https://gcc.gnu.org/bugzilla/show_bug.cgi?id=100778
--- Comment #12 from rguenther at suse dot de <rguenther at suse dot de> --- On Fri, 2 Jul 2021, gabrielle.hugo at cern dot ch wrote: > https://gcc.gnu.org/bugzilla/show_bug.cgi?id=100778 > > --- Comment #11 from Gabrielle Hugo <gabrielle.hugo at cern dot ch> --- > Awesome, thanks a lot Richard! > > > Applying your patch in tree-vect-slp.c to gcc 11, I now get the vectorized > division divpd after the if as expected: > > if (norm .gt. 1.D+00) then > 400826: 76 7b jbe 4008a3 <normalize_+0xb3> > 400828: 66 0f 28 d0 movapd %xmm0,%xmm2 > x = x / norm > y = y / norm > write (*, '(A,F5.3)') 'Normalized x and y.', norm > 40082c: 48 8b 05 c5 01 00 00 mov 0x1c5(%rip),%rax # > 4009f8 > <options.2.0+0x28> > 400833: 48 8d 6c 24 10 lea 0x10(%rsp),%rbp > 400838: 48 c7 44 24 18 78 09 movq $0x400978,0x18(%rsp) > 40083f: 40 00 > 400841: 66 0f 14 d2 unpcklpd %xmm2,%xmm2 > 400845: 48 89 ef mov %rbp,%rdi > 400848: c7 44 24 20 1d 00 00 movl $0x1d,0x20(%rsp) > 40084f: 00 > x = x / norm > 400850: 66 0f 5e ca divpd %xmm2,%xmm1 > > > So if I understand correctly the fix in SLP vectorization > (is_a <bb_vec_info> (vinfo)), > when there are possibly trapping operations > (gimple_could_trap_p (stmt_info->stmt)), > is to explicitely constrain them to come from the same BB > (special handling when gimple_bb (last_stmt) != gimple_bb (stmt_info->stmt) ). Yes. > Do I understand correctly that trunk is basically gcc 12.0, which will > eventually end up being released as gcc 12.1 ? Yes. > What about gcc 11, will this fix also make its way to the next gcc 11 release? Yes, we're usually waiting a bit to see if fallout is detected by autotesters before backporting to release branches.
