[PATCH] D29425: [SLP] Use SCEV to sort memory accesses

[Michael Kuperstein via Phabricator via llvm-commits]

mkuper created this revision.
Herald added a subscriber: mzolotukhin.

This generalizes memory access sorting to use SCEVs instead of relying on constant offsets.

I'm not entirely sure my use of SCEV here is sane, both in terms of using the cache (if it's ok to rely on the cache, I can get rid of the map and simplify the whole thing), and in terms of expecting "SCEV.getMinusSCEV(X,Y) returns a constant" to be transitive. @sanjoy , I'll really appreciate feedback on both.


https://reviews.llvm.org/D29425

Files:
  include/llvm/Analysis/LoopAccessAnalysis.h
  lib/Analysis/LoopAccessAnalysis.cpp
  test/Transforms/SLPVectorizer/X86/jumbled-load.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D29425.86714.patch
Type: text/x-patch
Size: 13303 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170201/1408f079/attachment.bin>