// Returns a new thread that is running work_func and is identified
// (for debugging/performance-analysis) by thread_name.
//
// The given param (which may be null) is passed to work_func when the thread
// starts. In this way, data may be passed from the thread back to the caller.
//
// Caller takes ownership of the result and must call TF_JoinThread on it
// eventually.

// TPUReplicatedOutput(input=x, num_replicas=2)` un-packs the parallel tensor
// into its components.
//
// The filled `device` struct and the allocated `device_info` struct may be
// passed to TFE_RegisterCustomDevice. The `device_name` arguments must match.
void AllocateParallelDevice(const char* device_name,
                            const char* const* underlying_devices,

}

int
returnAfterGrowFromGo(void)
{
	extern int goReturnVal(void);
	return goReturnVal();
}

void
callGoWithString(void)
{
	extern void goWithString(GoString);
	const char *str = "string passed from C to Go";
	goWithString((GoString){str, strlen(str)});

#endif

// TF_Device is a C wrapper to the C++ TF Device class. This is to be passed
// through TF_OpKernelContext, and is opaque to plugin.
typedef struct TF_Device TF_Device;

typedef struct TF_VariableInfo TF_VariableInfo;

// Returns a `TF_Device` pointer, which actually points to a C++ `Device`.
// Currently we only allow `NextPluggableDevice` to be casted as `TF_Device`,
// but in theory every this is a C API for every kind of device.