msg, ok := parseCniLog(l)
		if !ok {
			continue
		}
		messages = append(messages, msg)
	}
	// Lock log message printing to prevent log messages from different CNI
	// processes interleave.
	l.mu.Lock()
	defer l.mu.Unlock()
	for _, m := range messages {
		logger := pluginLog
		// For any k/v pairs, add them back
		for k, v := range m.Arbitrary {
			logger = logger.WithLabels(k, v)
		}

      if (result == CancellationException.class) {
        assertTrue(future.isCancelled());
        assertTrue(cancellationSuccess.get());
        // cancellation can interleave in 3 ways
        // 1. prior to setFuture
        // 2. after setFuture before set() on the future assigned
        // 3. after setFuture and set() are called but before the listener completes.

      if (result == CancellationException.class) {
        assertTrue(future.isCancelled());
        assertTrue(cancellationSuccess.get());
        // cancellation can interleave in 3 ways
        // 1. prior to setFuture
        // 2. after setFuture before set() on the future assigned
        // 3. after setFuture and set() are called but before the listener completes.

	var head, tail, zerobase loader.Sym
	ldr := ctxt.loader
	sl := make([]symNameSize, len(syms))

	// For ppc64, we want to interleave the .got and .toc sections
	// from input files. Both are type sym.SELFGOT, so in that case
	// we skip size comparison and do the name comparison instead
	// (conveniently, .got sorts before .toc).

    *   Add delegate support for `QUANTIZED_16BIT_LSTM`.
    *   Converts hardswish subgraphs into atomic ops.
*   Add support for defaulting the value of `cycle_length` argument of
    `tf.data.Dataset.interleave` to the number of schedulable CPU cores.
*   `parallel_for`: Add converter for `MatrixDiag`.
*   Add `narrow_range` attribute to `QuantizeAndDequantizeV2` and V3.
*   Added new op: `tf.strings.unsorted_segment_join`.

  let summary = "BatchToSpace for N-D tensors of type T.";

  let description = [{
This operation reshapes the "batch" dimension 0 into `M + 1` dimensions of shape
`block_shape + [batch]`, interleaves these blocks back into the grid defined by
the spatial dimensions `[1, ..., M]`, to obtain a result with the same rank as
the input.  The spatial dimensions of this intermediate result are then