errors for fallback behaviour.
    *   Refactors `NNAPI` Delegate to support detailed reason why an operation
        is not accelerated.
    *   Converts hardswish subgraphs into atomic ops.
*   Other
    *   Critical stability updates for TPUs, especially in cases where the XLA
        compiler produces compilation errors.
    *   TPUs can now be re-initialized multiple times, using

build:windows --features=compiler_param_file
build:windows --features=archive_param_file

# Speed Windows compile times. Available in VS 16.4 (we are on 16.11). See
# https://groups.google.com/a/tensorflow.org/d/topic/build/SsW98Eo7l3o/discussion
build:windows --copt=/d2ReducedOptimizeHugeFunctions
build:windows --host_copt=/d2ReducedOptimizeHugeFunctions

# Enable the runfiles symlink tree on Windows. This makes it possible to build