search

gnina / libmolgrid

Comprehensive library for fast, GPU accelerated molecular gridding for deep learning workflows
https://gnina.github.io/libmolgrid/
Apache License 2.0
144 stars 48 forks source link

CUDA error #83

Open JIBSN opened 2 years ago

JIBSN commented 2 years ago

/tmp/libmolgrid/src/grid_maker.cu:279: invalid argument

CLI error 2022-01-27 12:32:12.810627: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-01-27 12:32:12.810659: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 1 2 3 4 5 6 7 8 9 2022-01-27 12:32:12.810665: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N N N N N N N N N N 2022-01-27 12:32:12.810667: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 1: N N N N N N N N N N 2022-01-27 12:32:12.810670: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 2: N N N N N N N N N N 2022-01-27 12:32:12.810672: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 3: N N N N N N N N N N 2022-01-27 12:32:12.810675: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 4: N N N N N N N N N N 2022-01-27 12:32:12.810677: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 5: N N N N N N N N N N 2022-01-27 12:32:12.810680: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 6: N N N N N N N N N N 2022-01-27 12:32:12.810682: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 7: N N N N N N N N N N 2022-01-27 12:32:12.810684: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 8: N N N N N N N N N N 2022-01-27 12:32:12.810687: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 9: N N N N N N N N N N 2022-01-27 12:32:12.822802: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device: GPU:0 with 8811 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 3080, pci bus id: 0000:1a:00.0, compute capability: 8.6) 2022-01-27 12:32:12.825625: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device: GPU:1 with 8503 MB memory) -> physical GPU (device: 1, name: NVIDIA GeForce RTX 3080, pci bus id: 0000:1b:00.0, compute capability: 8.6) 2022-01-27 12:32:12.828273: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device: GPU:2 with 9012 MB memory) -> physical GPU (device: 2, name: NVIDIA GeForce RTX 3080, pci bus id: 0000:1c:00.0, compute capability: 8.6) 2022-01-27 12:32:12.830885: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device: GPU:3 with 9012 MB memory) -> physical GPU (device: 3, name: NVIDIA GeForce RTX 3080, pci bus id: 0000:1d:00.0, compute capability: 8.6) 2022-01-27 12:32:12.833468: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device: GPU:4 with 9012 MB memory) -> physical GPU (device: 4, name: NVIDIA GeForce RTX 3080, pci bus id: 0000:1e:00.0, compute capability: 8.6) 2022-01-27 12:32:12.836048: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device: GPU:5 with 9012 MB memory) -> physical GPU (device: 5, name: NVIDIA GeForce RTX 3080, pci bus id: 0000:3d:00.0, compute capability: 8.6) 2022-01-27 12:32:12.838643: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device: GPU:6 with 9012 MB memory) -> physical GPU (device: 6, name: NVIDIA GeForce RTX 3080, pci bus id: 0000:3e:00.0, compute capability: 8.6) 2022-01-27 12:32:12.841233: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device: GPU:7 with 9012 MB memory) -> physical GPU (device: 7, name: NVIDIA GeForce RTX 3080, pci bus id: 0000:3f:00.0, compute capability: 8.6) 2022-01-27 12:32:12.843835: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device: GPU:8 with 9012 MB memory) -> physical GPU (device: 8, name: NVIDIA GeForce RTX 3080, pci bus id: 0000:40:00.0, compute capability: 8.6) 2022-01-27 12:32:12.846432: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device: GPU:9 with 9012 MB memory) -> physical GPU (device: 9, name: NVIDIA GeForce RTX 3080, pci bus id: 0000:41:00.0, compute capability: 8.6) 2022-01-27 12:32:12.850270: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x5623d422fef0 initialized for platform CUDA (this does not g uarantee that XLA will be used). Devices: 2022-01-27 12:32:12.850310: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 3080, Compute Capability 8.6 2022-01-27 12:32:12.850323: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (1): NVIDIA GeForce RTX 3080, Compute Capability 8.6 2022-01-27 12:32:12.850332: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (2): NVIDIA GeForce RTX 3080, Compute Capability 8.6 2022-01-27 12:32:12.850340: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (3): NVIDIA GeForce RTX 3080, Compute Capability 8.6 2022-01-27 12:32:12.850347: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (4): NVIDIA GeForce RTX 3080, Compute Capability 8.6 2022-01-27 12:32:12.850355: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (5): NVIDIA GeForce RTX 3080, Compute Capability 8.6 2022-01-27 12:32:12.850364: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (6): NVIDIA GeForce RTX 3080, Compute Capability 8.6 2022-01-27 12:32:12.850372: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (7): NVIDIA GeForce RTX 3080, Compute Capability 8.6 2022-01-27 12:32:12.850379: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (8): NVIDIA GeForce RTX 3080, Compute Capability 8.6 2022-01-27 12:32:12.850387: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (9): NVIDIA GeForce RTX 3080, Compute Capability 8.6 [I 2022-01-27 12:33:10.380 ServerApp] Saving file at /Untitled.ipynb /tmp/libmolgrid/src/grid_maker.cu:279: invalid argument[I 2022-01-27 13:13:14.314 ServerApp] Saving file at /Untitled3.ipynb /tmp/libmolgrid/src/grid_maker.cu:288: no kernel image is available for execution on the device

I have installed molgrid 0.2.1 with conda, but when I ran a the train_basic_CNN_with_Tensorflow script, there's an error occured. What does the error about?

dkoes commented 2 years ago

You need a build with support for newer GPUs. Try building from source until we have an updated conda package.

JIBSN commented 2 years ago

Thanks for your advise, I'll try to build from source.