tensorflow多GPU训练编程

本文主要借鉴了[Multi-GPU basics]https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/6_MultiGPU/multigpu_basics.ipynb

1. 导入所需模块

import tensorflow as tf
import numpy as np
import datetime

#Processing Units logs
log_device_placement = True

#num of multiplications to perform
n = 10

# Define matrix power
def matpow(M, n):
    if n < 1: #Abstract cases where n < 1
        return M
    else:
        return tf.matmul(M, matpow(M, n-1))

2. 建图

# Example: compute A^n + B^n on 2 GPUs

# Create random large matrix
A = np.random.rand(1e4, 1e4).astype('float32')
B = np.random.rand(1e4, 1e4).astype('float32')

# Creates a graph to store results
c1 = []
c2 = []

• single gpu：

# Single GPU computing

with tf.device('/gpu:0'):
    a = tf.constant(A)
    b = tf.constant(B)
    #compute A^n and B^n and store results in c1
    c1.append(matpow(a, n))
    c1.append(matpow(b, n))

with tf.device('/cpu:0'):
  sum = tf.add_n(c1) #Addition of all elements in c1, i.e. A^n + B^n

t1_1 = datetime.datetime.now()
with tf.Session(config=tf.ConfigProto(log_device_placement=log_device_placement)) as sess:
    # Runs the op.
    sess.run(sum)
t2_1 = datetime.datetime.now()

• multi-gpu：

# Multi GPU computing
# GPU:0 computes A^n
with tf.device('/gpu:0'):
    #compute A^n and store result in c2
    a = tf.constant(A)
    c2.append(matpow(a, n))

#GPU:1 computes B^n
with tf.device('/gpu:1'):
    #compute B^n and store result in c2
    b = tf.constant(B)
    c2.append(matpow(b, n))

with tf.device('/cpu:0'):
  sum = tf.add_n(c2) #Addition of all elements in c2, i.e. A^n + B^n

t1_2 = datetime.datetime.now()
with tf.Session(config=tf.ConfigProto(log_device_placement=log_device_placement)) as sess:
    # Runs the op.
    sess.run(sum)
t2_2 = datetime.datetime.now()

3. 测试结果：
   Single GPU computation time: 0:00:11.833497
   Multi GPU computation time: 0:00:07.085913
   可见并行地使用GPU计算可以提高提高运行速度。