https://gcc.gnu.org/bugzilla/show_bug.cgi?id=77776
--- Comment #23 from g.peterh...@t-online.de --- Hello Matthias, you've given me new ideas. I think we agree on implementing hypot3 using a scaling factor. But the correct value is not yet implemented here either; do you have a suggestion? A version here: https://godbolt.org/z/Gd53cG9YG I've intentionally broken hypot_gp into small pieces so that you can play around with it. This is of course unnecessary for a final version. General * The function must of course work efficiently with all FP types. Questions * Sorting: It is theoretically sufficient to sort the values x,y,z only to the extent that the condition x,y <= z is fulfilled (HYPOT_SORT_FULL). * Accuracy: This is better with fma (HYPOT_FMA). * How do you create the benchmarks? I could do this myself without getting on your nerves. thx Gero