some confusing Warning and notes output when run gmx2020.2+deepmd-kit #4689
Replies: 1 comment 3 replies
-
This message means the CUDA libraries (including cuDNN) are not loaded. Maybe they are not installed or their directories are not within
Just follow this link.
From the source code, https://github.com/tensorflow/tensorflow/blob/7e4367bede5828c5831f7aab068e9e898c92ff43/tensorflow/core/util/util.cc#L137-L167, it seems that it just tells oneDNN does not support FP64... I feel that this message should be improved. |
Beta Was this translation helpful? Give feedback.
-
Thanks for your reply ! Actually, I do not train the machine learning force field but directly use others' trained force field, does it means that i do not have to load/install CUDA libraries in the situation as shown in :W0000 00:00:1743409673.309237 1217084 gpu_device.cc:2344] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform. |
Beta Was this translation helpful? Give feedback.
-
|
Do you mean you don't have a GPU? That's, of course, okay. |
Beta Was this translation helpful? Give feedback.
-
|
Thanks a lot ! I have gpu, but i only use gpu when running "gmx mdrun" with gpu accelerated version, since i just use others' trained machine learning force field and do not want to train force field by myself. |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
I execute "gmx mdrun" using the simulation system in deepmd-kit-r3.0/examples/water/gmx with some confusing warnings and notes output.
Currently, the simulation runs normally without abruption, however, I am not sure whether the warnings and notes could be ignored bellow:
...
Init deepmd plugin from: input.json
Setting lambda: 1
Setting pbc: 1
Number of atoms: 768
Begin Init Model: ../../../../frozen_model.pb
DeePMD-kit WARNING: Environmental variable DP_INTRA_OP_PARALLELISM_THREADS is not set. Tune DP_INTRA_OP_PARALLELISM_THREADS for the best performance. See https://deepmd.rtfd.io/parallelism/ for more information.
DeePMD-kit WARNING: Environmental variable DP_INTER_OP_PARALLELISM_THREADS is not set. Tune DP_INTER_OP_PARALLELISM_THREADS for the best performance. See https://deepmd.rtfd.io/parallelism/ for more information.
DeePMD-kit WARNING: Environmental variable OMP_NUM_THREADS is not set. Tune OMP_NUM_THREADS for the best performance. See https://deepmd.rtfd.io/parallelism/ for more information.
2025-03-31 16:27:53.259949: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
W0000 00:00:1743409673.309237 1217084 gpu_device.cc:2344] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.
Skipping registering GPU devices...
I0000 00:00:1743409673.355648 1217084 mlir_graph_optimization_pass.cc:401] MLIR V1 optimization pass is not enabled
Successfully load model!
DeePMD-kit WARNING: Environmental variable DP_INTRA_OP_PARALLELISM_THREADS is not set. Tune DP_INTRA_OP_PARALLELISM_THREADS for the best performance. See https://deepmd.rtfd.io/parallelism/ for more information.
DeePMD-kit WARNING: Environmental variable DP_INTER_OP_PARALLELISM_THREADS is not set. Tune DP_INTER_OP_PARALLELISM_THREADS for the best performance. See https://deepmd.rtfd.io/parallelism/ for more information.
DeePMD-kit WARNING: Environmental variable OMP_NUM_THREADS is not set. Tune OMP_NUM_THREADS for the best performance. See https://deepmd.rtfd.io/parallelism/ for more information.
installed to: /root/deepmd-kit/dp_c
source: v3.0.2
source branch: HEAD
source commit: 70bc6d8
source commit at: 2025-03-02 11:04:28 +0800
support model ver.: 1.1
build variant: cuda
build with tf inc: /usr/local/lib/python3.11/dist-packages/tensorflow/include;/usr/local/lib/python3.11/dist-packages/tensorflow/include
build with tf lib: /usr/local/lib/python3.11/dist-packages/tensorflow/libtensorflow_cc.so.2
set tf intra_op_parallelism_threads: 0
set tf inter_op_parallelism_threads: 0
Summary:
Atom map: O H
Successfully init plugin!
starting mdrun 'lw_256.pdb'
500000000 steps, 250000.0 ps.
2025-03-31 16:27:53.618151: W tensorflow/core/util/util.cc:163] Not handling type DT_DOUBLE
2025-03-31 16:27:53.618954: W tensorflow/core/util/util.cc:163] Not handling type DT_DOUBLE
2025-03-31 16:27:53.619067: W tensorflow/core/util/util.cc:163] Not handling type DT_DOUBLE
2025-03-31 16:27:53.619884: W tensorflow/core/util/util.cc:163] Not handling type DT_DOUBLE
2025-03-31 16:27:53.619998: W tensorflow/core/util/util.cc:163] Not handling type DT_DOUBLE
2025-03-31 16:27:53.620354: W tensorflow/core/util/util.cc:163] Not handling type DT_DOUBLE
2025-03-31 16:27:53.620458: W tensorflow/core/util/util.cc:163] Not handling type DT_DOUBLE
...
step 0
step 100, will finish Tue Oct 14 04:03:31 2025
step 200, will finish Wed Oct 8 17:17:44 2025
step 300, will finish Tue Oct 7 00:40:09 2025
step 400, will finish Tue Oct 7 03:55:00 2025
...
Appreciate if anyone can help me !!! Do i need to avoid all those warnings and notes (especially the notes of Not handling type DT_DOUBLE) ?
Beta Was this translation helpful? Give feedback.
All reactions