GPU上的Tensorflow Matmul计算比CPU慢 [英] Tensorflow matmul calculations on GPU are slower than on CPU

问题描述

我第一次尝试使用GPU计算，当然希望能够大幅度提高速度.但是，使用张量流中的一个基本示例，实际上更糟:

I'm experimenting with GPU computations for the first time and was hoping for a big speed-up, of course. However with a basic example in tensorflow, it actually was worse:

在cpu:0上，十次运行的平均时间为2秒，gpu:0耗时2.7秒，而gpu:1比cpu:0差3秒，即降低了50％.

On cpu:0, each of the ten runs takes on average 2 seconds, gpu:0 takes 2.7 seconds and gpu:1 is 50% worse than cpu:0 with 3 seconds.

代码如下:

import tensorflow as tf
import numpy as np
import time
import random

for _ in range(10):
    with tf.Session() as sess:
        start = time.time()
        with tf.device('/gpu:0'): # swap for 'cpu:0' or whatever
            a = tf.constant([random.random() for _ in xrange(1000 *1000)], shape=[1000, 1000], name='a')
            b = tf.constant([random.random() for _ in xrange(1000 *1000)], shape=[1000, 1000], name='b')
            c = tf.matmul(a, b)
            d = tf.matmul(a, c)
            e = tf.matmul(a, d)
            f = tf.matmul(a, e)
            for _ in range(1000):
                sess.run(f)
        end = time.time()
        print(end - start)

我在这里观察到什么?运行时间可能主要由在RAM和GPU之间复制数据主导吗?

What am I observing here? Is run time maybe mainly dominated by copying data between RAM and GPU?

推荐答案

用于生成数据的方式在CPU上执行(random.random()是常规的python函数，而不是TF-one).同样，执行一次10^6次将比一次运行请求10^6个随机数要慢. 将代码更改为:

The way you use to generate data is executed on CPU (random.random() is a regular python function and not TF-one). Also, executing it 10^6 times will be slower than requesting 10^6 random numbers in one run. Change the code to:

a = tf.random_uniform([1000, 1000], name='a')
b = tf.random_uniform([1000, 1000], name='b')

以便数据将在GPU上并行生成，而不会浪费时间将其从RAM传输到GPU.

so that the data will be generated on a GPU in parallel and no time will be wasted to transfer it from RAM to GPU.

这篇关于GPU上的Tensorflow Matmul计算比CPU慢的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！