[TF:XLA] Fix an issue where plugin/Executor backend is used by default when TF

is built from source with XLA support. See Github issue .

The priority of the executor backend is set to be higher than the default (50)
and CPUs (<100), and is therefore selected as the default when tf.device is not
explicitly specified.

PiperOrigin-RevId: 161717173
This commit is contained in:
Kay Zhu 2017-07-12 14:22:54 -07:00 committed by TensorFlower Gardener
parent 6b28eb0843
commit 6d6dda807c

View File

@ -47,7 +47,12 @@ Status XlaExaDeviceFactory::CreateDevices(const SessionOptions& options,
return Status::OK();
}
REGISTER_LOCAL_DEVICE_FACTORY(DEVICE_XLA_EXEC, XlaExaDeviceFactory, 110);
// Set priority to be below the default priority (50), so that Executor is not
// selected as a high priority device over other default devices.
// See constructor comments for Registrar in
// tensorflow/core/common_runtime/device_factory.h for a list of priority for
// devices.
REGISTER_LOCAL_DEVICE_FACTORY(DEVICE_XLA_EXEC, XlaExaDeviceFactory, 40);
// Kernel registrations