//
// See Ulf Adams, "Ryū: Fast Float-to-String Conversion" (doi:10.1145/3192366.3192369)
//
// Fixed precision formatting is a variant of the original paper's
// algorithm, where a single multiplication by 10^k is required,
// sharing the same rounding guarantees.

// ryuFtoaFixed32 formats mant*(2^exp) with prec decimal digits.
func ryuFtoaFixed32(d *decimalSlice, mant uint32, exp int, prec int) {
	if prec < 0 {

    // [-512, 512], instead of [-32767, 32767].
    // For now this behavior is specific for SVDF, where 6 bits are reserved for
    // the reduce operation after element-wise multiplication between state and
    // time weights.
    if (tensor_property.number_of_bits == 10) {
      SmallVector<double, 4> mins(1, std::numeric_limits<double>::max());

      return true;
    }
  },
  /**
   * This strategy uses all 128 bits of {@link Hashing#murmur3_128} when hashing. It looks different
   * from the implementation in MURMUR128_MITZ_32 because we're avoiding the multiplication in the
   * loop and doing a (much simpler) += hash2. We're also changing the index to a positive number by
   * AND'ing with Long.MAX_VALUE instead of flipping the bits.
   */
  MURMUR128_MITZ_64() {
    @Override

      return true;
    }
  },
  /**
   * This strategy uses all 128 bits of {@link Hashing#murmur3_128} when hashing. It looks different
   * from the implementation in MURMUR128_MITZ_32 because we're avoiding the multiplication in the
   * loop and doing a (much simpler) += hash2. We're also changing the index to a positive number by
   * AND'ing with Long.MAX_VALUE instead of flipping the bits.
   */
  MURMUR128_MITZ_64() {
    @Override

    assertEquals(1, future.get(-1, SECONDS).intValue());
  }

  @J2ktIncompatible
  @GwtIncompatible // threads
  public void testOverflowTimeout() throws Exception {
    // First, sanity check that naive multiplication would really overflow to a negative number:
    long nanosPerSecond = NANOSECONDS.convert(1, SECONDS);
    assertThat(nanosPerSecond * Long.MAX_VALUE).isLessThan(0L);

  }

  const int64_t rows = lhs_shape[lhs_dims - 2];
  const int64_t cols = rhs_shape[rhs_dims - 1];

  if (lhs_shape[lhs_dims - 1] != rhs_shape[rhs_dims - 2]) {
    // Input dimensions must be compatible for multiplication.
    return failure();
  }

  const auto matmul_type = RankedTensorType::get({rows, cols}, element_type);

  if (lhs_dims == 2 && rhs_dims == 2) {

    assertEquals(1, future.get(-1, SECONDS).intValue());
  }

  @J2ktIncompatible
  @GwtIncompatible // threads
  public void testOverflowTimeout() throws Exception {
    // First, sanity check that naive multiplication would really overflow to a negative number:
    long nanosPerSecond = NANOSECONDS.convert(1, SECONDS);
    assertThat(nanosPerSecond * Long.MAX_VALUE).isLessThan(0L);

    double ySumOfSquaresOfDeltas = yStats.sumOfSquaresOfDeltas();
    checkState(xSumOfSquaresOfDeltas > 0.0);
    checkState(ySumOfSquaresOfDeltas > 0.0);
    // The product of two positive numbers can be zero if the multiplication underflowed. We
    // force a positive value by effectively rounding up to MIN_VALUE.
    double productOfSumsOfSquaresOfDeltas =
        ensurePositive(xSumOfSquaresOfDeltas * ySumOfSquaresOfDeltas);

// The following assembly functions are implemented in p256_asm_*.s

// Montgomery multiplication. Sets res = in1 * in2 * R⁻¹ mod p.
//
//go:noescape
func p256Mul(res, in1, in2 *p256Element)

// Montgomery square, repeated n times (n >= 1).
//
//go:noescape
func p256Sqr(res, in *p256Element, n int)

// Montgomery multiplication by R⁻¹, or 1 outside the domain.

	"F0",
	"F2",
	"F4",
	"F6",
	"F8",
	"F10",
	"F12",
	"F14",
	"F16",
	"F18",
	"F20",
	"F22",
	"F24",
	"F26",
	"F28",
	"F30",

	"HI", // high bits of multiplication
	"LO", // low bits of multiplication

	// If you add registers, update asyncPreempt in runtime.

	// pseudo-registers
	"SB",
}

func init() {
	// Make map from reg names to reg integers.
	if len(regNamesMIPS) > 64 {