On 6/30/2026 6:48 AM, Michael Matz wrote:
Hello,
On Tue, 30 Jun 2026, Richard Biener wrote:
But the cmov will still serialize this? So the point is that the longer
non-power-of-two sequence (plus the cmov) is faster than the idiv?
Without cmov, it's always faster, yes. We're "always" expanding idiv by
constants via granlund-montgomery-like methods at expand_divmod. A shift
for the power of two should be faster still, and so the whole sequence
should be bounded on the non-pow2 length + cmov. Targets where shift is
slow (avr?) may prefer the idiv, though. So ...
And not all designs are going to serialize around the cmov. The two
RISC-V designs I'm most familiar with wouldn't. Point being there's
quite a bit of target/uarch variation here.
That's a pretty target specific thing, so again I think this is
something for RTL expansion where we evaluate division-by-constant costs
appropriately
... yeah, I agree, on gimple seems too early.
Seems like gimple->RTL expansion would be a good place. Past that it
gets much harder to recover the range information Hongtao needs.
jeff
