Intel's 45nm chips coming next year

Page 6 - Seeking answers? Join the Tom's Hardware community: where nearly two million members share solutions and discuss the latest tech.
wow ycon, your sooo bias, go away, dvdpiddy is a little bias towards amd but they are better at the moment, so what's wrong with that, also, some of you need to shorten your posts[lt data], man i read one sentence and skip it. ALSO, conroe is mainly speculation right now, and someone said, i thinkj it was mcdonalds guy, that amd cleans up intels mistakes so they have an advantage, but now with conroe having such a low clock speed for intel, it seems they are copying amd, and since most people see a lower clock speed as crap, that may be bad for intel's sales.
Actually, Intel had an EXTREMELY efficient architecture before AMD that AMD copied while it had heat problems. Pentium 3 anyone? Pentium M's come from Pentium 3's...which were extremely efficient chips. Thus, a current Pentium M is actually a far superior performer and low heat/power component when compared clock-to-clock with the K8 architecture.
 
IF there is one thing I hate its fanboys.
Seriously, AMD is blah blah blah... Intel is blah blah blah..
SHUTUP.
OK?
actually when i here an intel fanboy talk about how great prescott is compared to venice or san diego and amd is bad cause they are so slow i get sick to me its like the sound of

DIARRHEA SPEWING FROM SOMEONES MOUTH!!!!!
Prescotts were shit. Intel learned their mistake, and Cedar Mill is a massive fix. Also, Prescotts still scaled far better than the AMD's with good cooling (no, not just liquid nitrogen/phase changing) because Strained Silicon is simply better than 90nm SOI.
 
The P3 derived architecture is a lot better than the P4 architecture.

P3s and their derivatives are actually decent CPUs for the most part ;-)

AMD64 is still architecturally superior tho 😀
BS Put an FX55 and an OC'ed Pentium M 715 at 2.5 in almost any game benchmark and guess who wins ?
FX55 dominates it in every other benchmark for one reason: Pentium M's are built for EXTREME low voltage; thus, they have a terribly weak BUS bandwidth power, and motherboards and settings for the few motherboards out on 479 are harder even there.
 
The P3 derived architecture is a lot better than the P4 architecture.

P3s and their derivatives are actually decent CPUs for the most part ;-)

AMD64 is still architecturally superior tho 😀
BS Put an FX55 and an OC'ed Pentium M 715 at 2.5 in almost any game benchmark and guess who wins ?
FX55 dominates it in every other benchmark for one reason: Pentium M's are built for EXTREME low voltage; thus, they have a terribly weak BUS bandwidth power, and motherboards and settings for the few motherboards out on 479 are harder even there.

Pentium M beats AMD clock for clock (even 200mhz less) at super pi (raw math) and Doom3 also beats everything clock for clock and better - go do some reading whoever doesnt believe, and look at them take on a turion - 200mhz more to beat and intel, they cant even give it enough cache.

http://xtremesystems.org/forums/showthread.php?t=36835

And yonah - clock for clock equal to an A64.

AMD has there 90nm till next year, can they survive another 9 months with a core that wont get past 3.2ghz?

Conroe is coming out as 2.66ghz initially and they say its 20% quicker (clock for clock) that fits concidering that AMD will release a 2.8ghz dual core at the same time - it fits perfectly, aswell as ramping to 3+ghz at the end of the year.

P6 has never let us down and conroe is by the israle/pentium m team not the netbust team.

ak47is1337 - intels time will come, patients my friend, patience.
 
I don't mind fanboys, I just dislike dumb***es. Too many are the later around here. The ones that can't understand or be honest. To be a fan of someone, some team, or something is just for fun and not to be a personal attack. I like hot debates but I hate a lousie cop out of someone unwilling to see other points of views.
 
What about floating-point performance? That's one thing I care about... and Intel's has been sh*t the past few years. That's the main reason Athlons perform better in games... they have the superior floating-point performance... even over Dothan.
 
Pretty nice, the quad core will be on next year I hope. Im very satisfied already with my 90nm chip but 45nm, man that would be more performance increase! I don't care much of the watt to performance thingie since Im using desktop. But I'll stick with 90nm chip for now and skip the 65 and just go for the 45 hopefully next year. 😀

My big concern is the price, since its 45nm, does it mean more expensive or cheaper due to mass production? I don't wanna pay another grand for a new chip. I get broke everytime I upgrade. 🙁
 
45nm should cost less to produce (heck a 250nm P2 core with no L2 cache is more then 4 times bigger then a prescott) but usually it dont go down in price for a while (and they use the excuse "more cache" and so on for higher cost chips).

Sadly smaller nanos doesnt instantly translate into performance but allows more overclocking (higher speeds, lower heat and power) then larger nanos and more cache can be packed into a similar area.

As crap as P4s are it would be interesting to see em at 45nm - see how far cmos technology can go in terms of raw speed
 
45nm should cost less to produce (heck a 250nm P2 core with no L2 cache is more then 4 times bigger then a prescott) but usually it dont go down in price for a while (and they use the excuse "more cache" and so on for higher cost chips).

Sadly smaller nanos doesnt instantly translate into performance but allows more overclocking (higher speeds, lower heat and power) then larger nanos and more cache can be packed into a similar area.

As crap as P4s are it would be interesting to see em at 45nm - see how far cmos technology can go in terms of raw speed

First off, SRAM transistors (those of what L1 & L2 caches are made of), are very expensive to produce in large quantities; hence, its huge cost;

Second, smaller nodes do not - linearly - translate into 'performance' gains: if 'performance' is meant to be multi-GHz multithreading, then no, no much gain in such kind of performance & no much room for overclocking either, due to leakage/inductance/capacitance/quantum tunnel effects and... heat, of course, at the transistor level;

Third, physics being the same for everyone, everywhere, "raw" speed is only a part of the equation: smaller fab nodes allow for more features to be included & becomes a challenge for designers/architects & engineers to be able to squeeze the most out of the underlying microarchitecture (that's how & what AMD did, for instance);

Again, the laws of physics are the same for everyone (in this case, AMD, Intel, IBM, nVIDIA, ATi,...); all things being equal (physics included), one manufacturer would suffice, in each computing branch...


Cheers!
 
45nm should cost less to produce (heck a 250nm P2 core with no L2 cache is more then 4 times bigger then a prescott) but usually it dont go down in price for a while (and they use the excuse "more cache" and so on for higher cost chips).

Sadly smaller nanos doesnt instantly translate into performance but allows more overclocking (higher speeds, lower heat and power) then larger nanos and more cache can be packed into a similar area.

As crap as P4s are it would be interesting to see em at 45nm - see how far cmos technology can go in terms of raw speed

No, Pentium's will no longer exist by the time Fall comes in favor of Intel's shiny new architecture, Conroe.
 
yeah i know that, but as a laugh to see em at 45nm and see how far they could go (i wanna see the 10ghz barrier broken) but yes i know they canned the P4 design for conroe

joset already know that you just overanalised my post
 
yeah i know that, but as a laugh to see em at 45nm and see how far they could go (i wanna see the 10ghz barrier broken) but yes i know they canned the P4 design for conroe

joset already know that you just overanalised my post

Oh, sorry. But yes, that would f*cking kick ass I agree. A 10ghz cpu, no matter how crappy the architecture...simply could kick ass in anything
 
Isn't it just getting harder for AMD?!

And why??

It's a sweet joke for me to know that Intel's 65nm aren't cool enough than AMD's tried-and-true 90nm. :lol:

Did you see the new AM2 processors (specifically the 35W X2 3800+) which will consume no more than 65W (excluding the FX-62)?
Let's not forget that these are still 90nm 8) [/code]
65 watts?! My XBOX runs 75 watts load!