https://gcc.gnu.org/bugzilla/show_bug.cgi?id=85048
--- Comment #13 from Matthias Kretz (Vir) <mkretz at gcc dot gnu.org> --- Should I open a new PR for the remaining ((u)int64, 16) <-> (float, 16) conversions? https://godbolt.org/z/x3xPMYKj3 Note that __builtin_convertvector produces the code we want. template <class T, int N, int Size = N * sizeof (T)> using V [[gnu::vector_size (Size)]] = T; template <class From, class To> V<To, 16> cvt16 (V<From, 16> x) { #if BUILTIN return __builtin_convertvector (x, V<To, 16>); #else return V<To, 16>{ To (x[0]), To (x[1]), To (x[2]), To (x[3]), To (x[4]), To (x[5]), To (x[6]), To (x[7]), To (x[8]), To (x[9]), To (x[10]), To (x[11]), To (x[12]), To (x[13]), To (x[14]), To (x[15]) }; #endif } #define _(name, from, to, size) \ auto name (V<from, size> x) { return cvt##size<from, to> (x); } // integral -> float _ (vcvtqq2ps, int64_t, float, 16) _ (vcvtuqq2ps, uint64_t, float, 16) // float -> integral _ (vcvttps2qq, float, int64_t, 16) _ (vcvttps2uqq, float, uint64_t, 16)
