On 9/13/23 3:48 PM, Segher Boessenkool wrote:
- "TARGET_POWER10 && TARGET_POWERPC64"
+ "TARGET_POWER10 && TARGET_POWERPC64 && !RS6000_DISABLE_SCALAR_MODULO"
"vmoduq %0,%1,%2"
Did we ever test if this insn in fact is slower as well? I don't mean
either way, orthogonality is good, but just for my enlightenment.
Yes, I tested quadword too and saw the same result, div/mul/sub is the
better option.
With improved changelog: okay for trunk. Okay for all backports as
well (after some soak time).
Thanks, updated changelog and committed to trunk. Will backport after
burn-in.
-Pat