process technology, now that both AMD's and Intel's cpu designs are on the same page. Amd's interconnect advantages will keep them in the game, but if Intel improves theirs, which could happen, then Amd could get into trouble, running a full process generation behind. The future of cpu design once again seems very captivating, can't wait to see it unfold!

4:48 PM, March 08, 2006  
Anonymous Anonymous said...

"I almost forgot the news about AMD's upcoming Turion dual core (X2), it seems they'll top out at 2GHz. They're also set to be released in May... Intel has nice price cuts also in May, along with a new 2.33Ghz Core Duo processor. Owned. Again."

Hum... When Windows Vista is out, wouldn't Core Duo be owned? Or you are expecting Core Duo user to use the 3rd world version of Windows Vista that runs on 32bit?

6:38 PM, March 08, 2006  
Anonymous Anonymous said...

TO those who forgot how Microsoft works, they announce a date and deliver the product at least a year later. Vista is more than a year late already and chances are it will be delayed again.
For the guy who thinks Turion 64 means 64 bit processor, you are fooled by the naming of the processor. It is not a native 64-bit processor. And while we are on that subject, how many applications do you know that are 64-bit apps? By the time we get 64 bit apps that take advantage of the VISTA OS, it will be 3-5 years later. So Turion 64 is a marketing gimmic, nothing more..

11:31 PM, March 11, 2006  
Anonymous Anonymous said...

Guys,

Get off Intel's back.. Even the most anti-intel sites (ex the Inquirer and the Register) believe intel microprocessors will have a performance edge over the AMD offerings starting with Conroe..

11:55 PM, March 11, 2006  

Post a Comment

Links to this post:

Create a Link

<< Home