Moore's Law Nearing Collapse, Says Physicist

In a 1965 paper, Intel co-founder Gordon E. Moore predicted that the number of transistors on an integrated circuit would double approximately every two years. This prediction has proven to be uncannily accurate over the years and has come to be known as Moore’s Law. But it’s not going to hold true forever, is it? Well, it’s believed that like all things good, Moore’s Law too will come to an end one day. The question that remains, though, is when. Noted theoretical (and often theatrical) physicist Michio Kaku feels he has the answer.

Click to expand...

Read more at:
Maximum PC | Moore's Law Nearing Collapse, Says Physicist

Hi there
I love that guy doing the video -- but maybe if you read between his lips (or watch between his eyebrow movements) maybe Moore's Law itself isn't appropriate any more -- we need another measure.

If you watch this guy he's simply brilliant on Discovery / Science channels in all sorts of areas.

However I propose a new law: "Jimbo's Law" : Whatever you think might happen won't happen at all in the way you expect it to".

Cheers
jimbo

I thought Jimbo's law was that every post must be way off topic by the 3rd paragraph

An yet another reference to the best show on TV was the mention of the "Heisenberg" theory. Great when you learn a little "Moore" each day !

z3r010 said:

I thought Jimbo's law was that every post must be way off topic by the 3rd paragraph

Click to expand...

Cheers
how can I respond to that

Anyway it's not the intention.

Jimbo

Ah, I like this physicist, he's like "Bill Nye" for me.

More importantly, the processor frequency hasn't increased very much nor has the Instructions per clock cycle, certainly not exponentially like the transistor count has. The transistor count growth has been absorbed in more on-die functionality like integrated graphics, PCI-E, and more cores - not improving computational performance (except for the latter for much-threaded applications). There are some advances in computational power that can be partially attributed to the freedom more transistors give you, like improved FP with the AVX instruction set.

For instance, in Ivy bridge, most of the increased transistor count went to graphics (aka cramming more sh*t on the die).

Michio Kaku is a pertty cool guy, I'm reading his book Physics of the future right now. Interesing stuff.