AMD vs. Intel: Refuting Historical Inaccuracies

[The_Blood_Raven]

Yeah I had one run in with AMDzone, I was having problems overclocking a 9850 and I wanted to make sure that there weren't any tricks that I did not know about. I posted on AMDzone, naturally, since I thought they would know. My thread was deleted because I was, allegedly, an Intel fanboy because I was saying that I could not hit 3.0 GHz on a 9850 with an SB750 motherboard. Never got it to 3.0 Ghz, but 2.9 Ghz was not too bad.

Thankfully, I find that AMD fanboys, like those at AMDzone, are a dying breed and are out of date. nVidia fanboys on the other hand are on the up swing...

 

[BadTrip]

Now if we can get JJ and ActionMan back. Hell even Madmodmike, lol

 

[someguy7]

What you are talking about has nothing to do with AMD vs Intel. It logical people vs complete retards.

 

[Cryslayer80]

Yeah I had one run in with AMDzone, I was having problems overclocking a 9850 and I wanted to make sure that there weren't any tricks that I did not know about. I posted on AMDzone, naturally, since I thought they would know. My thread was deleted because I was, allegedly, an Intel fanboy because I was saying that I could not hit 3.0 GHz on a 9850 with an SB750 motherboard. Never got it to 3.0 Ghz, but 2.9 Ghz was not too bad.

Thankfully, I find that AMD fanboys, like those at AMDzone, are a dying breed and are out of date. nVidia fanboys on the other hand are on the up swing...

ROFL!

 

[Uncle Meat]

2.

AMD were the first to Integrate the Memory Controller onto the CPU die for an x86 processor

This one is just false. Intel were actually the first to integrate a memory controller onto an x86 architecture based processor. In fact Intel did so on the mobile variant of their 386 and 486 processors as seen here: http://smithsonianchips.si.edu/intel/i386sx.htm

There were no mobile versions of the 386 and 486 processors. The link you provided only shows a chip with an integrated Memory Management Unit, which all x86 chips have had since the 80286, NOT an integrated memory controller. Big difference.

 

[jamesgoddard]

Is Dunnington really a native 6 core CPU....... I mean it is a collection of 3 dual core CPU's (exact copy's of C2D's) that just happen to have been placed on a single due - but does that make it really native?

And Intel's QPI is a copy, but then again so is HT, both a plain rip off from EV7 - but to be honest who cares....

One last thing to remember is the very complicated cross licensing Intel and AMD have (that they both need - hey how do you think Intel managed to copy AMD64, and AMD use SSE xxx) thus this bus copying ho har is all pointless, and each party is well within their rights to just use the any tech the other party has copyright on, and they do.

 

[randomizer]

Now if we can get JJ and ActionMan back. Hell even Madmodmike, lol

Maybe even throw in BaronMatrix on the side and we could really get the party started again. :lol:

 

[Upendra09]

and dragonslayer, he would defend AMD even after it was long gone

 

[jimmysmitty]

First off, great post. I'm glad there are people out there willing to find out things for themselves rather than just repeating what they hear being said. Just one thing, dunnington was not the first native six core processor because dunnington isn't a native six core. In that article you posted, it said dunnington was a compilation of 3 penryn cores one one die. That conflicts the very definition of being 'native'. Penryn is a native dual core, combining them together doesn't make dunnington a native six core. This is the same argument used as to why core2 quad isn't a native quad core - because its 2 penryn cores on one die. So the award doesn't go to intel, or amd because as far as I know, neither company has made a native six core processor.

edit: note: Technical error - forgot about conroe. c2q can be combinations of penryn or conroe. Conroe core was used in 65nm variations.

Dunnington was a "naitive" six core. Just because it actually used 3 dual core Penryn CPUs does not mean it couldn't be. All 6 cores were on one die thus the term naitive. Each set of dual cores ahd independent caches and one large shared cache.

So in a way it was like a C2Q but still naitive in design.

As for the OP, AMDFanzone is what it is. They are the hard core fans who also would use AMD marketing as proof of a superiority and claim that all benchmarks except the ones that they approve of are rigged and paid for by Intel.

They also claim any site that says Intel has a better CPU is a Intel paid site, such as THG and Anand.

Its kinda sad cuz I remember back during the Athlon 64 days and how touted those chips were among THG, Anand tech and most people here.

 

[chowmanga]

Dunnington was a "naitive" six core. Just because it actually used 3 dual core Penryn CPUs does not mean it couldn't be. All 6 cores were on one die thus the term naitive. Each set of dual cores ahd independent caches and one large shared cache.

So in a way it was like a C2Q but still naitive in design.

Indeed. The pictures above tell the same story and was all the explanation I needed.

 

[jimmysmitty]

Yessir. Istanbul is also a native Hexa-core processor but it came after Dunnington. What you will often hear is that Istanbul was the first Native Hexa-core (Baron Matrix is notorious for spreading such FUD) and it is just not true.

Thanks for commenting though, it forced me to grab some links and enforces/cements my above comments

Peace.

What I find more interesting about Istanbul is that AMD plans to do a MCM of them to make a 12 core. After so much trash thrown at Intel for the MCM C2Qs they themselves are going to utilize its ability.

Now with HTT and a IMC it will be different but still I always love watching one company dog another for something then they themselves do it too.

Well I'm not quite familiar with Intel fanbois as I don't know many of them right now (I can't tell them apart from the general public because right now they do support the better processor).

But I do remember Intel fanbois back during the days of the Pentium D (I ran AMD exclusively back then). And they would make outlandish claims but never delusional to the point of creating their own website and kicking anyone out who disagrees (referring to AMDZone).

But by all means, if you have certain allegations Intel fans are making which you think are not true, run them by me. I will objectively do the research and then give you the facts (I won't lie to you that's a promise).

I remember the Pentium D days. No real reason to buy one unless you bought it on the verge of Core 2. Or if you had a low budget but could afford decent air cooling the Pentium D 805 was great for its OCing ability for so cheap ($125 at the time).

But at that same time Asus had released a 479 to 478 adaptor for its 478 desktop mobos and THG did a report on it. They took a Pentium M of the best class and OCed it on my mobo in my old machine (Asus P4P800 Deluxe) and found that the Pentium M not only beat the Pentium 4s but also the Athlon 64s. Of course that is where Core 2 came from.

I think I only knew one person with a Pentium D though. He worked for Intel in Chandler after graduating with a 2 year in Electronics from our local community college. They gave him a Pentium D EE for free. A engineering sample too. So we found a nice mobo and other stuff for it because it was a free $1K CPU.

Other than that everyone was getting Athlon X2s. I unfortunately am always building right before a new release. I got my Pentium 4 system before Athlon 64 came out and my C2Q Q6600 I have now a few months before their 45nm lineup was out. Kinda sucks.

 

[Upendra09]

Pentium G? you mean D right?

 

[jimmysmitty]

Pentium G? you mean D right?

Maybe.... maybe not......

Pentium G, the GeForce CPU!!!!!!!!!!!!!

 

[chowmanga]

1.

Hypertransport was an AMD Innovation and QPi is a copy cat

You know what, maybe it's not just fanboi's can are misinformed. Suggestive titles may also contribute to misinformation being passed around.

For instance: http://www.tomshardware.com/reviews/Intel-i7-nehalem-cpu,2041.html

Title is "Intel Core i7 (Nehalem): Architecture by AMD?" Anyone just browsing may get the impression that intel had copied something from amd just form the title.

Also, if they chose to click around the article, they may find comments like this...

The solution Intel chose—called QuickPath Interconnect (QPI)—was nothing new; an integrated memory controller is an extremely fast point-to-point serial bus. The technology was introduced five years ago in AMD processors...

Anyone choosing to stop reading there will not realize that it continues to say...

...but in reality it’s even older than that. These concepts, showing up in AMD and now Intel products, are in fact the result of work done ten years ago by the engineers at DEC during the design of the Alpha 21364 (EV7)

which is what you touched on in your post. After reading that when the article first came out, I realized why there was a question mark in the title. I didn't think twice about it before reading that sentence. Its true that some amd fanboi's are delusional and spread misinformation on purpose, but maybe its not just them. There could be some people who just can't read who spread it as well.

I'm no psychologist, but its just a thought.

edit: 1. cut down quote from op, we've all read it. 2. Direct link to pages specifically quoted: http://www.tomshardware.com/reviews/Intel-i7-nehalem-cpu,2041-8.html

 

[jimmysmitty]

^I think the one thing though that he continues to explain is how in a technical way Intel owns HTT since it owns the IP of Alpha.

So in a way HTT was a innovation of Intel that they let AMD use since they would be a monopoly but they temselves did not use since on the DT a IMC was not yet needed.

 

[Upendra09]

what is IP and DT?

 

[chowmanga]

^I think the one thing though that he continues to explain is how in a technical way Intel owns HTT since it owns the IP of Alpha.

So in a way HTT was a innovation of Intel that they let AMD use since they would be a monopoly but they temselves did not use since on the DT a IMC was not yet needed.

Yes, I understand what he was saying. However, the point of his post was to dispel myths that supposed fanboi's carry. I was raising the level of abstraction to people in general and possibly provide an explanation. That's what I was trying to explain.

 

[randomizer]

And people say THG are Intel fanboys, yet that article says quite the opposite

 

[caamsa]

Maybe even throw in BaronMatrix on the side and we could really get the party started again. :lol:

I would have to say no thanks to having all those big egos back. I think it was very distracting and drove the mods crazy.

 

[bgd73]

That was interesting. As a normal user, 10 years, I knew obviously there are anti-monopolies. Companies are results of one fantastic standard..by one company..it could even be university , before companies. like the computer and internet humbly at mit...
At a time when silos were in the ground in the cold war secrecy death game...hmmm. who would actually have a public truth anyway...

AMD has been a childish underthunk assmunch since my first AMD, they are lucky to have intels thoughts, as well as ATI...they are getting better.

I read these arguments out loud, in early 2000s, I am one who mysteriously lost a gigantic compaq to bankruptcy, and a big chunk of change...as a complete non-nerd newbie user who had to be taught how to dial out...

the pc is intels. It is as if to pretend it isn't. 😗
I actually do not care, seriously.

 

[SpidersWeb]

well the PC is really IBM (I still have one from 1982, although their newer workstations since the Pentium era I've found to be poopy)
But x86 is Intel.
Has AMD ever made their own architecture (historically I mean, doing it now would be a bad choice)?
Motorolla did that, with pretty good success too until they ran out of puff.

 

[jimmysmitty]

what is IP and DT?

IP: Intellectual Property (think patents)

DT: Desktop......

well the PC is really IBM (I still have one from 1982, although their newer workstations since the Pentium era I've found to be poopy)
But x86 is Intel.
Has AMD ever made their own architecture (historically I mean, doing it now would be a bad choice)?
Motorolla did that, with pretty good success too until they ran out of puff.

Yea technically the PC is IBMs but would not have been possible without Intel and Microsoft too.

ANd historically, no. AMD has never made thier own architecturs. In fact x86-64 is just x86 with 64bit (wa all know) but was designed mainly by IBM who tends to help AMD out a lot.

 

[Upendra09]

i hate motorolla

they have good headsets other than that they suck

 

[Upendra09]

DT= Desktop

of course wow i am stupid

 

[SpidersWeb]

Ah yep.
I remember when IBM jumped in on the x86 action themselves too. Back in the Pentium era. Cyrix 5x86, 6x86 etc.