Bad start for Intel

[hashv2f16]

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?

 

[SU-37]

i think that is not a bad start but a ,fresh new start .in my opinion

 

[neocristi]

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)

 

[Flakes]

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.

 

[tygrus]

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scrapping the P3 killer 'P4' heritage and going back to CPU's designs based descending from the 'P3' technology they superseded (when they aimed for clockspeed growth and tried to beat AMD into the ground).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.

 

[ChipDeath]

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.

 

[slvr_phoenix]

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.

 

[ChipDeath]

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]

 

[laitainion]

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.

 

[slvr_phoenix]

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. :?

 

[slvr_phoenix]

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.

 

[Flakes]

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,

 

[sylvez]

yeah read it somewhere in physorg. but. its physorg lol. lets just hope they can solve the various design issues....

 

[ElMoIsEviL]

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.

 

[slvr_phoenix]

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.

 

[slvr_phoenix]

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.

 

[Flakes]

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..

 

[slvr_phoenix]

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.

 

[pat]

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..

 

[hergieburbur]

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.

 

[pat]

SOD can...

 

[endyen]

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.

 

[hashv2f16]

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.

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

 

[hashv2f16]

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.

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...

 

[hashv2f16]

Imagine Intel this year
Socket LGA775
DDR2
no new Dual Cores
65nm
lower frequencies
....and yes... Celeron DUAL CORE!