CYCybiote·Apr 9, 2021
It looks like training is on CPU too: https://github.com/nodchip/Stockfish/blob/master/src/nnue/ev....
In CPU-based algorithm trains deep neural nets up to 15 times faster than top GPUnodchip
Stockfish
C++2021–2021
nodchip / Stockfish
Stockfish
UCI chess engine
2Distinct people
2Mentions
0Explicit recommenders
104GitHub stars
What to know before exploring
What it is
UCI chess engine
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:56:07 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by week2 dated mentions
Observed mentions: 2021-01-13 15:21:29 UTC to 2021-04-09 13:08:12 UTC. Weeks start Monday, UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Jan 11 | 2021-01-11 00:00:00 UTC | 2021-01-18 00:00:00 UTC | 1 | 0 | 1 |
| Jan 18 | 2021-01-18 00:00:00 UTC | 2021-01-25 00:00:00 UTC | 0 | 0 | 0 |
| Jan 25 | 2021-01-25 00:00:00 UTC | 2021-02-01 00:00:00 UTC | 0 | 0 | 0 |
| Feb 1 | 2021-02-01 00:00:00 UTC | 2021-02-08 00:00:00 UTC | 0 | 0 | 0 |
| Feb 8 | 2021-02-08 00:00:00 UTC | 2021-02-15 00:00:00 UTC | 0 | 0 | 0 |
| Feb 15 | 2021-02-15 00:00:00 UTC | 2021-02-22 00:00:00 UTC | 0 | 0 | 0 |
| Feb 22 | 2021-02-22 00:00:00 UTC | 2021-03-01 00:00:00 UTC | 0 | 0 | 0 |
| Mar 1 | 2021-03-01 00:00:00 UTC | 2021-03-08 00:00:00 UTC | 0 | 0 | 0 |
| Mar 8 | 2021-03-08 00:00:00 UTC | 2021-03-15 00:00:00 UTC | 0 | 0 | 0 |
| Mar 15 | 2021-03-15 00:00:00 UTC | 2021-03-22 00:00:00 UTC | 0 | 0 | 0 |
| Mar 22 | 2021-03-22 00:00:00 UTC | 2021-03-29 00:00:00 UTC | 0 | 0 | 0 |
| Mar 29 | 2021-03-29 00:00:00 UTC | 2021-04-05 00:00:00 UTC | 0 | 0 | 0 |
| Apr 5 | 2021-04-05 00:00:00 UTC | 2021-04-12 00:00:00 UTC | 1 | 0 | 1 |
What Hacker News says
2 sourcesIf anyone wants to experiment with training these nets, it's a great way to get exposed to a nice mix of chess and machine learning.
There are two trainers currently, the original one, which runs on CPU: https://github.com/nodchip/Stockfish, and a pytorch one which runs on GPU: https://github.com/glinscott/nnue-pytorch.
The SF Discord is where all of the discussion/development is happening: https://discord.gg/KGfhSJd.
Right now there is a lot of experimentation to try adjusting the network architecture. The current leading approach is a much larger net which takes in attack information per square (eg. is this piece attacked by more pieces than it's defended by?). That network is a little slower, but the additional information seems to be enough to be stronger than the current architecture.
Btw, the original Shogi developers really did s
Read the rest
omething amazing. The nodchip trainer is all custom code, and trains extremely strong nets. There are all sorts of subtle tricks embedded in there as well that led to stronger nets. Not to mention, getting the quantization (float32 -> int16/int8) working gracefully is a huge challenge.