11–17 of 17 posts
For some reason the clickbait title ender "and the XYZ May Surprise You" Bothers the hell out of me. I don't know why, it just feels so disengaged of my time. Makes me feel like they think I'm a child. Is there any research as this?
Watch the interview, you won't regret it: https://www.youtube.com/watch?v=Nb2tebYAaOA
We can get more transistors by going 3D, but what about the heat? The real tragedy has been the degradation (although not yet death) in Dennard Scaling. And even then Landauer's limit will begin to rear it's head around 10,000-100,000X lower power. Reversible computing is an option, but does not cover I/O and will furthermore set us back in performance and transistor efficiency.
For some reason the clickbait title ender "and the XYZ May Surprise You" Bothers the hell out of me. I don't know why, it just feels so disengaged of my time. Makes me feel like they think I'm a child. Is there any research as this?
Learn the one simple trick that internet users HATE!
; )
For some reason the clickbait title ender "and the XYZ May Surprise You" Bothers the hell out of me. I don't know why, it just feels so disengaged of my time. Makes me feel like they think I'm a child. Is there any research as this?
We can get more transistors by going 3D, but what about the heat? The real tragedy has been the degradation (although not yet death) in Dennard Scaling. And even then Landauer's limit will begin to rear it's head around 10,000-100,000X lower power. Reversible computing is an option, but does not cover I/O and will furthermore set us back in performance and transistor efficiency.
Dennard scaling, also known as MOSFET scaling, is a scaling law based on a 1974 paper co-authored by Robert H. Dennard, after whom it is named.[1] Originally formulated for MOSFETs, it states, roughly, that as transistors get smaller, their power density stays constant, so that the power use stays in proportion with area; both voltage and current scale (downward) with length.
Landauer's principle is a physical principle pertaining to the lower theoretical limit of energy consumption of computation. ...
At 20 °C ..., the Landauer limit represents an energy of approximately 0.0175 eV, or 2.805 zJ. Theoretically, room‑temperature computer memory operating at the Landauer limit could be changed at a rate of one billion bits per second with energy being converted to heat in the memory media at the rate of only 2.805 trillionths of a watt (that is, at a rate of only 2.805 pJ/s). Modern computers use millions of times as much energy per second.
[But there's a limit to how far we can improve that leading to hitting it around 2050].
We can get more transistors by going 3D, but what about the heat? The real tragedy has been the degradation (although not yet death) in Dennard Scaling. And even then Landauer's limit will begin to rear it's head around 10,000-100,000X lower power. Reversible computing is an option, but does not cover I/O and will furthermore set us back in performance and transistor efficiency.
Had to look up those two terms, from Wikipedia: Dennard scaling, also known as MOSFET scaling, is a scaling law based on a 1974 paper co-authored by Robert H. Dennard, after whom it is named.[1] Originally formulated for MOSFETs, it states, roughly, that as transistors get smaller, their power density stays constant, so that the power use stays in proportion with area; both voltage and current scale (downward) with l…