Conroe (intel) vs AMD SERIOUS ONLY

[MU_Engineer]

AMD's dual-cores (or Intel's, or IBM's, or Sun's for that matter) aren't cheap, but they aren't *that* expensive anymore. Sure, they used to be $600 or more for the cheapest one, but now you can get an X2 3800+ for about $290- less than $100 more than the very midrange 3500+ single-core. I waited until now to buy an X2 as the price on the one I got (4200+) dropped by almost half since its introduction, and that saved me several hundred dollars.

Yeah, sure the FXs are expensive, but isn't Intel's Pentium D 955EE about a grand too? I remember the first Intel 3.06GHz HT chip being WELL over $1000. This is nothing new- it is just a ruse to separate the fool gamers from their overly large wallets while the rest of us can get reasonable chips with 80-90% of the performance for about 1/4 to 1/3 of the price.

 

[linux_0]

Yes, I think that the 20% numbers are more or less legit. 40% is an enormous gain but haven't the AMDs been beating the Intels by something around 20% in games and some number-crunching-intensive benchmarks for some time? The Opterons beat the Xeons even more that 20% in those apps.

I would fully expect that Intel would be able to pull a reversal of that with a brand-new microarchitecture, given its large resources to draw upon. If they merely matched AMD's year-old chips based on a 3-year-old core with their brand-spanking-new chip on a smaller process, Intel would face a stockholder revolution.

Ya know what AMD64s are still 25-70% faster in 64bit benchmarks so even if the Conroe really is 20% faster in 32bit mode BIG DEAL -- AMD64s will still be 5-50% faster in 64bit mode than Conroe in 32bit mode.

And the fact that Opteron memory bandwidth SCALES VERY well is another plus that Intel is going to have a hard time beating.

16 or 32 Opteron Cores inside 8 PHY CPUs with Dual or Quad on board controllers would offer 8 16 or 32 times the memory bandwidth.

Xeons still have to share memory bandwidth for the foreseeable future.

2 Xeons = 1/2 bandwidth

4 Xeons = 1/4 bandwidth

8 Xeons = 1/8 bandwidth ( theoretical )

16 Xeons = 1/16 bandwidth ( theoretical )

32 Xeons = 1/32 bandwidth ( theoretical )

 

[luminaris]

Yeah, I have take sides with linux here. I do agree that benchmarks from either company are just "sketch material" and we should only take them with a grain of salt.

I was thoroughly impressed with the testing performed and I do have my hopes up however, we're in the "now" and not the "later" so, until I get a conroe machine built on my bench, I myself, will not make any further assumptions.

I will say that Intel put on a good show and I was rather more impressed with the mobile side of things with the robson cache and where they're going in that market.

 

[MU_Engineer]

Oh, I wasn't saying which chips are better 😉 I was only stating the fact that it is not *suprising* to see this. Any way you look at it, 2007 will be a very good year for computer users.

And yes, it is pretty surprising to not see Intel bench its much-lauded dual-dual "quad" core Kentsfield that it is supposed to also have sort-of ready. That one I think Intel will not win, and for the reasons you state. They will do okay in single-socket setups, but do worse and worse in dual, quad, and 8-socket setups.

They do have two independent FSBs, but two FSBs for four cores brings them back to the problem they had with the Smithfield two-single-cores-on-one-die chip. About the only way that Intel can try to have any sort of performance with that architecture is to massively increase the FSB. I have heard a quad-pumped 600MHz ("2400MHz") bus is possibly in the works. And then maybe eight cores on a board is about as high as they can go.

 

[conroe]

They did bench quadcore, with cinebench. I don't know anything about that bench but people at XS are impressed.

 

[cisco]

One thing that you really need to know is that these are only initial results. In general all companies always cherry pick the processors that are used in these type of tests. It is easier to make one very fast processor than one million. Not to mention that most of the benchmarks were designed by Intel. But all that aside until it can be confirmed from benchmarks not created by Intel, you really don't know exactly what we have yet. If you remember we saw a 4ghz P4 being demonstrated in 2003 and we never actually saw one on the market. I'm not saying this is a direct parallel. I'm just saying until you see it on the market the way they state it, take it with a grain of salt. I believe Conroe will be on the market, obviously, but before I just hand them the crown I actually want to see the processor made available to the public with performance promised. It doesn't look good right now for AMD simply because the only release they have made in the way of the AM2 shows no real performance gain. Granted this was not the final model that is designed to run with 800mhz ddr2 but I can guarantee you that IF the Intel benchmarks hold up, AMD will not answer with the initial AM2 release. I would look for AMD's real answer to come from their 65nm chip at the end of the year. These are just the facts I love AMD so I am being honest and impartial. I am not loyal to any company that doesn't pay me. People who are fanboys to inferior products are just idiots. If they are paying you fine, but if you are spending your money why reward someone for an inferior product. I own Intels and AMDs, Nvidia and ATI. I buy whatever is the best in price range I'm looking at.

 

[pip_seeker]

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

Fanboy doesn't even describe you. sheesh.

 

[ltcommander_data]

Ya know what AMD64s are still 25-70% faster in 64bit benchmarks so even if the Conroe really is 20% faster in 32bit mode BIG DEAL -- AMD64s will still be 5-50% faster in 64bit mode than Conroe in 32bit mode.

It really wouldn't be fair to compare K8 running on 64-bit mode to a Conroe on 32-bit mode. I have no idea how Conroe will do in 64-bit mode so I'm not really going to comment on it. We can only hope that Intel decides to do it right this time since they have an opportunity to design and integrate it from the ground up.

2 Xeons = 1/2 bandwidth

4 Xeons = 1/4 bandwidth

8 Xeons = 1/8 bandwidth ( theoretical )

16 Xeons = 1/16 bandwidth ( theoretical )

32 Xeons = 1/32 bandwidth ( theoretical )

Now that isn't exactly correct. Intel is introducing dual and quad FSBs so both 2 and 4-way systems will operate with full bandwidth with 1333MHz per chip. Going up to 8-way or when quad cores are introduced, Intel will probably be able to squeeze by since the Yonah architecture that the Core family is based on doesn't seem as memory bandwidth hungry as Netburst, and the larger caches will help too. It's not the most elegent solution by any means, but if it works out in the end thats really all the matters. Now for 16 and 32-way systems, Intel is hopeless.

 

[Caboose-1]

Well I am surpised that there isn't (that much) fanboyism. I personally have no idea which chip to place my bet on. Conroe is getting all the spotlight because its the chip closest to launch, and the fact that it was "tested," raises eyebrows with fanboys I mean enthusiasts. Then they will gossip of course.

 

[pip_seeker]

yeah it's really too soon to say what will happen, it's only natural that if a company was working on something new and they made a release they would do whatever they could to paint that product as the best thing since the light bulb.

I mean if you have a product that you had been working on for 6 months or whatever you're not going to say... "Well we tried to beat xyz company, better luck on the next generation, please continue to buy our products our R&D needs the money as well as our PR machine." :lol:

Personally I kinda hope Intel's Conroe lives up to the claims, I've got my eyes on a Amd x2 4800+ dirt cheap! 😛

Plus we'll see Amd ramp it up even more, so nothing but good things can come from it. Even if Intel flubs it, with what they've shown Amd will likely be very close to beating these anyways.

The only thing Intel can test against is what we have today, Assuming Amd is standing still Intel would win. But we all know what happens when you assume.

 

[RichPLS]

Actually, AM2 is the chip closest to launch, it is Conroe that boasts the best performance and price together.

 

[pip_seeker]

Actually, AM2 is the chip closest to launch, it is Conroe that boasts the best performance and price together.

Oh really, where is the price list for conroe? :?

 

[conroe]

Another AM2 bench, and this is the fixed one. I dont understand much of it.
http://www.computerbase.de/news/hardware/prozessoren/amd/2006/maerz/cebit06_athlon_64_x2_am2_benchmarks/
translted - http://translate.google.com/translate?u=http%3A%2F%2Fwww.computerbase.de%2Fnews%2Fhardware%2Fprozessoren%2Famd%2F2006%2Fmaerz%2Fcebit06_athlon_64_x2_am2_benchmarks%2F&langpair=de%7Cen&hl=en&ie=UTF-8&oe=UTF-8&prev=%2Flanguage_tools

Then this at the INQ,
http://www.theinquirer.net/?article=30221

Oh really, where is the price list for conroe?

http://forums.extremeoverclocking.com/showthread.php?t=206422

 

[Caboose-1]

Actually, AM2 is the chip closest to launch, it is Conroe that boasts the best performance and price together.

Thats good news.

 

[RichPLS]

The 2.67GHz Conroe as tested and creating the buzz is anticipated to launch at $530, and the Intel dual core 805 currently can be had for $140...
So once again, seems believable but time will tell within 4 months...
Even if it launches at a high end of $700, it still appears to be faster than AMD's fastest, and still cheaper...
Who knows tho till it gets here, by that time, AMD may decide to sell their FX-62's for $400... That would probably keep me with them if I saw that kind of action taken... Otherwise, I will buy the best performance for my budjet, even if it is Cyrix that is the true WINNER! :twisted:

 

[conroe]

Those prices are leaked by moles in Intel, and with almost all oter info being correct it's safe to bet on it being too.

A 2.9ghz ~$800, and a 3.33 XE ~$1000 fits the price scale.

 

[ltcommander_data]

Oh really, where is the price list for conroe?

Here:

http://www.dailytech.com/article.aspx?newsid=787

The Pentium D pricing for the next few months is also here:

http://www.digitimes.com/news/a20060213PR218.html

 

[ak47is1337]

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.

right? and..?

 

[ak47is1337]

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.

The reason they were originally very, very wrong is because of Anandtech's stupidity. They set the resolutions wrong for a few games, so obviously the Intel got much higher FPS. They determined it was highly unlikely Intel staged it.

 

[ak47is1337]

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!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
that test would be awesome

 

[pip_seeker]

Oh really, where is the price list for conroe?

http://forums.extremeoverclocking.com/showthread.php?t=206422


Ok where do I go to buy one? ROFLMAO :lol:

 

[conroe]

If you find one get one for me, a E6700 please.

 

[pip_seeker]

Oh really, where is the price list for conroe?

Here:

http://www.dailytech.com/article.aspx?newsid=787




Lovely, I wonder what those ??? next to the prices mean? :lol:

 

[RichPLS]

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

Didn't realize AMD was this threatened by Intel...
If fanboi's feel that one of Intel's Dempsey xeon's against a pair of Opteron 146's are similar to benching a Opteron 285 against a Pentium 1 at 60MHz with no cache... Then AMD must be on dark times indeed... :roll:

 

[ak47is1337]

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

Didn't realize AMD was this threatened by Intel...
If fanboi's feel that one of Intel's Dempsey xeon's against a pair of Opteron 146's are similar to benching a Opteron 285 against a Pentium 1 at 60MHz with no cache... Then AMD must be on dark times indeed... :roll:
=P would still be funny to have 2 charts on 3dmark: one with 10, the other with several thousand =D
However, server users are more for power management than performance, and the fact is that Intel could very well overtake AMD with 65nm should they need to become competitive in the server markets again.