// invalid scalars and the zero value. BytesX returns an error for the point
	// at infinity, but in a prime order group such as the NIST curves that can
	// only be the result of a scalar multiplication if one of the inputs is the
	// zero scalar or the point at infinity.

	if boring.Enabled {
		return boring.ECDH(local.boring, remote.boring)
	}

	boring.Unreachable()

//      From step 1, we have
//         expm1(x) = either 2**k*[expm1(r)+1] - 1
//                  = or     2**k*[expm1(r) + (1-2**-k)]
//   4. Implementation notes:
//      (A). To save one multiplication, we scale the coefficient Qi
//           to Qi*2**i, and replace z by (x**2)/2.
//      (B). To achieve maximum accuracy, we compute expm1(x) by
//        (i)   if x < -56*ln2, return -1.0, (raise inexact if x!=inf)

			desc: "negative uint",
			in: `go test fuzz v1
uint(-32)`,
			reject: true,
		},
		{
			desc: "int8 too large",
			in: `go test fuzz v1
int8(1234456)`,
			reject: true,
		},
		{
			desc: "multiplication in int value",
			in: `go test fuzz v1
int(20*5)`,
			reject: true,
		},
		{
			desc: "double negation",
			in: `go test fuzz v1
int(--5)`,
			reject: true,
		},
		{
			desc: "malformed bool",

    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);

}

def TF_XlaSparseDenseMatmulWithStaticBufferSizeOp : TF_Op<"XlaSparseDenseMatmulWithStaticBufferSize", [Pure]> {
  let summary = "A XLA op which performs the dense-sparse matrix multiplication.";

  let arguments = (ins
    TF_Int32Tensor:$row_pointers,
    TF_Int32Tensor:$sorted_sample_ids,
    TF_Int32Tensor:$sorted_token_ids,
    TF_Float32Tensor:$sorted_gains,

	size := uintptr(class_to_size[c.spanclass.sizeclass()])

	s := mheap_.alloc(npages, c.spanclass)
	if s == nil {
		return nil
	}

	// Use division by multiplication and shifts to quickly compute:
	// n := (npages << _PageShift) / size
	n := s.divideByElemSize(npages << _PageShift)
	s.limit = s.base() + size*n
	s.initHeapBits(false)
	return s

  }

  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);

// 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.

		computeDivMagic(&classes[i])
	}

	return classes
}

// computeDivMagic checks that the division required to compute object
// index from span offset can be computed using 32-bit multiplication.
// n / c.size is implemented as (n * (^uint32(0)/uint32(c.size) + 1)) >> 32
// for all 0 <= n <= c.npages * pageSize
func computeDivMagic(c *class) {
	// divisor
	d := c.size
	if d == 0 {
		return
	}