The end of Moore's law has already happened?

krazykoding.com

4 points·PKeeble··3 comments

It looks like we are approaching the end of Moore's law. Heat is making it impossible to add additional transistors into CPUs and GPUs and the end result is that today’s computer technology is about as fast as silicon transistors can go. Future gains are going to have to be based on architecture changes in the hardware to be more efficient and software algorithm improvements. That's not going to bring gains at the same pace we've seen in the past.

I'll put my money on the creativity and imagination of the engineers that build this stuff, the business men behind it that demand it, and the marketers that will convince you it's not true.

If Moore's Law hadn't taken hold so prominently, it's possible that the level of aggressiveness the industry took towards shrinking chips would not have been 2x every 18 months. Most people inside the industry will tell you it's more of a self-fulfilling prophecy

People also never seem to realize that Gordon Moore made his prediction with only four datapoints... He's clearly a brilliant man, but that's usually hardly enough data to claim anything :)

original graph on page 3 -

ftp://download.intel.com/museum/Moores_Law/Articles-Press_Releases/Gordon_Moore_1965_Article.pdf

Seems like this article needs references.

AMD and Intel are both working on building out more cores, and building in new instruction sets (AVX, etc.) that allow for vector FP. That said, we're not seeing the single core clockspeed increase like in the late 90's.

On the other hand, the chip shrink is getting us stuff like Flash SSDs and very nice power reductions so those 4-8 core chips will go in new 10-hour laptops...

Moore law is only that the price of a given set of transistors will diminish over time.

Nowhere in the original definition it says that all of those transistors have to be in the same processor.

Reply on news.ycombinator.com