Allow min/max detection to see through casts.

[oota-llvm.git] / lib / CodeGen / CodeGenPrepare.cpp

diff --git a/lib/CodeGen/CodeGenPrepare.cpp b/lib/CodeGen/CodeGenPrepare.cpp
index 91bd5656b74c26baa8f5f8f3d23e57c8a2376c46..f37a2874b2565ac79ced410323b4d9ca9d0e2582 100644 (file)
--- a/lib/CodeGen/CodeGenPrepare.cpp
+++ b/lib/CodeGen/CodeGenPrepare.cpp
@@ -531,8 +531,8 @@ static void computeBaseDerivedRelocateMap(
   for (auto &U : AllRelocateCalls) {
     GCRelocateOperands ThisRelocate(U);
     IntrinsicInst *I = cast<IntrinsicInst>(U);
-    auto K = std::make_pair(ThisRelocate.basePtrIndex(),
-                            ThisRelocate.derivedPtrIndex());
+    auto K = std::make_pair(ThisRelocate.getBasePtrIndex(),
+                            ThisRelocate.getDerivedPtrIndex());
     RelocateIdxMap.insert(std::make_pair(K, I));
   }
   for (auto &Item : RelocateIdxMap) {
@@ -581,15 +581,15 @@ simplifyRelocatesOffABase(IntrinsicInst *RelocatedBase,
     GCRelocateOperands MasterRelocate(RelocatedBase);
     GCRelocateOperands ThisRelocate(ToReplace);
 
-    assert(ThisRelocate.basePtrIndex() == MasterRelocate.basePtrIndex() &&
+    assert(ThisRelocate.getBasePtrIndex() == MasterRelocate.getBasePtrIndex() &&
            "Not relocating a derived object of the original base object");
-    if (ThisRelocate.basePtrIndex() == ThisRelocate.derivedPtrIndex()) {
+    if (ThisRelocate.getBasePtrIndex() == ThisRelocate.getDerivedPtrIndex()) {
       // A duplicate relocate call. TODO: coalesce duplicates.
       continue;
     }
 
-    Value *Base = ThisRelocate.basePtr();
-    auto Derived = dyn_cast<GetElementPtrInst>(ThisRelocate.derivedPtr());
+    Value *Base = ThisRelocate.getBasePtr();
+    auto Derived = dyn_cast<GetElementPtrInst>(ThisRelocate.getDerivedPtr());
     if (!Derived || Derived->getPointerOperand() != Base)
       continue;
 
@@ -598,15 +598,50 @@ simplifyRelocatesOffABase(IntrinsicInst *RelocatedBase,
       continue;
 
     // Create a Builder and replace the target callsite with a gep
-    IRBuilder<> Builder(ToReplace);
+    assert(RelocatedBase->getNextNode() && "Should always have one since it's not a terminator");
+
+    // Insert after RelocatedBase
+    IRBuilder<> Builder(RelocatedBase->getNextNode());
     Builder.SetCurrentDebugLocation(ToReplace->getDebugLoc());
+
+    // If gc_relocate does not match the actual type, cast it to the right type.
+    // In theory, there must be a bitcast after gc_relocate if the type does not
+    // match, and we should reuse it to get the derived pointer. But it could be
+    // cases like this:
+    // bb1:
+    //  ...
+    //  %g1 = call coldcc i8 addrspace(1)* @llvm.experimental.gc.relocate.p1i8(...)
+    //  br label %merge
+    //
+    // bb2:
+    //  ...
+    //  %g2 = call coldcc i8 addrspace(1)* @llvm.experimental.gc.relocate.p1i8(...)
+    //  br label %merge
+    //
+    // merge:
+    //  %p1 = phi i8 addrspace(1)* [ %g1, %bb1 ], [ %g2, %bb2 ]
+    //  %cast = bitcast i8 addrspace(1)* %p1 in to i32 addrspace(1)*
+    //
+    // In this case, we can not find the bitcast any more. So we insert a new bitcast
+    // no matter there is already one or not. In this way, we can handle all cases, and
+    // the extra bitcast should be optimized away in later passes.
+    Instruction *ActualRelocatedBase = RelocatedBase;
+    if (RelocatedBase->getType() != Base->getType()) {
+      ActualRelocatedBase =
+          cast<Instruction>(Builder.CreateBitCast(RelocatedBase, Base->getType()));
+    }
     Value *Replacement = Builder.CreateGEP(
-        Derived->getSourceElementType(), RelocatedBase, makeArrayRef(OffsetV));
+        Derived->getSourceElementType(), ActualRelocatedBase, makeArrayRef(OffsetV));
     Instruction *ReplacementInst = cast<Instruction>(Replacement);
-    ReplacementInst->removeFromParent();
-    ReplacementInst->insertAfter(RelocatedBase);
     Replacement->takeName(ToReplace);
-    ToReplace->replaceAllUsesWith(Replacement);
+    // If the newly generated derived pointer's type does not match the original derived
+    // pointer's type, cast the new derived pointer to match it. Same reasoning as above.
+    Instruction *ActualReplacement = ReplacementInst;
+    if (ReplacementInst->getType() != ToReplace->getType()) {
+      ActualReplacement =
+          cast<Instruction>(Builder.CreateBitCast(ReplacementInst, ToReplace->getType()));
+    }
+    ToReplace->replaceAllUsesWith(ActualReplacement);
     ToReplace->eraseFromParent();
 
     MadeChange = true;
@@ -1288,13 +1323,25 @@ bool CodeGenPrepare::OptimizeCallInst(CallInst *CI, bool& ModifiedDT) {
                      cast<PointerType>(Arg->getType())->getAddressSpace()), 0);
       Value *Val = Arg->stripAndAccumulateInBoundsConstantOffsets(*TD, Offset);
       uint64_t Offset2 = Offset.getLimitedValue();
+      if ((Offset2 & (PrefAlign-1)) != 0)
+        continue;
       AllocaInst *AI;
-      if ((Offset2 & (PrefAlign-1)) == 0 &&
-          (AI = dyn_cast<AllocaInst>(Val)) &&
+      if ((AI = dyn_cast<AllocaInst>(Val)) &&
           AI->getAlignment() < PrefAlign &&
           TD->getTypeAllocSize(AI->getAllocatedType()) >= MinSize + Offset2)
         AI->setAlignment(PrefAlign);
-      // TODO: Also align GlobalVariables
+      // Global variables can only be aligned if they are defined in this
+      // object (i.e. they are uniquely initialized in this object), and
+      // over-aligning global variables that have an explicit section is
+      // forbidden.
+      GlobalVariable *GV;
+      if ((GV = dyn_cast<GlobalVariable>(Val)) &&
+          GV->hasUniqueInitializer() &&
+          !GV->hasSection() &&
+          GV->getAlignment() < PrefAlign &&
+          TD->getTypeAllocSize(
+            GV->getType()->getElementType()) >= MinSize + Offset2)
+        GV->setAlignment(PrefAlign);
     }
     // If this is a memcpy (or similar) then we may be able to improve the
     // alignment
@@ -3157,8 +3204,8 @@ bool CodeGenPrepare::OptimizeMemoryInst(Instruction *MemoryInst, Value *Addr,
 
     // For a PHI node, push all of its incoming values.
     if (PHINode *P = dyn_cast<PHINode>(V)) {
-      for (unsigned i = 0, e = P->getNumIncomingValues(); i != e; ++i)
-        worklist.push_back(P->getIncomingValue(i));
+      for (Value *IncValue : P->incoming_values())
+        worklist.push_back(IncValue);
       continue;
     }