Stockfish NNUE speed is improved a lot
Moderators: hgm, Rebel, chrisw
-
- Posts: 3293
- Joined: Wed Mar 08, 2006 8:15 pm
Stockfish NNUE speed is improved a lot
GitHub says: On CPUs supporting modern vector instructions (avx2 and similar), the NNUE evaluation results in stronger playing strength, even if the nodes per second computed by the engine is somewhat lower (roughly 60% of nps is typical). I also remember first NNUE versions speed was about 65-70% of classic. I tested 8.1.2021 version (bmi) with bench. Now NNUE runs with about 88% of classic speed . Nice speed-up and optimization. Soon 100%?
Jouni
-
- Posts: 476
- Joined: Sun Mar 17, 2019 12:00 pm
- Full name: Henk Drost
Re: Stockfish NNUE speed is improved a lot
Because in the past NNUE was pure and now it's hybrid.
Most of the speedup comes from classical eval being used on some nodes.
Most of the speedup comes from classical eval being used on some nodes.
-
- Posts: 3293
- Joined: Wed Mar 08, 2006 8:15 pm
Re: Stockfish NNUE speed is improved a lot
If I use evalType == "NNUE" for bench still classical eval?
Jouni
-
- Posts: 41
- Joined: Tue Oct 29, 2019 8:33 pm
- Location: French Polynesia
- Full name: Roger C.
Re: Stockfish NNUE speed is improved a lot
Hi, i have a 102% speed between pure NNUE vs hybrid on SD865+ processor on last Cfish and 8 cores.Jouni wrote: ↑Mon Jan 11, 2021 4:24 pm GitHub says: On CPUs supporting modern vector instructions (avx2 and similar), the NNUE evaluation results in stronger playing strength, even if the nodes per second computed by the engine is somewhat lower (roughly 60% of nps is typical). I also remember first NNUE versions speed was about 65-70% of classic. I tested 8.1.2021 version (bmi) with bench. Now NNUE runs with about 88% of classic speed . Nice speed-up and optimization. Soon 100%?
Optimizations pushed the pure eval to be faster on heavy vector processors + big cache levels. Should be the same on Intel i9.