Moore’s Law is struggling against the limits of what’s physically possible and the days of massive jumps in performance each generation are long over. It’s hard to advertise a new CPU when it’s running at nearly the same clock speed models ran at ten years ago and all you’ve done is thrown more L3 cache at an otherwise 99% unchanged previous model.
Even the number of cores has stagnated, and that was their Hail Mary to keep the performance gains coming. And I bet the Spectre/Meltdown mitigations eroded a large part of those gains too - IIRC existing chips lost ~12% performance after the firmware patches, and new ones had to be redesigned to handle speculative execution in a less efficient (but more secure) way.
Though there has recently been another step forward with transistors being able to get under a nanometer, 0.7 nm from 2 nm to be precise, and the last time a measurement needed to go another level smaller was in 1984 when it went from 1 micrometer to 0.8 micrometers.
That 0.7 nm one marks another jump in power while being significantly more efficient, which is I guess Moore’s law living out of spite of not actually being a scientific law.
Also it’s funny this is about the 2nd or third time I’ve seen someone say “Moore’s law is dead” since that 0.7 nm process was figured out not that long ago.
Interesting! I’d always heard that the nanometer wars were mostly marketing fluff these past several years and the quoted numbers divorced from reality, but they’re claiming genuinely sub-nanometer chips. And 3d chip designs, which is equally impressive. I haven’t followed chip tech in a few years, but last I knew heat dissipation was still a huge bottleneck preventing stacked designs.
Though it’s a shame they’re focusing all that innovation towards the AI sector. Their consumer lines have been stagnant for a while now.
Intel’s nanometer-ish numbers are BS. They call their 14nm process “Intel 10”, their 10nm process “Intel 7”, their 7nm “Intel 4”, etc. As far as I know, other companies are more truthful.
Moore’s Law is struggling against the limits of what’s physically possible and the days of massive jumps in performance each generation are long over. It’s hard to advertise a new CPU when it’s running at nearly the same clock speed models ran at ten years ago and all you’ve done is thrown more L3 cache at an otherwise 99% unchanged previous model.
Even the number of cores has stagnated, and that was their Hail Mary to keep the performance gains coming. And I bet the Spectre/Meltdown mitigations eroded a large part of those gains too - IIRC existing chips lost ~12% performance after the firmware patches, and new ones had to be redesigned to handle speculative execution in a less efficient (but more secure) way.
Though there has recently been another step forward with transistors being able to get under a nanometer, 0.7 nm from 2 nm to be precise, and the last time a measurement needed to go another level smaller was in 1984 when it went from 1 micrometer to 0.8 micrometers.
That 0.7 nm one marks another jump in power while being significantly more efficient, which is I guess Moore’s law living out of spite of not actually being a scientific law.
Also it’s funny this is about the 2nd or third time I’ve seen someone say “Moore’s law is dead” since that 0.7 nm process was figured out not that long ago.
Interesting! I’d always heard that the nanometer wars were mostly marketing fluff these past several years and the quoted numbers divorced from reality, but they’re claiming genuinely sub-nanometer chips. And 3d chip designs, which is equally impressive. I haven’t followed chip tech in a few years, but last I knew heat dissipation was still a huge bottleneck preventing stacked designs.
Though it’s a shame they’re focusing all that innovation towards the AI sector. Their consumer lines have been stagnant for a while now.
Intel’s nanometer-ish numbers are BS. They call their 14nm process “Intel 10”, their 10nm process “Intel 7”, their 7nm “Intel 4”, etc. As far as I know, other companies are more truthful.