cannot make a move with GeForce GTX 650

[Nefeste]

Trying to run ./gtp.sh ./v0.bin --verbose --gpu 0 --num_block 20 --dim 224 --mcts_puct 1.50 --batchsize 16 --mcts_rollout_per_batch 16 --mcts_threads 2 --mcts_rollout_per_thread 512 --resign_thres 0.05 --mcts_virtual_loss 1 under supported environment I try to play with command: genmove B and get this error: ... /root/anaconda3/lib/python3.6/site-packages/torch/cuda/__init__.py:116: UserWarning: Found GPU0 GeForce GTX 650 which is of cuda capability 3.0. PyTorch no longer supports this GPU because it is too old. ... THCudaCheck FAIL file=/opt/conda/conda-bld/pytorch-nightly_1525389156111/work/aten/src/THCUNN/generic/Threshold.cu line=34 error=48 : no kernel image is available for execution on the device Traceback (most recent call last): File "df_console.py", line 78, in <module> GC.run() File "/root/ELF/src_py/elf/utils_elf.py", line 435, in run self._call(smem, *args, **kwargs) File "/root/ELF/src_py/elf/utils_elf.py", line 398, in _call reply = self._cb[idx](picked, *args, **kwargs) File "df_console.py", line 60, in actor return console.actor(batch) File "/root/ELF/scripts/elfgames/go/console_lib.py", line 302, in actor reply = self.evaluator.actor(batch) File "/root/ELF/src_py/rlpytorch/trainer/trainer.py", line 97, in actor state_curr = m.forward(batch) File "/root/ELF/src_py/elfgames/go/df_model3.py", line 274, in forward s = self.init_conv(s) File "/root/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in __call__ result = self.forward(*input, **kwargs) File "/root/anaconda3/lib/python3.6/site-packages/torch/nn/modules/container.py", line 91, in forward input = module(input) File "/root/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in __call__ result = self.forward(*input, **kwargs) File "/root/anaconda3/lib/python3.6/site-packages/torch/nn/modules/activation.py", line 46, in forward return F.threshold(input, self.threshold, self.value, self.inplace) File "/root/anaconda3/lib/python3.6/site-packages/torch/nn/functional.py", line 603, in threshold return torch._C._nn.threshold(input, threshold, value) RuntimeError: cuda runtime error (48) : no kernel image is available for execution on the device at /opt/conda/conda-bld/pytorch-nightly_1525389156111/work/aten/src/THCUNN/generic/Threshold.cu:34

There is no way to run ELF with CUDA capability 3.0? Which compute capability is enough - 3.5, 5.2, 6.1, 7.0? It would be nice to mention this requirements in prerequisites.

[bochen2027]

just out of curisoity is LZ-ELF working for you?

[Nefeste]

Yes, leela-zero works fine with OpenCL. Both playing and training.

[jma127]

Thanks for your interest! Unfortunately, I don't think we'll be able to support capabilities <6 for the foreseeable future.