https://gcc.gnu.org/bugzilla/show_bug.cgi?id=38768
Wilco <wilco at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |wilco at gcc dot gnu.org
--- Comment #11 from Wilco <wilco at gcc dot gnu.org> ---
Documentation for -fschedule-insns is now accurate for x86(_64) and AArch64:
index 6f0779b900c..304de88db07 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -13507,7 +13507,9 @@ helps machines that have slow floating point or memory
load instructions
by allowing other instructions to be issued until the result of the load
or floating-point instruction is required.
-Enabled at levels @option{-O2}, @option{-O3}.
+Conventionally enabled at optimization levels @option{-O2} and @option{-O3}.
+However, many targets override this behavior. For example, on x86, it is
+disabled at all levels, while on AArch64, it is enabled only at @option{-O3}.
@opindex fschedule-insns2
@item -fschedule-insns2
