[PPC] Prefer direct move on power8 if load 1 or 2 bytes to VSR

Power8 has MTVSRWZ but no LXSIBZX/LXSIHZX, so move 1 or 2 bytes to VSR through MTVSRWZ is much faster than store the extended value into stack and load it with LXSIWZX.
This patch fixes pr31144.

Differential Revision: https://reviews.llvm.org/D27287

llvm-svn: 289473

1 files changed, 7 insertions, 1 deletions

diff --git a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
index 75b5180a943..aa3ffde24b9 100644
--- a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -6606,11 +6606,17 @@ void PPCTargetLowering::spliceIntoChain(SDValue ResChain,
 /// \brief Analyze profitability of direct move
 /// prefer float load to int load plus direct move
 /// when there is no integer use of int load
-static bool directMoveIsProfitable(const SDValue &Op) {
+bool PPCTargetLowering::directMoveIsProfitable(const SDValue &Op) const {
   SDNode *Origin = Op.getOperand(0).getNode();
   if (Origin->getOpcode() != ISD::LOAD)
     return true;
 
+  // If there is no LXSIBZX/LXSIHZX, like Power8,
+  // prefer direct move if the memory size is 1 or 2 bytes.
+  MachineMemOperand *MMO = cast<LoadSDNode>(Origin)->getMemOperand();
+  if (!Subtarget.hasP9Vector() && MMO->getSize() <= 2)
+    return true;
+
   for (SDNode::use_iterator UI = Origin->use_begin(),
                             UE = Origin->use_end();
        UI != UE; ++UI) {