JupyterHub with GPU

Create a jupyterhub instance with GPU support enabled.

setup

• Connect to login node of Anunna
• Install miniconda

Create conda environment that we can use for a jupyter kernel

conda create -y -n kernel_test python=3 ipykernel && conda activate kernel_test
python -m ipykernel install --user --name kernel_test

NOTE: You can specific the python version for you conda environment with python=3 Please take care what python version is compatible with you required packages.

Install required packages

For pytorch you can find information here and for TensorFlow here.

As an example I use the following pytorch installation:

pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118

Start jupyter notebook with GPU

Go here and select:

• Select a location for your server: on the cluster (default option)
• Partition to use: gpu
• Partition to use: gpu
• Memory (in MB): desired memory
• Number of CPUs: desired CPU count
• Maximum execution time (hours:minutes:seconds): maximum amount of time the notebook is available
• Extra options: --gres=gpu:1 (default when selecting GPU, gpu:x for x amount of GPUs)

Test GPU availability

Pytorch

def check_all_cuda_devices():
    device_count = torch.cuda.device_count()
    for i in range(device_count):
        print('>>>> torch.cuda.device({})'.format(i))
        result = torch.cuda.device(i)
        print(result, '\n')

        print('>>>> torch.cuda.get_device_name({})'.format(i))
        result = torch.cuda.get_device_name(i)
        print(result, '\n')


def check_cuda():
    print('>>>> torch.cuda.is_available()')
    result = torch.cuda.is_available()
    print(result, '\n')

    print('>>>> torch.cuda.device_count()')
    result = torch.cuda.device_count()
    print(result, '\n')

    print('>>>> torch.cuda.current_device()')
    result = torch.cuda.current_device()
    print(result, '\n')

    print('>>>> torch.cuda.device(0)')
    result = torch.cuda.device(0)
    print(result, '\n')

    print('>>>> torch.cuda.get_device_name(0)')
    result = torch.cuda.get_device_name(0)
    print(result, '\n')

    check_all_cuda_devices()


def check_cuda_ops():
    print('>>>> torch.zeros(2, 3)')
    zeros = torch.zeros(2, 3)
    print(zeros, '\n')

    print('>>>> torch.zeros(2, 3).cuda()')
    cuda_zero = torch.zeros(2, 3).cuda()
    print(cuda_zero, '\n')

    print('>>>> torch.tensor([[1, 2, 3], [4, 5, 6]])')
    tensor_a = torch.tensor([[1, 2, 3], [4, 5, 6]]).cuda()
    print(tensor_a, '\n')

    print('>>>> tensor_a + cuda_zero')
    sum = tensor_a + cuda_zero
    print(sum, '\n')

    print('>>>> tensor_a * cuda_twos')
    tensor_a = tensor_a.to(torch.float)
    cuda_zero = cuda_zero.to(torch.float)
    cuda_twos = (cuda_zero + 1.0) * 2.0
    product = tensor_a * cuda_twos
    print(product, '\n')

    print('>>>> torch.matmul(tensor_a, cuda_twos.T)')
    mat_mul = torch.matmul(tensor_a, cuda_twos.T)
    print(mat_mul, '\n')
    try:
        get_version()
    except Exception as e:
        print('get_version() failed, exception message below:')
        print(e)

    try:
        check_cuda()
    except Exception as e:
        print('check_cuda() failed, exception message below:')
        print(e)

    #print('>>>> time.sleep(20)')
    #time.sleep(20)

    try:
        check_cuda_ops()
    except Exception as e:
        print('check_cuda_ops() failed, exception message below:')
        print(e)

Tensorflow

import tensorflow as tf
hasGPUSupport = tf.test.is_built_with_cuda()
gpuList = tf.config.list_physical_devices('GPU')
print("Tensorflow Compiled with CUDA/GPU Support:", hasGPUSupport)
print("Tensorflow can access", len(gpuList), "GPU")
print("Accessible GPUs are:")
print(gpuList)

tf.debugging.set_log_device_placement(True)
# Place tensors on the GPU
with tf.device('device:GPU:0'):
  a = tf.constant([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]])
  b = tf.constant([[1.0, 2.0], [3.0, 4.0], [5.0, 6.0]])

# Run on the GPU
c = tf.matmul(a, b)
print(c)