It took awhile for AMD to build a large performance lead over the Pentium 4. At launch the Athlon 64 didn't blow the Pentium 4 out of the water, with Core 2 Duo the difference is that Intel has a considerable lead right from the get go.
Well the actuality was that the Athlon XP and the Northwood Pentium 4's were trading blows during the 400FSB/533FSB stages, with each architecture having it strengths, AMD was priced much cheaper during this time though, since AMD wasn't well known and had a lack of confidence.
When we reached the 800FSB Northwood they took the lead, a Pentium 4 2.4C equaled a Athlon XP 2800+ in performance, with the 2.8C equaling the XP 3200+, the 3.0C and 3.2C were basically untouchable, and then AMD released the Athlon 64's in September and that equalized things again, each architecture had it strengths, and slowly from that point forward Intel had issues so they slowly fell behind, Intel was only able to extract 400MHZ more from Prescott, while AMD was able to extract 600MHZ from Athlon 64. So it slowly turned more and more to AMD's favor. Once we shifted to the X2, where AMD dropped only 200MHZ and Intel had to drop 600MHZ, Intel fell alot more behind and that was the time when AMD started dominating on performance, but unlike Core 2 it wasn't a consistent domination more like really strong on some suits, mildly better in others.
If I'm not mistaken, that's a review for Athlon X2. Were you around during the days of Clawhammer?
The only P4 in that article is a single core Prescott at 3.2 GHz and it's getting beaten by Pentium Ds and X2s. What does that supposed to demonstrate? Dual core is faster?
Yellowbeard
Golden Member
- Sep 9, 2003
- 1,542
- 2
- 0
Intel, New transistor materials and die shrink:
http://www.msnbc.msn.com/id/16839253/
From the article:
Intel said new materials help provide a 20 percent boost in transistor performance. IBM did not release specifics of its project.
?This gives the entire chip industry a new life in terms of Moore?s Law, in all three of the big metrics ? performance, power consumption and transistor density,? said David Lammers, director of WeSRCH.com, a social networking Web site for semiconductor enthusiasts and part of VLSI Research Inc. ?It opens the door to some pretty rapid improvements.?
Intel appears the farthest along in bringing a product based on the technology to market.
AMD is tied in with the IBM crowd on this one. However, it appears that Intel is farther along. This can't be good news for AMD. I don't see the "crown" changing hands any time soon.
http://www.msnbc.msn.com/id/16839253/
From the article:
Intel said new materials help provide a 20 percent boost in transistor performance. IBM did not release specifics of its project.
?This gives the entire chip industry a new life in terms of Moore?s Law, in all three of the big metrics ? performance, power consumption and transistor density,? said David Lammers, director of WeSRCH.com, a social networking Web site for semiconductor enthusiasts and part of VLSI Research Inc. ?It opens the door to some pretty rapid improvements.?
Intel appears the farthest along in bringing a product based on the technology to market.
AMD is tied in with the IBM crowd on this one. However, it appears that Intel is farther along. This can't be good news for AMD. I don't see the "crown" changing hands any time soon.
Will K8L be able to match the performance of existing Conroe chips? I'd be very surprised if it didn't. However, Conroe has a lot of headroom for clock speed increases. They're regularly clocked past 3.5GHz without even breaking a sweat. If Intel wanted to make a high-performance (high-price) part with a much higher offficial clock speed, it quite easily could. Whether K8L would be able to perform on a level with that is harder to say. I hope so, but I don't know.
Once Penryn comes along (with the combination of 45nm and high-k dielectric, etc.) I suspect things will swing back in Intel's favour. AMD won't be making the transition to 45nm any time soon. And by the time it does, it will have Nehalem to deal with.
Once Penryn comes along (with the combination of 45nm and high-k dielectric, etc.) I suspect things will swing back in Intel's favour. AMD won't be making the transition to 45nm any time soon. And by the time it does, it will have Nehalem to deal with.
Yellowbeard
Golden Member
- Sep 9, 2003
- 1,542
- 2
- 0
Seeing as how AMD has only recently gotten 65nm to market I don't see 45nm for them anytime soon. My impression is that Intel has put themselves into position to "1-UP" AMD for quite some time to come. They are not "showing their hand" just yet. I suspect that for everything AMD releases for the next 2 years+, Intel will trump it.
It's like Admiral Yamamoto said after Pearl Harbor about awakening a giant (with Intel being the giant) and he will be filled with a terrible wrath.
Another major problem was that AMD revealed too much information too early. Word about K8L already got out before anyone has even heard of Conroe. At the time AMD still had the crown and people expected great things from K8's successor. Then all of a sudden Intel released that mysterious E6700 w/ Bad Axe 2 benchmark in spring that dominated the FX-60 (which was a god-like chip at the time). After that people were banking on K8L to simply overcome the performance deficit.
StopSign, I think the solution is simple just clarify what you really mean.
The performance lead Athlon 64 had on the Pentium 4 HT was nowhere near the kind of lead the Core 2 Duo (Conroe) has on the Athlon 64x2.
Am I right? Or do you mean something else?
Originally posted by: SparkyJJO
I don't know but we'll find out.
What I find interesting is how ever since C2D it seems that the prediction is AMD has no chance to keep up now. Why not? AMD did it once, and pushed intel to #2 performance-wise for 3 years. So intel took the crown again (took them long enough to ditch that P4!) and people act like AMD is a goner now. Hasn't even been a year with intel on top yet.
People were disappointed with AM2 in comparison with C2D but AMD never said it was going to be that much better performing than s939. It was just a step towards something bigger (K8L). So far I haven't seen AMD release anything hyped up to be something it wasn't, they didn't hype up AM2 or the new 65nm chip. I haven't seen AMD fail to live up to what they said yet at this point.
I think that while Intel obviously hates AMD with a passion they still don't want AMD to totally go away. If they forced AMD to go under (not likely its gonna happen, just saying IF) then intel would be in trouble for monopolistic practices. I'm sure that if it wasn't for that intel would have pulled some stupid stunt to force AMD out and then charge us that $500 for a P2
The reason that some people think AMD has no chance is because Athlon 64 success largely came from that fact that Intel made a misprediction with where to drive their architecture allowing AMD to take the lead over time. The fact that the K8 architecture was designed well also helped.
Now that Intel has seen the error of it's ways, it is not likely Intel will mispredict on the architecture front again. With Intel focusing on developing good products from a engineering standpoint instead of a marketing standpoint, Intel is pretty much a very tough opponent to beat.
It is actually expected that Intel stay in the lead considering their sheer manpower and resources available as their disposal.
Though there is some chance that Intel might get complacent if AMD isn't tough competition, but that isn't likely to happen just yet.
Also if you consider overall performance Athlon 64's didn't garner the lead till the X2's arrived, so they had the overall lead for a little over a year as the Pentium 4's with HyperThreading still had tasks they excelled at over the Athlon 64's.
TRENDING THREADS
-
News NVIDIA and Intel to Develop AI Infrastructure and Personal Computing Products- Started by poke01
- Replies: 250
-
Discussion Zen 5 Speculation (EPYC Turin and Strix Point/Granite Ridge - Ryzen 9000)- Started by DisEnchantment
- Replies: 25K
-
Discussion Intel Meteor, Arrow, Lunar & Panther Lakes + WCL Discussion Threads
- Started by Tigerick
- Replies: 22K
-
Discussion Intel current and future Lakes & Rapids thread- Started by TheF34RChannel
- Replies: 23K
Facebook
Twitter