why rush to 45nm?
To crush the competition.
It is going to have all kinds of problems that affect bin splits and yields, such has been the trend since 130nm and has only been getting worse...
Apparently 45nm is looking particularly good for Intel:
theinquirer.net
EARLIER WE POINTED OUT that the 45nm shrink of Merom is going to be called Penryn, the Moldavian term for moldy Apple(1). The interesting thing is not about the chip itself, but the process. Since the 65nm process is on the verge of release, it means that this coming IDF, they will probably start talking about the 45nm process.
Think happy thoughts here people, from what several sources have told the INQ, the leakage problem is solved, and I mean solved, not lessened. This will be a massive gain for Intel, and unless AMD and IBM can match it, it will pretty much hand it the mobile space, not to mention anything else where power matters.
From what we have been told, the 65nm process is better than 90nm in leakage, but it is an advance, not an answer by any means. Sadly, the process breakthroughs can't be backported to 65 in a way that would do the same there. There are some other 45nm breakthroughs, and I am not using that word in lightly, in the yield area that will get sucked into 65nm. Expect improvements on this process over time, and then a huge leap at 45.
[...] |
