Sign in with
Sign up | Sign in
Your question

Bad start for Intel

Last response: in CPUs
Share
January 16, 2006 6:42:06 AM

Intel seems to have a bad start this year. First their useless slogan and now processors that have no name. What will they think of next?

More about : bad start intel

January 16, 2006 7:00:56 AM

i think that is not a bad start but a ,fresh new start .in my opinion
January 16, 2006 8:38:31 AM

I agree, BAD BAD START for Intel. I am an AMD fan so my opinion might be disconsidered here but please take a look at latest CPU benchmarks from THG and Anandtech.

Conclussion:

The newest Intel 955 with new tech process 65nm, dual core, DDR2, 3.46Ghz !!! Gets kicked in the but by an old AMD tech process 90nm, DDR, dual core ,2.6Ghz (yes it s the FX60 but it's only an overclocked 4800+).

In the single core area,
what intel can beat the very common (and old) 4000+ ?

Imagine AMD this year :) 
Socket AM2
DDR2
new Dual Cores
65nm
higher frequencies
....and yes... FX62.

Intel will LOOSE even more customers (anyway all Gamers are now playing AMD)
Related resources
January 16, 2006 10:21:11 AM

Quote:
Intel needs to overhaul their processors, look at P4, it was a bad CPU. let's be honest, and now they need to start from scratch, completely, AMD has the upperhand now, cuz their Atlon64, was a much better CPU than Intel's P4


which they havnt done they went back to the Pentium 3 and changed a few things and are now selling it as there new proccessor.

i can pull up a few articles on the matter if anyone wants proof that the new CPUs are just P3s.
January 16, 2006 10:35:45 AM

Q. What will they think of next ?
1. Marketing campaigns with no substance.
2. More money for co-marketing *cough* bribes *cough*.
3. Focus on everything but performance (or perf/watt).
4. System/architecture names which include Intel components and no credible benchmark results to back up claims.

Could AMD use the Intel numbering if they have no trademakable name ?
Remember the hassle Intel had over 386, 486, 586 etc. because everyone else was using it.

AMD has built their own brand names of Athlon and Opteron. They are not going to throw that away.

Still have to wait till 2nd-half for anything interesting for desktop and servers from both Intel and AMD this year.

AMD should be able to make newer/faster 65nm CPU's that Intel won't "leap ahead".

Intel's marketing of "leap ahead" could be taken as admission that they are behind. Also they are scrapping the P3 killer 'P4' heritage and going back to CPU's designs based descending from the 'P3' technology they superseded (when they aimed for clockspeed growth and tried to beat AMD into the ground). "Back to the future" dare I say.
January 16, 2006 11:35:20 AM

Quote:
which they havnt done they went back to the Pentium 3 and changed a few things
So? an A64 is just an Athlon 'classic' but they've "changed a few things".

Of Intel and AMD, the only one who's created anything completely new from scratch (for the consumer desktop market) is Intel, with the P4. AMD have just evolved the Athlon design over time.

The PIII and the Athlon were both very similar in terms of performance. Hence the modified PIII (P-M) and the modified Athlon (A64) aren't really all that different (performance-wise) in many areas. The A64 has been more heavily modified from the original than the P-M (As far as I understand these things), but then they've been doing so for longer. Athlon classic (Forget the code name.. Noco-something? Or that might have been an Intel Core), the Thunderbird, the Various thoroughbred XP cores, Barton XP, and then the 64-bit chips...

There's no shame in improving an old design. Especially when the design was actually pretty good in the first place. People have had later PIII-based chips (Tully Celerons mostly I think) up to around 1.8Ghz - And it's been Chipsets holding them back (no AGP lock) rather than the CPUs themselves.... If they'd stuck with it and done the same as AMD in the first place, they'd probably be in a better position than they are now.
January 16, 2006 11:47:19 AM

Quite right.

And even the Northwood core was a good one. It had a lot of potential. The P4 architecture in and of itself had a lot of promise.

Had Intel concentrated on fixing the weaknesses of the architecture instead of higher clock rates, Scotty would never have happened. Scotty was just a major step backwards.

All in all, Intel really just needs to pull their head out of their bum.
January 16, 2006 11:53:31 AM

Quote:
And even the Northwood core was a good one.
True. It's easy to forget that in these Dark days of Scotty. I'd still like to see what a Simple die-shrunk and SOI'd woody would have been like :mrgreen:. We'd probably already have seen an EE at 4.5Ghz or so... [/Wanton speculation]
January 16, 2006 12:03:46 PM

I think the main point is not so much that working off an older core is a bad thing, more that Intel wasted the better part of 5 years on the P4 (whatever it's promise). The fact that they're going back to the P3 architecture shows it was ultimately a failure.
January 16, 2006 12:05:12 PM

Yeah, Scotty is a very dark cloud indeed. Granted, there were some good fixes in Scotty, most particularly in the L2 cache address handling. Those would be nice to carry back over into a Northy-based P4 redesign. But yeah, imagine a 65nm SoI P4 based on Northwood with a few such minor fixes, with double the cache, queues, and tables for a more dedicated HT, and with EM64T. It'd be an amazing chip.

But oh well. If Intel can design a good desktop PM-based system there will be some definite power-usage advantages there that anything based on Northy would likely never see. I like it when CPUs don't consume tons of power. Even AMD is going overboard IMHO these days. Now if Intel would just add another FPU to the PM...

You know, when you think about it, Intel really doesn't seem to appreciate floating point enough. The P4s had the same problem. :?
January 16, 2006 12:11:26 PM

Quote:
The fact that they're going back to the P3 architecture shows it was ultimately a failure.
I don't know if I can really agree with that statement, for two reasons. The first is that Intel learned a lot from the P4 architecture, and some of that is going back into the P3 upgrades. Had Intel stuck with the P3 all along, we likely never would have seen any of this.

The second is that the reason that the P4 architecture was a failure was because Intel became so concerned with clockspeed over all else that they severely castrated Prescott with high cache latency so that they could clock it high ... in theory. (The fact that Scotty wouldn't clock high because of leakage problems made it a rather ironic situation.) Had Intel never become so obsessed with clock speed, Northwood fairly well proved that the P4 architecture itself could have gone quite far.
January 16, 2006 1:39:47 PM

Quote:
Of Intel and AMD, the only one who's created anything completely new from scratch (for the consumer desktop market) is Intel, with the P4. AMD have just evolved the Athlon design over time.


sorry what i meant, is Intel should of tested more thourghly with there design first before going over to the P4. as for AMD they already had a design that worked and improved it which is what Intel should of done.

Personnally im waiting for fibre optic CPUs i read a article awhile back about one that had been produced it was 15cm * 15 cm and 2cm high, they reckoned in ten years time they would have them down to the same size as current chips, the one that had been developed could do over 7trillian calculations a second or some insane figure, i cant seem to find the article but its out there somewhere,
January 16, 2006 2:21:10 PM

yeah read it somewhere in physorg. but. its physorg lol. lets just hope they can solve the various design issues....
a b à CPUs
January 16, 2006 4:10:15 PM

Quote:
Intel seems to have a bad start this year. First their useless slogan and now processors that have no name. What will they think of next?


Intel's new processors (mainly Core Duo) are more efficient clock for clock then an Athlon64. They also use up less power (way less) at a total of 50w for two cores.

They're based on the PentiumM, which is NOT a P3. Yes, both are based on the P6 architecture, but the Core Duo has been revamped soo much that it's a completely different processor.

It's own downside is that it's FPU units aren't all too spectacular only matching the A64. But the upside is that they outperform AMD's CPU's running at the same clock speed... all the while having less memory bandwidth and a slower system bus.
January 16, 2006 5:34:49 PM

Quote:
It's own downside is that it's FPU units aren't all too spectacular only matching the A64. But the upside is that they outperform AMD's CPU's running at the same clock speed... all the while having less memory bandwidth and a slower system bus.
From what I've seen so far, that's a rather ... optimistic ... point of view. The FPU seems to be under AMD's performance. But clock for clock their other operations are pretty similar. It's definately a tough race.
January 16, 2006 5:41:30 PM

Quote:
Personnally im waiting for fibre optic CPUs i read a article awhile back about one that had been produced it was 15cm * 15 cm and 2cm high, they reckoned in ten years time they would have them down to the same size as current chips, the one that had been developed could do over 7trillian calculations a second or some insane figure, i cant seem to find the article but its out there somewhere,
There are several articles, and several attempts. Personally I like the concept of using different spectrums of light so that each 'bit' can actually represent more data. (Just imagine an octal or even 0-255 based 'bit' instead of a binary system.) Of course then you need an optical memory storage mechanism or else you'll be sucking up memory like mad.

Of course, that's all still ages away.

There are times though when I'm surprised that no one has as of yet designed a motherboard using optical paths instead of electrical ones. It'd greatly reduce signal noise while also allowing all sorts of extra levels of intricacy where path lengths no longer have to be nearly as equal. I guess no one is doing glass-fibre-on-silicon layers yet. Heh heh. Of course, cost would probably also be a concern, but then again, I'd pay it.
January 16, 2006 10:06:46 PM

Quote:
There are times though when I'm surprised that no one has as of yet designed a motherboard using optical paths instead of electrical ones


i believe there was a system a couple of years back that was completly Fibre Optic(so friends have told me havnt seen anything of it though)

either way it would be great to have systems that run at the speed of light but also a dissapointment cause once we get there that will be as fast as we can go..
January 17, 2006 1:48:52 PM

Nah. No worries. Besides that from what I've read the speed of light is relative to its medium, meaning that there will always be freaky physics means of speeding it up, there is the more important detail that the processor itself will always have room for improvements and refinements. Just because the data travels at the speed of light doesn't mean that the system cycles at the speed of light. And even if the processor did cycle at the speed of light, it doesn't mean that it has no room for improvement. An end is only a failure to look farther.
January 17, 2006 11:53:04 PM

Quote:
Intel seems to have a bad start this year. First their useless slogan and now processors that have no name. What will they think of next?


No.. they are doing a good move. First, no more men in blue ads.. can't be worst that that. Then Intel is searching itself a new identity, hense the no named CPU. Then U2 had a succes with the song "where the streets has no name"..

I have nothing against Intel.. but marketing is always making me laugh..
January 18, 2006 1:03:32 AM

The speed of light is releatvie to its medium, but it still maxes out in a vacuum at 186,000 miles per second. Most fiber optics don't quite reach that speed yet.
January 18, 2006 1:07:12 AM

SOD can...
January 18, 2006 2:16:34 AM

Quote:
But the upside is that they outperform AMD's CPU's running at the same clock speed..

Really, the benchmarks I've seen say the extra pipes they added to dothan cost them ~ 10%. The new desktops will have more pipes again, so there goes another 10% behind A64s at the same clock.
Seems like they've added pipes to dothan, to help it scale. Same story different page.
BTW, if they added FD SOI and another layer to the Northwood, and put it on 65 nanos, it would be well over 5 ghz by now, and probably ~ 80 watts.
When Intel gets scared, they make stupid decisions.
January 18, 2006 2:24:25 AM

Quote:
Quote:

BTW, if they added FD SOI and another layer to the Northwood, and put it on 65 nanos, it would be well over 5 ghz by now, and probably ~ 80 watts.


fat chance... i dont know for sure but i think with a pipeline as short as the northwoods i'd say it wouldn't be stable at that speed. and the intel 661 (cedar mill core) at 3.6ghz shrunk to 65nm puts out around 80w, so i doubt you'd get anything running at 5gigs down to 80watts.

Quote:
Quote:
When Intel gets scared, they make stupid decisions.


i agree, well... just cos they havent had as much luck during the last couple of years as their competitor have. however they are still in the game at least
January 18, 2006 2:32:42 AM

Quote:
I agree, BAD BAD START for Intel. I am an AMD fan so my opinion might be disconsidered here but please take a look at latest CPU benchmarks from THG and Anandtech.

Conclussion:

The newest Intel 955 with new tech process 65nm, dual core, DDR2, 3.46Ghz !!! Gets kicked in the but by an old AMD tech process 90nm, DDR, dual core ,2.6Ghz (yes it s the FX60 but it's only an overclocked 4800+).

In the single core area,
what intel can beat the very common (and old) 4000+ ?

Imagine AMD this year :) 
Socket AM2
DDR2
new Dual Cores
65nm
higher frequencies
....and yes... FX62.

Intel will LOOSE even more customers (anyway all Gamers are now playing AMD)


i smell bias in your post. you must be an AMD fan.

and are AMD really going to move to 65nm this year? i havent heard anything solid on that.

Quote:

Intel will LOOSE even more customers (anyway all Gamers are now playing AMD)


don't forget who owns the mobility/notebook market and pretty much all of the corporate offices and all their corporationey people, who make money...
January 18, 2006 2:36:08 AM

Imagine Intel this year :) 
Socket LGA775
DDR2
no new Dual Cores
65nm
lower frequencies
....and yes... Celeron DUAL CORE!
January 18, 2006 2:39:50 AM

I know too many people who have clocked northwoodCs to 5ghz to think they cant do it and be stable. Going to 1/2 the gate size should make it a cake walk.
The scotties have serious leakage current problems, but they started with northwood. FD SOI and a realigning of the current paths to a lower level would help a lot.
We'll probably find out in about 5 years, when Intel needs to speed up because multicores just dont give the umf we want anymore.
January 18, 2006 3:13:09 AM

AMD does (supposedly) plan to move to 65nm this year, though they don't really need to rush. Their designs are still better than intels (From an engineering standpoint), and as a result, their newly announced processors outperform the 65nm Intel chips, and still use i think about the same power.

Intel has to complete their transition away from the Netburst Architecture to a more streamlined design before they can really compete again.

With AMD working toward a mobile platform and Dell supposedly being open to selling AMD, Intel needs to work fast (though more importantly smart) to heat up the competition.

I am not siding with one or the other, as I personally prefer there to be stiff competition between the two, it means better overall designs for all of us.
January 18, 2006 3:23:54 AM

I'm really starting to hate Intel's new chip naming scheme already. Why don't they just give them a name rather than use very confusing random numbers and letters that nobody can possibly know what they mean let alone remember.
January 18, 2006 12:22:21 PM

Quote:
When Intel gets scared, they make stupid decisions.
Ain't that the truth! :lol:  :lol:  :lol: 
January 18, 2006 12:26:15 PM

Quote:
I'm really starting to hate Intel's new chip naming scheme already. Why don't they just give them a name rather than use very confusing random numbers and letters that nobody can possibly know what they mean let alone remember.
It's funny. When Intel used primarily MHz to differentiate their product lines everyone complained that Intel is pushing the MHz Myth. But then Intel switches to part numbers and people complain that it's too confusing. Well gee.
January 18, 2006 12:41:05 PM

Quote:
I know too many people who have clocked northwoodCs to 5ghz to think they cant do it and be stable. Going to 1/2 the gate size should make it a cake walk.
Yep. Northwood had a lot of potential left in it.

Quote:
The scotties have serious leakage current problems, but they started with northwood. FD SOI and a realigning of the current paths to a lower level would help a lot.
I really don't know why Intel is resisting improving the process so much. :? It seems kind of weird. It can't really just be about the cost, can it?

Quote:
We'll probably find out in about 5 years, when Intel needs to speed up because multicores just dont give the umf we want anymore.
:lol:  They'll probably invent some weird NetBurst2/virtualization technology that reintroduces a giant pipeline. Not that this would be a bad thing, if done right.

Of course I'm still waiting for an array of small completely virtual 'cores' that share a unified set of registers, L1, and L2 cache set within a master control core that breaks down the incoming code into order-adjustable microcode so that it can relabel and distribute the code to these cores as efficiently as possible, regardless of the way the original code was written. You know, a CPU that really does good instruction-level-parallelism from x86 code. It'd take a lot of R&D and a truck load of testing, but if no one starts it, how can we ever get there? Once the kinks are worked out it'd have to be better than just cramming in more x86 cores into a single package.

I mean imagine how much of the resources of these dual-core x86 chips go wasted, especially when only running one intensive single-threaded app at a time? The more seperated things are, the less efficient they are, and the more of the die is wasted with unnecessary redundant units.
January 18, 2006 7:10:54 PM

Quote:
Of course I'm still waiting for an array of small completely virtual 'cores' that share a unified set of registers, L1, and L2 cache set within a master control core that breaks down the incoming code into order-adjustable microcode so that it can relabel and distribute the code to these cores as efficiently as possible, regardless of the way the original code was written. You know, a CPU that really does good instruction-level-parallelism from x86 code. It'd take a lot of R&D and a truck load of testing, but if no one starts it, how can we ever get there? Once the kinks are worked out it'd have to be better than just cramming in more x86 cores into a single package.


That is sorta the direction that the cell processor is starting toward.
January 19, 2006 1:09:55 PM

Quote:
That is sorta the direction that the cell processor is starting toward.
Sort of, but not really. The idea is to get rid of as much of the duplicate units as possible. Why have each 'core' use its own decoders, cache, registers, tables, queues, schedulers, yada yada yada? And they still have to talk to each other instead of openly sharing data. As cores shrink more and more, having just one 'core' do all of that part and the remaining 'cores' being just execution units, will really allow for a lot more efficient design. From what I've read the Cell processor is kind of a step in that direction, but not nearly enough of one.
January 19, 2006 6:57:38 PM

True. However, from a design standpoint, what you are saying is more difficult than it sounds, and it will be a few years before something like that is seen.

(Though on one level, that is kinda how a current processor works, with different elements, such as the ALU, included on one core). I know it is not the same as what you are talking about though.
January 20, 2006 2:43:44 PM

Quote:
True. However, from a design standpoint, what you are saying is more difficult than it sounds, and it will be a few years before something like that is seen.
Oh, I know. Which is why work should be started now. (Should have started already.) It only really starts to make an economical sense once we reach quad-cores anyway.

Quote:
(Though on one level, that is kinda how a current processor works, with different elements, such as the ALU, included on one core). I know it is not the same as what you are talking about though.
Exactly. This is just taking that to a much further extreme. Procs are already breaking up the x86 code into microcodes specific to the proc. We just need to take this further.
January 20, 2006 9:45:47 PM

Earlier than Corprinicus, Aristotle invented the Scientific method. But your point still stand, if we are going to compare products then you must limit the number of variables being shown. In an ideal world both Intel and AMD would run on th exact same motherboard with the exact same ram, etc etc. Comparing one overclocked processor to a known overclocked processor is a gross violation of the scientific method. Not to mention that there are still cache differences and things of that nature. An Athlon X2 3800 overclocked to FX dual speed is not the same as a dual FX, there are cache differences.
January 21, 2006 1:05:58 AM

Quote:
>
DON'T GO TO PUBLIC SCHOOLS!!


xDxD true....but if there's no choice......
January 21, 2006 1:07:38 AM

Quote:
The speed of light is releatvie to its medium, but it still maxes out in a vacuum at 186,000 miles per second. Most fiber optics don't quite reach that speed yet.


I read on a Popular Mechanics magazine that some scientists made light travel faster than "itself" and lowered its speed on a special type of fyber optic...

Indeed it would be VERY XXXpensive pc....
January 21, 2006 3:49:51 AM

well said supremelaw

it would be a high risk venture for intel to put their money into a bunch of theory no one knows much about and they probably figure they've come so far, lets just improve on what we wasted so much money on already
January 21, 2006 4:31:12 AM

but um.. isn't light fast enough anyway?

anyhow. you couldn't make a computer chip out of fibre optics because fibre obtics don't work through cables that r bent at more than 90 degrees and i don't think you can fit enough fibre optic cable into the size of a processor core without bending some of the fibre optics
January 21, 2006 6:31:27 AM

Quote:
The performance of the Presler is exceptional for an Intel based system

Perhaps, for an Intel system. Not to be compared to an Amd, or they would look bad.
Sad that they did not include what the scotties do best. These little puppies are great heaters.
January 21, 2006 8:00:51 AM

water heaters.
a b à CPUs
January 21, 2006 10:23:28 AM

Intels got conroe round the corner, that will atleast catch up to an A64 and might beat it if intel gets it right (its there "new" architecture - ground up new design so it should dam hell should even if its not equal clock for clock), either way Intel's conroe will be cooler and quicker then the current netburst rubish.
!