Sign in with
Sign up | Sign in
Your question

Detailed analysis of Core architecture

Tags:
  • CPUs
  • Core
Last response: in CPUs
Share
May 1, 2006 8:53:43 PM

Would anyone care to translate this for us non-engineers?
Or even better, put it into redneck English "so I kin unnerstand it."
Thanks! :D 

http://www.anandtech.com/cpuchipsets/showdoc.aspx?i=274...

More about : detailed analysis core architecture

May 1, 2006 10:57:35 PM

The Core processor is practically a revamped Pentium 3, with lots of good features added onto it. Of course, it isn't exactly a revamped P3, but it owes a alot of its design to the success of the P3. It has huge bandwidth capabilities and is a very flexible processor, much more so than the current AMD architecture (Which is very good... so it says something about the upcoming Core processor). Plus, the move away from hyperthreading is good, meaning less emphasis on threading applications in order to get more performance out of them, and less threading means less debugging for those lazy developers!
May 1, 2006 11:09:27 PM

Do you guys think this is it for AMD or will they be able to counter?
Related resources
May 1, 2006 11:22:45 PM

Quote:
Do you guys think this is it for AMD or will they be able to counter?



I believe we will pleasantly surprised by the 65nm AMDs.
May 1, 2006 11:38:44 PM

Quote:
Do you guys think this is it for AMD or will they be able to counter?



I believe we will pleasantly surprised by the 65nm AMDs.

Is there some major architecture change that is being made or is just shrinking the die?
May 1, 2006 11:44:42 PM

Well... think about it, whilst they are shrinking the die, it would be rather stupid not to make some improvements. Come on, by shrinking the die, they also get some extra headroom for the improvements, so by not adding extra features and optimising the architecture more would be seen as a very foolish move by AMD. Plus, AMD have still got the advantage of having the memory controller integrated, so with the with the new 65nm process, we should see some nice optimisations. All in all, AMD should still surprise us all, even Intel.
May 1, 2006 11:49:31 PM

Optimization does not mean new architecture and that was my question. We can certainly speculate all day but I thought maybe there was a more definitive answer by the way the post was made.
May 1, 2006 11:51:21 PM

Quote:
Well... think about it, whilst they are shrinking the die, it would be rather stupid not to make some improvements. Come on, by shrinking the die, they also get some extra headroom for the improvements, so by not adding extra features and optimising the architecture more would be seen as a very foolish move by AMD. Plus, AMD have still got the advantage of having the memory controller integrated, so with the with the new 65nm process, we should see some nice optimisations. All in all, AMD should still surprise us all, even Intel.



Aye :-D

We'll have to wait and see.
May 1, 2006 11:52:49 PM

Ok so it's all speculation, thanks!
May 1, 2006 11:54:23 PM

Indeed it is all specualtion, but that makes it fun. :twisted:

I agree with Bluefinger.
AMD will be a little down for a couple of months. Until the begining of Q1 07 but then they will get a die shrink.

Along with the die shrink it has been widely reported that a change in how AMD makes their transistors should yield something like ~15% faster performance. Added to that (what I expect to be) significant revisions in the on-die mem. controler and it should be about neck and neck between Intel and AMD.
May 2, 2006 12:01:42 AM

I personally think that AMD is going to take the back seat when Intel releases Conroe's Core architecture for the desktop. But AMD will eventually come back with something better than Core. Its like Nvidia and ATI.
May 2, 2006 12:13:47 AM

Quote:
I personally think that AMD is going to take the back seat when Intel releases Conroe's Core architecture for the desktop. But AMD will eventually come back with something better than Core. Its like Nvidia and ATI.


Many of us would be very surprised if this didn't happen. Like you said it's NVidia vs ATI type of situation. It's being very optimistic to think that AMD will just pull something out of thin air and be ready by Q1 '07. Processor design and manufacturing is very expensive and exhausting, after all a modern processor can have 150,000,000 - 300,000,000+ transitors.
May 2, 2006 12:30:45 AM

Quote:
Well... think about it, whilst they are shrinking the die, it would be rather stupid not to make some improvements. Come on, by shrinking the die, they also get some extra headroom for the improvements, so by not adding extra features and optimising the architecture more would be seen as a very foolish move by AMD. Plus, AMD have still got the advantage of having the memory controller integrated, so with the with the new 65nm process, we should see some nice optimisations. All in all, AMD should still surprise us all, even Intel.


Funny you say that I remeber the process shift for the K7.
May 2, 2006 1:49:28 AM

Quote:
Well... think about it, whilst they are shrinking the die, it would be rather stupid not to make some improvements. Come on, by shrinking the die, they also get some extra headroom for the improvements, so by not adding extra features and optimising the architecture more would be seen as a very foolish move by AMD. Plus, AMD have still got the advantage of having the memory controller integrated, so with the with the new 65nm process, we should see some nice optimisations. All in all, AMD should still surprise us all, even Intel.

no, the micro-arch improvements are not connected with the lithographic process.
no, the IMC is not adventage, it is disadventage for the DDR2, becouse it is not optimized for high latency. it is taking space on the die, and that space is used as L2 on the Core arch chips.
May 2, 2006 2:53:45 AM

Quote:
Do you guys think this is it for AMD or will they be able to counter?
I made a whole thread about that and it has over 700 posts and over 35000 hits. Apperantly people were interested and the general aura was that they will survive.
May 2, 2006 3:16:09 AM

So what kind of multi-tasking performance is this architechture going to have? It sounds like they're dismissing the whole issue.
May 2, 2006 3:29:56 AM

A dual core, short pipeline, 4MB L2, one-cycle to complete all SSE instructions, memory disambiguating, fully shared cache architecture is overlooking multitasking? Nah. There just haven't been many multitasking benchmarks released yet. I doub't they overlooked it, just be patient. 8)
May 2, 2006 7:00:01 AM

Quote:
Well... think about it, whilst they are shrinking the die, it would be rather stupid not to make some improvements. Come on, by shrinking the die, they also get some extra headroom for the improvements, so by not adding extra features and optimising the architecture more would be seen as a very foolish move by AMD. Plus, AMD have still got the advantage of having the memory controller integrated, so with the with the new 65nm process, we should see some nice optimisations. All in all, AMD should still surprise us all, even Intel.

no, the micro-arch improvements are not connected with the lithographic process.
no, the IMC is not adventage, it is disadventage for the DDR2, becouse it is not optimized for high latency. it is taking space on the die, and that space is used as L2 on the Core arch chips.

Well, an IMC may not give a full advantage, but I see it as one. I have noticed that the current IMC in the first lineout of processors for AM2 aren't optimised that well to DDR2, though they do get a performance boost out of the RAM, the latencies do cut down on that boost, limiting the overall boost in performance to about 5%, give or take. The thing is AMD has a lot of pressure coming in from Intel over the Core processor and so, whilst AMD shrinks the lithographic process for their current architecture, it would be foolish not to optimise the architecture at the same time. The IMC really needs the extra optimisations in order to be able to deal with the current latencies of DDR2 RAM, so it can really make use of that extra bandwidth. Besides, though the IMC reduces the amount of L2 cache that can be put on die, it shortens the pipeline required in order to access memory, which is why these latencies affect AMD processors more than Intel processors. Of course, all of this is speculation in the end of the day, and I am very keen in seeing what both companies can do with their new processors once they are out on the market.
May 2, 2006 9:05:13 AM

I am still wondering how good the multitasking performance will be. It seems like HT is now history for the time being?? I'm confused...help!
May 2, 2006 10:16:03 AM

Multi-tasking should be fine. Look at AMD's dual-core processors, they don't have an equivalent of hyper-threading on their processors, but they still do very well, if not better than Intel's dual-core processors, which have hyper-threading. Just by looking at the Core processor specs, I can see that Intel are aiming for overall performance rather than just mult-tasking or boosting threaded apps, which is a good thing if I remind you. I reckon you will still be able to play a decent game and have loads of stuff running in the background with Intel Core processors, but of course, to really know if it can do what it says, we will have to wait for the chips to come out and for some serious testing and benchmarking to be conducted.
May 2, 2006 10:18:35 AM

Quote:
Multi-tasking should be fine. Look at AMD's dual-core processors, they don't have an equivalent of hyper-threading on their processors, but they still do very well, if not better than Intel's dual-core processors, which have hyper-threading. Just by looking at the Core processor specs, I can see that Intel are aiming for overall performance rather than just mult-tasking or boosting threaded apps, which is a good thing if I remind you. I reckon you will still be able to play a decent game and have loads of stuff running in the background with Intel Core processors, but of course, to really know if it can do what it says, we will have to wait for the chips to come out and for some serious testing and benchmarking to be conducted.



Indeed. :trophy: :-D

HT is a more of a gimick than anything else. Sometimes it helps and sometimes it hurts.
May 2, 2006 10:55:05 AM

How is it a gimmick if it helps?
May 2, 2006 11:20:01 AM

Quote:
Multi-tasking should be fine. Look at AMD's dual-core processors, they don't have an equivalent of hyper-threading on their processors, but they still do very well, if not better than Intel's dual-core processors, which have hyper-threading. Just by looking at the Core processor specs, I can see that Intel are aiming for overall performance rather than just mult-tasking or boosting threaded apps, which is a good thing if I remind you. I reckon you will still be able to play a decent game and have loads of stuff running in the background with Intel Core processors, but of course, to really know if it can do what it says, we will have to wait for the chips to come out and for some serious testing and benchmarking to be conducted.



Indeed. :trophy: :-D

HT is a more of a gimick than anything else. Sometimes it helps and sometimes it hurts.

I wouldn't say it is a gimmick, since it does help performance, but I wouldn't go so far as saying it is a good feature, since its performance boost does not apply to all programs. If Intel decided to leave it out of their Core processors, it means Intel didn't see how hyperthreading could benefit the architecture, unlike with Netburst. Besides, hyperthreading does increase problems with hotspots on the processor.
May 2, 2006 11:51:05 AM

Of course they will, the question is when.
May 2, 2006 1:14:26 PM

Well if it like the PIII then i hope they don't go back to the good ol SEC cartridge type CPU's.
May 2, 2006 1:45:57 PM

Umm, they are staying with the current Intel sockets, so we wont see any cartridges, thankfully. What I meant by being similar to P3 is in the general architecture of the chip, not the exterior chip design.
May 2, 2006 5:07:42 PM

Aren't the only Pentium D's with hyperthreading the Extreme edition ones?
May 2, 2006 5:28:29 PM

Quote:
Optimization does not mean new architecture and that was my question. We can certainly speculate all day but I thought maybe there was a more definitive answer by the way the post was made.


So are you expecting from someone in the inner AMD 65nm design team to chirp up now and tell you EXACTLY what architecture changes to expect? Don't hold your breath, pilgrim.

I have a friend that does architecture design for Intel and although he used to be pretty loose-lipped about all the great stuff he/they does/do, these days he's learned to treat his knowledge like it's the key to the season-ending surprise for 24. I wouldn't expect a company like Intel or AMD to serve up the goodies for us - those concepts are the reason they can sell the stuff they do!
Anonymous
a b à CPUs
May 2, 2006 5:31:16 PM

Posted that in another thread...I was wondering why nobody mentionned that AT article...
Quote:

After reading that I had some insight on what you should expect from K8L. They keep saying K8L its evolutionary and not revolutionnary. I can see quite a few tweaks AMD could do on the K8 to bring it back on par with the <expected> conroe performance. If you look at the life of the K7/K8 architechture, you will see that all the evolution provided a good bump in performance and that this architchture has the potential too scale much further before a total re-design has to take place, thats unlike NetBurst and much more like the P6/Banias/dothan/yonah.

My feeling on this right now is that Conroe should have a good edge over K8 when it comes out. After that, K8L should be able to catch up if AMD engeneer do a good job. And then we might see a good fight between the two compagnies and that would be the best for every consumer.

I really dont see why people think AMD will get nailed for 3 years just because intel release a new architechture. Intel NEEDED a brand new architechture because they obviously did the wrong thing with NETBurst and they could'nt continue doing so. AMD on the other hand has a good and strong scalable architechture. AMD engeneer have'nt been sleeping either and Im sure they can do some tweaks intel's just did with core and bring performance back on par.

I dont see how some people think AMD is unbeatable and that core will suck but thats another story


Is there any more detail on K8L that I'm not aware. Is there any reason not too expect AMD to be able to increase internal bandwith, and too manage a better,broader OoO implementation,etc? Just like intel did with Core...

Because yes a shrink, higher clock speed re-worked controller can help but i'd assume other technique could and should eb used to inscrease ILP and stay competitive with Intel
May 2, 2006 5:34:01 PM

Yes, the only Pentium Dual core processors with HT are the Extreme Edition ones. Though I really was focusing on the extreme edition processors, since they have HT and are supposed to compete with the current AMD X2 lineout.
May 2, 2006 6:02:42 PM

Quote:
Well, an IMC may not give a full advantage, but I see it as one. I have noticed that the current IMC in the first lineout of processors for AM2 aren't optimised that well to DDR2, though they do get a performance boost out of the RAM, the latencies do cut down on that boost, limiting the overall boost in performance to about 5%, give or take. The thing is AMD has a lot of pressure coming in from Intel over the Core processor and so, whilst AMD shrinks the lithographic process for their current architecture, it would be foolish not to optimise the architecture at the same time. The IMC really needs the extra optimisations in order to be able to deal with the current latencies of DDR2 RAM, so it can really make use of that extra bandwidth. Besides, though the IMC reduces the amount of L2 cache that can be put on die, it shortens the pipeline required in order to access memory, which is why these latencies affect AMD processors more than Intel processors. Of course, all of this is speculation in the end of the day, and I am very keen in seeing what both companies can do with their new processors once they are out on the market.

Only with low latency CL3, 800MHz DDR2 the sAM2 K8 will overperform for about 5%-10%, the DDR-400 CL2 for memory operations. But memory bandwidth does not mean performance. The s939 have double the bandwidth of s754, but is only 0%-5% faster at same clock. This means that the K8 is not starving for more memory bandwidth, and the 10% faster RAM opeartion does not mean 10% in performance.
The 65nm is more becouse of the yelds and the production cost. It will be 3th generation of SOI (DSL+STL+applied SiGe), will spend less energy and produce less heat, therefore enabling 4 core K8 on 1 package. It will be a try to compete against Kentsfield, the dual Conroe, or quadcore Core arch. chip.
May 2, 2006 6:08:55 PM

Quote:
Only with low latency CL3, 800MHz DDR2 the sAM2 K8 will overperform for about 5%-10%, the DDR-400 CL2 for memory operations. But memory bandwidth does not mean performance. The s939 have double the bandwidth of s754, but is only 0%-5% faster at same clock. This means that the K8 is not starving for more memory bandwidth, and the 10% faster RAM opeartion does not mean 10% in performance.
The 65nm is more becouse of the yelds and the production cost. It will be 3th generation of SOI (DSL+STL+applied SiGe), will spend less energy and produce less heat, therefore enabling 4 core K8 on 1 package. It will be a try to compete against Kentsfield, the dual Conroe, or quadcore Core arch. chip.


A Quad-Core Core arch. chip heh? Sounds beefy to me... and yes you do have a point. I'm just really eager to see both Conroe and 65nm AM2 chips become available to all, along with some proper benchmarks...
May 2, 2006 6:57:31 PM

I'm still expecting it to be a pretty tight race between Conroe and AM2. Of course I don't have any hard numbers to back up that prediction, but then neither does anyone else.

And if they are close, I expect the real loser will be the Pentium 4. Why on Earth would anyone buy one when the Conroe is available? They will probably re-badge them all "Celerons" and try to give them away. There goes your bottom end product line, Intel.

Because let's face it. There are Intel fanboys and AMD fanboys. And there are those like me who just want the best system for the money without any major weird problems. If Conroe and the AM2 systems tie for performance, then whichever one is cheaper looks really good to me. But let's take another look at the fanboys.

The AMD fanboys will take a considerable amount of force to make them consider buying "Evil Inside" Intel. So given time they **might** come off the fence and consider a Conroe, but not a P4. So the AMD fanboys won't buy the P4's.

The Intel fanboys are happy as clams that Conroe is coming to save the day. And if it's even close to the AM2 performance benchmarks, they will buy it. WooHoo! Conroe! Conroe! Conroe! But then why would they consider buying the P4, the system that Conroe had to save them from? So the Intel fanboys won't buy the P4's.

For the fence-sitters like me, whichever is the cheapest is a good deal. If the price of the P4 drops below that of a comparable AMD system, then I would buy it. But if not, I won't buy a P4.

So there you have it. The Intel fanboys won't buy P4. The AMD fanboys won't buy P4. The fence-sitters won't buy P4 unless they go for dirt cheap. Refer back to what I said at the beginning. Call them Celerons and give them away. That's about all you can do.
May 2, 2006 7:38:08 PM

Quote:
Do you guys think this is it for AMD or will they be able to counter?



I believe we will pleasantly surprised by the 65nm AMDs.

Is there some major architecture change that is being made or is just shrinking the die?

It will just be a shrink as they said the would put the X2 on it, but K8L -- reported by Tom's is a quad core product, likely integrating all 4 cores onto the same die. Not much detail around K8L--MMM will certainly be able to tell you exactly what will be used -- HT 3.0 likely etc. etc.

Don't expect much from 65 nm though, 15-20% from where they are now so 3.2-3.6 GHz will max out for them on the K8 architecture. It would take a 3.8 to 4.0 GHz K8 just to achieve parity with Conroe it appears.

Jack

Well, I would agree that Core (NMGA) seems to be a very good design. It appears to keep the strengths of Dothan while fixing the weaknesses. Although I had some doubts that this would be as much of an improvement as had been suggested I would definitely call this a full generation ahead of Dothan. How does it compare to K8? Well, it is not really accurate to say that it is a full generation ahead however it is clearly more advanced in several respects. I suppose I should do some kind of FAQ to answer the most common questions.

Q. Can K8 compete with Core?
A. Not for very long. As Intel continues to develop Core in 2007 it would surpass anything that AMD could do with K8. AMD would once again be K7 to P4.

Q. So then this is really good for Intel, right?
A. Not exactly. If Intel had been able to deliver Core at the beginning of 2006 they would be in a much better position. Instead, their revenues will be down in the first two quarters and then they will have to scramble to try to hit their estimate of a 3% loss for the year.

Q. But even with a loss won't Intel stay in the lead for a long time like they did with P4? After all, K7 was briefly in the lead but couldn't hold it against P4.
A. No. Intel has very little hope of staying in the lead in 2007. If Intel only had to contend with K8 on 90nm they would be in very good shape. If they had to compete with K8 on 65nm they could still hold the lead on the desktop. However, Core faces the much newer K8L in early 2007. Core has almost no chance of holding the lead against a new architecture on the same process. Intel's first hope of regaining the lead will be the release of Nehalem on 45nm in late 2008.

Q. Wait, so you mean that Conroe will be like K7 and only get ahead for a short time?
A. Yes, most likely no more than two quarters.

Q. But Intel is so much bigger than AMD. They can cut prices or something. Surely Intel can take market share back from AMD.
A. No. Things are different now than they used to be. With the trial still underway Intel would be foolish to try the same monopoly tactics. Also, Intel's price advantage over AMD is completely gone. If Intel does cut prices their revenue will shrink. None of the old Intel strategies will work against a competitor with a more advanced FAB process, flexible manufacturing, and 300mm wafer size. This isn't like the old days when Intel was more advanced on process technology and AMD had no high end or server processors.

Cheers.
May 2, 2006 8:03:52 PM

Quote:
I'm just really eager to see both Conroe and 65nm AM2 chips become available to all, along with some proper benchmarks...


Me too! There are some exciting months up ahead. A much-anticipated heavyweight matchup.

Take your seats...
May 2, 2006 8:08:34 PM

Wasnt there a post recently about Intel slashing prices?

I think old Pentium 4/D will be sold in budget computers. Whatever loss they recieve from the mark down of the P4 they can write off on their tax statement, it seems much more foolish to try to sell off P4/D at full price when they have a much better product that could help them manuever into a better position for the years to come.
May 2, 2006 8:12:48 PM

Quote:
I suppose I should do some kind of FAQ to answer the most common questions.


Or maybe you should just speculate on stocks...
May 2, 2006 8:13:08 PM

who will buy them? just don't see many people buying them, when you can buy a faster, cooler, and supposed less expensive than the competition conroe machine.... and I am sure they would rather sell conroe than P4's anyway. Even though, they have to sell the P4's too... kind of in a hard place.
May 2, 2006 8:17:43 PM

Quote:
I'm just really eager to see both Conroe and 65nm AM2 chips become available to all, along with some proper benchmarks...


Me too! There are some exciting months up ahead. A much-anticipated heavyweight matchup.

Take your seats...

I got popcorn!! Anyone want some popcorn!! It's sweet too!! :lol: 
May 2, 2006 8:50:05 PM

Quote:
I'm just really eager to see both Conroe and 65nm AM2 chips become available to all, along with some proper benchmarks...


Me too! There are some exciting months up ahead. A much-anticipated heavyweight matchup.

Take your seats...

I got popcorn!! Anyone want some popcorn!! It's sweet too!! :lol: 


Yes, please, hook me up :-D
May 2, 2006 9:17:57 PM

Along with the introduction of Conroe, and sometime afterward, the introduction of new AMD X2 cpus built on a 65nm process (possibly with some new surprises in store), we also have this to watch -- Opteron accelerators :

http://www.theinquirer.net/?article=31398


Won't impact the desktop -- unless, maybe, a graphics or physics co-processor could be made to fit in the second socket on a dual-Opteron board -- now that's something I would consider. Hate to think about the cost, though -- a $300-plus Opteron and a $250 co-processor ... hmmm.
May 2, 2006 9:30:24 PM

Quote:
Along with the introduction of Conroe, and sometime afterward, the introduction of new AMD X2 cpus built on a 65nm process (possibly with some new surprises in store), we also have this to watch -- Opteron accelerators :

http://www.theinquirer.net/?article=31398


Won't impact the desktop -- unless, maybe, a graphics or physics co-processor could be made to fit in the second socket on a dual-Opteron board -- now that's something I would consider. Hate to think about the cost, though -- a $300-plus Opteron and a $250 co-processor ... hmmm.



These are mainly intended for specialized setups. Most people do not need something like this.

Unfortunately it is getting more and more expensive to be a gamer these days with physics boards, $500 VGA cards, and more on the way... granted you don't have to have a physics board but a $300 - $600 VGA is almost a requirement if you want to play Oblivion :-/

AWESOME($game) && STEEP($requirements);
May 3, 2006 4:37:29 AM

You got to admit it was a pretty funny troll post.
May 3, 2006 6:30:42 AM

Jack, not that I am arguing anything about 65nm cpu's but I do believe they have produced 65nm SRAM. And also, I have read that they made a 45nm SRAM wafer.... just what I read though.... you may have heard differently
May 3, 2006 6:37:59 AM

and Action Man, I know you hate AMD with passion(or so you make it seem) but at least try to behave and not start referring to someones post as a troll post just because you disagree with it. See how jack did it? Facts not names.... I do get a kick out of your keyboard and slinky posts, although at times they can get a little repetitive..... I guess that is the point though..... and my point is, people may actually listen to you if you use a little constructive criticism and not be so condescending.... but that is just my opinion..... I almsot expect the keyboard and slinky from you though.
May 3, 2006 6:47:33 AM

Quote:
Action Man, I know you hate AMD with passion


Amusing to say the least.

Link 1.
Link 2.
Link 3.

Yes damn AMD! Damn them to hell!

Quote:
but at least try to behave and not start referring to someones post as a troll post just because you disagree with it. See how jack did it?


Hmm.

Jack:

Quote:
How to respond Rolling Eyes Rolling Eyes


Jack had already layed down the law, I'm too lazy/busy at work. It was a troll post.

Quote:
I almsot expect the keyboard and slinky from you though.


Damn, you have pretty low expectations of me you also don't understand each concept.

Keyboard = All caps post.
Slinky = For the horde when they're trolling.
May 3, 2006 7:03:29 AM

yes I do understand the concepts, they make threads all caps, and I do understand the slinky, it is self explanatory..... I am just judging you from the posts I have seen you respond to. I don't really have low expectations.... I just normally only see you post the same things, and maybe, like you said, if is because you do not have the time.... in which case, I can understand.... but for people that aren't aware of your personal life it might look like something else.... and no, you don't have to go and tell everyone why you do what you do, just saying how it may appear at times..... but now..... I see you in a different light..... I was only able to judge you from what I have seen thus far.... but thank you for clarifying.... and most of the time I would have probably responded the same way Jack did..... just seems you have some of that stuff on auto post....
http://www.ixbt.com/cpu/semiconductor/intel-65nm/65nm_s...
will this link work for proof jack? :tongue: [/img]
May 3, 2006 7:04:32 AM

Quote:
How to respond :roll: :roll: how to respond :roll: :roll:

Normally FAQs have answers that are based in fact, could you please provide the data that supports the 'answers' you gave to the questions above?

Also, your question 1 is misleading, you are implying Intel will show a financial loss this year, this is not true... Intel is forecasting a decline of 3% in revenue YoY, they were not forecasting being in the red. Intel will likely show a net profit for the fiscal year of between 4 to 8 billion dollars. (Assume worst case 1 Bill per quarter).

Finally, could you please add these to your FAQ:

Have we seen a functional 65 nm device from AMD, never mind a CPU how about SRAM or a test chip?

What special details about K8L will propel it back into the lead?

What is K8L? Sounds like an L stepping of a normal K8 to me...

If AMD has 65 nm at 40% improvement, why aren't they releasing now, why Q1 2007?

Why is the data showing AMD's 65 nm device metrics ~ 15% slower than Intel's 65 nm?

Have we seen benchmarks, even underground data or AMD trade show information, showing the superiority of K8L?

....


I'm glad you responded to that, otherwise I was going to have to. you do it better though.

it's a shame some people will read his post and assume it's fact when it's really anything but. biased opinions put into FAQ form don't make them true.
May 3, 2006 7:08:19 AM

They should have just called it Pentium 3 at 2ghz and pretended like pentium 4 never happened.

What? That's not an intel, that's a fake intel sticker!
see intel stickers are round... :lol: 
May 3, 2006 7:25:08 AM

Quote:
How to respond :roll: :roll: how to respond :roll: :roll:

Normally FAQs have answers that are based in fact, could you please provide the data that supports the 'answers' you gave to the questions above?

Also, your question 1 is misleading, you are implying Intel will show a financial loss this year, this is not true... Intel is forecasting a decline of 3% in revenue YoY, they were not forecasting being in the red. Intel will likely show a net profit for the fiscal year of between 4 to 8 billion dollars. (Assume worst case 1 Bill per quarter).

Finally, could you please add these to your FAQ:

Have we seen a functional 65 nm device from AMD, never mind a CPU how about SRAM or a test chip?

What special details about K8L will propel it back into the lead?

What is K8L? Sounds like an L stepping of a normal K8 to me...

If AMD has 65 nm at 40% improvement, why aren't they releasing now, why Q1 2007?

Why is the data showing AMD's 65 nm device metrics ~ 15% slower than Intel's 65 nm?

Have we seen benchmarks, even underground data or AMD trade show information, showing the superiority of K8L?

....


I'm glad you responded to that, otherwise I was going to have to. you do it better though.

it's a shame some people will read his post and assume it's fact when it's really anything but. biased opinions put into FAQ form don't make them true.

this guy that posted that q&a session is no other than scientia from amdzone (worlds most hardcore fanboys) failing that he is some loser that steals posts from other forums and passes it of as his on drivel.

here is the thread were he originaly posted http://www.amdzone.com/index.php?name=PNphpBB2&file=vie...

gallag
      • 1 / 2
      • 2
      • Newest
!