logoalt Hacker News

toshtoday at 12:23 PM5 repliesview on HN

> in the time that Python can perform a single FLOP, an A100 could have chewed through 9.75 million FLOPS

wild


Replies

patmorgan23today at 1:07 PM

Why are we comparing a programing language and a GPU. This is a category error. Programing languages do not do any operations. They perform no FLOPs, they are the thing the FLOPs are performing.

"The I7-4770K and preform 20k more Flops than C++" is an equally sensible statement (i.e. not)

show 2 replies
toshtoday at 2:12 PM

re comments:

yes of course this is apples to oranges but that's kind of the point

it shows the vast span between specialized hardware throughput IFF you can use an A100 at its limit vs overhead of one of the most popular programming languages in use today that eventually does the "same thing" on a CPU

the interesting thing is why that is so

CPU vs GPU (latency vs throughput), boxing vs dense representation, interpreter overhead, scalar execution, layers upon layers, …

show 1 reply
p1esktoday at 12:48 PM

This statement makes zero sense

xyzsparetimexyztoday at 12:31 PM

Single core vs multi core accounts for much of this

show 1 reply