[llvm] [Transform][LoadStoreVectorizer] allow redundant in Chain (PR #163019)

[Drew Kersnar via llvm-commits]

================
@@ -964,22 +977,24 @@ bool Vectorizer::vectorizeChain(Chain &C) {
 
     // Build the vector to store.
     Value *Vec = PoisonValue::get(VecTy);
-    unsigned VecIdx = 0;
-    auto InsertElem = [&](Value *V) {
+    auto InsertElem = [&](Value *V, unsigned VecIdx) {
       if (V->getType() != VecElemTy)
         V = Builder.CreateBitOrPointerCast(V, VecElemTy);
-      Vec = Builder.CreateInsertElement(Vec, V, Builder.getInt32(VecIdx++));
+      Vec = Builder.CreateInsertElement(Vec, V, Builder.getInt32(VecIdx));
     };
     for (const ChainElem &E : C) {
       auto *I = cast<StoreInst>(E.Inst);
+      int EOffset = (E.OffsetFromLeader - C[0].OffsetFromLeader).getSExtValue();
+      int VecIdx = 8 * EOffset / DL.getTypeSizeInBits(VecElemTy);
       if (FixedVectorType *VT =
               dyn_cast<FixedVectorType>(getLoadStoreType(I))) {
         for (int J = 0, JE = VT->getNumElements(); J < JE; ++J) {
           InsertElem(Builder.CreateExtractElement(I->getValueOperand(),
-                                                  Builder.getInt32(J)));
+                                                  Builder.getInt32(J)),
+                     VecIdx++);
         }
       } else {
-        InsertElem(I->getValueOperand());
+        InsertElem(I->getValueOperand(), VecIdx);
       }
     }
----------------
dakersnar wrote:

And another detail that reassures me that this is correct: sortChainInOffsetOrder tiebreaks using the BB order, so you won't accidentally reorder stores to the same location, thus you preserve the write-after-write dependency I talk about above.

https://github.com/llvm/llvm-project/pull/163019