Re:Launch HN: Blyss (YC W23) – Homomorphic encryption as a s...
by byteware on Tuesday March 14, 2023 @06:11PM
(#35159725)
interesting prize, I wonder why they fix that it has to be radix-2 NTT, using higher radix speeds things up an order of magnitude on GPU (granted I am using a 256 bit field, so it might be more memory bound)
From a hardware perspective, NTT can be done in parallel, but has a fairly large working set of data (~512 MB) with lots of unstructured accesses. This is too big to fit in even the largest CPU L3 caches, so DRAM bandwidth is still relevant. It may be eventually be feasible to build an ASIC with this much on-chip memory, but in the meantime, GPUs do a pretty decent job with their massive HBM bandwidth.