Intel ''64'' finally

[Dustswirl]

Heads up guys, it's finally coming

Pentium F

 

[Alkaline5]

Wow, that shot of the CPU confirms it.

Seriously, though, isn't it a little early for Intel to be putting out a 64-bit CPU aimed at the average consumer?

 

[SickBeast]

Pentium F??

That's even worse than Sempr0n.

Hopefully with intel doing the iAMD64 thing we'll see 64-bit Windows XP much sooner.

 

[Dustswirl]

Hopefully with intel doing the iAMD64 thing we'll see 64-bit Windows XP much sooner.[/quote]

Amen to that bro

 

[ectx]

Anyone else has more information on this?

See if Intel can pull a rabbit out of the hat. Never one to root for Intel (especially after I sold my Intel stocks), but I hope Intel can foce AMD to come up more reasonable priced A64's.

Own 4 AMD rigs and 1 Intel rig currently. Looking foward to an upgarde to A64 at a reasoable price.

 

[lookouthere]

it seems that intel want to cuss about their pentium
LOL

 

[Avalon]

A prescott with 64bit capabilities tacked on?

 

[Yanagi]

WTH? Pentium F!?!?! I wish their marketing team would come up with better names.. I swear. By the end of 2005 we'll see Pentium A-Z in same clockspeeds. And people bash AMD for their naming scheme.. sheesh...

 

[magomago]

That is more code revision of processors MY friends think a P4 is the same whether it is a P4A or a P4E I think only the Celeron are advertised as "celeron D"

 

[TK-421]

Dell is selling these now in their new Precision 370 Workstations:

http://www1.us.dell.com/content/products/productdetails.aspx/precn_370?c=us&cs=04&l=en&s=bsd

 

[DAPUNISHER]

Unless they move the memory controller on-die they will still be getting their a$$ handed to them I suspect.

 

[orangat]

Originally posted by: DAPUNISHER
Unless they move the memory controller on-die they will still be getting their a$$ handed to them I suspect.

I think so too. Memory latencies haven't kept up with CPU clockspeeds. AMD made a wise move.

 

[Canterwood]

Don't expect to see these in the mainstream market like AMD for a while. These are just to keep the big OEM's happy.

Another linky

 

[Zebo]

F is approporaite nomenclature since it's based on the failure that is prescott.

truth in advertising form Intel? who'd thunk it?

 

[RaynorWolfcastle]

Originally posted by: DAPUNISHER
Unless they move the memory controller on-die they will still be getting their a$$ handed to them I suspect.

I read a while ago that Intel had a different solution to that problem. They wanted to put a high speed buffer/interface on RAM sticks. The result is that you could use any memory architecture behind the buffer and the motherboard would be none the wiser. Basically, you'd be decoupling the memory from the rest of the system; that would allow more flexibility for memory and since the buffer is basically a cache chip, the latencies would be much lower for many cases. I'll see if I can find the article.

 

[AWhackWhiteBoy]

Originally posted by: DAPUNISHER
Unless they move the memory controller on-die they will still be getting their a$$ handed to them I suspect.

DDR2 is shaping up to be extremely impressive. i woudln't speak so soon!

 

[DAPUNISHER]

Originally posted by: RaynorWolfcastle

Originally posted by: DAPUNISHER
Unless they move the memory controller on-die they will still be getting their a$$ handed to them I suspect.

I read a while ago that Intel had a different solution to that problem. They wanted to put a high speed buffer/interface on RAM sticks. The result is that you could use any memory architecture behind the buffer and the motherboard would be none the wiser. Basically, you'd be decoupling the memory from the rest of the system; that would allow more flexibility for memory and since the buffer is basically a cache chip, the latencies would be much lower for many cases. I'll see if I can find the article.

Thanks, I'd like to read that

Originally posted by: AWhackWhiteBoy

DDR2 is shaping up to be extremely impressive. i woudln't speak so soon!

I must admit I haven't been closely following DDR2 benchmarks but what I've seen most certainly wasn't impressive. Could you please link some benchies that demonstrate this? TIA

 

[AWhackWhiteBoy]

while there isn't much of a performance difference between really good 400mhz DDR ram against 533mhz DDR2, it still doesn't actually fall behind in any benchmark, it always stays ahead. also the fact that these very first DDR2 chips are seeing OCs are much as 650mhz,i'd say the technology has PLENTY of room to grow. furthermore, these benchmarks are on first generation chipsets,with first generation DDR2 mobos,with first generation sticks of ram.

remember how much 200mhz DDR ram sucked back when it first came out? then the 266 blew us away. just wait another year, DDR2 will be on everyones list of upgrades.

 

[DAPUNISHER]

Originally posted by: AWhackWhiteBoy
while there isn't much of a performance difference between really good 400mhz DDR ram against 533mhz DDR2, it still doesn't actually fall behind in any benchmark, it always stays ahead. also the fact that these very first DDR2 chips are seeing OCs are much as 650mhz,i'd say the technology has PLENTY of room to grow. furthermore, these benchmarks are on first generation chipsets,with first generation DDR2 mobos,with first generation sticks of ram.

remember how much 200mhz DDR ram sucked back when it first came out? then the 266 blew us away. just wait another year, DDR2 will be on everyones list of upgrades.

Price DDR2 lately? The small performance gains certainly don't justfy the price. As to "down the road" I too am certain the DDR vs SDRAM senario will repeat itself. However, AMD 64bit CPUs don't benefit from extra bandwidth much and Intel will be getting away from the current architecture if the news I've seen is correct. The advantages of bandwidth that P4&Prescott see may not apply to the new core so much. What was mentioned about decreasing latencies sounds more effective to me, but I'm no IEEE guy so that's just a poorly educated guess If that did happen though DDR2 would become the new RAMBUS, needed for awhile in order for Intel to get the performance from the CPU they desire than abandoned in favor of another tech.

 

[AWhackWhiteBoy]

its not THAT much more expensive in relation to the stuff its benchmarked against, 2 2-2-5 or whatever high grade ram. and thats just because there not much demand, it will come down like anything else. i'm not sure how the next generation processors will take to ram. i think it will just raise the bar like anything else. just because AMD doesn't double pump the FSB doesn't mean it won't still scale with the extra FSB being pumped through it. the barton core(266/333/400) is a prime example.we'll soon see how the Dothan does when they start pairing it with higher FSB frequencies in the next few months,also.

 

[DAPUNISHER]

Originally posted by: AWhackWhiteBoy
its not THAT much more expensive in relation to the stuff its benchmarked against, 2 2-2-5 or whatever high grade ram. and thats just because there not much demand, it will come down like anything else. i'm not sure how the next generation processors will take to ram. i think it will just raise the bar like anything else. just because AMD doesn't double pump the FSB doesn't mean it won't still scale with the extra FSB being pumped through it. the barton core(266/333/400) is a prime example.we'll soon see how the Dothan does when they start pairing it with higher FSB frequencies in the next few months,also.

You are comparing apples to grapefruit now brudda Barton is old tech, AMD doesn't have an FSB anymore, and FX vs A64 clearly demonstrates that dual channel and the extra bandwidth it provides is only good for about 4% which isn't enough to "feel in real world situations" Consequently speculation about what bandwidth can do for AMD isn't required because it is already known that AMDs current architecture doesn't need more bandwidth.

AMD has already stated it doesn't intend to use DDR2 anytime soon, and since we are looking at precedence, the RAMBUS senario is a prime example of how Intel will rely on a solution when needed and drop it like a letter full of anthrax ASAP if something better comes along BTW, have a look at Sempron on sktA vs skt754 and it becomes readily evident that putting the memory controller on-die is pure genius :light:

 

[Vee]

The big question is how it performs with true 64-bit addressing.

Otherwise, I'd say if we can get cheap, well performing 4GB-8GB RAM solutions from this Pentium4F and chipsets, this is interesting.

 

[AWhackWhiteBoy]

it is already known that AMDs current architecture doesn't need more bandwidth.

we'll see what happens with two cores on one die fighting for the memeory bandwidth

 

[DAPUNISHER]

Originally posted by: Vee
The big question is how it performs with true 64-bit addressing.

Otherwise, I'd say if we can get cheap, well performing 4GB-8GB RAM solutions from this Pentium4F and chipsets, this is interesting.

Good question, but IME cheap and performance are not used together with Intel sorry 'bout that Wingz I couldn't resist

 

[DAPUNISHER]

Originally posted by: AWhackWhiteBoy

it is already known that AMDs current architecture doesn't need more bandwidth.

we'll see what happens with two cores on one die fighting for the memeory bandwidth

It hasn't crippled dual Opteron setups why should it cripple dual core?