Re:Three chips in and Google Tensor is on life support
by financltravsty on Thursday November 23, 2023 @08:15AM
(#38392407)
Parallelization.
Each "unit of work" in matrix multiplication is not dependent on any other unit of work. Stuff as many cores as you can into a chip, and then simply feed in all your vectors at the same time.
Re:Three chips in and Google Tensor is on life support
by Symmetry on Thursday November 23, 2023 @10:24AM
(#38393706)
A million element square matrix is a lot of data. To process that in a second is much more bandwidth than a single socket can support, so you'll need many sockets too.
Each "unit of work" in matrix multiplication is not dependent on any other unit of work. Stuff as many cores as you can into a chip, and then simply feed in all your vectors at the same time.
I.e. basically a beefed up GPU or an "AI" chip.