pentium m desktop boards
 

i saw this, http://www.techreport.com/reviews/20...f/index.x?pg=1
(sorry if this/something simialer has been posted, i havn't been around in awhile)
i am the only one who would love for someone to get one of these and toss water cooling on it?
-anyone seen this done anywhere? i'm curious what the cpu's true overclocking potential is with something other then a tiny aluminum heatsink on it.

but the processor is deffinatly showing potential, mem bandwith is kinda low, but its gaming preformance is deffinatly impressive.

I have been thinking about the same thing, But I am waiting from the MBs that will have the dual channel DDR and 533fsb. Also the mounting holes for the HS look quite close and may be a problem mounting, I was thinking of maybe the NexxxosXP since it is only 50x50mm might be close to the size that may allow it to mount or drill/tap holes in it and mount from the bottom. Or use a good chipset block on it.

You probably wont want to watercool a mobile processor, they already run VERY cool. A decent heatsink should take care of it nicely.

the only drawback i see to using a heatsink is the incredably small area with which it would fit. heatpipes would probably work, but it'd probably be easier to fit in a small cpu block or northbridge/gpu block.

Unless you want to put a 226Watt TEC on it...
see how cold it can get and how good of an overclock that is possible with some realy good ram :)

And crank up the CPU voltage offcourse...
Aggressive cooling, high voltage, super ram and take your chances to beat desktop processors with a mobile...
If only I had the money, I'd be on it first thing in the morning

The Dothan is no doubt a good CPU clock-per-clock, in general matching or exceeding what the 512KB L2 cached XP64's can do. However I do see this as a definite apples/oranges comparison.

Dothan has a 2MB L2 cache. The Dothan is top-ending at ~2.4GHz. The Dothan does not run hot, and due to this one can speculate that there is minimal overclock overhead to be gained with cooling short of chilling (phase-change/TEC). What is missing from the tech-report review, which they admit, is the Dothan with dual-channel memory bandwidth performance, but also at 2.4GHz the Dothan's FSB is already overclocked and giving it a substantial speed boost even though it's single-channel.

This, to my mind, raises just as many "what could be?" questions with respect to the CPU's pitted against it. What if the P4's all had 2MB of L2 cache? What if their FSB's were oc'ed by 50%? The same questions apply to the AMD CPU's too.

The Dothan does not strike me as a glittering diamond that Intel have overlooked, but rather as simply an alternative, not without its quirks, and with even less MHz headroom than even the relatively immature 90nm Winchester A64's. Power/heat-wise the Dothan kicks butt, and it is primarily for this reason alone that Intel will have to abandon the Netburst architecture as it is unsustainable to continue down that road.

Like both the XP64 and the Netburst P4's, there are things that it's good at, and things which it isn't. Aside from the heat/power issue it doesn't seem particularly compelling in terms of offering a clear and distinct marketable advantage over the competition.

Really, I don't see what all the fuss is about. It's new, and that makes it exciting I guess, but it's hardly kicking butt. The next spin of A64's with more cache, and if Intel does decide to do it one last time, Prescott, will see much of Dothan's perceived superiority disappear.

Also the current mobile chipset only supports agpx4 did the a64 and p4 games tests run at 8x ? this along with single channle memory on the dothan would make the benchmarks impressive.

When Intel release the new Mobile chipset I915M which has dual channle ddr2 memory and pci-e and 533fsb as standard the 2.4ghz dothan would be very close to the top score in all tests and if they have better overclocking options getting higher than 2.4ghz / 533fsb would take it.

intel mobile chipset information

I personaly would like one for a HTPC system setup for silent running.
but it might prove to be a winner all round.
There is even mantion of dual core dothan's too.

i have to disagree with cather on a few points, the dothan might not be running extremly hot, but you have to look at the heatsink with which they acheived 20% overclock.
also the next wave(or possibly wave after) of cpu's is going to go multi core, rumors say intel has this planned with a p4 type core, but if you look at the heat output of a single core dual core is going to have very limited head room, and what about more then 2? i don't see it happening well. Intel already has yohan (dual core slightly modified dothans) in it's roadmaps. How long before intel wants 4 core chips, i don't see a p4 core being able to handle this in a consumer board just due to heat, let alone the size limitations of the core. the dothan is smaller and would be much better more feasible in terms of power consumption and heat output, dual core yohan rated at only 31W.
i agree i don't think we'll be seeing the dothan beating out all the desktop chips anytime soon, but without a new chip to replace the p4 i see it(or a beefed up version) crossing over into the desktop segment as soon as more then 2 cores will be demanded.

came across this. yes it's from theinquirer. so take it how you will.
http://theinquirer.net/?article=21091

I think the people who should be excited about dothan are the silentpc crowd - looks like equivalent/nearly equivalent performance as the top desktop processors can be had in a solution that could be passively cooled.

If Intel had even released a single core version of the Yohan, I would have been significantly more impressed than I am with the Dothan today. No real reason why the features planned for the Yohan could not have already existed in the Dothan (in a single core format).

Now THAT would've made me sit up and say that's an excellent CPU.

Like I said, the Dothan as it is today is not particularly exceptional in comparison to other CPU's. That comment may not apply to upoming CPU's, and if Yohan turns out as planned, definitely does not apply, but again, Yohan is not Dothan.

I agree with Cathar, the Dothan is a nice CPU for sure, but in a desktop environment I just dont see the 'wow' appeal. IMO the Dothan rules for what it is designed for, laptops.

why cant they put something into dual core cpu's to handle the work load of both cores without the software needing to be multi thread optimised.

Simple answer: because thats not the way math works.

More complicated answer: Any program running concurrently on more then one processor will have variables that need to be used by more then one processor. Access to these variables needs to be carefully considered, and generally complicated structures are used to avoid conflicts.

A processor that attempted to run a thread on two cores would have to have some way to figure out what the thread was going to do, and it would have to do it before running the program. Theres no way you can get information like that because its only available to the programmer and is lost as soon as (s)he compiles the code.

There are already compilers out that can look for extra thread level parallelism in code, but they work poorly and optimize only the most trivial examples. And of course they do so with the extra high level code and not a binary.

i agree cather currently it's not a huge thing, i'm deffinatly not going to run out and drop a couple grand to build one of these into gaming rig, my enthusiasm comes more from what will/can be done with the processors in the near future. i see much more potential in them then the presscot type cores.

Prescott will be with us a while longer yet. At 65nm they'll probably run a lot cooler. Not to mention theres been mention of newer Prescott derived cores, both single and dual, so who knows when (or even if) they'll launch Yohan on the desktop.