News for hackers. Stuff that matters.
Re:GPUs for Deep Learning in 2023 – An In-depth Analysis by tyfighter on Wednesday January 18, 2023 @07:12PM (#34435013)
I can't really judge the accuracy of the rest of the article, but if they can't even get the names of the GPUs they're recommending correct, it's tough to trust the rest of their supposedly thorough analysis. Throughout the whole article, the author refers to the "NVIDIA RTX 40 Ampere series", which is wrong. The RTX 30 series is Ampere [1] and the RTX 40 series is Ada [2].

1. https://en.wikipedia.org/wiki/Ampere_(microarchitecture) 2. https://en.wikipedia.org/wiki/Ada_Lovelace_(microarchitectur...

Re:GPUs for Deep Learning in 2023 – An In-depth Analysis by jph00 on Wednesday January 18, 2023 @07:26PM (#34435130)
It's not "throughout the whole article". It looks like he has updated a previous post and made one editing mistake, which he then copied incorrectly once. In all other mentions he correctly describes RTX 40 as Ada.

The analysis is thorough, even if the editing is imperfect.

Re:GPUs for Deep Learning in 2023 – An In-depth Analysis by muxr on Thursday January 19, 2023 @08:55AM (#34440270)
The author also says that AMD doesn't have Tensor cores. No shit, Tensor core is an Nvidia trademark. AMD has matrix multiplication units in their CDNA GPUs.