On Mon, 14 Jul 2025 15:43:58 GMT, Raffaello Giulietti <rgiulie...@openjdk.org> wrote:
> This is my hunch as well. So while the use of `nextUp()` and `ceil()` > certainly help to achieve an overestimate, I'm less sure that this is > sufficient when using `pow()`. If the latter has some error bigger than a few > ulps, then we are in trouble. If the results are guaranteed to be semi-monotonic, then `nextUp()` and `ceil()` should be sufficient to achieve an overestimate... ------------- PR Review Comment: https://git.openjdk.org/jdk/pull/24898#discussion_r2205267660
