Success or Failure of ASI, Robotaxi and Teslabot Will Not Be Compute Limited

The big winners of the last 200 years of the Industrial and Information revolution were ones who created previously unimagined scale to win. We went from many monks and scribes hand writing manuscripts to the printing press and eventually to the reel to reel newspaper presses. The circulation of daily weekday newspapers in the United …

Read more

B-100 and X-100 Nvidia AI Chips and Zettaflops AI Compute Clusters

The NVIDIA H100 GPU has 30 teraflops of peak standard IEEE FP64 performance, 60 teraflops of peak FP64 tensor core performance, and 60 teraflops of peak FP32 performance. It also has a second-generation secure multi-instance GPU technology that makes it possible to partition the chip into seven smaller, fully isolated instances to handle multiple workloads …

Read more

Will 1000 ExaFlop Supercomputers Come from Brute Force Scaling or New Technology?

Next year the world will have its first ExaFlop Supercomputer. This supercomputer will likely be built in China. The USA will follow about 12 months after with the A21 ExaFlop supercomputer in 2021. Ten researchers from China’s National University of Defense Technology (NUDT) recently published a paper that describes pushing current technologies to 1000 times …

Read more

The Supercomputer Race After ExaFlops is Super Cool

The first Exaflop supercomputers are just scaling up with energy efficient modifications the technologies that have enabled the 100-200 petaFlop supercomputers. Super Cool Technologies Beyond the Exaflop Supercomputer DownUnder GeoSolutions (DUG) has started making petaflop supercomputers that are much more energy efficient by switching to dielectric liquids for cooling. They are cutting energy usage and …

Read more

Non-von Neumann zettaFLOPS supercomputers, yottaFLOPS cryogenic supercomputers and beyond with molecular nanotechnology

Thomas Sterling has retracted his prediction that we will never reach ZettaFLOP computers. He now predicts zettaFLOPS can be achieved in less than 10 years if innovations in non-von Neumann architecture can be scaled. With a change to cryogenic technologies, we can reach yottaFLOPS by 2030. The world is currently on the verge of ExaFLOP …

Read more