https://gcc.gnu.org/bugzilla/show_bug.cgi?id=102178
Richard Biener <rguenth at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Last reconfirmed|2021-09-03 00:00:00 |2022-4-11
--- Comment #31 from Richard Biener <rguenth at gcc dot gnu.org> ---
For the testcase I still see 58 vmovq GPR <-> XMM at -Ofast -march=znver2,
resulting from spilling of xmms. And there's still cases like
movq .LC0(%rip), %rax
...
vmovq %rax, %xmm2
vmovq %rax, %xmm4
Honza - you said you wanted to have some look here. As I understand Vlad
costing isn't taken into account when choosing alternatives for reloading.
