Add support for combining GEPs across PHI nodes

Currently LLVM will generally merge GEPs. This allows backends to use more
complex addressing modes. In some cases this is not happening because there
is PHI inbetween the two GEPs:

  GEP1--\
        |-->PHI1-->GEP3
  GEP2--/

This patch checks to see if GEP1 and GEP2 are similiar enough that they can be
cloned (GEP12) in GEP3's BB, allowing GEP->GEP merging (GEP123):

  GEP1--\                     --\                           --\
        |-->PHI1-->GEP3  ==>    |-->PHI2->GEP12->GEP3 == >    |-->PHI2->GEP123
  GEP2--/                     --/                           --/

This also breaks certain use chains that are preventing GEP->GEP merges that the
the existing instcombine would merge otherwise.

Tests included.

rdar://15547484

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@209049 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 59 insertions, 0 deletions

diff --git a/lib/Transforms/InstCombine/InstructionCombining.cpp b/lib/Transforms/InstCombine/InstructionCombining.cpp
index 4c36887f62..35b4889a83 100644
--- a/lib/Transforms/InstCombine/InstructionCombining.cpp
+++ b/lib/Transforms/InstCombine/InstructionCombining.cpp
@@ -1220,6 +1220,65 @@ Instruction *InstCombiner::visitGetElementPtrInst(GetElementPtrInst &GEP) {
     if (MadeChange) return &GEP;
   }
 
+  // Check to see if the inputs to the PHI node are getelementptr instructions.
+  if (PHINode *PN = dyn_cast<PHINode>(PtrOp)) {
+    GetElementPtrInst *Op1 = dyn_cast<GetElementPtrInst>(PN->getOperand(0));
+    if (!Op1)
+      return nullptr;
+
+    signed DI = -1;
+
+    for (auto I = PN->op_begin()+1, E = PN->op_end(); I !=E; ++I) {
+      GetElementPtrInst *Op2 = dyn_cast<GetElementPtrInst>(*I);
+      if (!Op2 || Op1->getNumOperands() != Op1->getNumOperands())
+        return nullptr;
+
+      for (unsigned J = 0, F = Op1->getNumOperands(); J != F; ++J) {
+        if (Op1->getOperand(J) != Op2->getOperand(J)) {
+          if (DI == -1) {
+            // We have not seen any differences yet in the GEPs feeding the
+            // PHI yet, so we record this one.
+            DI = J;
+          } else {
+            // The GEP is different by more than one input. While this could be
+            // extended to support GEPs that vary by more than one variable it
+            // doesn't make sense since it greatly increases the complexity and
+            // would result in an R+R+R addressing mode which no backend
+            // directly supports and would need to be broken into several
+            // simpler instructions anyway.
+            return nullptr;
+          }
+        }
+      }
+    }
+
+    GetElementPtrInst *NewGEP = dyn_cast<GetElementPtrInst>(Op1->clone());
+
+    if (DI == -1) {
+      // All the GEPs feeding the PHI are identical. Clone one down into our
+      // BB so that it can be merged with the current GEP.
+      GEP.getParent()->getInstList().insert(GEP.getParent()->getFirstNonPHI(),
+                                            NewGEP);
+    } else {
+      // All the GEPs feeding the PHI differ at a single offset. Clone a GEP
+      // into the current block so it can be merged, and create a new PHI to
+      // set that index.
+      PHINode *NewPN = Builder->CreatePHI(Op1->getOperand(DI)->getType(),
+                                          PN->getNumOperands());
+      for (auto &I : PN->operands())
+        NewPN->addIncoming(dyn_cast<GEPOperator>(I)->getOperand(DI),
+                           PN->getIncomingBlock(I));
+
+      NewGEP->setOperand(DI, NewPN);
+      GEP.getParent()->getInstList().insert(GEP.getParent()->getFirstNonPHI(),
+                                            NewGEP);
+      NewGEP->setOperand(DI, NewPN);
+    }
+
+    GEP.setOperand(0, NewGEP);
+    PtrOp = NewGEP;
+  }
+
   // Combine Indices - If the source pointer to this getelementptr instruction
   // is a getelementptr instruction, combine the indices of the two
   // getelementptr instructions into a single instruction.