[PATCH] D110342: [x86] convert logic-of-FP-compares to FP logic-of-vector-compares

Simon Pilgrim via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Thu Sep 23 10:10:52 PDT 2021


RKSimon added inline comments.


================
Comment at: llvm/lib/Target/X86/X86ISelLowering.cpp:45511
+  SDValue InsN11 =
+      DAG.getNode(ISD::INSERT_VECTOR_ELT, DL, VecVT, BaseVec, N11, ZeroIndex);
+  SDValue Setcc0 = DAG.getSetCC(DL, BoolVecVT, InsN00, InsN01,
----------------
Why not use SCALAR_TO_VECTOR ?


================
Comment at: llvm/test/CodeGen/X86/fcmp-logic.ll:155
 
+; This uses ucomis because the types do not match.
+
----------------
These could still be merged (as long as we only use the lower 32-bits).?


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D110342/new/

https://reviews.llvm.org/D110342



More information about the llvm-commits mailing list