GPU Cloud VMs - Revision history

Atambo at 20:11, 8 May 2025

2025-05-08T20:11:05Z

2025-05-08T20:08:50Z

2025-05-08T19:57:50Z

2025-05-08T19:49:03Z

2025-05-08T19:43:47Z

2025-05-08T19:37:11Z

2025-05-08T19:32:27Z

2025-05-08T19:32:05Z

2025-05-08T19:23:33Z

2025-05-08T19:22:28Z

@@ Line 149: / Line 149: @@
     sbatch  job.mpi
 </code>
 [[File:TensorFlow_logo.svg.png|350px]]

@@ Line 103: / Line 103: @@
 edit the last line to include your commands to pw.x, and submit with slurm:
 <code bash>
-    sbatch  test.mpi
+    sbatch  job.mpi
 </code>
 == [https://asciinema.org/a/F5Q7kQ9cUjxwSY291T6W3b38y Watch Quantum Espresso Demo] ==
@@ Line 113: / Line 113: @@
      $ mpirun -np 1  /usr/local/bin/yambo
 </code>
 ===== Advanced usage with slurm: =====
 to run yambo in the GPU vm with slurm, create a submission script with the following contents:
@@ Line 127: / Line 141: @@
   ##SBATCH --partition=jobs
+ cd $HOME/examples/Silicon/YAMBO/4x4x4
-  mpirun -np 1 yambo  ...
+  mpirun -np 1 yambo -F Inputs/01HF_corrections -J HF_XXRy
 </code>
 give the file a name like job.mpi,
 edit the last line to include your commands to yambo, and submit with slurm:
 <code bash>
-    sbatch  test.mpi
+    sbatch  job.mpi
 </code>

@@ Line 253: / Line 253: @@
 </code>
 This code downloads some training MNIST data, runs a convolutional neural network based training, and gives a summary of the accuracy at the end 99%).  There is no need to install PyTorch since its aready preconfigured in the `pt` environment.
 Up:
 [[ HPC_Usage| HPC_Usage]]

@@ Line 116: / Line 116: @@
 to run yambo in the GPU vm with slurm, create a submission script with the following contents:
 <code bash>
-   #!/bin/bash
+ #!/bin/bash
-   ##SBATCH --job-name="example-name"
+ ##SBATCH --job-name="example-name"
-   ##SBATCH --get-user-env
+ ##SBATCH --get-user-env
-   ##SBATCH --output=_scheduler-stdout.txt
+ ##SBATCH --output=_scheduler-stdout.txt
-   ##SBATCH --error=_scheduler-stderr.txt
+ ##SBATCH --error=_scheduler-stderr.txt
-   ##SBATCH --nodes=1
+ ##SBATCH --nodes=1
-   ##SBATCH --ntasks-per-node=1
+ ##SBATCH --ntasks-per-node=1
-   ##SBATCH --cpus-per-task=1
+ ##SBATCH --cpus-per-task=1
-   ##SBATCH --time=23:58:20
+ ##SBATCH --time=23:58:20
-   ##SBATCH --partition=jobs
+ ##SBATCH --partition=jobs
-   mpirun -np 1 yambo  ...
+ mpirun -np 1 yambo  ...
 </code>
 give the file a name like job.mpi,
@@ Line 212: / Line 212: @@
 /469 [==============================] - 1s 2ms/step - loss: 0.1189 - sparse_categorical_accuracy: 0.9660 - val_loss: 0.1096 -
    val_sparse_categorical_accuracy: 0.9666
-   Epoch 4/6
+   ...
    Epoch 6/6
 /469 [==============================] - 1s 2ms/step - loss: 0.0599 - sparse_categorical_accuracy: 0.9827 - val_loss: 0.0775 -
@@ Line 224: / Line 219: @@
 We have run tensorflow+Keras on the MNIST dataset, with a final accuract of 98%.
 [[File:Pytorch_logo.png|350px]]

@@ Line 149: / Line 149: @@
 We can now attempt to run some code, place the following code in a plain text file, call it `example.py`
 <code python>
-  import tensorflow as tf
+ import tensorflow as tf
-  import tensorflow_datasets as tfds
+ import tensorflow_datasets as tfds
-  (ds_train, ds_test), ds_info = tfds.load(
+ model.fit(
-      'mnist',
+     ds_train,
-      split=['train', 'test'],
+     epochs=6,
-      shuffle_files=True,
+     validation_data=ds_test,
-      as_supervised=True,
 </code>

@@ Line 105: / Line 105: @@
     sbatch  test.mpi
 </code>
 [[File:yambo_logo_overlay.png|350px]]

@@ Line 63: / Line 63: @@
 give the file a name like '''job.mpi''',
 edit the last line to include your commands to gromacs, and submit with slurm:
 <code bash>
-   sbatch  test.mpi
+  sbatch  test.mpi
 </code>
-== [https://asciinema.org/a/bPFAntHZt1xyLcpFkowGpoFZ3 Watch Demo] ==
+== [https://asciinema.org/a/bPFAntHZt1xyLcpFkowGpoFZ3 Watch Gromacs Demo] ==
 [[File:Quantum_ESPRESSO_logo.jpg|350px]]