Conroe (intel) vs AMD SERIOUS ONLY

[Action_Man]

So the original results were completely invalid.

How so? There's practically no difference between both results.

Is that not what Anandtech actually conceded?

Nope.

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

What problems?

In the media encoding tests we saw absolutely no performance impact other than a 1 second reduction in iTunes encoding time. F.E.AR. at 1024 x 768 saw a reasonable gain of 4%. Quake 4 remained virtually unchanged.

 

[linux_0]

So the original results were completely invalid.

How so? There's practically no difference between both results.

Is that not what Anandtech actually conceded?

Nope.

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

What problems?

In the media encoding tests we saw absolutely no performance impact other than a 1 second reduction in iTunes encoding time. F.E.AR. at 1024 x 768 saw a reasonable gain of 4%. Quake 4 remained virtually unchanged.

This power consumption graph is AWESOME

The new Intel CPUs clearly pwn the Opterons!!!!!!!!!

I will have to write my congressional delegation and urge them to buy as many of those machines as possible so we have to import more oil from the Middle East and totally trash the environment.

This is GREAT!!!!!!!!!!

OPEC is going to LOVE us!!!!!!

 

[linux_0]

Here are some real benchmarks:

http://www.linuxhardware.org/article.pl?sid=05/02/24/1747228&mode=thread

http://www.anandtech.com/linux/showdoc.aspx?i=2163

http://www.intel.com/performance/desktop/extreme/em64t.htm

I will post some REAL Conroe benchmarks as soon as Intel releases a production version of the Conroe and the new Xeons.

 

[Action_Man]

Thanks for completely ignoring everything I said and linking to a power consumption chart and ranting about it in large type.

 

[Action_Man]

Yes we're all aware the opterons are better then the P4 xeons.

 

[linux_0]

Thanks for completely ignoring everything I said and linking to a power consumption chart and ranting about it in large type.

Please forgive the large type some people on these forums have trouble reading small type.

I apologize.

 

[Action_Man]

Yes I can see that.

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

Never heard of that site before.

 

[linux_0]

Yes we're all aware the opterons are better then the P4 xeons.

Thank you sir!

And we can all agree the Conroe is better than the P4s as well because it is based on the PIII / P6 architecture which is better than the P4 netburst architecture.

The Israeli Intel team did their homework and for that they deserve our respect!

How much better remains to be seen when the production version is released and compared to the new production version AM64s.

 

[endyen]

Actually, there were two sites that gave the same scores. The other was german. For prescott's 20%, the review came from a japanese site. It was 20% faster than the northwoodC.
Begin to understand why I dont believe Intel's 20% faster previews?
After the dust settles on conroe, I will bring one home, and test it. It wont get my seal of approval for my customers before that.

 

[Action_Man]

Actually, there were two sites that gave the same scores. The other was german. For prescott's 20%, the review came from a japanese site.

Well to be fair they aren't high profile sites.

Begin to understand why I dont believe Intel's 20% faster previews?

Oh definately but Intel knew they had a dud and thats when things like that happen, just like Nvidia with the FX series.

After the dust settles on conroe, I will bring one home, and test it. It wont get my seal of approval for my customers before that.

I agree, always best to do things yourself.

 

[Atolsammeek]

I agree. I rather see 3 or 4 differnt tech sites to get real facts. I dont care if Intel or amd wins. I would like the public to know.

 

[linux_0]

I agree. I rather see 3 or 4 differnt tech sites to get real facts. I dont care if Intel or amd wins. I would like the public to know.

Thank YOU!

I applaud you SIR! :trophy: :trophy:

 

[apache_lives]

I agree. I rather see 3 or 4 differnt tech sites to get real facts. I dont care if Intel or amd wins. I would like the public to know.

Thank YOU!

I applaud you SIR! :trophy: :trophy:

i second that, if only mike would agree to that!!!!

 

[linux_0]

I agree. I rather see 3 or 4 differnt tech sites to get real facts. I dont care if Intel or amd wins. I would like the public to know.

Thank YOU!

I applaud you SIR! :trophy: :trophy:

i second that, if only mike would agree to that!!!!


I say we wait and see.

Patiently.

 

[Atolsammeek]

I say this I use both systems. Each systems has good years and bad years. You can say this with everything. To stock market to Gold and silver prices. (That why I buy gold and silver when they are cheap and sell them when they are high)

But one note I dont want Intel or Amd to fall. If it happens we will be paying higher prices.

Amd athlons where great for a while untel what 2200+ Then intel seem to be king untel moving from northwood to presscott. Then amd seem to be king. If intel wins some it will show each company has good years and bad ones. I dont care about that.

One major fact when it get to 1 to 20% differnce in speed You really dont tell a differnce. But when it get higher we might see a differnce.

 

[CompGeek]

That's my only concern right now. I've been waiting and seeing for quite a while and really,if it weren't for Pressler 2005 would have ended a lot worse. I'm positively sure Intel has learnt their lesson and that Conroe will beat AMD M2 socket. By what margin,we'll see.
AMD stated they haven't got ANYTHING special for 2006. Maybe the Conroe results made them change their mind? Hope so cause if there is no real competition Intel will raise prices sky high(like AMD did with the FX single cores).

 

[Atolsammeek]

ComputerGeek In anyrate what will happen. It will help lower prices in both systems if amd loses. If intel loses They will lower there prices. It the only safe way for any company. It also might force amd to get into the lower nm.

 

[mdd1963]

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

Nonetheless, the press was given a chance to clearly view bios settings, device drivers, game versions/demos, and a nice wide variety of games were benchmarked, and the 20% margin of victory was pretty much across the board, including games (UT2k4) which had been previously known as being rather "weak for Intel".

I, for one, hope AMD can close this gap to perhaps as little as 10% with a tweak here and there and use of DDR2/1066 or 1333, etc...; but as it appears now, this will be a case of the P2-350 vs. K6-2/350, and the COnroe is looking quite nice! (Dare we even hope for the Conroe to successfully OC by even 200-400 MHz?)

All we desktop fans need now is, a good 'ole fashioned pricewar, with COnroes available for $199! 🙂

 

[Cochise]

But one note I dont want Intel or Amd to fall. If it happens we will be paying higher prices.

EXACTLY!! As has been said many times before....the competition is good for us all (consumers).

/wipes drool from mouth - low priced opty

 

[Atolsammeek]

What I do Cochise is watch both companys and view the facts when they come in. One website will show anything. It a group of comapanys that show facts. It like Antivirus programs if one could delete all virus we would not have to use 2 3 antivirus programs.

All we can do is wait and see what Amd dose. If they lose they will work on something better. If they dont they will do like they been doing for the last year. Keep the crown and wait. I hope intel wins so it Forces Amd to work on new tech and give us something to hope for.

 

[CompGeek]

Well that's the main reason why i love competition and i love it more if Intel is ahead 😀 (fanboyism eh).

 

[Atolsammeek]

I love the leap froging of both systems. I wish Amd was as strong as Intel. But That a another matter. But price ver cpu I agree with u. Right now both my computers are Intel. But there two laptops. But we all know Intel make better laptops. But later Amd might change that. like intel might make a better server. Or cpus. That three jumps of each

I hope it something like this

Amd wins in Servers for a while then intel wins
Intel wins at desktops for a while and then amd
Intel wins at Laptops for a while then Amd wins.

So at least Amd wins 1 or 2 of the 3 as intel. wins 1 or 2 at a time Out of 3. So neather company is doing bad.

 

[MU_Engineer]

Supposedly the biggest increases with the Conroe vs. the Core Duo are higher clock speeds, four FPUs and ALUs per core (up from something like 1 and 2 per core), twice the shared cache, and a 1066 MHz FSB. I think that #1 and #3 are really the big deals in the performance increase as the Pentium M architecture has weak FPU performance vs. the K8s and Intels have been memory bandwidth-starved, and it gets even worse as you have TWO CPUs fighting for the same FSB with the Core Duo.

And last but not least, they are supposedly going to be less expensive than AMD's comparable chips.

 

[MU_Engineer]

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.

 

[conroe]

Anand said he would have one in his lab soon.
Intel said, "sooner than you think."
20% did not come from "rigging." That's mindless.
The Pixar guys story at IDF showed even in the sever front Intel will have a large lead. He is using them now for the next movie, "Cars."

The 128 bit SEE will do all SSE instructions in one clock, other cpus will need two. Macro opp fusion will eleminate many more cycles. The four issue core will give even more IPC. New prefetch will keep the out of order execution working with very few pipeline stalls. That is not all of it, just what comes off the top of my head.