[Bug rtl-optimization/79149] bad optimization on MIPS and ARM leading to excessive stack usage in some cases

[arnd at linaro dot org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79149

--- Comment #5 from Arnd Bergmann <arnd at linaro dot org> ---
-fno-schedule-insns is comparable in stack frame size to
"-fno-sched-critical-path-heuristic -fno-sched-dep-count-heuristic" on all
architectures (give or take a few bytes), but actually produces much better
code.

In my simulated mips64 run, I see these numbers:

-O2:  49.0Mbit/s
-O2 -fno-sched-critical-path-heuristic -fno-sched-dep-count-heuristic: 109.7
Mbit/s
-O2 -fno-schedule-insns: 179.2 Mbit/s

The trend is the same on arm an aarch64 for emulated runs, and I confirmed
earlier that the results on real hardware are comparable to what we get in
qemu.