AMD vs. Intel: Refuting Historical Inaccuracies

Page 11 - Seeking answers? Join the Tom's Hardware community: where nearly two million members share solutions and discuss the latest tech.
Status
Not open for further replies.
Intel was still the first with IMC, irrelevant of weither performance was a focus or not. That's pretty simple. Doesn't mean that AMD doesn't deserve credit for HyperTransport. Thing is though, these people wont give Intel credit for 32nm, MMX, Core i7 architecture etc etc

I give AMD credit where it's due and recommend the Phenom II to lots of users on here. I just get tired of the one sided folk (and yeah I know there are fanboys on both sides).

When I first read your post, I never thought it was anti-AMD, but rather anti-bs, to clear up those frustrating statements that uneducated fanboys use (on both sides, just happens to be AMD this time).
 


Actually I'm talking about your implied argument: That this fact was somehow actually important in the scheme of things.


Let me put it into different words you might be able to understand: "So Intel invented the IMC. They didn't implement it or use it for years so that fact is irrelevant."


Now please keep attempting to teach me the "truth" and lead me to "the light" so I can go forth and propagate your opinion. (Or whatever it was that was you said earlier.) Since you can't do that... we'll just let you keep ranting about how your first fact is true and ignoring the fact that is not very important.


I repeat yet again: I was NOT arguing intent against your first valid fact. I am mentioning that it diminishes your implied argument. And nothing you have said up until the last inflammatory post you just made changes that fact.

EDIT: Or to use the words from your last post: "You don't have a single argument." All you have is just one fact and you're getting angry because I'm not agreeing that it is important in any way. But you keep pretending that means I don't agree with the fact itself because that is the only thing you can fall back on.
 
He is being a troll? So, what was your thread's attempt? I'll tell you what. It was intended to calm you down and get a 1000 responses agreeing with your bias (later in text, first post was amazingly true) since you got a shoe from people who are not short-sighted.
 
So you guys aren't disagreeing with facts?
It is all about the spin?

Why not just post "Yes Intel did it first, but AMD made it a performance success, and they deserve credit for that!"

Rather than all this bulls**t you guys have been causing??
and who cares? Nobody is going to not buy an AMD because "well they didn't really do IMC first". That's rediculous.


Edit: Cryslayer - if I'd seen keithlm more often contributing to THG, I'd say he wasn't a troll, but it seems he's just rolled in from amdzone to cause trouble and discredit a thread that may impact on people's opinon of AMD. It's not that he doesn't make some good points, just could've been summed up quite quickly at the start without all the BS and all the 'your just an intel fanboy' and 'they'll never listen' bull. It's the pot calling the kettle black, and I expect it was just put there to piss people off.
 
this thread is not a troll thread, i found it very informative

this is the farthest from a troll thread ever, obviously, Cryslayer hasn't seen my "is AMD doomed" thread now that was a troll thread and so is "is Intel Doomed?" by AFG
 


But they did use it:
I’m not saying Intel will or won’t go this route someday. History shows we’ve gone both ways. We integrated the memory controller in our CPUs as far back as 1990 (i386SL w/ Page Mode DRAM + SRAM + FLASH MC) and 1992 (i486SL w/ Fast Page mode 3.3v DRAM, x4, x8, x16). We do it now with our X-scale based products. And, we had it as part of a desktop PC chip project called Timna that we cancelled in the late 90s.

This is X-scale: http://en.wikipedia.org/wiki/XScale it used to be an Intel product (now a Marvell product).

On June 27, 2006, the sale of Intel's XScale PXA mobile processor assets was announced. Intel agreed to sell the XScale PXA business to Marvell Technology Group for an estimated $600 million in cash and the assumption of unspecified liabilities. The move was intended to permit Intel to focus its resources on its core x86 and server businesses.

http://www.intel.com/design/intelxscale/xscaleproductbriefweb.pdf (check the date year 2000).
http://www.cpu-world.com/CPUs/Timna/ (Check the dates as well)

So Intel did implement an IMC across various products. The idea for a desktop variant was shelved in the late 90s but was reborn around 2005 (when Intel began changing it's strategy).



You're not being reasonable. What is the reason why the intent is somehow relevant to the accomplishment? Explain that.
 

I'm not spinning.. I'm sticking to the original evidence. Keith here is spinning the evidence so as to be able to diminish the impact of Intel being the first to use an IMC on an x86 processor. He's doing so because this fact diminishes AMDs stance on the topic (exposing it as not being factual) and anything that goes again AMD must be wrong. He is looking for some sort of victory for AMD... somehow... for some reason... by spinning the facts so as to facts not looking as bad as they do right now (towards AMD in his mind).

He has effectively created a straw man and is arguing the straw man in an attempt to discredit me (and thus tarnish the evidence contained in this thread). He sounds like Bill Clinton arguing what the definition of "is" is.

Fanboism is a disease.. it makes people delusional.
 



Sure. It has nothing to do with the fact that Intel created something and then abandoned it for years and didn't bother using it one their mainstream processors until another company showed them that it was in fact a good idea. But somehow that is "spin".

Sadly... nothing you said supports your implied argument. It's still not important.

And yes... you are delusional.

 
Yeah I was replying to cryslayer/keithlm not you.
I never took your OP as being anti-AMD, was more anti-BS as I said before.

But irrelevant of spin, QPI in triple channel has more memory bandwidth than HT without overclocking, and with the new Core i7 architecture which you've overclocked 1.8Ghz over factory, that would be more reason to favour Intel at present. I haven't seen the AMD fans congratulate Intel.

At the moment the only positive to using AMD as I see it, is price. But for this reason, I have been recommending the Phenom II to many users on here, and also today applauding the three-core option. I say this just to point out I'm not some crazy Intel nut.
 

Why did you not simply say "I still think AMD deserves full credit for HyperTransport" rather than all this carry-on? Even if he disagrees with you, you apparently beleive that you should accept alternative opinions.

How is he delusional for beleiving Intel had IMC first - thats actually a fact? Or is he delusional about other things? and are you sure you're not delusional as well??

Why are you fighting this so much? Do you really think people will stop buying AMD because Intel put an IMC in a 386?

Are you going to give Intel credit for their innovations too?
 

Well Intel did not feel they needed an Integrated Memory Controller. And in fact they were right. Intel did not beat K8 by using an IMC and a Point to Point interconnect. Intel beat K8 using a P6 derived processor (see Intel Core 2) which relied on a Front Side Bus and a chipset (Comprised of a North bridge which housed the Memory Controller and South bridge).

This format was enough to allow Intel to regain the performance lead.

That having been said Intel is a Corporation and wants to dominate all the markets in which it's products are sold. So Intel brought back the idea of an Integrated Memory Controller (which they still used on several of their products such as the X-Scale lineup). They dubbed this new architecture Nehalem (which is, for the most part, a Core 2 with a point to point interconnect and an IMC). This is meant to increase performance in MP systems (high end server/workstations). When many nodes (CPUs) are connected together.. the bottleneck becomes the communications protocol used (formerly referred to as being a Bus). Intel rectified this with QPi. But having a single memory controller in an I/O Hub also posed another bottleneck. Therefore Intel opted to integrate the memory controller into the processor. This allowed the processor to communicate directly with the memory rather than doing so through an IOH. When you have something to the tune of 8x Quad Core Processors attempting to access memory through a single IOH.. things are bound to get pretty crammed.

So Intel brought back the Integrated Memory Controller out of sheer need in order to compete with their competitors.

Now having stated all that.. I still have to ask. What is your line of reasoning? How can you reason that "intent" somehow diminishes accomplishment. Please share this with us all (I've only asked about 3 times now).

AMDs accomplishment when it comes to an IMC is to have it used across their entire product line (even when not specifically needed).

PS. I'm not delusional. I stick to the evidence.. you're the one attempting to straw man the argument with unreasonable claims. You might also want to refer to the definition of the word "Delusional" as it suits you perfectly:

de⋅lu⋅sion
  /dɪˈluʒən/ Show Spelled Pronunciation [di-loo-zhuhn] Show IPA
Use delusional in a Sentence
See web results for delusional
See images of delusional
–noun
1. an act or instance of deluding.
2. the state of being deluded.
3. a false belief or opinion:
4. Psychiatry. a fixed false belief that is resistant to reason or confrontation with actual fact: a paranoid delusion.
 


AHAH... great attempt to divert. But it didn't work though.

You still haven't supported your implied opinion. The fact that they released an IMC first is not important. Especially since they abandoned it. The "intent" was not a strawman but an attempt to actually show that they weren't even considering the IMC for mainstream; only as a chipset replacement on low end chips. But go ahead and keep pretending if you want. It doesn't matter. You've said everything you can and you haven't been able to support your opinion.

Sorry. It's just not important that Intel had IMC on a low scale low end chips. But you can keep using the tactic you accuse others of: Spin. Go right ahead. It still won't change the facts.

(Or you probably won't use spin like you just tried to do... now you'll probably go back to inflammatory remarks. OH... I see you already did in your last edit on that last message. Never mind.)
 
Well the fact is Intel did IMC first. He doesn't need to change that fact.

I'm also pretty sure he's not saying that HyperTransport was't an achievement or innovative.

So I have no idea what you are trying to achieve here keith.
 


Did anybody attempt to refute that? If so... please point that person out so I can mention to them that they are not correct.

However... I'll also mention that the fact is not important. Which of course will make this guy go ballistic yet again.
 

Oh piss off.



And what is this opinion exactly?



I'm pretty sure I've just disproved that. Intel did not abandon the idea, they shelved the idea. Read above.



And what is this: http://www.cpu-world.com/CPUs/Timna/ exactly? Timna was geared as a mainstream product. Where as the i386SL and i486SL processors were geared towards the high end mobile segment.



What I've said isn't opinion but rather fact. You simply don't want to believe the facts. There is no "implied" opinion. You simply see one because you are Delusional. Let's see that definition again:
de⋅lu⋅sion
  /dɪˈluʒən/ Show Spelled Pronunciation [di-loo-zhuhn] Show IPA
Use delusional in a Sentence
See web results for delusional
See images of delusional
–noun
1. an act or instance of deluding.
2. the state of being deluded.
3. a false belief or opinion: delusions of grandeur.
4. Psychiatry. a fixed false belief that is resistant to reason or confrontation with actual fact: a paranoid delusion.




i386SL, i486SL were not low end chips.


I have been attempting to reason with you using evidence and facts and you're resistant to the evidence and facts therefore you are by definition a Delusional person. Fanboism is a mental disorder and you my friend are showing some rather alarming symptoms :)
 


Og came up with the concept of the wheel. Zog came along, and put two of them together with something in between, which he called the 'axle'.

Maybe a bit too subtle for this forum...

Neither Intel nor AMD 'innovated' (invented) the IMC. DEC and HP were both using the technology long before. The IMC concept had some good features (shorter 'wire' lengths, reduced latency) and some drawbacks as well (change memory type, build new CPU). The concept may very well have been dreamed up in Armonk for all I know, and then dropped (shelved, in IBM terms) for reasons valid to their engineers at the time.
So arguing about who 'innovated' the IMC is pretty much a pointless excercise in futility, only showing the ignorance of those that take sides.
 
Yeah I just mean that's the only real fact he's backing up.
Your opinion of it's importance is valid, particularly in modern day computing.

I still beleive it's important/interesting information. As "AMD was the first to make IMC a success in performance comptuing" is a different statement to "AMD made IMC first" - not that you personally would say that, but there are lots that do.

Anybody who reads this, and stops supporting or buying AMD because of his OP, is a fan you want nothing to do with anyway. I took this as more of a history lesson, possibly anti-fanboy, but not anti-AMD.

I'm only posting because what was an education/history thread as become a nightmare to read.

So can we agree:
- "Intel did IMC first"
- "AMD was the first to make IMC a success in performance/desktop computing"
- "If you change your mind about buying AMD because Intel put IMC in a 386 you're a moron"
???

On the education front, I have memories of using a 486SLC desktop, did they run the IMC as well?
 


I don't view it as a "side" issue. The thread was simply started to refute common made allegations by AMD fanbois. It was a response to this post on AMDZone made by BaronMatrix:
BaronMatrix_1.jpg


As for can see I was "TheWaywardWanderer". I refuted his claims and this is where it all started. KeithLM is just another delusional fanboi from that website. They banned me from the website and claimed victory (because by banning me I could no longer counter their claims).

So I came here. :) They can't silence the evidence here (no ability to ban me).

There is no reason to pick a side. What matters are the products. But when some folks cling to one side to such an extent that they spread FUD... I take offense and I rectify the situation (I despise fanboism). If this means taking on false claims made by Intel fans, AMD Fans, ATi Fans, nVIDIA fans then so be it. The evidence and the facts know no bias.
 


I can understand your point of view, but my point was that neither Intel nor AMD can claim to have 'innovated' or 'invented' the concept of an IMC as it was already in use well before either company started playing around with the concept. So debating who did it first is akin to flogging a dead horse. The horse is dead. Bury it, for my nose's sake.

Totally OT, could you PM me the link that you posted prior? Seems that the 'spam' filter blocked out part of that link....
 


Taking desktop motherboards for instance,

Foxconn G45 motherboard - 89.99
http://www.newegg.com/Product/Product.aspx?Item=N82E16813186162

ASUS P6N7A-VM motherboard - 119.99
http://www.newegg.com/Product/Product.aspx?Item=N82E16813131348

Taking netbook for instance,

ASUS EEEPC 1008HA Seashell - 479.99
http://www.newegg.com/Product/Product.aspx?Item=N82E16834220653

Lenovo S12 - 549.99
http://www.newegg.com/Product/Product.aspx?Item=N82E16834146606




Like I said, I agree that the industry is slowly moving towards this direction. However, the speed of this transition is not as fast as you may think. The applications that actually take advantage of GPU's computing power is only multi-media, and nothing else. And for the most part, Intel IGP can perform well in most situation. The X4500HD even have hardware decoding capability, for those who actually has programs that take advantage of that. The only situations that it may fail is the gaming. But again, like I said earlier, most people don't play games on their computers.




I think you're still overstating the importance of GPGPU. Like I said earlier, very few programs in the consumer market take advantage of GPU computing power, and few of them are in the works. GPU-accelerated flash don't even have a launch time line yet. Most DVD / Blu-Ray playback programs still use CPU as decoder, not GPU. For Nvidia's CUDA, its mostly just geared towards supercomputing solutions, not consumers. So while GPGPU may have a place in the supercomputing realm, the adoption is painfully slow, if not moving at all on the consumer side.

However, will GPGPU someday be very relevant? Perhaps, but the time is not in the next few years, but rather more than 5 year timeframe.
 



Yeah I'm delusional and showing alarming symptoms.

But then I'm also not the one getting inflammatory and resorting to name calling because somebody won't accept my opinion as a "fact".



 


I've noticed this also, our new friend elmo here does tend to crack a bit under the weight of irrefutable logic. I get pissed off lol, but that is through sheer frustration vs many intel fanboys.

Here I see you standing up for your views, with elmo getting a lot of support from others...yet he is the one cracking up. I can see why he got banned from AMDZone - although I'm not a fan of people being banned sometimes you have to look at their motives. Why was such an obvious intel fanboy there to start with, for example?

I've read a few others here saying that they went to AMDZone simply to wind up the natives. Of course they should be banned.
 

That should be 'old friend' as he was here long before you, actually. And if we were to start banning people who 'just come in to wind up the natives' who's names would make it onto the list I wonder? [:mousemonkey]
 
Status
Not open for further replies.