https://gcc.gnu.org/bugzilla/show_bug.cgi?id=61245
--- Comment #5 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
The loop is still vectorized though. As it looks like it was versioned.
t6.cc: In function ‘void doT(SoA<N>&) [with int N = 3]’:
t6.cc:34:17: warning: ignoring loop annotation
34 | for (auto i=0U; i<soa.size(); ++i)
| ^
t6.cc:10:17: optimized: loop vectorized using 16 byte vectors
t6.cc:10:17: optimized: loop vectorized using 8 byte vectors
t6.cc:34:17: optimized: loop vectorized using 16 byte vectors
t6.cc:34:17: optimized: loop versioned for vectorization because of possible
aliasing
t6.cc:34:17: optimized: loop vectorized using 8 byte vectors
I don't know how useful "#pragma GCC ivdep" is these days really.
