import tensorflow as tf

session_config = tf.ConfigProto(
   log_device_placement=True,
   inter_op_parallelism_threads=0,
   intra_op_parallelism_threads=0,
   allow_soft_placement=True)

sess = tf.Session(config=session_config)

a = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[2,3], name='b')
b = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[3,2], name='b')

c = tf.matmul(a,b)
print(sess.run(c))

session_config.gpu_options.allow_growth = True

session_config.gpu_options.per_process_gpu_memory_fraction = 0.4

tf.test.is_built_with_cuda()

import tensorflow as tf

sess = tf.Session()

with tf.device('/cpu:0'):
  a = tf.constant([1.0, 3.0, 5.0], shape=[1, 3])
  b = tf.constant([2.0, 4.0, 6.0], shape=[3, 1])

  with tf.device('/gpu:0'):
    c = tf.matmul(a, b)
    c = tf.reshape(c, [-1])

  with tf.device('/gpu:0'):
    d = tf.matmul(b, a)
    flat_d = tf.reshape(d, [-1])

  combined = tf.multiply(c, flat_d)
  print(sess.run(combined))