);

  TF_DerivedOperandTypeAttr shape_dtype = TF_DerivedOperandTypeAttr<2>;
  TF_DerivedResultTypeAttr dtype = TF_DerivedResultTypeAttr<0>;
}

// TODO(lyandy): Investigate supported dtypes (`minval`, `maxval`, `output`) for
// `tf.StatefulUniformInt`. tf2xla kernels support i32, i64, ui32, and ui64
// while TensorFlow CPU/GPU kernels only support i32 and i64.

// since there aren't exact equivalent instructions.
// The corresponding s390x instructions appear in the
// comments.
// Implementation for big endian would have to be
// investigated, I think it would be different.
//
//
// Vector multiply word
//
//	VMLF  x0, x1, out_low
//	VMLHF x0, x1, out_hi
#define VMULT(x1, x2, out_low, out_hi) \
	VMULEUW x1, x2, TMP1; \
	VMULOUW x1, x2, TMP2; \