Please post here anything else (not relating to Maxwell technical matters)
User avatar
By michaelplogue
#220977
Intel Corporation researchers have developed the world’s first programmable processor that delivers supercomputer-like performance from a single, 80-core chip not much larger than the size of a finger nail while using less electricity than most of today’s home appliances.
http://www.intel.com/research/platform/ ... us|k8098|s

:shock:
User avatar
By michaelplogue
#220984
Maxer wrote:I would like about 100 of these implanted in my brain so I can render with Maxwell all the time. :D
But then you'd need buy 200 licenses.......... :shock:
User avatar
By michaelplogue
#220986
Don't be sad... You should have enough licenses now to run at least one of these chips... :wink:
User avatar
By -Adrian
#220996
Sounds impressive :shock:

Also on topic, some news from IBM.
User avatar
By Thomas An.
#221005
Sounds like, it might be possible to have a realtime Maxwell shaded viewport :P
User avatar
By ivox3
#221023
ASCI Red was the first computer to benchmark at a teraflops (1996). That system used nearly 10,000 Pentium® Pro processors running at 200MHz and consumed 500kW of power plus an additional 500kW just to cool the room that housed it. Although not a general purpose computing device, this Teraflops Research Chip delivers 1.0 teraflops of performance and 1.6 terabits aggregate core to core communication bandwidth, while dissipating only 62W.
I'm telling ya --- someone's been haning out with aliens. Moore's Law ..... hah, ..gibberish.
User avatar
By deadalvs
#221032
Mihai wrote:Image
i remember that story ......
User avatar
By deadalvs
#221063
well, let's do a little math with these TeraFlops.

i may not take all factors, but it shows my thoughts.

wikipedia says that a normal Pentium4 @ 3 GHz reaches around 6 GigaFlops.
Maximus' pentium 4 3 GHz takes for the speedtest around 4 hours.

one of these chips is a little faster (factor 1 x 1000 / 6) than the pentium, based on frequency and number of cores:
would be around: 86.4 seconds.
that's 1.5 minutes. if we compare now to a computer today with 8 cores (25 minutes) we see a speed increase of factor 15.

for the chip release in (i don't know) six years, this seems to me like totally moore's law.

100 of these chips would calculate the test in about a second. so we still are faaaar away from anything «realtime» with large resolutions, heavy geometry @ 24 fps !

ok thanks for explaining. actually I do copy the T[…]

Sketchup 2026 Released

Fernando wrote: " Now that Maxwell for Cinema[…]

Hello Gaspare, I could test the plugin on Rhino 8[…]

Hello Blanchett, I could reproduce the problem he[…]