tree d49cf273545a315949f09e662d0bf213a1843618
parent a1937d2eb7498dd26700a2362d7c5f34416dfca1
author David Sherwood <david.sherwood@arm.com> 1756199843 +0100
committer GitHub <noreply@github.com> 1756199843 +0100
gpgsig -----BEGIN PGP SIGNATURE-----
 
 wsFcBAABCAAQBQJorXujCRC1aQ7uu5UhlAAAn2IQABAKWpbw8P99/bkvUmR3yq4C
 EFrFoP/CEm86STv+WLhA3aHvpejKN+mG/hUs9dniTquP03cSaWpE7BJ/AkK3G/0V
 x987SlUNlQ+YTPerPfUhDYjvPma46raKB/0HtaTaea26a5fvNd363mQ4h+uMJuk7
 uoCGbX5cpocd8gfNBTuYhV14ByCYa74LN5UOfKXc58Cnc7hItW1zb8/ZG5nl2HvP
 HolXd7VbEh8H/AcYys3ylXNcqsJte1B1MgddKrdMJfBSYKpHBwTI3EUrqrVuGIBS
 0eKIbFUkNcu2h75eE4WTInXrKmv8lYKvZryJMMYo13TTdsLovpw976w5T9PA7YUw
 1CRIyAxYGQLP2ZuZMtWQNvQx7/iwueb8N2c3S+Ge6rFV/NWxDoHFvPO9Oc2ijJqF
 DPPHXiBbyQhosyLExAhDw/BA1PaYVLidWLlE4iyy5mHd8i/osZxq2Gfo32t0cRG1
 1WAeS8zvNm2JHs9Lh5eAvz+QsofFPNyfkRfk5RL+CR6CykfOv0L9FgyyGFdJIQ9o
 B+0a09+x9zhGIJpUdrvdOOOt3UAlI1dbJJ0+7dJv5qZAlJdQh8uXfutPheVimE++
 CMsG3DvwNpZ0rq9piWOGpG7DkSBAO/1NF+UntLcg91oJwkalZ77CLNexEKBw6vtm
 uipMxmemNTylkxwbaVNZ
 =2918
 -----END PGP SIGNATURE-----
 

[LV] Stop using the legacy cost model for udiv + friends (#152707)

In VPWidenRecipe::computeCost for the instructions udiv, sdiv, urem and
srem we fall back on the legacy cost unnecessarily. At this point we
know that the vplan must be functionally correct, i.e. if the
divide/remainder is not safe to speculatively execute then we must have
either:

1. Scalarised the operation, in which case we wouldn't be using a
VPWidenRecipe, or
2. We've inserted a select for the second operand to ensure we don't
fault through divide-by-zero.

For 2) it's necessary to add the select operation to
VPInstruction::computeCost so that we mirror the cost of the legacy cost
model. The only problem with this is that we also generate selects in
vplan for predicated loops with reductions, which *aren't* accounted for
in the legacy cost model. In order to prevent asserts firing I've also
added the selects to precomputeCosts to ensure the legacy costs match
the vplan costs for reductions.