perform DSE through invariant.group.barrier

[Prazek]

Summary

Alias Analysis knows that llvm.invariant.group.barrier
returns pointer that mustalias argument, but this information
wasn't used, therefor we didn't DSE through invariant.group.barrier

[• dberlin]

This is obviously correct, its the same test we use in other places (gvn, etc).

[Prazek]

Fixed test

[Prazek]

• format

[Prazek]

update

[Prazek]

Rename test file

llvm/trunk/lib/Transforms/Scalar/DeadStoreElimination.cpp

 /// overwritten by a latter (smaller) store which doesn't write outside the big
 /// store's memory locations. Returns 'OW_Unknown' if nothing can be determined.
 static OverwriteResult isOverwrite(const MemoryLocation &Later,
                                    const MemoryLocation &Earlier,
                                    const DataLayout &DL,
                                    const TargetLibraryInfo &TLI,
                                    int64_t &EarlierOff, int64_t &LaterOff,
                                    Instruction *DepWrite,
-                                   InstOverlapIntervalsTy &IOL) {
+                                   InstOverlapIntervalsTy &IOL,
+                                   AliasAnalysis &AA) {
   // If we don't know the sizes of either access, then we can't do a comparison.
   if (Later.Size == MemoryLocation::UnknownSize ||
       Earlier.Size == MemoryLocation::UnknownSize)
     return OW_Unknown;
 
   const Value *P1 = Earlier.Ptr->stripPointerCasts();
   const Value *P2 = Later.Ptr->stripPointerCasts();
 
   // If the start pointers are the same, we just have to compare sizes to see if
   // the later store was larger than the earlier store.
-  if (P1 == P2) {
+  if (P1 == P2 || AA.isMustAlias(P1, P2)) {
     // Make sure that the Later size is >= the Earlier size.
     if (Later.Size >= Earlier.Size)
       return OW_Complete;
   }
 
   // Check to see if the later store is to the entire object (either a global,
   // an alloca, or a byval/inalloca argument).  If so, then it clearly
   // overwrites any other store to the same object.
while (InstDep.isDef() || InstDep.isClobber()) {
       // If we find a write that is a) removable (i.e., non-volatile), b) is
       // completely obliterated by the store to 'Loc', and c) which we know that
       // 'Inst' doesn't load from, then we can remove it.
       // Also try to merge two stores if a later one only touches memory written
       // to by the earlier one.
       if (isRemovable(DepWrite) &&
           !isPossibleSelfRead(Inst, Loc, DepWrite, *TLI, *AA)) {
         int64_t InstWriteOffset, DepWriteOffset;
-        OverwriteResult OR =
-            isOverwrite(Loc, DepLoc, DL, *TLI, DepWriteOffset, InstWriteOffset,
-                        DepWrite, IOL);
+        OverwriteResult OR = isOverwrite(Loc, DepLoc, DL, *TLI, DepWriteOffset,
+                                         InstWriteOffset, DepWrite, IOL, *AA);
         if (OR == OW_Complete) {
           DEBUG(dbgs() << "DSE: Remove Dead Store:\n  DEAD: "
                 << *DepWrite << "\n  KILLER: " << *Inst << '\n');
 
           // Delete the store and now-dead instructions that feed it.
           deleteDeadInstruction(DepWrite, &BBI, *MD, *TLI, IOL, &InstrOrdering);
           ++NumFastStores;
           MadeChange = true;

llvm/trunk/test/Transforms/DeadStoreElimination/launder.invariant.group.ll

+; RUN: opt < %s -basicaa -dse -S | FileCheck %s
+
+; CHECK-LABEL: void @skipBarrier(i8* %ptr)
+define void @skipBarrier(i8* %ptr) {
+; CHECK-NOT: store i8 42
+  store i8 42, i8* %ptr
+; CHECK: %ptr2 = call i8* @llvm.launder.invariant.group.p0i8(i8* %ptr)
+  %ptr2 = call i8* @llvm.launder.invariant.group.p0i8(i8* %ptr)
+; CHECK: store i8 43
+  store i8 43, i8* %ptr2
+  ret void
+}
+
+; CHECK-LABEL: void @skip2Barriers(i8* %ptr)
+define void @skip2Barriers(i8* %ptr) {
+; CHECK-NOT: store i8 42
+  store i8 42, i8* %ptr
+; CHECK: %ptr2 = call i8* @llvm.launder.invariant.group.p0i8(i8* %ptr)
+  %ptr2 = call i8* @llvm.launder.invariant.group.p0i8(i8* %ptr)
+; CHECK-NOT: store i8 43
+  store i8 43, i8* %ptr2
+  %ptr3 = call i8* @llvm.launder.invariant.group.p0i8(i8* %ptr2)
+  %ptr4 = call i8* @llvm.launder.invariant.group.p0i8(i8* %ptr3)
+
+; CHECK: store i8 44
+  store i8 44, i8* %ptr4
+  ret void
+}
+
+declare i8* @llvm.launder.invariant.group.p0i8(i8*)