AMD K8L

[GiDDY_SOUL]

Read more ->
wikipedia!

x-bit labs

Conclusion in X-bit labs

The future processor from AMD, currently known as K8L, will be the next step in the evolution of the K8 series. The improvements we learned about so far such as increased to 32 bytes instruction sample, improved branch prediction algorithm, introduction of out-of-order reading, will eliminate a few bottlenecks and improve the integer performance. The expansion of SSE instruction sets will help improve the performance significantly in applications dealing with heavy floating-point or integer calculations using SSE instructions, where K8L will be able not only to compete successfully but even to outperform Conroe. The inability to decode and retire 4 commands per clock cycle in some cases may result into tangible performance gaps in integer applications. However, it may not be of that much importance in most cases, because the typical instruction execution pace in real integer applications does not exceed 2-2.5 instructions per cycle because of the data dependence. K8L performance may also be increased in other ways without raising the number of decoding and retirement pipes. Here I am talking about increasing the scheduler queue depth, reducing the number of false dependences (thanks to mechanisms similar to stack engine) and performing out-of-order reading skipping the writes. We do not know today if AMD will be able to implement these features in their new processor. We also do not know if they will modify the caching and prefetch system. However, this is very important for successful competition of the new K8L against Conroe processor in the entire range of tasks.

The successors to K8 architecture require a lot of work. They need not just to compete with Intel solutions, but to outperform them, and that is why their architecture needs to be free from the K8 bottlenecks and has to be able to decode and process up to four instructions per clock. Alas, developing and perfecting a new core is a tremendously laborious and time-consuming task. Even if a new architecture is under development at AMD, it will hardly become market-ready in the next couple of years. It’s hard to tell what this rapidly developing industry will have become like by that time!

Dynamic I/O bus introduced in K8L architecture

AM2 get upgraded to AM2+: AM3 is postponed!
Gud news + Bad news :!

AMD to enter K8L era in 2H 2007

AMD Quad-Core Altair upcoming in 2007 Q3
Here AMD claims more than 40% improvement! Now is it truely possible?



If u have more Info on K8L. Link it here!

 

[mpjesse]

Clearly, K8L is something of a revolutionary platform. The processors themselves aren't anything new, but HTX and Torrenza... that's some cool stuff. And it might just be enough to kill Conroe/Woodcrest (as far as platforms go).

Something else I've noticed is enhanced RAS. RAS is sometimes more important than CAS. If they manage to do something cool with RAS, K8L could see low latencies with existing DDR2 memory.

 

[SuperFly03]

Even if a new architecture is under development at AMD, it will hardly become market-ready in the next couple of years.

?

 

[BaronMatrix]

Something else I've noticed is enhanced RAS. RAS is sometimes more important than CAS. If they manage to do something cool with RAS, K8L could see low latencies with existing DDR2 memory.
_________________

They mean Remote Access Services.

 

[mpjesse]

I knew that! ;-)

Seriously, I thought they were refering to Row Address Strobe.

 

[jamesgoddard]

I knew that! ;-)

Seriously, I thought they were refering to Row Address Strobe.

Both wrong tbh.... RAS = reliability and stability

http://www.eweek.com/article2/0,1895,1844683,00.asp

 

[jamesgoddard]

It's better than Intel's current products for sure... I would just be wary of what Intel may pull out of the bag, 45nm before the end of 07 is possible from Intel....

 

[gOJDO]

I knew that! ;-)

Seriously, I thought they were refering to Row Address Strobe.

Both wrong tbh.... RAS = reliability and stability

http://www.eweek.com/article2/0,1895,1844683,00.asp
quite no!
BaronBS is ALWAYS RIGHT, remember: ALWAYS RIGHT!
mpjesse=noob jesus

 

[Action_Man]

Don't post heaps of pictures like that you stupid noob.

 

[RedZone]

awww poor 56ker complaining about pics.

lol

 

[m25]

Don't post heaps of pictures like that you stupid noob.

Did he step on any Intel fanboy's nerve?! :lol:
Your intel couldn't give us not even these diagrams for 3 years so go and learn how to talk to people; good manners I mean, you really need it.

 

[TechnologyCoordinator]

Don't post heaps of pictures like that you stupid noob.

I appreciated the pictures and found them informative.......noob!

Very exciting this kay eight el. I don't think it will be a Conroe killer, but AMD has a lot of cool things cooking up. I found the two most interesting to be:

DICE
Dedicated L1, L2, shared L3

 

[cyborg_ninja-117]

Something else I've noticed is enhanced RAS. RAS is sometimes more important than CAS. If they manage to do something cool with RAS, K8L could see low latencies with existing DDR2 memory.
_________________

They mean Remote Access Services.

Fail

nelahem would beat K8L by price to performance ratio

 

[m25]

Hey, NetBurst was suppose to turn your copper wire into optic fibre and speed up your Internet!

Yes...But it just turned the PC into a toaster. P3/K6 sucessors were the only evolutive winners.

 

[angry_ducky]

Cool. Too bad I can't understand most of it 😳

 

[blueocean]

certainly K8L will beat intel's conroe,but thats not point of discussion becasue main question is when AMD will come out with it? and Will intel be able to switch to 45mn from current 65mn by then and what about new architecture in first half of 2008 and intel is hiring few professional with expertise in graphics development, is it just for ati alternative or something else. lets not forgets that intel can put memory controller onchip, atleast they had sample of it, in 2005 spring IDF.

 

[mjp1618]

By the time K8L comes out, or even paper-launched, Intel's products would be based on Penryn; not Conroe.

But still, I think the K8L would be better; as it would be released about a year after the Core architecture.

But then, Core is supposed to be replaced with Nehalem in 2008...

 

[mpjesse]

certainly K8L will beat intel's conroe,but thats not point of discussion becasue main question is when AMD will come out with it? and Will intel be able to switch to 45mn from current 65mn by then and what about new architecture in first half of 2008 and intel is hiring few professional with expertise in graphics development, is it just for ati alternative or something else. lets not forgets that intel can put memory controller onchip, atleast they had sample of it, in 2005 spring IDF.

To me, K8L is more of a platform than it is a processor. And to my knowledge, Intel doesn't have anything CLOSE to what the K8L platform will be.

So to me, what Intel will have in 2008 to compete w/ K8L is irrelevant if they keep using the same chipset platform which hasn't really changed since the original P4.

 

[Heyyou27]

Fail

nelahem would beat K8L by price to performance ratio

So you're saying both Intel and AMD have sent you engineering samples of their new chips, and have already told you the pricing for them once they're available?

 

[GiDDY_SOUL]

Don't post heaps of pictures like that you stupid noob.

Why not?

Atleast those were informative... unlike ur stupid post!

 

[Action_Man]

No you stupid noob. I'm quite certain its against the tos and its poor netiquette.

 

[Action_Man]

Did he step on any Intel fanboy's nerve?!

And you're pulling this assumption from your ass? Moron. Don't you mean stepping on toes rather then nerves? Dipsh!t.

Your intel couldn't give us not even these diagrams for 3 years

WTF are you talking about moron? Did you miss all those IDF shows? :roll:

so go and learn how to talk to people; good manners I mean, you really need it.

Go learn to not be such a dipsh!t, you really really need it fanboy.

 

[Action_Man]

No noob the slides are old and its against the tos.

 

[enewmen]

wusy:

Seriously.
Where can I find info on the VIA Cyrix ?
I remember years back, the Cyrix benchmarks gave people with weak hearts - complications!
How are things different now? I need to care about this if VIA will start using lots of it's chips in UMPCs..

Thanks.

 

[guyinyourattic37]

Careful action man ur starting to sound like MMM.