tensorflow - 如何使用 XLA 编译器？

Question

我们正在尝试为 TensorFlow XLA 编译器实现我们自己的后端，但我们遇到了一个有点尴尬的情况:我们似乎无法让现有的 CPU 编译器做任何事情。使用此处的 TensorFlow XLA 示例:

https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/tutorials/mnist/mnist_softmax_xla.py

我们在配置步骤中使用 TF_ENABLE_XLA=1 从源构建 TensorFlow，并在上面调试信息。然后我们在 LLDB 中运行 softmax 示例并尝试中断对 CpuCompiler::Compile() 的调用。如下所示，程序运行到完成，没有中断 Compile() 函数，或者显然是预期调用它的任何函数。

~/tflow$ lldb -- python3 mnist_softmax_xla.py 
(lldb) target create "python3"
Current executable set to 'python3' (x86_64).
(lldb) settings set -- target.run-args  "mnist_softmax_xla.py"
(lldb) b CpuCompiler::Compile
Breakpoint 1: no locations (pending).
WARNING:  Unable to resolve breakpoint to any actual locations.
(lldb) r
Process 10331 launched: '/usr/bin/python3' (x86_64)
2 locations added to breakpoint 1
Process 10331 stopped and restarted: thread 1 received signal: SIGCHLD
Extracting /tmp/tensorflow/mnist/input_data/train-images-idx3-ubyte.gz
Extracting /tmp/tensorflow/mnist/input_data/train-labels-idx1-ubyte.gz
Extracting /tmp/tensorflow/mnist/input_data/t10k-images-idx3-ubyte.gz
Extracting /tmp/tensorflow/mnist/input_data/t10k-labels-idx1-ubyte.gz
2017-04-13 15:35:52.612498: I tensorflow/compiler/xla/service/platform_util.cc:58] platform Host present with 8 visible devices
2017-04-13 15:35:52.616628: I tensorflow/compiler/xla/service/service.cc:183] XLA service 0x2b38780 executing computations on platform Host. Devices:
2017-04-13 15:35:52.616642: I tensorflow/compiler/xla/service/service.cc:191]   StreamExecutor device (0): <undefined>, <undefined>
0.9195
Process 10331 exited with status = 0 (0x00000000) 

Answer 1

在 GitHub 上回答:

https://github.com/tensorflow/tensorflow/issues/9194

TensorFlow 开发提示中尚未启用 CPU JIT。它应该适用于 GPU。