AMD K8L: Next generation CPU

AM2's memory controller is just like the old Socket 939 memory controller, but it's improved and updated for only DDR2.
 
AMD is also promising 45nm processors by mid-2008!!!! Replacing the 65nm fabrication process is a new 45nm SOI process that is expected to be in production soon. K8L is still being developed as a 65nm platform and expected for its initial release in 2007.
 
They're already thinking of the 45nm process?! That's incredible! Did I miss something, or has AMD even released a processor with the 65nm process in it yet... Is AM2 incorporating the 65nm process at all?
 
Yes it will.

AMD 65nm Desktop Processor Roadmap 2006:

Athlon 64 4800+ AM2 2.4GHz 2x1MB
Athlon 64 4600+ AM2 2.4GHz 2x512KB
Athlon 64 4400+ AM2 2.2GHz 2x1MB
Athlon 64 4200+ AM2 2.2GHz 2x512KB

I may wait for those.
 
Probably just a die shrink, but K8L is four cores....kinda pointless if you ask me. dual core is fast enough for me. Ill just stick with Conroe and my future water cooling :D
 
Ah, so they are incorporating the 65nm process... That's a relief. I agree, TRD; I would wait for one of those with the smaller process than to buy one now with the older 90nm process.

Ownage, do you know when Conroe is supposed to officially be released to the general public? I know some folks at Xtreme Systems have them, but I mean like when is Newegg going to get them in? And do you know the pricing?
 
conroe5258ol.jpg
 
ownage said:
No major flaws? I think not. IMC was flawed beyond belief for enthusiasts. Cold bug especially. Not being able to run 4 DIMMS @ 1T was also a flaw.
Im pretty sure K8 had its major flaws just like P4.

Hmm, Lets get back to the subject here. Were talking about the overall architecture of the K8, and in comparrison to the P4 there is no major flaws! Yeah, you HAD your Cold bug problem, but like EVERY other CPU out there, they all have their bugs. A bug macro code fixes with every new update (slight differences in stepping numbers?). In this case, the problem was sorted in the San Diago and Venice cores. A Intel example, the huge instability problems of the Coppermine P3s. Your Integrated Memory Controller problem? Please expand, as none come to mind. If you don't use recomended memory, it's not a problem. Not being able to run 4Dimms at 1T, show me a non-AMD desktop board that does. The IMC is far superior to any Intel setups!

The Point I was trying to make is, the K8 Architecture itself is still worthy, has NO major flaws and still is perfecting fit to expand on. IE, the Hypertransport/Integrated Memory Controller/K8 Architecture is sound and still has potential. In comparison to Intels overheating, over pipelined, only good at encoding CPU without half decent Multi-cored architecture the K8 has the foundations such as the half decent multicore potential Intel never planned. Intel had to redesign from the ground up to get this expandibility. AMD with the K8 doesn't need to and there's no reason for AMD to release anything different. Strap on some extra cache, another couple of cores (totaling 4 - as I'm guessing they'll need to get a license for Hyperthreading of Intel in order to use it), upp the Hypertransport bus and lower the size of the fabrication process, increase the clock speed, and you'll end up with a CPU that will still be able to compete towards without changing the Architecure. Now try that on a P4.... oh, wait. It's been done, and it's still hit a brick wall. Thats my point, thats why there still using K8!
 
"AMD announced at its Technology Analyst Day plans for a enthusiast platform based on dual-core processors and dual-socket motherboards. In 2007, when AMD releases its quad-core chip, the “4x4” will support a total of eight cores. The platform will use the recently launched AM2 socket. Through Direct Connect tech it will allow each core to access the other ones as well as directly communicate with system memory."

You can learn all of AMD's plans here. New for 2006 and beyond:

http://www.amd.com/us-en/assets/content_type/DownloadableAssets/PhilHesterAMDAnalystDayV2.pdf

http://www.amd.com/us-en/assets/content_type/DownloadableAssets/MartySeyerAMDAnalystWebV2.pdf

http://www.amd.com/us-en/assets/content_type/DownloadableAssets/DarylOstranderAMDAnalystDay.pdf

http://www.amd.com/us-en/assets/content_type/DownloadableAssets/JoeMenardAMDAnalystDayv2.pdf
 
connchri said:
Hmm, Lets get back to the subject here. Were talking about the overall architecture of the K8, and in comparrison to the P4 there is no major flaws! Yeah, you HAD your Cold bug problem, but like EVERY other CPU out there, they all have their bugs. A bug macro code fixes with every new update (slight differences in stepping numbers?). In this case, the problem was sorted in the San Diago and Venice cores. A Intel example, the huge instability problems of the Coppermine P3s. Your Integrated Memory Controller problem? Please expand, as none come to mind. If you don't use recomended memory, it's not a problem. Not being able to run 4Dimms at 1T, show me a non-AMD desktop board that does. The IMC is far superior to any Intel setups!

The Point I was trying to make is, the K8 Architecture itself is still worthy, has NO major flaws and still is perfecting fit to expand on. IE, the Hypertransport/Integrated Memory Controller/K8 Architecture is sound and still has potential. In comparison to Intels overheating, over pipelined, only good at encoding CPU without half decent Multi-cored architecture the K8 has the foundations such as the half decent multicore potential Intel never planned. Intel had to redesign from the ground up to get this expandibility. AMD with the K8 doesn't need to and there's no reason for AMD to release anything different. Strap on some extra cache, another couple of cores (totaling 4 - as I'm guessing they'll need to get a license for Hyperthreading of Intel in order to use it), upp the Hypertransport bus and lower the size of the fabrication process, increase the clock speed, and you'll end up with a CPU that will still be able to compete towards without changing the Architecure. Now try that on a P4.... oh, wait. It's been done, and it's still hit a brick wall. Thats my point, thats why there still using K8!

It will be good until July 23rd, I gurantee it. K8 is getting old. It used to be good, but not anymore. Core 2 will destroy it. I dont see AMD setting any records in 3D anymore. Even less in Super Pi 1M AND 32M. Conroe has better clock for clock performance than Windsor or Toledo. K8s are getting extremely hot too. 125W TDP, that is pushing the envelope toward Prescotts. Is K8L a new type of architecture? No, its only a tweaked K8. 4 core? give me a break, we barely use two right now. Intel automatically diverts to 2T, so what? It makes up for it in the higher FSB. The only thing that K8 have is high memory bandwidth. Why? cuz of IMC. Even with recommended memory, K8 will still go to 2T with 4 DIMMs populated. It is very difficult to achieve 1T with 4 DIMMs. AMDs K8 is getting old and it needs to be retired. They can try to tweak it even more, but the performance isnt going to be a drastic improvement. While Core 2 has a whole new road in front of it. There is more room for expansion. I would really like to see a 9sec super pi from ANY AMD processor.
 
Back
Top Bottom