While waiting for slow computer program to run, thought I’d have a look at when Moore’s Law broke.
Moore’s Law works better on storage than speed. For computer chip speed, Moore’s Law broke in 2001, improvements have been totally negligible since then. See following graph, showing the fastest Intel processing chips released each year.
How’s Moore’s Law doing for computer memory?
mollwollfumble said:
While waiting for slow computer program to run, thought I’d have a look at when Moore’s Law broke.
Moore’s Law works better on storage than speed. For computer chip speed, Moore’s Law broke in 2001, improvements have been totally negligible since then. See following graph, showing the fastest Intel processing chips released each year.
How’s Moore’s Law doing for computer memory?
I was reading about this and we still get improvements but its something along the lines of double the number of transistors equal a 10 – 20 % increase in performance. I think it’s why they went to multicores on the single chip to try and fix this. In regards to GPU’s the latest Nvidia 1080X is twice as fast (or close enough) as the 980 ti (previous generation) and is cheaper which is good deal for serious gamers. I imagine the heat dissipation is a major problem as well
https://en.wikipedia.org/wiki/Clock_rate
As of 2011, the Guinness World Record for fastest CPU is by AMD with a Bulldozer based FX chip “overclocked” to 8.805 GHz, trumping the maximum recorded 8.670 GHz performance of their next generation FX “Piledriver” chips.
As of mid-2013, the highest clock rate on a production processor is the IBM zEC12, clocked at 5.5 GHz, which was released in August of 2012.
Engineers continue to find new ways to design CPUs that settle a little more quickly or use slightly less energy per transition, pushing back those limits, producing new CPUs that can run at slightly higher clock rates. The ultimate limits to energy per transition are explored in reversible computing, although no reversible computers have yet been implemented.
The first fully reversible CPU, the Pendulum, was implemented using standard CMOS transistors in the late 1990s at MIT.
Engineers also continue to find new ways to design CPUs so that they complete more instructions per clock cycle, thus achieving a lower CPI (cycles or clock cycles per instruction) count, although they may run at the same or a lower clock rate as older CPUs. This is achieved through architectural techniques such as instruction pipelining and out-of-order execution which attempts to exploit instruction level parallelism in the code.
See also: Moore’s law
https://en.wikipedia.org/wiki/Moore%27s_law
Moore’s law (/mɔərz.ˈlɔː/) is the observation that the number of transistors in a dense integrated circuit doubles approximately every two years. The observation is named after Gordon E. Moore, the co-founder of Intel and Fairchild Semiconductor, whose 1965 paper described a doubling every year in the number of components per integrated circuit, and projected this rate of growth would continue for at least another decade. In 1975, looking forward to the next decade, he revised the forecast to doubling every two years.
His prediction proved accurate for several decades, and the law was used in the semiconductor industry to guide long-term planning and to set targets for research and development. Advancements in digital electronics are strongly linked to Moore’s law: quality-adjusted microprocessor prices, memory capacity, sensors and even the number and size of pixels in digital cameras.
Which version of Moore’s Law do you mean? The original article says that the number of transistors in an integrated doubles roughly every two years. That has nothing at all to do with CPU speed. A variation says that the cost to manufacturers of ICs increases exponentially to keep pace with the first version.
A different, but closely related, “law” is that computer power doubles roughly every two years. While the speed of CPUs seems to have reached a plateau, the number of cores per CPU is increasing, so the actual computer power is still increasing, albeit less quickly than predicted (probably doubling in about three years.)
Some impressive technology and design goes into CPU’s, GPU’s and memory.
Timelines exist at least for CPU’s on the architecture on the next half a dozen or more generations and the possible technological problems including a substitute for silicon
>That has nothing at all to do with CPU speed
maybe’s related though, packing stuff together (too smaller tr junctions) has obvious speed advantages (less C), but these things clock into the gig range which i’d expect comes with (like radio frequency) design challenges.
dunno
I think part of the explanation is that there was not much point in spending the money to push it higher because it was cheaper to just use more chips…
dv said:
I think part of the explanation is that there was not much point in spending the money to push it higher because it was cheaper to just use more chips…
Sounds a bit fishy.
Ultra-low power graphene-based transistor could enable 100 GHz clock speeds
Ultra-low power graphene-based transistor could enable 100 GHz clock speeds
For years, the two-dimensional material, graphene, has shown promise in making electronics smaller and more efficient. Now scientists have designed a graphene-based transistor that works with ultra-low power consumption and which could ultimately be used to increase the clock speed of processors up to a staggering 100 GHz.
more…