[PATCH] D111460: [X86][LoopVectorize] "Fix" `X86TTIImpl::getAddressComputationCost()`

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon added inline comments.


================
Comment at: llvm/lib/Target/X86/X86TargetTransformInfo.cpp:3852
+    // essentially just fallback to the same sequence as gather) but we can
+    // model the cost of gather, and the cost is more favorable. et the
+    // interleaved load is better in general in reality.
----------------
et?


================
Comment at: llvm/lib/Target/X86/X86TargetTransformInfo.cpp:3854
+    // interleaved load is better in general in reality.
+    // AVX2 is a cut-off because we have correct intereaving costs
+    // for a select number of triples.
----------------
"TODO: AVX2 is the current cut-off......"


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D111460/new/

https://reviews.llvm.org/D111460