tree 9a9b1ab5028ff103ec4c742a0ed91ebc7cc1a086
parent dfddd3c4f8e104fde218776b2da95f3601e103ad
author David Green <david.green@arm.com> 1613648537 +0000
committer Copybara-Service <copybara-worker@google.com> 1613734131 -0800

[ARM] Add larger than legal ICmp costs

A v8i32 compare will produce a v8i1 predicate, but during codegen the
v8i32 will be split into two v4i32, potentially requiring two v4i1
predicates to be merged into a single v8i1. Because this merging of two
v4i1's into a v8i1 is very expensive, we need to make the cost of the
compare equally high.

This patch adds the cost of that to ARMTTIImpl::getCmpSelInstrCost.
Because we don't know whether the user of the predicate can be split,
and the cost model is mostly pre-instruction, we may be pessimistic but
that should only be for larger and legal types. This also adds min/max
detection to the costmodel where it can be detected, to keep those in
line with the cost of simple min/max instructions. Otherwise for the
most part, costs that were already expensive have become more expensive.

Differential Revision: https://reviews.llvm.org/D96692

GitOrigin-RevId: 1a6744e3dc671d92662c94a77bbae50a6a34d316