News for hackers. Stuff that matters.

A comment on TFHE: Fast Fully Homomorphic Encryption over the Torus. Parent comment

Re:TFHE: Fast Fully Homomorphic Encryption over the Torus by rjeli on Monday April 13, 2020 @12:28PM (#22857243)
From some napkin math and googling, a 6502 has 4.5k transistors, which at 13 ms per gate is about a minute per cycle, divided by how many gates there really are per transistor.

How does your implementation compare?

[ Parent | on HN ]
Re:TFHE: Fast Fully Homomorphic Encryption over the Torus by mmastrac on Monday April 13, 2020 @12:36PM (#22857324)
~20k gates total (ShapeCPU was ~30k gates), but the _real_ bottleneck for FHE computing is the longest path from input to output as FHE computers are highly parallel.

I am sure I had a stat for the longest path from input to output, but I'm a few years swapped out on this project.

Note that adding pipelining to a CPU drastically reduces the longest path. ShapeCPU is not pipelined at all which probably means there's a bunch of low-hanging fruit.

[ Parent | on HN ]