On Tue, 23 Sep 2025 13:06:05 GMT, Raffaello Giulietti <rgiulie...@openjdk.org> wrote:
> @jddarcy Why can't we simply require a zero sign bit, like IEEE 754 does? > After all, IIUC this is exactly what the implementation does. As an intrinsic candidate, the method could be replaced with a hardware instruction and earlier editions of IEEE 754 didn't require the NaN behavior so hardware might not implement that policy. I could check on what contemporary chips are specified to do. ------------- PR Comment: https://git.openjdk.org/jdk/pull/27443#issuecomment-3324747241
