toms article on core 2

[tigger]

forgive me if you've all read it but its quite interesting-
http://www.hardwareanalysis.com/content/columns/article/1834/






http://miniprofile.xfire.com/bg/bg/type/0/tiggerhull.png (http://profile.xfire.com/tiggerhull)

[Alec§taar]

Cool by me!

Hey - never hurts to get someone else's "take" on things... especially if it is consistent w/ other reviews findings!

(& even moreso if it finds "HOLES" others have not!)

:)

* Thanks for "the good word"...

APK

[tigger]

it is an interesting article indeed.


Also there’s no mention of their upcoming K8L architecture anywhere? Has that new architecture perhaps been obsoleted with the launch of these new Intel processors, even before it has been officially launched?


Either way it is a fruitless exercise if these new processors will not be ready to ship in due time, especially if you’re looking to buy a new PC this year. Considering the fact that AM2 needed several revisions to perform on par with S939 and there’s a ~50% performance gap between comparable AMD and Intel processors I don’t expect AMD to pull anything innovative out of their sleeve in the near future. As honestly that’s a pretty big performance gap that AMD needs to plug, whichever way you choose to look at it. As mentioned the focus for AMD seems to be on shrinking the manufacturing process to cut cost and up the volume. It looks like Intel will be in the driver's seat for a while and all AMD can do to stay competitive for now is reduce pricing on their processors.


i am looking forward to what amd is gonna do to combat core 2 duo,and not just in massive price cuts.

edit-
just found this-Another tribute to the competence of the design team is the fact that despite not having an on-die memory controller the Core 2 processor has lower memory latency than AMD’s much heralded on-die memory controller. Although the Core 2 processor uses the 128-bit DDR2 memory controller on Intel’s 965 or 975X chipset the shared L2-cache between the two processors helps to keep all the cache to cache traffic off the FSB, freeing it up for memory access and other I/O. Other optimizations are put in place as well to reduce overhead, even simple ones such as only keeping one set of data that’s needed by both cores, rather than two.
in here-http://www.hardwareanalysis.com/content/reviews/article/1833/
the memory thing got me, i thought the controller on the die was better,does this say no?


http://miniprofile.xfire.com/bg/bg/type/0/tiggerhull.png (http://profile.xfire.com/tiggerhull)