Conroe (intel) vs AMD SERIOUS ONLY

[RowdyRob]

Ok, there has been alot of talk lately about the Conroe and how its going to be so much better than AMD's stuff. Also going through all that is a nightmare due to all of the AMD fanboys AND INTEL fanboys. So before you post anything, THERE IS NO FANBOY-ISM HERE! Only facts, i want this to be a SERIOUS thread unlike some of the other mindless dribble ive seen on this topic. Now lets get started!

Intel Claims that there conroe with be 20% or whatever faster than all of the current stuff out today. But is it possible that this is going to turn out like the mac's. Where the Core Duo only got 2x speed if it was beieng run with programms made for that core?

 

[Caboose-1]

Ok, there has been alot of talk lately about the Conroe and how its going to be so much better than AMD's stuff. Also going through all that is a nightmare due to all of the AMD fanboys AND INTEL fanboys. So before you post anything, THERE IS NO FANBOY-ISM HERE! Only facts, i want this to be a SERIOUS thread unlike some of the other mindless dribble ive seen on this topic. Now lets get started!

Intel Claims that there conroe with be 20% or whatever faster than all of the current stuff out today. But is it possible that this is going to turn out like the mac's. Where the Core Duo only got 2x speed if it was beieng run with programms made for that core?

Hate to break it to you but regardless this is going to end badly. And this has also been done a million times. We don't know yet which is better, anyone that tells you different is most likely a fanboy.

 

[RowdyRob]

I know but im hoping to get some REAL information on the battle. Not just: "OMG AMD IS THE BEST AND CONROE IS JUNK" or... "OMG INTEL IS ALWAYS THE BEST AND CANNOT BE BEAT" so im trying to keep this strictly facts only. But from the looks of it INTEL has the upper hand... http://anandtech.com/tradeshows/showdoc.aspx?i=2716

Done with FX-60@2.8 All updated BIOS. So far things are not looking good for AMD from these results. Just remember that the mobo used on the intel is a normal one that is out right now so its nothing special.

 

[dwave]

The only fact is we won't know how good it will really be until it is sold to the public.

 

[linux_0]

This was an Intel controlled and administered test and just like any AMD controlled and administered test should BE IGNORED without a fair and properly administered test by an independent and objective 3rd party!!!

That's right folks I do not trust AMD's or Intel's own benchmarks!


The Fact is Intel chose the motherboard, CPU and drivers for a REASON.

It was an Intel controlled and administered test so it was automatically RIGGED.

I reject their results until the product actually launches and we can test actual PRODUCTION hardware.

I am just as skeptical about AMD benchmarks - so please do not try to challenge my statement.

Intel's marketing dept. routinely selectively publishes benchmarks in which their products beat AMD by a wide margin.

These benchmarks should be taken with a mountain of SALT -- most of the time they are RIGGED, FAKE, unreliable and highly questionable.

I want to see REAL, fair and properly administered tests by multiple independent and objective 3rd parties!!

Thank YOU

Live long and prosper

 

[endyen]

And to those who suggest that Anand knows which cup the pea is under, Anand is the one with the pea in his hand.
Just look at the # of hits his site has gained. That's pure gold.
Do you think for 1 second that Anand is interested in killing that goose?

(For those not used to the three cups and a pea trick, a mark is shown a pea being put under a cup. The gypsy then moves the three cups around, and bets the mark he cant guess which cup the pea is under. In reality, at that point, the pea is in the gypsy's hand.
I hope everyone knows of the tale of the goose that laid the golden egg)

 

[Schmide]

Seriously, from my perspective the numbers add up.

+10% 4mb cache
+10% 4 execution units
+5% SSE improvements
-5% Non-Ondie memory controller.

Now AMD would have to put out a DDR2 K8L with extra cache to even be competitive.

Although it may have come out of nowhere and blindsided AMD, at least they are making their transition to a new socket and may still have some crystals to insert.

 

[RowdyRob]

I have to disagree with you linux. The system setup is legit. Everything there, except the conroe, you are able to get right now. I understand what you are saying about it not being the final product. But if the final product and the preview has a 10%-20% difference... well i just dont think that is going to happen.

 

[Action_Man]

Anandtech wasnt the only site to run the benchmarks.

 

[endyen]

+10% 4mb cache
+10% 4 execution units
+5% SSE improvements
-5% Non-Ondie memory controller

1 for cache? This is not netburst, 3-5% is more realistic
2 This isn't Itanic, an extra EU will do a little,but only when out of order exec is busy.
3 May even be a little more.
4 Again not netburst, 5% is too high
You forgot the extra stages, that could be a major penalty. At 14 stages, it could be as high as 20%.

 

[endyen]

Oh yes, I'm sure that nexhex is far less interested in site hits than Anand.
Wonder what kind of lotery Intel used to pick who got the big wet kiss?

 

[Action_Man]

I'd imagine they would be.

 

[linux_0]

Let's compare Opterons vs. Xeons here:

Currently 2 x 940 CPUs with 1 OMC each and 4 stix of PC3200 have 2 TIMES the memory bandwidth = 12.8GB/s

4 x 940 CPUs with 1 OMC each and 8 stix of PC3200 have 4 TIMES the memory bandwidth = 25.6GB/s

8 x 940 CPUs with 1 OMC each and 16 stix of PC3200 have 8 TIMES the memory bandwidth = 51.2GB/s

In the Xeon line memory bandwidth is

1/2 with 2 CPUs

1/4 with 4 CPUs

It doesn't scale at all!


With socket 1207 AMD will be able to easily add Quad Channel RAM or Dual Memory Controllers for Dual-Core CPU's so:

You have 1 PHY CPU

2 cores

2 on board memory controllers

2xDual Channel RAM -- 2 stix / Core -- 4 stix total for TWICE the memory bandwidth!

In a 2way Dual Core SMP Opteron 1207 you would QUADRUPLE your memory bandwidth = 51.2GB/s MAX Theoretical Memory Bandwidth

In a 4way Dual Core SMP Opteron 1207 you would have 8 TIMES the bandwidth = 102.4GB/s MAX Theoretical Memory Bandwidth

in an 8way Dual Core SMP Opteron 1207 you would have 16 TIMES the bandwidth = 204.8GB/s MAX Theoretical Memory Bandwidth

It scales very well.

 

[ak47is1337]

Anandtech wasnt the only site to run the benchmarks.

Andandtech RERAN the tests and reviewed some problems they encountered. The problems involving drivers, BIOS, memory timings and such were addressed and it was decided the system was more than legit. The original test where Conroe held a +40% advantage was redone, and it got the 20% advantage predicted.
I highly doubt Intel somehow put a super-processor in their machine or hindered the FX60. They would be REALLY bad PR, and Intel owns AMD in sales because of marketing. They wouldn't be so retarded as to rig results and expect nobody to figure it out.

 

[apache_lives]

Seriously, from my perspective the numbers add up.

+10% 4mb cache
+10% 4 execution units
+5% SSE improvements
-5% Non-Ondie memory controller.

Now AMD would have to put out a DDR2 K8L with extra cache to even be competitive.

Although it may have come out of nowhere and blindsided AMD, at least they are making their transition to a new socket and may still have some crystals to insert.

Sorry i have to disagree, Cache doesnt matter really (all depends on architecture), Execution engines same deal, SSE improvements - as in SSE4 arnt used cause nothing would support it yet, and on die memory conrtoller (or lack of) would hamper performance, thats whats coming up after conroe i suppose, it supposed to come in 2008?

Look at the P4 design - 2x2mb cache didnt do anything, and northwoods 512k clock for clock the chip is quicker then the Prescott with 1mb cache.

Conroe is a Pentium M on steroids with twice the fsb, cache and an up to date alu/fpu etc aswell as the best bits from P4 added, the architectures potential shows, and it can get better as can AMDs design, altho Intels architecture may be better cause its only just begun.

Intel for once seems like its on track (looks to be the best run in history) and did everything right - Fast (P4 launch - slow, hot and expensive etc), Efficent (colder and faster then the previous gen), and schedual is looking good to keep infront of AMD - 45nm when AMD gets 65nm (and 3+ghz with headroom wheree as AMD is getting close to the 90nm limite, quite impressive actually), Quad core looking good and in 2008 integrated memory controllers for an even more impressive boost.

Im actually hoping AMD will return where they are in the AthlonXP days - cheap and quick (P4c was quicker, but still within the same class and ), and like those days that seemed bad for AMD they came back stronger then ever (A64 - best run sofar by AMD?), but on the other hand I dont think anyone would mind an X2-4400 for half the price then now even if performance isnt on par with Intels offering.

 

[Ycon]

All that theory looks nice, but it doesnt have anything to do with reality...
Conroe is a 4-issue core (w00t, 4-issue core, its gonna own everything!) but still any processor hardly can process 1 instruction per clockcycle.

@ topic:
Its obvious that AMD is not going to be able to match Conroes performance (I do think that everyone agrees on this one), but that means that AMD is finally gonna lower the extremely high prices of their dual-cores and perhaps even move the FX to sub-1000$. That would be a nice thing for some of my mates (AMD Fanboys) if they could finally get some dual-core

 

[Guest]

The only fact is we won't know how good it will really be until it is sold to the public.

That's the point. Everyone who claims else is just naive. plain and simple.

 

[Action_Man]

Um.

 

[ak47is1337]

All that theory looks nice, but it doesnt have anything to do with reality...
Conroe is a 4-issue core (w00t, 4-issue core, its gonna own everything!) but still any processor hardly can process 1 instruction per clockcycle.

@ topic:
Its obvious that AMD is not going to be able to match Conroes performance (I do think that everyone agrees on this one), but that means that AMD is finally gonna lower the extremely high prices of their dual-cores and perhaps even move the FX to sub-1000$. That would be a nice thing for some of my mates (AMD Fanboys) if they could finally get some dual-core

Man, its naive to think Intel will them take that sector too. Intel can mass produce, giving them the ability to produce really cheap fair performing processors. Celeron's are great and just toned down prescotts/cedar mills, and Intel has some cheap ass Pentium D's at 2.66/2.8 that are the cheapest dual core's you can buy. So, for performance versus price, AMD wins, but for sheer power of cheapness Intel has it.

 

[ak47is1337]

Um.

...?

 

[Action_Man]

The problems involving drivers, BIOS, memory timings and such were addressed and it was decided the system was more than legit. The original test where Conroe held a +40% advantage was redone, and it got the 20% advantage predicted.

 

[linux_0]

All that theory looks nice, but it doesnt have anything to do with reality...
Conroe is a 4-issue core (w00t, 4-issue core, its gonna own everything!) but still any processor hardly can process 1 instruction per clockcycle.

Let me ask you something.

Do you know how many operations per clock cycle a P4 can perform? How about an AMD64? Pentium M?

Please do tell.

Thank you.

@ topic:
Its obvious that AMD is not going to be able to match Conroes performance (I do think that everyone agrees on this one), but that means that AMD is finally gonna lower the extremely high prices of their dual-cores and perhaps even move the FX to sub-1000$. That would be a nice thing for some of my mates (AMD Fanboys) if they could finally get some dual-core

Forgive me, but your thesis is Conroe pwnz all? Is that correct? Yet you reject any CPU AMD might respond to the conroe with?

I presume you are an engineer working for AMD and are intimately familiar with all the cores they have under development.

 

[endyen]

And, for those who liked the Conroe preview, we have a preview of two Intel chips destroying an opteron

 

[linux_0]

So the original results were completely invalid.

Is that not what Anandtech actually conceded?

Several very bright people including people from VoodooPC knew these results were not right and Anandtech had to go back and correct them and admit there were problems with them.... hmm.... this does not pass the smell test or any other test for that matter.

Intel's entire marketing department deserves to spend 25-life in a federal resort for the wonderful job they did.

 

[linux_0]

And, for those who liked the Conroe preview, we have a preview of two Intel chips destroying an opteron

Oh my gosh..... in the name of all that is holly...... what kind of benchmarks are these????????

Where are the dual-core Opterons?!?

I'm sure I will catch a ton of heat about including a pair of Opteron 246s in this comparison. The truth of the matter is... They are the only Opterons I have to test with. I have been in touch with AMD recently to plead my case and they have promised to rectify this situation very soon. I will definitely rerun all the numbers (and add a few more, I'm sure) if/when that happens.

The author of the article admits this is not a fair test??? What are you trying to say here?

How would Intel like it if I compared an Opteron 285 against a Pentium I @ 60MHz without any cache??????

PLEASE!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!