The Dual-Core War - Is Intel in Trouble? 411
michaelMSFT writes "Cooltechzone has a column stating that Intel has already lost the dual-core war against AMD. From the article: 'From the performance numbers published on numerous online publications, Intel has lost the Dual-Core War. The only competing factor that Intel has right now is the possibility to keep their prices low enough to attract those with strict budget...I would like to forward a special note to Intel: Please make sure your next generation of processors aren't as atrocious as the Prescott, as AMD is making you look pretty silly right now.'"
I Disagree (Score:5, Insightful)
Hack! And not the good kind... (Score:5, Insightful)
I had a root cannal done yesterday, so it might be the Percocet talking:
This article is total hackery. Any two comments will have better background and more insight than TFA.
It's just a "AMD is better!" article that mentions dual core CPUs for some reason. No context, no information.
Silly? (Score:5, Insightful)
Yeah - but the thing is - is the performance worth twice the price? Being that's the only way you can go with AMD right now - paying twice as much (if not more) for their dual core chips compared to Intels.
Funny that.
Ah the usual /. overstatement (Score:5, Insightful)
Intel will only be in trouble when Dell, HP, Fujitsu and every other major manufacturer drop them in favour of AMD. Until that happens its business as normal.
Intel hasn't lost until Dell sells AMD (Score:5, Insightful)
The other thing is volume. I believe one of the reasons AMD is able to create superior processors is because they don't crank out nearly the volume that intel does.
If they did it would take them longer and cost more to upgrade the fabs each generation.
The power of marketing (Score:5, Insightful)
I disagree, and I say that as someone who hasn't built an Intel machine in years. There are a lot of regular Joe consumers out there who are barely even familiar with AMD, primarily due to Intel's aggressive marketing (ding-ding-ding-DONG) and their partner relationship with major manufacturers (cf. Dell).
Good marketing will keep inferior products afloat for quite some time.
Only an opinion piece - don't bother reading (Score:5, Insightful)
Turns out this was nothing more than an extended opinon piece (yes, yes, I know that's perfectly fine) but I was looking for something with some hard-core comparisons, especially since they started out saying "we'll just compare the desktop scenario to keep matters simpler" --- *click to next page* Aw what!? nothing!
Sounds like someone was just after some slashdot publicity.
Did I miss the proof? (Score:3, Insightful)
If this is true it would make some sense. I get to use an AMD64 at home and a similar P4 at work on computers with similar specs and I enjoy the AMD's performance a lot more.
This whole thing sounds familiar though...
I seem to remember when Prefetching was hitting the adverts, and AMD was doing some hefty investing in those prefetching adverts just to have Intel turn around and produce more powerful prefetching technology. I guess it can go both ways.
Re:Better Review Over At... (Score:3, Insightful)
AMD is faster and more expensive.
Intel is slower and cheaper.
Am I right?
Re:And Furthermore... (Score:5, Insightful)
Wars aren't won or lost on the first shot. Wars go on for a long time.
Article Summary (Score:5, Insightful)
From TFA:
This nicely sums up the entire article...a two page personal opinion, berift of any real facts, statistics, or figures.
This 'story' was pointless.
Re:Silly? (Score:2, Insightful)
The 4000+ just dropped in price, presumably in anticipation of pricing the dual cores above that. That they offer single threaded performance that isn't too much further below their single core counterparts (AMD seems to have dual core at higher relative frequency to their single core products than intel) and multithreaded content that isn't constrained by the north bridge memory bandwidth (hypertransport seems very long sighted now) makes it a viable option even for those who use primarily single threaded apps, i.e. games.
I would get a dual 2.2 GHZ A64 machine over a single 2.6GH A64 machine if the price were comparable, informed consumers will likely do the same, but the number of informed consumers buying computers is compartively small.
To the person who said marketing wins, you're right, and everything I just typed doesn't really mean al that much.
Democratization of tech (Score:3, Insightful)
The mainframe makers had their lunch eaten by the minicomputer makers. The minicomputer makers had their lunch eaten by the PC makers. Now the PC makers are going to see their lunch eaten by the consumer electronic makers. Everytime someone comes up with a way to find more customers (on the low-end), they create tech that eventually supplants the tech of the prior, more limited, customer base.
From this standpoint, IBM is in a good position with processors (the Power/PPC family) that work in consumer electronics, desktop, and mainframe applications. Intel is also doing well with low-cost processors that can run Media PCs. On the otherhand, I fear that AMD's niche in the high-end PC and server market will disappear once consumer electronic processors become fast enough to handle desktop and work-group server applications (just like PC-grade processors supplanted SGI's specialty graphics machines). Sure, there will always be room for specialty processors (e.g., for super-duper clustered DB servers) but it won't be a big market.
Why are we reading somebody's rant? (Score:5, Insightful)
Re:Ah the usual /. overstatement (Score:5, Insightful)
I would agree with other posters that right now AMDs largest issues are capacity and marketing (people need to ask for AMD) as the technology is there.
Suprise!? No. (Score:4, Insightful)
What's making Intel look silly is not the fact that dual-core Athlons outperform dual-core Intels, but the fact that AMD has out planned Intel in the somewhat long term. Intel's short term goal of chasing GHz into oblivion is biting them in the posterior.
None of it amounts to much if AMD can't gain ground on Intel in the market. Call me when AMD's market share moves by more than 0.1% per quarter [itfacts.biz].
Re:I Disagree (Score:4, Insightful)
Intel isn't losing money, but talented engineers are a limited resource. They would have bought the farm on Itanium if they weren't making money on Pentium.
What is interesting is that in spite of being so wealthy, their main Pentium line is suffering. It uses more power, it's stopped advancing in MHz, it doesn't scale in SMP well at all, and it loses benchmarks to chips in the same price range with 1/2 to 2/3 the clock rate.
I think what has happened is that HP/Intel got into a rut with Itanium that will take a long time to recover from. Intel won't go anywhere, but they will have to accept getting trumped by their competitors for a few years, now.
To add insult to injury, Opterons are benchmarking faster than even the Itaniums, and in floating point, no less!
This is Way (Score:3, Insightful)
The reason that the AMD chip is so much higher is that it is harder to make and THAT much technically better that the Intel processor.
AMD
As many of you know AMD has decided to toss the old memory access system and access main memory directly from the processor.
This allows AMD to have a true dual core chip sharing memory resources with on chip Core-to-Core communication.
The real benefit is the direct memory access and on chip core-to-core communication.
Intel
The Intel dual core chip is as big of a marketing trick as hyper threading. Intel took to generic P4 processors ground off the edges and placed
them on a single die. I am not making this up!! this means that any communication processor to processor has to actual touch the system bus.
If you know anything about the way processors work you know memory management for SMP machines is not easy, but imagine trying to manage
a shared cache and shared main memory when the only core-to-core communication has to hit the system bus!
AMD did something very right but needs to bring the price down to ever get any reward.
Before anyone gets in a war about AMD kicking Intel down just recall the Intel marketing budget is more that the entire operation capitol of AMD.
Codeman
Re:I Disagree (Score:2, Insightful)
Data that moved from one register into another part of the pipeline operating at a much higher frequency would then eventually have to leave this higher clocked space into the register again. Thus, the high clocked registers would process data much faster than it could be fed, and would spit it out much faster than the rest of the chip registers could accept it.
I can already see one way around that (that being having more pipes out than in) but from a cost benefit analysis, you just end up building a Cell type CPU eventually (with different speed FPU's etc instead of SPE's), and that seems to be where their going, multiple general purpose cores, then eventually specific purpose cores.
Kind of like having the math co-processor on the board, and then eventually moving it onto the chip. Who says you can't put the next big thing (maybe the PPU) on the chip as just another core!
one word... headache!
CoolTechZone (Score:2, Insightful)
It amazes me how little people appreciate about business in the IT world.
Who wins when everyone agrees Beta was a technically better format, but only sell VHS?
Branding works, and Intel has that on their side for a little bit longer. They would have to lose several of these battles before they start to lose their branding advantage. And just because you think Prescott is atrocious, if it performs better than previous Intel chips, the ones that business owners are replacing, who is going to look elsewhere?
Re:Hack! And not the good kind... (Score:5, Insightful)
The guy says "I think" and "I feel as though" too many times for me to take it any more serious then a forum or Slashdot post.
It's some dude that thinks he can be an online "journalist" by posting garbage like that on a web site.
Two-Faced Market (Score:3, Insightful)
Re:Silly? (Score:2, Insightful)
With AMD, if you are currently running a 939 mobo all you need to do is a firmware update when you buy the new chip.
TFA... (Score:3, Insightful)
However, he is of course correct - but it's a useless read without any references.
Intel Ok, AMD Ok, Everybody Can Win (Score:5, Insightful)
Intel of course has nothing to worry about. They have the volume customers through deals with Dell, HP, and others. And they are picking up the low end of the market for dual core chips. These are not as good performance-wise as the AMD chips, but the lower cost is appealing to a more budget minded market. And with economies of scale, Intel certainly makes a nice profit. So it is unlikely they'll be shutting their doors anytime soon.
Everybody can win here. AMD has the harder job for now because their survival depends on continuing to produce better chips and growing their niche of customers. But as long as they make a profit, they can stay in the game.
Intel failures (Score:2, Insightful)
AMD is faster and cheaper.
Intel is slower and more expensive.
Currently, AMD beats Intel with pure performance in high-end market, AND wins over Intel with cost-performance ratio in other segments.
This is a BIG problem for Intel - they're losing everywhere. Their advantage is starting to erode in all three segments: market, technology, and mindshare. Their past failures are now cursing them back.
- Decision to go with clock-based marketing
- Failure to keep clockspeed up due to heat problem
- Several product recalls due to design issue
- Failure to introduce new memory standard (RDRAM)
- Application trend still going after single-processor capability and speed (killing hyperthreading effectively)
All these failures/decisions only helped AMD to beat Intel. Yes, Intel is now trying to get back to the right track, but it'll take some time to catch up with AMD.
Re:Any dual core vs dual cpu benchmarks? (Score:5, Insightful)
Pretty simple: Slightly better than two single cores, mainly due to the fact that the Opterons are close coupled, and teh CPU cores commun icate directly in the package over a Hypertransport channel.
In the case of the Intel dual cores?
They have no direct communication, no HT bus, and all messages and RAM access has go to the northbridge chip and face a FIFO queue to memory.
In the case of thermal/power performance?
At similar performance the AMDs are using about 60% the power, and making corresdpondingly less heat than the Intels.
Despite what the "Intel fanboys" are saying, Intel HAS lost this war at the first battle.
And Dell will keep selling Intel, for a while.
Until it start to hurt the bottom line.
In the meantime, the changes are already happening.
SuperMicro, who NEVER build boards for anything but Intel CPUs, are now selling a dual Opteron board.
The Emperor really does have no clothes!
Re:Dual core with Linux? (Score:2, Insightful)
You now have your answer.
Do you remember Cyrix? (Score:5, Insightful)
So now we've got AMD and the Athl/opteron. AMD has done better than any other competitor, so far, and has managed to maintain a narrow performance gap for several years. On a couple of occasions, they've opened a wide performance gap for a short time, but Intel has always closed it to a narrow one.
Neither great technical merit for a short time nor slight technical merit over a long time is enough to establish a market. The competition can always work around that by starting a skunk-works project, as Intel did to Cyrix, and Transmeta, and, more recently, with their implementation of x86-64. To catch up with AMD now, all Intel needs to do is build a dual-core x86-64 chip with a smaller power envelope.
Didn't I hear that x86-64 and dual cores were coming to the Mobile Pentium class soon? Hmm...I wonder why?
War? (Score:3, Insightful)
Free Markets? (Score:2, Insightful)
Intel has lost a little bit (Score:5, Insightful)
Intel maintains market dominance, high-level industry connections, a huge advertising behemoth, and a vast amount of resources.
There is no possibl scenario for AMD to 'remove' Intel from the market. No company of that size can be defeated quickly, unless from within (corruption).
Intel isn't going anywhere, they've got the resources to play for a long time.
AMD isn't going anywhere, they've got the brain power to stay ahead, and they've proven over the last few years that they ready to push the envelope as many times as needed. They are no longer a 'one-hit-wonder'.
Competition is good, folks. Both companies work harder because of the current situation, and its a good thing that they hate each other.
Re:Better Review Over At... (Score:4, Insightful)
You do not rule the home/desktop market when every Dell ships with an Intel CPU.
Re:And Furthermore... (Score:3, Insightful)
The fact is that right now we are just on the cusp of the whole Multi-Core processors 'era.' The fact is for CoolTechZone to say that Intel has already lost is foolish.
First off, Intel has TONS of resources to basically do whatever they want. Why do you think they were able to try forever and a day to make IA64 work and basically fail (or at least really never make the splash they wanted)? Intel has tons of cash, and can fight the good fight for a long time. Where AMD has the edge right now is that they are busting their humps to get better performance and doing it well. But Intel can and probably will, catch up.
Second, AMD just needs to falter just a bit and they will fall behind. AMD has had the performance lead since the intro of the Athlon64, because they developed a set of 64 bit "extensions" to x86. This allowed them to jump ahead of Intel last year, which they have worked hard to make sure they don't lose the lead. But it was really Intel's preocupation with IA64 that let them fall to second (not to discount what AMD did). If AMD makes a similar slip, then Intel could quickly and suddenly jump right back out front.
Finally some of the arguments are made based on insignificant information. QUOTE:What does the enthusiast market really have to do with ANY of this? Intel isn't worried about them, because they make up a SLIVER of the market. The fact is the mainstream is what you want to go for. Intel still has a big name, and "Intel Inside", for whatever reason, still carries a lot of weight. Frankly Intel doesn't care about the enthusiast market at all. If they did, they wouldn't have gone to lenghts to clock lock their chips as best as they can.
To make this statement is the equivelant of writing an article and saying that ATI has won the war of the 512 MB video cards. Of course what else is to be expected of Mom's basement tech site that touts itself as "The Ultimate Source for Tech News"? Of course for these guys to make statements like: really makes me wonder about their knowledge at all. If you understand architecture, you realize that MHZ ISN'T king. Intel hyped that for a long long long time, until AMD was finally able to turn that against them with their naming scheme. The fact is that Intel was able to really get the masses to buy this for a long time, but now that the masses are realizing that performance is the real issue, Intel is shifting to that, because they know 1- what people want and 2- they know they better get with the program or get left behind.
RonB
Neither one's in trouble (Score:2, Insightful)
Just like there's been a solid user base for Apple -- mostly graphics folks -- that kept the company afloat during its dark years, AMD has the geeks, and Intel has their name embedded in most consumers' heads. Intel is not in trouble, and even if AMD gets overtaken, it too will never be in trouble.
Re:Do you remember Cyrix? (Score:4, Insightful)
And that's just looking at the desktop offering. Via hands Intel it's ass on a platter for embedded solutions. Not only are Intel's Ultra Low Voltage solutions more expensive, they draw more power. A 600MHz Celeron ULV draws 7V typical. A 1GBz Eden-N draws 7W peak.
you need vendors (Score:5, Insightful)
IBM has one product that uses opteron, dell hasn't started selling one yet. Before opteron can really take off, I think one of those guys needs to turn around on the issue. These guys aren't going to give up on intel chips because they've been unimpressive for the last couple of years. Intel would have to foul things up in a REALLY BIG way, or keep screwing up for five or six years before many enterprises would change direction.
As for dual cores, AMD was quite wise to release a server product before the consumer product. I already know that multiple CPUs work well for my server. I'm not really sure what I'd do with them on my desktop.
Re:Do you remember Cyrix? (Score:5, Insightful)
Then came the Pentium II/Celeron days. Cyrix really hit rock bottom here. They put out chips rated as a 300 (the M-II series) when the FPU still hadn't been addressed. That "300" could be beat by most Pentium 150's on FPU performance. Then there was the whole issue with how they handled the performance rating. Even on Cyrix's own website (where the tests are going to be setup to favor their equipment) they had tests showing that their M-II 266 came very close to a Pentium II 266 and that their M-II 300 came very close to a Pentium II 300 (and this was only in the straight business stuff). The Cyrix part came in slower, but hey, it was close right? When you looked at the actual benchmark results though, you could see that the Pentium II 266 was pretty close to the Pentium II 300. As a matter of fact, the Cyrix 300 had the EXACT score of the Pentium 266. Why the heck was it rated as a 300 (actual clock 233mhz) when it could only match the 266 and then even on Cyrix's own biased benchmarks.
Cyrix chips also ran very, very hot, for their time.
Now this is from someone who has owned a lot of Cyrix chips (a 586 100mhz, a 686 P200, and an M-II 300): they were junk. AMD was a far better choice than Cyrix even back then. I also had an IDT Winchip 225mhz for a while which also wasn't a very good performer but at least it ran cool.
With AMD though, things are different. AMD is beating Intel where it has always count: straight up performance. They're usually beating them on price too. Now it's no longer "settling with a little less performance because the chip is cheaper". Instead you're actually getting a BETTER chip for cheaper. AMD has been constantly making headway. They'll do far better than Cyrix, IDT, or Via (Via actually bought IDT and Cyrix which became their processor division).
Poor performance != trouble (Score:2, Insightful)
AMD will never beat intel on by making quality products. The only hope AMD has of taking the crown of CPU sales is to open a bunch of cheap fabs in China and hire a good advertising firm.
Add IBM to the list (Score:2, Insightful)
Re:I Disagree (Score:3, Insightful)
But in each case it was made pretty obvious that the products were hastily designed (if you could call them "designed" at all), and performed poorly compared to the competition.
I think part of this is due to the loss of resources from the hurricane-sucking ia64 mess. Intel is spending far too much on beating the ia64 dead horse, and it's hurting their core markets.
Sooner or later the shareholders are going to demand a change. It will be interesting to see if they finally let ia64 die.
Re:Bored with hardware? (Score:3, Insightful)
[1]
When I was in my teens, I had more time and less money. That made it worth the effort to keep up to the minute on hardware and to tweak and overclock things as much as I could. I also had other people giving me their old hardware (or at least, hardware that was old to them), so I had lots of spare parts lying around.
Now, if I need a newer system, I can go out and buy it. It's more economical to me that way than to devote a week to assembling and tweaking a system to the Nth degree.
[2]
Hardware advances have slowed. The jump from a 286-12 to a 386-16 was enormous. The 486 was incredible. Now, it's just "ho-hum" to see the latest CPU & video card running the newest technology. Smoother edges. Higher res. Better framerates. Bah, I've seen that cycle too many times for it to matter anymore.
Re:I Disagree (Score:3, Insightful)
This content-free Intel-hater article is trash. (Score:1, Insightful)
Oh, and the article is full of opinions and absolutely free of any benchmarks or facts. The article should not have been submitted, much less greenlit.
Re:And Furthermore... (Score:2, Insightful)
You say that Intel only needs to apply their will or desire? Then why haven't they done so already?
No, it is the GHz (Score:3, Insightful)
Furthermore, I have serious doubts about the competence of any reviewer who would suggest that there is an equivalent of 400MHz difference between two-way SMP on a single-chip and two-way SMP on two chips. The only real difference is that dual-core gives slightly lower latencies when it comes to inter-core communication, and the HyperTransport bus is so fast that the difference is practically negligible.
The only valid comparisons here are:
2x Opteron 248 vs. 1x Opteron 175
4x Opteron 848 vs. 2x Opteron 275
There's also 8x Opteron 848 vs. 4x Opteron 875, which is impossible, and makes a very compelling argument in favour of dual-core, as while the Opteron 8xx can support 8 processors, no 8-socket boards exist. But 4-socket boards exist, and they may be able to take dual-core processors...
Oh, and it is all about the GHz. A dual-core 175 is effectively two single-core 148s on the same die, with some communications bridges added. Same goes for 275/248 and 875/848. They're the same processor. GHz is a perfectly valid measurement when you're comparing the same sub-architecture.
Re:And Furthermore... (Score:3, Insightful)
They most likely did it on good faith and overoptimistic hopes.
Back when the first Prescott rumors started popping up, Intel's hopes for it were as high as 5GHz for the end of 2004... the Intel side has been stuck in the 3Gs for almost three years now. The story is similar AMD-wise but around 2Gs instead.
And now that it is open season on multicore, clock speed will soon become a secondary matter.