Yonah Preview at Anandtech!

[Carfax]

Yonah preview over at Anandtech:

Here

It did well considering it's amazing low TDP, but I think some people will be disappointed. Still, I'm sure that Yonah will look amazing when overclocked

The motherboard Anandtech used was a desktop version, with all the bells and whistles. So, we'll definitely see motherboard manufacturers making special motherboards for those of us who wish to use a mobile in our PCs.

[caater]

so, benches (spi, 3D) and games are going to be slower and all other things faster?

[Wrench]

Un-impressive I was expecting Yonah would do better then then a Dothan. I think when AMD releases the new socket for mobiles Intel will be in trouble in the mobile arena. It looks like AMD will have performance crown for at least another year or even more.

Although yonah is 65microns it might clock very well.

[cirthix]

interesting, clock for clock it is slower than the x2 (with 512k cache per core) whereas the dothan is faster clock for clock than an athlon64. i'm disappointed, but it all depends on how well they overclock. dual core is very nice though

[skane]

yonah looks dissapointing, i was expecting at least the same performance as dothan, except with a better floating point unit. do keep in mind that in the direct dothan vs yonah, the dothan had a 133 MHz advantage.
i also noticed that power consumption is pretty high, iirc, dothan has about 40 watts, so i expected yonah to be around 70-80 watts, it being 65nm.

[saaya]

hmmmm under load its 36W less than a dual core a64? and a dual core a64 is putting out how many watts? 80W? 90W? so yonah is at what, 40-50W?
hmmm thats great for a desktop cpu, but for a mobile cpu thats not good...

too bad he didnt compare it to a dothan plattform :/

[saaya]

yonah looks dissapointing, i was expecting at least the same performance as dothan, except with a better floating point unit. do keep in mind that in the direct dothan vs yonah, the dothan had a 133 MHz advantage.
i also noticed that power consumption is pretty high, iirc, dothan has about 40 watts, so i expected yonah to be around 70-80 watts, it being 65nm.

dothan is clocked 133mhz higher but its single core and has a 133mhz fsb, yonah is dual core and has a 166fsb... yonah should still beat dothan while running 133mhz lower... the fact that it doesnt in some benchmarks is dissapointing me... :/

and no, dothan isnt 40W, its 25W!
and yonah looks like around 50W... not good for a mobile cpu, not good at all.. hmmmm maybe the board set a higher than default vcore? i kinda hope so and yonah actually runs cooler... or the yonah board consumed more power than the a64 board for some reason... i cant believe its consuming around 50W at only 2ghz hmmm

its still a very decent cpu... but a single core yonah will probably be slower than a dothan it looks like...

[cirthix]

yonah is also 25w. i'm really hoping for 3ghz+ ocs, but i dont know if they can do it.

[wwwww]

yonah is also 25w. i'm really hoping for 3ghz+ ocs, but i dont know if they can do it.

I'd say 3GHz would be easy, they'll prob do around 3.0 - 3.2 given the ass'd L2 latency. C'mon, 14cc l2, I'm surprised they're even able to compete with the X2 at same clocks.

[Carfax]

One reason for the lower than expected performance is probably the FSB. We don't know what Anand set the FSB at, but I don't think it's over 533, and two cores sharing a 533 FSB will be starved for bandwidth.

So, jacking up the FSB will increase the performance by a great deal, just as with Dothan.

[skane]

if yonah is supposed to be around 50 watts, why do the power consumption numbers at the last page say the power consumption at load is 108?? Or do i read that graph wrong?

[onewingedangel]

Thats for total system not just processor

[rozzyroz]

guys, you have to remember that dothan was slower then the a64 when it was at stock speeds. (a64 vs dothan) yonah will every bit as powerful as dothan in games, but it will wipe the floor with it in everything else.... not to mention that it should be 3.0 ghz on a standard air oc. (crosses fingers on the ocing results)

[crotale]

I think it performs as one could expect. I would definitely like to see it with 200FSB though.

This Yonah at 200FSBx15 = 3GHz, and 3:5 mem divider could be a nice 24/7 rig

[alexio]

dothan is clocked 133mhz higher but its single core and has a 133mhz fsb, yonah is dual core and has a 166fsb... yonah should still beat dothan while running 133mhz lower... the fact that it doesnt in some benchmarks is dissapointing me... :/

and no, dothan isnt 40W, its 25W!
and yonah looks like around 50W... not good for a mobile cpu, not good at all..

They only messured total system power usage. remember that the AMD chipset is doing 200mhz while the Intel is only doing 166mhz, and so is the system RAM

I'm sure that can make up for another 10-20W. I don't think 30-40W is bad for a dual-core cpu with Yonah's performance.

[skane]

guys, you have to remember that dothan was slower then the a64 when it was at stock speeds. (a64 vs dothan) yonah will every bit as powerful as dothan in games, but it will wipe the floor with it in everything else.... not to mention that it should be 3.0 ghz on a standard air oc. (crosses fingers on the ocing results)

i remember that, but in the link you provided, dothan is faster clock-for-clock in ut2004 (the only bench that both articles have in common), and yonah is slower than a64 x2 in the yonah article. That is why i think it performs below expectations.

i didnt realize that graph was total system power usage. In that case, i think that is ok for a dual core cpu.

[R101]

Two questions/thoughts come to my mind -

a) How would things look like at FSB 266, DDR2 800? If 9xx series is anything to go by, we will have 3.2GHz air cooled Yonah cpus..

b) Does the single-core Yonah have the same latency penalties?

[saaya]

yonah is also 25w. i'm really hoping for 3ghz+ ocs, but i dont know if they can do it.

says who?
all the infos ive seen say up to around 55W

One reason for the lower than expected performance is probably the FSB. We don't know what Anand set the FSB at, but I don't think it's over 533, and two cores sharing a 533 FSB will be starved for bandwidth.

So, jacking up the FSB will increase the performance by a great deal, just as with Dothan.

all yonahs are 166fsb default, only the ulv ones are 133fsb
if he ran it at 133fsb he would have made a note about it because it would seriously limit the performence.

the article is called part1, wich sounds like there wil be a part2... but there have been many "previews" on anandtech and the actual "reviews" never got posted... but im pretty sure there will be a part2 this time
cant wait

and i hope this time he compares dothan to yonah

Two questions/thoughts come to my mind -

a) How would things look like at FSB 266, DDR2 800? If 9xx series is anything to go by, we will have 3.2GHz air cooled Yonah cpus..

b) Does the single-core Yonah have the same latency penalties?

a) no word about ocing yet from anybody yet you are already dreaming of 3.2ghz and even on air!
b) it might be lower since all the cache used will be directly attached to the cpu in use. on the dual core each core can use the cache of the other cpu wich definately icnreases the latencxy at least when it uses the cache of the other cpu.

but i think in the tes they used they only used the cache the no1 core has attached to itself, so i think the single core yonahs will have the same cache latency.

[R101]

a) no word about ocing yet from anybody yet you are already dreaming of 3.2ghz and even on air!

Just went overboard for a few moments. I was thinking about single core Yonah, though.

[16floz470ml]

Why does he say in the third paragraph that 479 lags behind p4 and amd in games?

[Bar81]

Why does he say in the third paragraph that 479 lags behind p4 and amd in games?

Because it's another in a long line of retarded "professional" reviews. You can tell right from the open that the reviewer has never actually used a Dothan. When it comes to gaming Dothan is still king clock for clock and an absolute knockout when it comes to performance per watt.

I'm really disgusted at Intel once again, for no reason, switching pinouts on these chips forcing everyone to use new chipsets and killing any upgrade path for P-M users.

Either way, I don't see any reason to get yonah over Dothan if you already have a Dothan.

[skane]

me too, i was thinking about going yonah after this, but i think that if i buy another proc within the next year, it will be a dothan.

[AgonxOC]

Once again Intel desapoints me. They have something good going for them and they literary f**k it up... The chip has a shared 2MB L2 cache. Why couldnt they have done two freaking dothans in a 65NM process side by side.

Alex

[kl0012]

I do not understand why many so are disappointed.
Doom3:
Dothan(2,13GHz): 95.5 fps
Yonah (2GHz): 93.8 fps
Dothan has 7% higher frequency and only 2% faster than Yonah in Doom3. It points that Yonah will beat Dothan in games.
It also drive less power than Dothan:
http://www.tomshardware.com/cpu/2005...ntium4-19.html
http://techreport.com/reviews/2005q3...9/index.x?pg=7

[skane]

i am disappointed because i thought the achilles heel of dothan, media encoding, would be drastically improved, and it hasn't. And , if they have the same clock speed, i expected yonah to be better than a64 x2, just like it is with a64 and dothan.

So unless yonah clocks REALLY good, im not going to trade my dothan for it, something i might have done if it had done the things i mentioned.

btw, it does use more power than dothan, you cant compare anand's data to thgs or techreports. I would be extremely surprised if yonah would consume less than dothan.