Fat Fritz Update

[Nordlandia]

Version .2 available.

Fritz Update in addition.

By the way, the multi gpu syntax "(backend=cuda-fp16,gpu=0),(backend=cuda-fp16,gpu=1)" does not work on Fat Fritz though. Do anyone know a quick fix ?

[Robert Flesher]

It does not work on my system either! Ryzen Cpu, RTX 2070

[pohl4711]

Version .2 available.

Fritz Update in addition.

By the way, the multi gpu syntax "(backend=cuda-fp16,gpu=0),(backend=cuda-fp16,gpu=1)" does not work on Fat Fritz though. Do anyone know a quick fix ?

This is a complete useless "update"...
No new 20x256 net and the new FatFritz 1.2-binary still does not support Cuda 11, which makes Lc0 run more than +35% faster on NVIDIA RTX GPUs.
OMG Chessbase, what are you doing?...

So, if anybody wants to use the FatFritz 20x256 net, just take Lc0 0.26.3-binary (Fat Fritz-binary is just a copy & paste- Lc0-binary). Update your NVIDIA driver and use the CUDA 11 version of Lc0 0.26.3. Then, FatFritz-net is at least running faster (only on RTX-GPUs! Otherwise use the older Lc0 Cuda-binary)

Cuda 11 Lc0-binary:
https://github.com/LeelaChessZero/lc0/r ... a-cuda.zip

[corres]

Version .2 available.
Fritz Update in addition.
By the way, the multi gpu syntax "(backend=cuda-fp16,gpu=0),(backend=cuda-fp16,gpu=1)" does not work on Fat Fritz though. Do anyone know a quick fix ?

...
OMG Chessbase, what are you doing?...

Only a new NET what is about ~70 Elo weaker than the actual Leela NET on the same GPU(s).
...
Maybe
Backend = Multiplexing
BackendOptions = (backend=cudnn-fp16,gpu=0),(backend=cudnn-fp16,gpu=1)
will work on a dual GPUs

[cc2150dx]

Seems like it supports Cuda to me:

Fat Fritz (in lc0)
Detected 6 core(s) and 12 thread(s) in 1 group(s).
Group 0 has 6 core(s) and 12 thread(s).
isready
readyok
ucinewgame
Found pb network file: C:\Users\Jason\AppData\Roaming\ChessBase\Engines.uci\Fat Fritz/FatFritzCpu.weights
Creating backend [cuda-auto]...
Switching to [cuda-fp16]...
CUDA Runtime version: 11.1.0
Latest version of CUDA supported by the driver: 11.2.0
GPU: GeForce RTX 2060
GPU memory: 6 Gb
GPU clock frequency: 1680 MHz
GPU compute capability: 7.5

[cc2150dx]

I forgot to point to the weights file so it chose FatFritzCpu.weights. It should be FatFritz.weights for GPU.

[pohl4711]

Seems like it supports Cuda to me:

Fat Fritz (in lc0)
Detected 6 core(s) and 12 thread(s) in 1 group(s).
Group 0 has 6 core(s) and 12 thread(s).
isready
readyok
ucinewgame
Found pb network file: C:\Users\Jason\AppData\Roaming\ChessBase\Engines.uci\Fat Fritz/FatFritzCpu.weights
Creating backend [cuda-auto]...
Switching to [cuda-fp16]...
CUDA Runtime version: 11.1.0
Latest version of CUDA supported by the driver: 11.2.0
GPU: GeForce RTX 2060
GPU memory: 6 Gb
GPU clock frequency: 1680 MHz
GPU compute capability: 7.5

Strange, I used the Fat Fritz 20x256 net and on my RTX 2060, Fat Fritz 1.2 did not run with new CUDA 11 libraries. But without releasing a new FatFritz-net, the Fat Fritz 1.2 binary alone is complete useless - so who cares? The old Fat Fritz net can be used with Lc0 0.26.3 binary...

[Albert Silver]

Seems like it supports Cuda to me:

Fat Fritz (in lc0)
Detected 6 core(s) and 12 thread(s) in 1 group(s).
Group 0 has 6 core(s) and 12 thread(s).
isready
readyok
ucinewgame
Found pb network file: C:\Users\Jason\AppData\Roaming\ChessBase\Engines.uci\Fat Fritz/FatFritzCpu.weights
Creating backend [cuda-auto]...
Switching to [cuda-fp16]...
CUDA Runtime version: 11.1.0
Latest version of CUDA supported by the driver: 11.2.0
GPU: GeForce RTX 2060
GPU memory: 6 Gb
GPU clock frequency: 1680 MHz
GPU compute capability: 7.5

Strange, I used the Fat Fritz 20x256 net and on my RTX 2060, Fat Fritz 1.2 did not run with new CUDA 11 libraries. But without releasing a new FatFritz-net, the Fat Fritz 1.2 binary alone is complete useless - so who cares? The old Fat Fritz net can be used with Lc0 0.26.3 binary...

It should come with the CUDA 11 libraries itself. The update was only because there were complaints it would not work with the new 30xx cards. The Lc0 it uses is faster, but it was not the reason for the update. I stopped development of the NN itself back in February.

[Nordlandia]

Albert Silver: is there any plans to resume NN improvement at some point later on ?

[corres]

...
I stopped development of the NN itself back in February.

So the new(.2)net = the old(.1) one?
The -70 Elo difference is not a motive for development?