https://gcc.gnu.org/bugzilla/show_bug.cgi?id=128010
--- Comment #4 from Drea Pinski <pinskia at gcc dot gnu.org> --- (In reply to nsz from comment #3) > for the record the linux syscall abi: > https://www.kernel.org/doc/html/latest/arch/arm64/sve.html#system-call- > behaviour "On syscall, V0..V31 are preserved (as without SVE). Thus, bits [127:0] of Z0..Z31 are preserved. All other bits of Z0..Z31, and all of P0..P15 and FFR become zero on return from a syscall. " Oh, this is worse. Because a normal function will only save [63:0] even (except for the vector ABI functions). So if you really need this case to work; my suggestion is not do any inline-asm system calls. "the point of inline syscalls is to minimize register spills and shuffling so such spill is not acceptable." Because the system call itself will be slow. So I am not sure you want to have this loop in general. Can you show where this was showing up because it sounds like just premature optimization.
