[PATCH] D113350: [X86][Costmodel] `getReplicationShuffleCost()`: implement cost model for 32/64 bit-wide elements with AVX512F

[Roman Lebedev via Phabricator via llvm-commits]

lebedev.ri added a comment.

The rough roadmap for the planned follow-ups:

1. i16 if +BWI
2. i8 if +VBMI
3. i16 ?ext -> i32 -> trunc i16 if -BWI
4. i8 ?ext -> i16 -> trunc i8 if -VBMI +BWI
5. i8 ?ext -> i32 -> trunc i8 if -VBMI -BWI
6. i1 ?ext -> i8 -> trunc i1 if +VBMI
7. i1 ?ext -> i16 -> trunc i1 if -VBMI +BWI
8. i1 ?ext -> i32 -> trunc i1 if -VBMI -BWI
9. ???
10. PROFIT!


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D113350/new/

https://reviews.llvm.org/D113350