Conroe debunked

[DejaWiz]

Comparing Conroe die size to Windsor is very legitimiate, as they will be out in the same time frame, as AMD will be still on the 90nm DSL SOI process when Conroe ships, AMD has no one to blame but itself for this. It's not Intel's problem that it is 9-12 months ahead of AMD on the 65nm transistion.

The comparison is legtimate becuase AMD will still be using 90nm technology when Intel is using 65nm such is the problem when your slower then your competitor on process transitions.

AMD will still be on 90nm and intel is 6-12 months ahead of AMD on the 65nm transition? ......You make it sound like there is a set date that all cpu manufacturers have to move to 65nm or the world will come to an end.


AMD designed their A64 core for efficiency so it will naturally have a long market life. They don't need to move to 65nm the exact same day intel does in order to catch-up.

I'm very happy that intel finally got their shit together and is releasing a processor that shows signs of substantial strength in almost every comparison benchmark test run so far, but this new Conroe isn't going to bury AMD outright. It isn't even available yet. Just like AMD 65nm processors aren't available yet. We can't trust data from preliminary testing until a majority of the tests run are by independent reviewers (we all should know better than this!).

I think Conroe will be a great product from intel, and if it happens to be better than AMD's first 65nm offerings, then I might upgrade to one.

This depends greatly on a number of things though:
1. Overall system price (cpu + motherboard + memory, etc).
2. Operating temperature.
3. Operating cost (annually).
4. Overall Efficiency (without overclocking).
5. Gaming performance, gaming performance, gaming performance!

It makes me lol at everyone getting stiff e-winkies because intel may actually release a product that will surpass what they have been trailing in for the last few years..overall processor performance. Too bad it took them yet another die shrink to maybe have accomplished that. I say to all these people: Go rub one out already and then wait until the product is on the shelves before assessing it and popping wood.

 

[Jmzais]

Why on earth would AMD having no financial reosurces be Intel's problem?

Because it's not fair!! [/sarcasm] Just waiting for some liberals to come in here and say that..

I wouldn't call Intel's spending "squandering". Developing new products isn't cheap, let alone something so specialized.

 

[kemist1117]

Comparing Conroe die size to Windsor is very legitimiate, as they will be out in the same time frame, as AMD will be still on the 90nm DSL SOI process when Conroe ships, AMD has no one to blame but itself for this. It's not Intel's problem that it is 9-12 months ahead of AMD on the 65nm transistion. . . .

The comparison is legtimate becuase AMD will still be using 90nm technology when Intel is using 65nm such is the problem when your slower then your competitor on process transitions.

While those statements are true to a certain extent. The april 4th post on http://penstarsys.com/ puts these statements into perspective.

heres a snippet:

For the past four months we have been hearing a lot about Intel's 65 nm process and the products being released on it. Unfortunately, I think that there is a lot of misunderstanding about where Intel exactly is at, as well as how their roadmap is shaping up. As tech enthusiasts we tend to be quite optimistic about how a certain product family or process node is going, because we simply want to see these new products and lines come forward as soon as possible so we can see the results and buy these new products. This optimism often leads us into making fallacious claims about the healthiness of a certain design or process node. Intel has a great marketing group, and with two Intel Developer Forums a year to spread the good word of Intel, we are often inundated with very positive information about Intel's products and production lines. This little editorial is not meant to reflect poorly on Intel's products and processes, but rather to help ground people in the fact that Intel is not perfect and they have to work hard to get these products and nodes out.

 

[FlyinBrian]

They could do what all of Microsoft's competitors do and sue them for being unfair and having a monopoly or any other BS they can bring to the courts. It annoys me greatly that a company is sued for being successful. Is it intel's fault amd is behind this year ? no.

When you have been building machines as long as I have you really quit being a !!!!!!* (if you like that term) and you start just loving technology period.

Admit it or not the truth is Intel's product based on what we do know about it seems to be much faster than anything AMD has or has coming out anytime soon. Combine that with the relative low cost of 65nm technology and the possibility of building a budget gaming machine that will beat a 2000 dollar gaming machine built using AMDs FX 60 OC'd or not doesnt matter is quite exciting and will probably inspire me to get rid of my Athlon 3500 OC'd 2.6gh and throw in a Conroe.

 

[r0t0man]

Wait, how did this thread get into the Intel forum? It was moved from the AMD section to Gen Hardware for being "flame bait". Now its here... lol wut?

 

[Donnie27]

Conroe performance claim being busted

Make of it as you will. The guy is clearly an AMD zealot. but he does make some good points.

One thing or should I say Name, "Sharikou". For those who know, this guy makes Van Smith look like an Intel Fan. I saw some of this guys stuff when he, just like Van Smith, said Intel should been out of the CPU business by now.

Example;
http://sharikou.blogspot.com/2006/02/we-all-live-in-aftermath-of-1ghz.html

1) Jan 2000: 1GHZ Athlon - with the goodies

2) Aug 2000: INTEL Pentium III at 1.13GHZ rushed out but recalled, INTEL found it impossible to push P3

3) Nov 2000: INTEL Plan B, 22 stage hyperpipeline Pentium 4 jacked up frequency to 3GHZ later

4) 2001: AMD abandoned the frequency fight with Athlon XP, but worked on 64 bit Hammer day and night

5) 2002: Meanwhile, INTEL marketing almost drove AMD to extinction using exclusive deals, AMD stock fell to $3

6) Jan 2003: INTEL dudes got over zealous, aiming 10.2GHZ Nahelem in 2005, 20GHZ to 100GHZ later

7) Feb 2003: Four Intel teams failed to do 64 bit on x86, and they didn't believe AMD could do it

8) Apr 2003: AMD came out with the 64 bit Hammers (AMD64), with better performance and perf/watt , pulled down version for desktop the Athlon 64 was released a bit later

9) Nov 2003: AMD start building new FAB

10) Feb 2004: INTEL execs got desperate, P4 pipeline jacked up to 38 stages, but no more performance, only more heat

11) Oct 2004: INTEL found 4GHZ impossible, silicon was melting. INTEL CEO admitted blindly racing at 200mph without noticing the brick wall ahead.

12) June 2005: INTEL does more exclusive deals, AMD hauled INTEL to Court

13) Sept 2005: AMD64 sales jumped up instantly

14) Jan 2006: INTEL goes back to 32 bit P3, but changed the name to Core (Core Duo, Core Solo)

15) Today: AMD cranking out AMD64 chips like crazy

Is this fiction clear enough? Now AMD fans might swallow such Crap but common sense says otherwise. All of the other link to his other BS is even worse. Just repeats of some of the most extreme Fan views ever posted then he quotes it.

 

[SLee]

The main programmer of ScienceMark likes what he sees so far from Conroe:

http://www.aceshardware.com/forums/read_post.jsp?id=115161094&forumid=1

 

[Donnie27]

Conroe performance claim being busted

Make of it as you will. The guy is clearly an AMD zealot. but he does make some good points.

http://techreport.com/reviews/2004q4/athlon64-fx55/index.x?pg=13

ScienceMark is optimized for SSE, SSE2, 3DNow! and is multithreaded, as well. In the interest of full disclosure, I should mention that Tim Wilkens, one of the originators of ScienceMark, now works at AMD. However, Tim has sought to keep ScienceMark independent by diversifying the development team and by publishing much of the source code for the benchmarks at the ScienceMark website. We are sufficiently satisfied with his efforts, and impressed with the enhancements to the 2.0 beta revision of the application, to continue using ScienceMark in our testing.

Now, for the very first time, someone actually got hold of a Conroe chip in their own lab and did some tests. It was a 2.4GHZ Conroe (Link: CPU-Z) against an Athlon 64 overclocked to 2.8GHZ. The overclocked Athlon 64 had a 2.8/2.4 -1 = 16.7% clockspeed advantage.

The following results were obtained by running 32 bit ScienceMark binaries optimized for Intel

This is BS, hehehehe! Simply ask Victor Wang if he'd want a Conroe or a 3GHz Athlon Single Core or a 2.8GHz X2? Saying AMD is honest is a lauffer at best. AMD wouldn't have hired Tim Wilkens and then continued to fund him if he truely optimized for BOTH Processors. There weren't any optimized for Conroe software=P

Even after this guy is proven wrong, he'll continue to post as if his other 50 wrong stories were dead on.

 

[DejaWiz]

Is this fiction clear enough? Now AMD fans might swallow such Crap but common sense says otherwise. All of the other link to his other BS is even worse. Just repeats of some of the most extreme Fan views ever posted then he quotes it.

While I agree with you for the most part of it being ridiculous fan!!! fiction, I do remember reading articles like the cancellation of the 4GHz Pentiums on sites such as CNet and MSN in the past. I don't put much faith at all in The Inq, and they were the site boasting claims to intel's 10 GHz parts. I strangely find much of what Sharikou states in that blog post about intel to be true for the most part. The only problem I see here is that he is taking the golden moments of AMD and pitting them against the toilet moments of intel to load one side of the balance. Hell, not once did he mention that intel had plans for Prescott and Tejas all the way back to early 2003 and Merom plans as well as having taped out their first dual-cores back in mid-2004. Oops wait, I guess that is the same thing as vaporware because there weren't any engineering samples of those back then.

I for one am glad that some ES of Conroe are in the hands of a few right now. It gives more insight to just how these new processors will perform in a variable use environment (not controlled/optimized...unless the recipients of said ES's are bound by an NDA and can only report fud).

Conroe looks to be an exciting new technology, but I'm certainly not going to throw my eggs at a rock until I know they won't break. I'll be waiting until Conroe and it's supporting motherboards are released to guage just how much of a cost/performance advantage it has over intel's competition.

 

[Scali]

Sciencemark...
Well I happen to know some of the guys who worked on it, I think... Sean 'Vulture' Stanek, and another one... his name escapes me.
Thing is, they were pretty much the most AMD-biased coders I know, and they did everything in their power to make the benchmark run as fast as possible on AMD CPUs.
Which is fine ofcourse, but it would explain why it's the only benchmark that doesn't run well on Conroe. Most other code is more 'neutral', and in that case the Conroe seems to fare better.

 

[Tetrahedron]

Sciencemark...
Well I happen to know some of the guys who worked on it, I think... Sean 'Vulture' Stanek, and another one... his name escapes me.
Thing is, they were pretty much the most AMD-biased coders I know, and they did everything in their power to make the benchmark run as fast as possible on AMD CPUs.
Which is fine ofcourse, but it would explain why it's the only benchmark that doesn't run well on Conroe. Most other code is more 'neutral', and in that case the Conroe seems to fare better.

hehe.. then I guess the 'Conroe' isnt that good, you mean it cant run AMD optimize code better than AMD, then what good is it.. sounds like a loser to me ......... just kidding

 

[mwarps]

Comparing Conroe die size to Windsor is very legitimiate, as they will be out in the same time frame, as AMD will be still on the 90nm DSL SOI process when Conroe ships, AMD has no one to blame but itself for this. It's not Intel's problem that it is 9-12 months ahead of AMD on the 65nm transistion.

*snip because math is wrong*

The comparison is legtimate becuase AMD will still be using 90nm technology when Intel is using 65nm such is the problem when your slower then your competitor on process transitions.

Again, people need to read before they go having a fight on the intarweb.

The assumptions stated in my mathematical arguement were sound. The inability of the reader to read and determine their actual meaning is not my problem. I did make a booboo in saying that at 90nm it would be 21mm square, it would only be 19mm square. My bad.

However, the use of linearity in die area shrinking is wrong. If a measurement is shrunk 28% linearly(90 to 65 is 28%) (.72K) (and it is, as die shrinks are done linearly with a K factor) it is squared when you do area, yielding 52%, so the sixty percent means truly nothing. [Assuming that *all* CD scaling is linear. VLSI guys, correct me if I am wrong]

Also, as we are not in possession of a set of photomasks of each of these designs verifying that the only pristine difference is a die shrink, the comparisons in die sizes between different products is utterly irrelevant.

So, again, we are left with the simple problem of this. AMD doesn't have 65nm yet. Intel does. Where does that leave AMD? Behind. Comparing a three-months-from-now process and architecture against a three-year old architecture and one-year old process? Pointless. There is no competition. The Conroe will win effortlessly (assuming all the hype is true).

*AMD F4NB0Y ADMITTING DEFEAT* Film at 11. Eat it up, boys, You've had it 3 years in the waiting.

My next chip will be a Conroe (assuming the hype is correct.) 1 cycle SSE dispatch? Shiver me proteins boys, she folds like a banshee!!!

 

[$BangforThe$]

This is really funny as last week I think Donnie27 or poncho said Science mark was soon to become the worlds most important benchmark. Donnie 27 you call them like we see them. LOL LOL LOL . Super PI is all cache related right. AMD is out there tring to do damage controll. That link was funnier than even the Voodoo link. Donnie when you read this get a link to the remark you made last week. Dam you beat me to the post on that one.

 

[coldpower27]

AMD will still be on 90nm and intel is 6-12 months ahead of AMD on the 65nm transition? ......You make it sound like there is a set date that all cpu manufacturers have to move to 65nm or the world will come to an end.


AMD designed their A64 core for efficiency so it will naturally have a long market life. They don't need to move to 65nm the exact same day intel does in order to catch-up.

I'm very happy that intel finally got their shit together and is releasing a processor that shows signs of substantial strength in almost every comparison benchmark test run so far, but this new Conroe isn't going to bury AMD outright. It isn't even available yet. Just like AMD 65nm processors aren't available yet. We can't trust data from preliminary testing until a majority of the tests run are by independent reviewers (we all should know better than this!).

I think Conroe will be a great product from intel, and if it happens to be better than AMD's first 65nm offerings, then I might upgrade to one.

This depends greatly on a number of things though:
1. Overall system price (cpu + motherboard + memory, etc).
2. Operating temperature.
3. Operating cost (annually).
4. Overall Efficiency (without overclocking).
5. Gaming performance, gaming performance, gaming performance!

It makes me lol at everyone getting stiff e-winkies because intel may actually release a product that will surpass what they have been trailing in for the last few years..overall processor performance. Too bad it took them yet another die shrink to maybe have accomplished that. I say to all these people: Go rub one out already and then wait until the product is on the shelves before assessing it and popping wood.

Nope, that is not what I am trying to convey, I said nothing on the fact that AMD won't be competitive without the 65nm process, all I am saying is that Intel is ahead 9 -12 months ahead on the 65nm transisition.

AMD will survive at 90nm SOI, but they have to do it at increased cost in relation to Intel , as their dies are larger not to mention the use of SOI technology which further increases their cost relative to Intel. They won't die but their potential for profits are lower then Intel 's.

If you wish to compare it to AMD's 65nm offerings your going to have to wait till H1 2007, as that is when AMD will start shipping 65nm products for the desktop. By this time Conroe would have gained a speed grade or 2, so this puts thing likely further in Conroes favor but we will have to see.

Overall system price shouldn't not be a problem, Intel will have i965 Broadwater Series chipsets for the mianstream people and their prices should be inline with what the i945 Series costs now. Memory shouldn't be an issue either as you can get value 2x1Gb DDR2-667 with 5-5-5-15 and they still work just fine with Conroe. The E6600 will be 316US representing a good cost on the processor itself AMD will have to do a massive price cut in order to match this. an Athlon FX 62 would have to be around 275US in order for AMD to remain competitive performance wise, that is massive drop for AMD to have to bear, but we will see if they can pull that one off.

Energy efficiency wise, Conroe should have the crown as Intel designed Conroe with performance/watt in mind. Gaming performance shouldn't be an issue either from hwat we have seen, but I will reserve final judgement till the product is launch the preliminary results look extremely promising.

Again why build Conroe on 90nm technology when they have access to a more economical 65nm to use and deliver us a great power efficient product at low prices.

 

[Donnie27]

This is really funny as last week I think Donnie27 or poncho said Science mark was soon to become the worlds most important benchmark. Donnie 27 you call them like we see them. LOL LOL LOL . Super PI is all cache related right. AMD is out there tring to do damage controll. That link was funnier than even the Voodoo link. Donnie when you read this get a link to the remark you made last week. Dam you beat me to the post on that one.

Just like I said. It presents a thread of Hope and Wa-La, its important It was I who said it.

 

[coldpower27]

Again, people need to read before they go having a fight on the intarweb.

The assumptions stated in my mathematical arguement were sound. The inability of the reader to read and determine their actual meaning is not my problem. I did make a booboo in saying that at 90nm it would be 21mm square, it would only be 19mm square. My bad.

*straight math conversions are uesless, you never get perfect optical shrinks*

Also, as we are not in possession of a set of photomasks of each of these designs verifying that the only pristine difference is a die shrink, the comparisons in die sizes between different products is utterly irrelevant.

So, again, we are left with the simple problem of this. AMD doesn't have 65nm yet. Intel does. Where does that leave AMD? Behind. Comparing a three-months-from-now process and architecture against a three-year old architecture and one-year old process? Pointless. There is no competition. The Conroe will win effortlessly (assuming all the hype is true).

*AMD F4NB0Y ADMITTING DEFEAT* Film at 11. Eat it up, boys, You've had it 3 years in the waiting.

My next chip will be a Conroe (assuming the hype is correct.) 1 cycle SSE dispatch? Shiver me proteins boys, she folds like a banshee!!!

60% means more then you would like to believe, you can never simply use theoretical conversions and label them as correct. The 60% figure is more real world and represent smore on the lines of what is gained in actuality from a die shrink then theoretical caclulation will give you. You don't need all available information to accertain what a die shrink will cause what effects, using past optical transistion as a guideline is a good place to start and shouldn't leave you too far off from where the actual size will be.

I imediaitely noticed your math is off from when you stated the 440mm^2 figure as there is no way in hell, that Conroe would be that size on 90nm node. Double an X2 my ass lol. Assuming atrociously incorrect figures for Conroe die size on 65nm and then doing math on those would lead to incorrect figures on 90nm as well, and then comparing to the correct figure for X2, is simply atrocious and represents distorted reality. If you wanted to do a comparison to X2 figures then you should have used more accurate numbers for Conroe's 65nm size from the get go and this situation would not have occured.

Like I said it's is legitimate becuase at the time of comparison it will be the best both parties have available at the time. Same as when by the time AMD has 65nm Brsibane cores for Athlon 64x2, they would have to be compared to a higher speed bin of Conroe as by that time Intel will have released higher speed bins. AMD new architecture is still a ways off we aren't gonna wait around till AMD has an upper hand and then compare rofl, you compare what is out at the current time to what is out at the current time. Intially Conroe will be compared to Windsor because at that particular time Windsor will be all AMD has.

 

[Donnie27]

While I agree with you for the most part of it being ridiculous fan!!! fiction, I do remember reading articles like the cancellation of the 4GHz Pentiums on sites such as CNet and MSN in the past. I don't put much faith at all in The Inq, and they were the site boasting claims to intel's 10 GHz parts. I strangely find much of what Sharikou states in that blog post about intel to be true for the most part. The only problem I see here is that he is taking the golden moments of AMD and pitting them against the toilet moments of intel to load one side of the balance. Hell, not once did he mention that intel had plans for Prescott and Tejas all the way back to early 2003 and Merom plans as well as having taped out their first dual-cores back in mid-2004. Oops wait, I guess that is the same thing as vaporware because there weren't any engineering samples of those back then.

I for one am glad that some ES of Conroe are in the hands of a few right now. It gives more insight to just how these new processors will perform in a variable use environment (not controlled/optimized...unless the recipients of said ES's are bound by an NDA and can only report fud).

Conroe looks to be an exciting new technology, but I'm certainly not going to throw my eggs at a rock until I know they won't break. I'll be waiting until Conroe and it's supporting motherboards are released to guage just how much of a cost/performance advantage it has over intel's competition.

There's an Intel of Paul Otellini before he became Boss at Intel. It was called something like The Brainiac vs The Speed Demon. It was about how Intel would have to move to something different than Netburst and 10GHz.

First read this two page interview and then go back read the Richard guy from AMD. Then you tell me who sounds closer to telling the truth?

CRN:I think there was an issue in the fourth quarter—I should say almost every system builder I talked to who was a good Intel partner, whether they were really small or a premiere partner, was having trouble getting the right motherboards. I think some people really got hurt by that. Many felt like they built their business around offering their customers and Intel-branded motherboard and chipset and that they were really let down. At the same time AMD made some noise about wanting to get into the corporate desktop space. They launched their first stable image program and some other programs. I would ask you, do you think you were hurt by that and what can you do to reassure partners?

Otellini: We clearly disappointed ourselves and the investor community with the fourth quarter performance. We missed our guidance. We missed what we said we would do. Much of the reason for that had to do with exactly the problem you are describing, which was our inability to bring on third-party chipsets and motherboards to match with our processors in time to meet the peak selling season.

We brought them on very rapidly over the fourth quarter but, quite frankly, much of it happened in December—late December. As we sit her in February, now the situation is dramatically different. There is adequate third-party supply of chipsets and motherboards with both Intel with third-party chipsets on them, and there are other motherboard manufacturers with third-party chipsets on them we think to fill the gap that was left there. And you just go forward. I feel quite confident in 2006 that particular supply issue is behind us. But that didn't just impact the channel. That impacted Intel pretty severely as well.

CRN: What makes you feel confident that the problem has been solved?

Otellini: Intel is building more and we have arrangements already flowing with third-party suppliers.

CRN: What did you learn from that experience?

Otellini: Start earlier

SO that's why I said Intel doesn't want to dally around getting Conroe out there.

Then read this page. I don't think Barret was a bad guy, just not seeing the market like this guy.

Lastly what Sharikou is doing is taking a little of whats true and spinning into FUD LOL! The example I gave is just one of many Gaffs and outright lies he tells. Though many folks are saying wait for Conroe and let them do their own tests, that's fine. They want to see what their own setups can do. Victor wang even admitted that the Board he's using is not ready for shipping. There will always be some software that a software based x86 Processor will have problems running=P Look hard enough you'll find it.

 

[Xeero]

omg all this talk about pointless numbers and manfacturing processes is killing my head.

lets just keep it simple:

-wait until its out to see how it performns
-hopefully it wont require massive cooling to keep her nice and quiet
-i seriously hope we aren't debating benchmarks instead of real world tests again.

 

[cupholder2.0]

Heat wont be a problem with the conroe. All the new Intel chips wont run hot anymore, now that Netburst is dying.

 

[Asian Dub Foundation]

Heat wont be a problem with the conroe. All the new Intel chips wont run hot anymore, now that Netburst is dying.

you never know man, i mean who expected prescott to run so hot?

 

[coldpower27]

you never know man, i mean who expected prescott to run so hot?

Yes, but that isn't going with what current indications are pointing too. It's "possible" but fairly unlikely.

Core Architecture is based on Pentium M philosophy, so it has performance per watt in mind, Intel is aiming for a 65W TDP, and 65nm even cools down NetBurst enough to make it on the same level as an Athlon FX 60. Pentium EE 965, consumes marginally more power then the FX 60 now. Also ES have been known to run at a mere 1.2V so it seems perf/watt is the emphasis Intel is trying to play right now.

We do have to wait till the final product is released to see what will happen, but the intial results are promising.

 

[Bao01]

deleted

 

[JetUsafMech]

Let me get this straight. At IDF, Intel benchmarked Conroe, the results were amazing, yet "It was faked, etc." Anandtech benchmarked it, great results, yet "It's fake, crap, etc." An XS member gets ahold of an ES of Conroe, runs it on a craptastic motherboard, with a craptastic bios, it benches great, yet "Wait until a real world sample." At the same time, we are reminded "You guys don't know how powerful AM2 will be." AM2 gets benched, and it's "Try this, that can't be right, run this DDR2, update this, etc." because, like many predicted, it's a small (in some cases, negative) percentage increase.

Now some guy posts FUD on his blog, and it's gospel?

I agree, let's really get excited when Conroe makes it way to review sites, etc. But considering that all the 'preview' examples of it are showing great results, I expect the launch results to be better than what we've seen. It'll have a board, bios, and a couple of months for optimization of both.

All IMHO.

 

[Bao01]

Conroe is smaller than Presler. The newest C1-stepping Presler do not run hot while being clocked higher than Conroe. Therefore, Conroe will run cool. There is no other evidence to suggest the contrary.

 

[Mav451]

Hehe, my parents who push pink sheets and pharma docs all day usually know way more than the doc who writes everyone's prescriptions. I always thank god that I got FDA heads in my family =D.

 

[Bao01]

Let me get this straight. At IDF, Intel benchmarked Conroe, the results were amazing, yet "It was faked, etc." Anandtech benchmarked it, great results, yet "It's fake, crap, etc." An XS member gets ahold of an ES of Conroe, runs it on a craptastic motherboard, with a craptastic bios, it benches great, yet "Wait until a real world sample." At the same time, we are reminded "You guys don't know how powerful AM2 will be." AM2 gets benched, and it's "Try this, that can't be right, run this DDR2, update this, etc." because, like many predicted, it's a small (in some cases, negative) percentage increase.

Now some guy posts FUD on his blog, and it's gospel?

I agree, let's really get excited when Conroe makes it way to review sites, etc. But considering that all the 'preview' examples of it are showing great results, I expect the launch results to be better than what we've seen. It'll have a board, bios, and a couple of months for optimization of both.

All IMHO.

Why is this thread in the Intel forum? Isn't it bad enough it's flamebait anywhere else? Isn't it an extreme slap on the face of the Intel forum to move this thread here considering it was based on this [censored] to begin with? This thread should have been locked and kept in the AMD forum.

 

[JetUsafMech]

Why is this thread in the Intel forum? Isn't it bad enough it's flamebait anywhere else? Isn't it an extreme slap on the face of the Intel forum to move this thread here considering it was based on this FUD to begin with? This thread should have been locked and kept in the AMD forum.

I agree, and I really shouldn't have posted in this thread and taken the high road. But it the Intel bashing does get old.

 

[coldpower27]

I agree, and I really shouldn't have posted in this thread and taken the high road. But it the Intel bashing does get old.

It's too bad but Intel's time for sovereignty is long overdue. AMD's fanatics just can't accept they will lose the performance crown on the desktop fairly soon, and these are last few months for some time where AMD will enjoy a performance reign on the desktop.

Like I said way overdue for Intel to make a real comeback such as Conroe.

 

[Bao01]

I agree, and I really shouldn't have posted in this thread and taken the high road. But it the Intel bashing does get old.

Yes, thanks for pointing that out, I'm going to delete my first post. It's not really necessary to respond to stuff like this.

 

[Mav451]

I'm a pretty hardcore AMD fan, but I think that this MUST, absoluetely MUST happen.

Imagine if Intel isn't competitive >> then we get a stagnant, lack of innovation from AMD. As much as I'd like AMD to stay on the top, if Intel didn't come out with something (and it's been 3 years, eventually you'll engineer something), then forward progress in technology would certainly suffer.

Plus, if this happens, I might even be able to stag some well-priced used Opty dual cores from the FS/FT forums =D.

 

[cupholder2.0]

Listen, AMDs time as the king has come to an end. They are done!(atleast till next gen), Conroe will completely stomp all X2s. Do people honestly think adding some cache and tweaking a few things on the X2 will make it faster than Conroe? I know the truth hurts, but the truth is the truth and the Conroe is a monster.

 

[MrGuvernment]

Like I have always said..

AMD > Intel - In terms of being an ethical (non-lying) company, imho... Intel = SONY to me.

lol - so because of some !!!!!!'s review you jump the bandwagon..... As said above, where are all the gaming benchmarks?

Your no better then the blog poster my friend - jmping to assumptions before something is on store shelves.

I knew it, there is no way I would take Intels word that thier "new" CPU is that fast.

I'm wondering if it is possible to run these benchmarks with 1MB of code (to stay within the A64 cache) and see what results they both produce...

And you should never take AMD's word their CPU is SO fast! i recall some rather LARGE claims of A64 when they were coming, and yes it was fast, but no where as fast was claimed.

It would be nice if someone could try this with an A64 - it would answer some questions.....


Too many of you jump the bandwagon first chance you have and you just look like an ass for it, but i guess your used to that anyways,not that you would admit it.

Why not just say "hey, i will wait for the REAL proof to come out" as in when [H] people own these in their hands, instead you have to jump on the wagon! and support people who claim and run, likely NON consitent claims and test by people who dont even OWN the cpu or have a final retail version.

sad.

 

[(cf)Eclipse]

Do people honestly think adding some cache and tweaking a few things on the X2 will make it faster than Conroe?

depends on what few things we're talking..

 

[Donnie27]

I agree, and I really shouldn't have posted in this thread and taken the high road. But it the Intel bashing does get old.

Anand on AM2

Cooler P4

Soon they'll be call Anand an Intel F@n

SO, is Intel listening to the "Integrated Memory Fans"?

http://techreport.com/etc/2005q3/idf/index.x?pg=3

To illustrate how such a thing might be implemented, Rattner showed off a package holding three chips: a Pentium M processor, a north bridge chip, and a CMOS VRM. He said this arrangement would allow both the CPU and the Memory Controller Hub to ramp voltages up and down very quickly in response to changes in utilization, saving power.

Rattner presented this concept as a power-saving measure and didn't mention the possibility that an on-package memory controller could help cut memory access latencies. I would expect that moving the memory controller onto the same package as the CPU would have that effect, though. Unfortunately, the CMOS VRM is still a few years off, according to a presenter who mentioned the subject in a session following Rattner's keynote. We will simply have to see when—and if—this concept makes it into an end-user product.

 

[duby229]

I'd just like to chime in here.....

The reason I posted this thread was not becouse of the author of the articles BIAS. Yes he sure does sound biased. That aside he has made some pretty good points. Also like other on this thread have pointed out. He also LEFT OUT some pretty good points.

The only reason I posted this on the AMD forum is becouse it is certainly more relevant there. Ever since it was moved to this forum, the content of the article has been flamed and burned. I agree the guy is clearly biased. I said so on my first post.

There is still plenty that can be discussed minus the clear bias on the authors part. For example. We all know that Science mark is a strong test of FP power. Since AMD seems to take an advantage here, it is clear that Conroe is a little slow On FP code. Also It is also clear that The binary that was being used was optimized for SSE and it's kin, and AMD still took the lead in some tests.

It looks like Intel's conroe will be a solid chip, but there are still some scenerios where it will not win at. For example FP intense code, (which there is still plenty of by the way) and even in a few examples some SSE code. Since the test suite used is limited to only Science Mark, there really isnt much more that can be concluded from this article.

Intel Has a solid chip on there hands, but will it be enough to take a clear victory? My take on it is Maybe.....

 

[Gorankar]

Wow, defeat, losers, etc, etc... Alot of folks around here just seem to believe they have some personal stake in this matter, be it pride or purchase justification, or whatever..
Conroe doesn't justify being an Intel loyalist or !!!!!! during Amd's reign with A64/X2.. Just as being an Amd loyalist or !!!!!! during what appears to be Intel's upcoming coronation with Conroe..
I personaly believe conroe will be faster in most things, (it had better be after all this hype)..
I guess I will just sit back and watch the fireworks, until Conroe and good mobo's for it come out, and hope much of the lunacy dies down afterword..

I'm sure glad I'm missing this round, already have an X2, and I don't think I will need to upgrade it for a year or more.. But when it is time I will buy that fastest I can afford regardless of Green or Blue..

END TRANSMISSION......................................... TRANSMISSION TERMINATED

 

[JetUsafMech]

I'd just like to chime in here.....

The reason I posted this thread was not becouse of the author of the articles BIAS. Yes he sure does sound biased. That aside he has made some pretty good points. Also like other on this thread have pointed out. He also LEFT OUT some pretty good points.

The only reason I posted this on the AMD forum is becouse it is certainly more relevant there. Ever since it was moved to this forum, the content of the article has been flamed and burned. I agree the guy is clearly biased. I said so on my first post.

There is still plenty that can be discussed minus the clear bias on the authors part. For example. We all know that Science mark is a strong test of FP power. Since AMD seems to take an advantage here, it is clear that Conroe is a little slow On FP code. Also It is also clear that The binary that was being used was optimized for SSE and it's kin, and AMD still took the lead in some tests.

It looks like Intel's conroe will be a solid chip, but there are still some scenerios where it will not win at. For example FP intense code, (which there is still plenty of by the way) and even in a few examples some SSE code. Since the test suite used is limited to only Science Mark, there really isnt much more that can be concluded from this article.

Intel Has a solid chip on there hands, but will it be enough to take a clear victory? My take on it is Maybe.....

http://www.xtremesystems.org/forums/showthread.php?t=95021&page=37


One of the Science Mark authors has some inputs.

 

[Scali]

Thing is, FP code is dead in Windows x64. No 64-bit application will, or even CAN use FP code. They have to use SSE/SSE2/SSE3. So only legacy 32-bit applications will be using FP to start with. And it's nothing new, Intel already sacrificied x87 for more efficient SSE/SSE2/SSE3 in the Pentium4, although it was perhaps a bit too early back then.
So I wouldn't be too worried about FP performance.

Oh and yea, redpriest was that other guy from Sciencemark I know. We used to hang out in the same channel on IRC. He was quite the AMD-fan at the time, just like vulture. Always working on getting code to run fast on AMDs.
I was mostly into SSE at the time, so I still preferred Intel

 

[powerade]

all i can do is watch and smile

 

[LstBrunnenG]

Here's the post from the guy who worked on ScienceMark, quoted by someone at XS:

Conroe's score is amazing.

Keep in mind that he tested both the Pentium-M optimized binary and the Pentium 4 binary. Out of both binaries, the Pentium 4 was faster. This is compiled with Intel's latest *publicly* available compiler.

Conroe is more similar to the Pentium-M than to the Pentium 4, but the binary doesn't utilize Conroe's wider resources. In *scalar* code, x87 code is generated by the Pentium 4 optimized binary because the Pentium 4 can't execute pipelined scalar sse adds, but can in x87 mode. (I had thought this was not the case but Intel's optimization guide says this is the case, I'm not sure if I 100% believe that, but given that x87 code was generated with the most aggressive flags possible -- sse/sse2 code was used sparingly in with some of the x87 code).

I imagine that if you ran the 64-bit binary Conroe's lead would widen even more.

What I am perplexed about is why Conroe bombs on the encryption code -- the entire instruction mix consists of BSWAP, XOR, and various MOV instructions, none of which are micro-coded on other processors, and no jump instructions. With Conroe's wide integer resources, I don't see why this is the case. I'm guessing there is an address generation limitation, but since I don't have a Conroe I can't really test that theory. It's a blind guess.

In any case, I see this as a *strong* showing for Conroe, not a weak one as the blogger claims. In the benchmarks that matter (BLAS, MolDyn, Primordia) Conroe is at least equal to if not exceeding an Athlon at the same clock speed. The fact that in 32-bit mode, an Athlon64 clocked 400 mhz higher cannot exceed Conroe's performance gap is telling.

I can't wait for a 64-bit run....

Speaking to the OP, I love how having a blog can suddenly add enormous weight to your uninformed opinion...