So let's say that you're Intel, and you've got this microprocessor architecture that's the backbone of your central product line, with millions invested into developing it and improving it. And let's say that the fundamental premise on which that microarchitecture was built craps out a few years too soon. What do you do? In Prescott's case, it looks like the answer is to try your best to adapt the old design to a new set of circumstances, rather than throwing it out the window. This means cranking way back on the clock speed increases, and taking advantage of Moore's Curves* by adding functionality to the die instead. This added functionality comes in the form of a whole other core, rather than a few new execution units and some cache.
Head on to Ars and read the article
marky! this is too much for me. i'm no geek! hehe... :j
ReplyDeletekaya nga di ko sya pini-pimp eh. agh. at least now that I have an outlet for my geekiness, maybe i would stop "blab"ing about them when im with you guys.
ReplyDeletehah. geek. indio. the name says it all.
ReplyDelete