[PATCH] D75624: [DAG] Combine fshl/fshr(load1,load0,c) if we have consecutive loads

Simon Pilgrim via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Wed Mar 4 12:57:18 PST 2020


RKSimon marked an inline comment as done.
RKSimon added inline comments.


================
Comment at: llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp:8271
+          (LHS->hasOneUse() || RHS->hasOneUse()) && ISD::isNON_EXTLoad(RHS)) {
+        if (DAG.areNonVolatileConsecutiveLoads(LHS, RHS, BitWidth / 8, 1)) {
+          SDLoc DL(RHS);
----------------
efriedma wrote:
> Do you need to check whether unaligned loads are supported for the given type?
Thanks, I'll add an TLI.allowsMemoryAccess check - speaking of which, a lot of combines seem to use a getABITypeAlignment check which seems like overkill to me?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D75624/new/

https://reviews.llvm.org/D75624





More information about the llvm-commits mailing list