this post was submitted on 28 May 2024
143 points (100.0% liked)

chapotraphouse

13530 readers
166 users here now

Banned? DM Wmill to appeal.

No anti-nautilism posts. See: Eco-fascism Primer

Gossip posts go in c/gossip. Don't post low-hanging fruit here after it gets removed from c/gossip

founded 3 years ago
MODERATORS
 
you are viewing a single comment's thread
view the rest of the comments
[–] [email protected] 46 points 5 months ago (3 children)

I would love to see a comparison of the energy, water, hardware and time that goes into this compared to just you know doing maths on a cpu like a sane person.

Capitalism truly is the most efficient system.

[–] [email protected] 20 points 5 months ago (1 children)

Well, addition is built into the instruction set of any CPU, so it only takes one operation. On the other hand, one evaluation of a neural net involves several repeated matrix-vector multiplies followed by the application of a nonlinear "activation function". Matrix-vector multiply for a square matrix will take 2020=400 multiply operations and about 2019 addition operations for a 20-dimensional input. So we'll say maybe on the order of 1,000-10,000 times more operations depending on how many layers?

[–] [email protected] 9 points 5 months ago (1 children)

This is up to 200 digit numbers, so you'd actually need to use a custom implementation for representing the integers and software addition but then a naive algorithm would still be like... 200 operations. Could probably drastically reduce that as well.

[–] [email protected] 2 points 5 months ago

200bit numbers only require like 10 registers. X86-64 has 16 general purpose registers so doing operations with 200 digit numbers should hypothetically only require 20 loads and 10 multiplies. So a well written bit of code could do it in under 100 ops (probably under 50). So assuming this LLM implementation is running on a big server, it's probably doing the same calculation, less accurately, with some exponentially larger amount of operations.

load more comments (1 replies)