quote: That's what the process node gives you. Average feature size yields a linear metric for transistor density.
quote: "The 32nm test shuttle that Intel announced yesterday was 1.9 billion transistors per chip"Ah, but that's 2 years away at least.
quote: Now we have chips that are a billion or so transistors, but 800 million of which are cache.
quote: NAND "sort of" made huge progress switching from SLC to MLC -- but again that's not really production yet anyway.
quote: Of course, thats exactly what I said. Moore simply mated a statement of geometry to the the assumption that new process nodes would appear in linear time.
quote: In my opinion, Moore's Law already died quite some time ago.
quote: But here's where the problem comes in. Moore didn't postulate "roughly" two years. He postulated ONE year. Intel, realizing the marketing value of "Moore's Law" has since restated it to 18 months, then 2 years. Soon it'll be 3 years.
quote: Density can be expected to be proportional to the reciprocal of area, so the contribution to improve density vs. time from the use of smaller dimensions is plotted in Figure 3.
quote: The new slope might approximate a doubling every two years, rather than every year, by the end of the decade.
quote: 3. The performance of processors double every 18 months.
quote: When Moore first stated his "law" in 1965, he gave the interval of 12 months. In the early 1980s, Intel was quoting it as 18 months. Today, its been revised to "about two years" between nodes. In a decade, Intel will be telling us Moore's Law means "transistor counts double every 3-4 years".