}
      return r;
    }});

  render();

  // Helper functions follow:

  // hilite changes the highlighting of elements corresponding to specified src.
  function hilite(src, on) {
    if (on) {
      matches.add(src);
    } else {
      matches.delete(src);
    }
    toggleClass(src, 'hilite', on);
    return true;
  }

  // Display action menu (triggered by right-click on a frame)

  function setNodeHighlight(n, set) {
    if (options && options.hiliter) return options.hiliter(n, set);

    const elem = document.getElementById('node' + n);
    if (!elem) return false;

    // Handle table row highlighting.
    if (elem.nodeName == 'TR') {
      elem.classList.toggle('hilite', set);
      return true;
    }

    // Handle svg element highlighting.

#include "tensorflow/compiler/mlir/lite/stablehlo/transforms/op_stat_pass.h"
#include "tensorflow/compiler/mlir/lite/stablehlo/transforms/passes.h"
#include "tensorflow/compiler/mlir/lite/stablehlo/transforms/stablehlo_util.h"
#include "tensorflow/compiler/mlir/lite/stablehlo/transforms/transforms.h"
#include "tensorflow/compiler/mlir/lite/tf_tfl_passes.h"
#include "tensorflow/compiler/mlir/lite/transforms/passes.h"

#include "tensorflow/compiler/mlir/lite/common/tfl_pass_config.h"
#include "tensorflow/compiler/mlir/lite/flatbuffer_export_flags.h"
#include "tensorflow/compiler/mlir/lite/schema/schema_generated.h"
#include "tensorflow/compiler/mlir/lite/tf_tfl_translate_cl.h"
#include "tensorflow/compiler/mlir/lite/tf_to_tfl_flatbuffer.h"
#include "tensorflow/compiler/mlir/lite/transforms/passes.h"

   * is not guaranteed to return zero when the dataset consists of the same value multiple times,
   * due to numerical errors. However, it is guaranteed never to return a negative result.
   *
   * <h3>Non-finite values</h3>
   *
   * <p>If the dataset contains any non-finite values ({@link Double#POSITIVE_INFINITY}, {@link

   *
   * <p>This is guaranteed to return zero if the dataset contains a single pair of finite values. It
   * is not guaranteed to return zero when the dataset consists of the same pair of values multiple
   * times, due to numerical errors.
   *
   * <h3>Non-finite values</h3>
   *
   * <p>If the dataset contains any non-finite values ({@link Double#POSITIVE_INFINITY}, {@link

#include "tensorflow/compiler/mlir/lite/ir/tfl_ops.h"
#include "tensorflow/compiler/mlir/lite/transforms/passes.h"
#include "tensorflow/compiler/mlir/lite/utils/lstm_utils.h"
#include "tensorflow/compiler/mlir/lite/utils/nms_utils.h"
#include "tensorflow/compiler/mlir/lite/utils/perception_ops_utils.h"
#include "tensorflow/compiler/mlir/lite/utils/tftext_utils.h"

func (x *Float) validate0() string {
	if x.form != finite {
		return ""
	}
	m := len(x.mant)
	if m == 0 {
		return "nonzero finite number with empty mantissa"
	}
	const msb = 1 << (_W - 1)
	if x.mant[m-1]&msb == 0 {
		return fmt.Sprintf("msb not set in last word %#x of %s", x.mant[m-1], x.Text('p', 0))
	}
	if x.prec == 0 {
		return "zero precision finite number"
	}
	return ""
}

   *
   * <p>This is guaranteed to return zero if the dataset contains a single pair of finite values. It
   * is not guaranteed to return zero when the dataset consists of the same pair of values multiple
   * times, due to numerical errors.
   *
   * <h3>Non-finite values</h3>
   *
   * <p>If the dataset contains any non-finite values ({@link Double#POSITIVE_INFINITY}, {@link

  public static int log2(double x, RoundingMode mode) {
    checkArgument(x > 0.0 && isFinite(x), "x must be positive and finite");
    int exponent = getExponent(x);
    if (!isNormal(x)) {
      return log2(x * IMPLICIT_BIT, mode) - SIGNIFICAND_BITS;
      // Do the calculation on a normal value.
    }
    // x is positive, finite, and normal
    boolean increment;
    switch (mode) {
      case UNNECESSARY: