Difference between revisions of "HTCondorGPU"

Latest revision as of 02:22, 12 May 2021

1 HTCondor에서 GPU 사용하기

1.1 Ex 1) Matrix

matrix.py

import numpy as np
from timeit import default_timer as timer
from numba import vectorize

@vectorize(['float32(float32, float32)'], target='cuda')

def pow(a, b):
    return a ** b

vec_size = 100000000
a = b = np.array(np.random.sample(vec_size), dtype=np.float32)
c = np.zeros(vec_size, dtype=np.float32)
start = timer()
c = pow(a,b)
duration = timer() - start
print(duration)

matrix.sh

#!/bin/bash
python3.6 -m virtualenv myvenv
source myvenv/bin/activate
pip3 install numba
python3.6 matrix.py

matrix.sub

executable              = matrix.sh
arguments               = $(ClusterId)$(ProcId)
output                  = matrix.$(ClusterId).$(ProcId).out
error                   = matrix.$(ClusterId).$(ProcId).err
log                     = matrix.$(ClusterId).log
should_transfer_files   = YES
transfer_input_files    = matrix.py 
when_to_transfer_output = ON_EXIT
request_GPUs = 1
request_CPUs = 1
queue

1.2 Ex 2) TensorFlow

tf_ex.py

import tensorflow as tf

mnist = tf.keras.datasets.mnist

(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

model = tf.keras.models.Sequential([
  tf.keras.layers.Flatten(input_shape=(28, 28)),
  tf.keras.layers.Dense(128, activation='relu'),
  tf.keras.layers.Dropout(0.2),
  tf.keras.layers.Dense(10, activation='softmax')
])

model.compile(optimizer='adam',loss='sparse_categorical_crossentropy',metrics=['accuracy'])

model.fit(x_train, y_train, epochs=5)
model.evaluate(x_test,  y_test, verbose=2)

tf_ex.sh

#!/bin/bash
python3.6 -m virtualenv myvenv
source myvenv/bin/activate
pip3 install tensorflow-gpu==2.0.0-rc1
python3.6 tf_ex.py

tf_ex.sub

executable              = tf_ex.sh
arguments               = $(ClusterId)$(ProcId)
output                  = tf_ex.$(ClusterId).$(ProcId).out
error                   = tf_ex.$(ClusterId).$(ProcId).err
log                     = tf_ex.$(ClusterId).log
transfer_input_files    = tf_ex.py
when_to_transfer_output = ON_EXIT
request_GPUs = 1
request_CPUs = 1
queue

1.3 Ex 3) Singularity & TensorFlow - cvmfs image

sing.sh

#!/bin/bash
python3.6 tf_ex.py

sing.sub

arguments               = $(ClusterId)$(ProcId)
output                  = sing.$(ClusterId).$(ProcId).out
error                   = sing.$(ClusterId).$(ProcId).err
log                     = sing.$(ClusterId).log
should_transfer_files   = YES
when_to_transfer_output = ON_EXIT
transfer_input_files    = tf_ex.py
request_GPUs = 1
request_CPUs = 1
+SingularityImage = "/cvmfs/singularity.opensciencegrid.org/opensciencegrid/tensorflow-gpu:latest"
queue

1.4 Ex 4) Singularity & TensorFlow - local image

sing-local.sub

executable              = sing.sh
arguments               = $(ClusterId)$(ProcId)
output                  = sing.$(ClusterId).$(ProcId).out
error                   = sing.$(ClusterId).$(ProcId).err
log                     = sing.$(ClusterId).log
should_transfer_files   = YES
when_to_transfer_output = ON_EXIT
transfer_input_files    = tf_ex.py
request_GPUs = 1
request_CPUs = 1
+SingularityImage = "/u/user/hanbi/tensorflow-gpu.sif"
queue

1.5 Ex 5) Singularity & TensorFlow - docker image

sing-docker.sub

executable              = sing.sh
arguments               = $(ClusterId)$(ProcId)
output                  = sing.$(ClusterId).$(ProcId).out
error                   = sing.$(ClusterId).$(ProcId).err
log                     = sing.$(ClusterId).log
should_transfer_files   = YES
when_to_transfer_output = ON_EXIT
transfer_input_files    = tf_ex.py
request_GPUs = 1
request_CPUs = 1
+SingularityImage = "docker://tensorflow/tensorflow:latest-gpu"
queue

1.6 참고자료

위의 예제들은 아래 문서들에서 참고했습니다. 좋은 내용이 많으니 이용에 참고하시기 바랍니다.

• https://batchdocs.web.cern.ch/tutorial/exercise10.html
• https://www.tensorflow.org/tutorials/quickstart/beginner
• https://sylabs.io/guides/3.6/user-guide/singularity_and_docker.html
• https://sylabs.io/guides/3.6/user-guide/gpu.html