166 FSB on Presscott

[juin]

http://www.watch.impress.co.jp/pc/docs/2002/0228/kaigai01.htm

in JAP

cheap, cheap. Think cheap, and you'll always be cheap.AMD version of semi conducteur industrie

 

[Matisaro]

cheap, cheap. Think cheap, and you'll always be cheap.AMD version of semi conducteur industrie

Please have an english friend check the spelling of your sig juin, ok.

"The Cash Left In My Pocket,The BEST Benchmark"
No Overclock+stock hsf=GOOD!

 

[Raystonn]

Prescott will have an 800MHz FSB, as compared to the 400MHz FSB currently offered on the Pentium 4.

From <A HREF="http://www.anandtech.com/showdoc.html?i=1593" target="_new">Anandtech</A>:
-----
On the Intel side of things we completely forgot to mention one very important characteristic of Prescott yesterday. If you'll remember back to our <A HREF="http://www.anandtech.com/cpu/showdoc.html?i=1542&p=1" target="_new">BBUL technology article</A> we gave a little preview of the FSB frequencies of future Intel processors - with Prescott coming in with an 800MHz FSB (presumably 200MHz quad-pumped). As far as other enhancements go, the move to a 0.09-micron manufacturing process will reduce the current Northwood die size by about half leaving quite a bit of room for additional architectural enhancements. Some theories we had included offering more cache (768KB or 1MB?) and maybe even moving to 32-bit ALUs instead of the current 16-bit units. The latter would make sense since Intel <A HREF="http://www.anandtech.com/cpu/showdoc.html?i=1584" target="_new">has been demonstrating high-speed 32-bit ALUs for quite a while now</A>.
-----

-Raystonn


= The views stated herein are my personal views, and not necessarily the views of my employer. =

 

[eden]

I'll be more impressed when they consider getting the FPU back. You may not be allowed to tell me if they will, but they better do so, or else they really don't know what they're doing with their competition.

--
For the first time, Hookers are hooked on Phonics!!

 

[juin]

The new was post after i have put the link.Also weird thing 800 FSB be only clock (sync)with dual DDR 400.

cheap, cheap. Think cheap, and you'll always be cheap.AMD version of semi conducteur industrie

 

[POPEGOLDX]

Mr RAY. What is INTEL's feeling about the HAMMER. I mean the last time INTEL mentioned AMD , they said they were more concerned with VIA than AMD.

I know Intel wants to accelerate the switch to 64-bit....

Will they let HAMMER blindside as Athlon did to some degree?

Are the readying PRESCOTT as thier answer?

 

[girish]

juin do you know Japanese?

<font color=red>Nothing is fool-proof. Fools are Ingenious!</font color=red>

 

[juin]

http://www.xbitlabs.com/news/story.html?id=1015045826

a fsb at 667 so 166 Quad

cheap, cheap. Think cheap, and you'll always be cheap.AMD version of semi conducteur industrie

 

[bikeman]

Can anybody explain to me, or post a url to a document that explains it to me, how a QDR-bus works? I get the DDR-principle, but QDR? I thought a signal had only 2 edges, not 4 ...

Tia!
Bikeman

 

[juin]

there is even ODR for 8 time per singnal

cheap, cheap. Think cheap, and you'll always be cheap.AMD version of semi conducteur industrie

 

[girish]

It looks that the Prescott will have two models, the Prescott A (533 MHz FSB) and Prescott B (667 MHz FSB) just like the Northwoods! Boyz get ready for changing your motherboards again! Because Intel wont release a 667 MHz chipset before the Prescott B, so you will have to buy them together! Just like you are waiting for the i850E for NWB!

Its interesting about the Yamhill, Intel should really include it with the Prescott. But even if they include it in earlier models a microcode update that would be distributed alongwith a BIOS update would quietly disable it and you would never know, unless you use a x86-64 based app!

girish

<font color=red>Nothing is fool-proof. Fools are Ingenious!</font color=red>

 

[girish]

Actually, I think what we should really be concerned about is the memory bandwidth available to the procesor on the frontside bus rather than its physical speed. With a FSB of 200 MHz (400 DDR) as acheived a number of times with the Iwill XP333 board, the Athlon gets a memory bandwidth of real 3.2 GB/sec which is the same as that of a 400 MHz FSB P4. If a comparison of these two processors could be made, it would be a real battle of the processors with equal justice.

I hope AMD will make the FSB of later Athlons (the Bartons) multi-channel high speed so that the memory bandwidth could be improved. The physical speed of the FSB is really approaching its max limit. Maybe 233 MHz, no more than that! A multichannel memory architechture would allow them to have much higher bandwidth.

girish

<font color=red>Nothing is fool-proof. Fools are Ingenious!</font color=red>

 

[eden]

Some have tested OCZ PC3000 memory (3GB bandwidth) on an Epox 8KHA+. Although it's known that PC3000 would not possibly offer any performance increase that is noticeable, knowing the fact the FSB is limited and there is no optimized bandwidth, the Sandra test on memory actually showed it above the NW's RDRAM 3.2GB! I dunno how true this is but it shows some indication Intel's 3.2GB RDRAM is not functionning properly or is not even optimized! Something normal I'd say, since it's so crippled.

--
For the first time, Hookers are hooked on Phonics!!<P ID="edit"><FONT SIZE=-1><EM>Edited by Eden on 03/03/02 05:19 PM.</EM></FONT></P>

 

[juin]

Even if the mory be as fast as the RDRAM due to a poor effectinest they still be slower that RDRAM

cheap, cheap. Think cheap, and you'll always be cheap.AMD version of semi conducteur industrie

 

[girish]

dint quite get you.

if you are saying that DDR has lower efficiancy than the RDRAM, I cannot help laughing. While the RDRAM may prove better due to its multiple channel operation, it has inherent latencies which hold it back. DDR however can operate as fast as CAS2 even at FSBs as high as 166 MHz and then drop the CAS timings on higher speeds.

At 200 MHz which is pretty much acheived on the Iwill XP333 board more than once, it brings 3.2 GB/sec memory bandwidth for the Athlon which is actually level field for comparison with the P4. How well it does is a question of testing, somebody should really do it for the rest of us.

girish

<font color=red>Nothing is fool-proof. Fools are Ingenious!</font color=red>

 

[eden]

Slower? The only reason it's 800MHZ, is that it can be achieved by that measily ridiculous 16 bit data path! It ain't faster at all. Plus it needs dual-channeling to compete.

--
For the first time, Hookers are hooked on Phonics!!

 

[eden]

Also they'd have to dual channel DDR to level it to mr. RDRAM! Or vice versa...either way DDR would win. But I would like to see how at same bandwidth, which is more effective at using it.

--
For the first time, Hookers are hooked on Phonics!!