Re:Three chips in and Google Tensor is on life support
by exikyut on Thursday November 23, 2023 @06:39AM
(#38391717)
As someone with a lot of interest in but no fluency with chip design, or the dividing and conquering of math within silicon, for that matter, how would you multiply a 1m² matrix?
[ Parent
| on HN ]
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.
I.e. basically a beefed up GPU or an "AI" chip.