[SLPVectorizer] Handle external load/store pointer uses with opaque pointers

In this case we may not generate a bitcast, so the new load/store
becomes the external user.

Author: nikic

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

@@ -7013,19 +7013,18 @@ Value *BoUpSLP::vectorizeTree(TreeEntry *E) {
       unsigned AS = LI->getPointerAddressSpace();
       Value *PO = LI->getPointerOperand();
       if (E->State == TreeEntry::Vectorize) {
-
         Value *VecPtr = Builder.CreateBitCast(PO, VecTy->getPointerTo(AS));
+        NewLI = Builder.CreateAlignedLoad(VecTy, VecPtr, LI->getAlign());
 
         // The pointer operand uses an in-tree scalar so we add the new BitCast
-        // to ExternalUses list to make sure that an extract will be generated
-        // in the future.
+        // or LoadInst to ExternalUses list to make sure that an extract will
+        // be generated in the future.
         if (TreeEntry *Entry = getTreeEntry(PO)) {
           // Find which lane we need to extract.
           unsigned FoundLane = Entry->findLaneForValue(PO);
-          ExternalUses.emplace_back(PO, cast<User>(VecPtr), FoundLane);
+          ExternalUses.emplace_back(
+              PO, PO != VecPtr ? cast<User>(VecPtr) : NewLI, FoundLane);
         }
-
-        NewLI = Builder.CreateAlignedLoad(VecTy, VecPtr, LI->getAlign());
       } else {
         assert(E->State == TreeEntry::ScatterVectorize && "Unhandled state");
         Value *VecPtr = vectorizeTree(E->getOperand(0));
@@ -7058,17 +7057,18 @@ Value *BoUpSLP::vectorizeTree(TreeEntry *E) {
       Value *ScalarPtr = SI->getPointerOperand();
       Value *VecPtr = Builder.CreateBitCast(
           ScalarPtr, VecValue->getType()->getPointerTo(AS));
-      StoreInst *ST = Builder.CreateAlignedStore(VecValue, VecPtr,
-                                                 SI->getAlign());
+      StoreInst *ST =
+          Builder.CreateAlignedStore(VecValue, VecPtr, SI->getAlign());
 
-      // The pointer operand uses an in-tree scalar, so add the new BitCast to
-      // ExternalUses to make sure that an extract will be generated in the
-      // future.
+      // The pointer operand uses an in-tree scalar, so add the new BitCast or
+      // StoreInst to ExternalUses to make sure that an extract will be
+      // generated in the future.
       if (TreeEntry *Entry = getTreeEntry(ScalarPtr)) {
         // Find which lane we need to extract.
         unsigned FoundLane = Entry->findLaneForValue(ScalarPtr);
-        ExternalUses.push_back(
-            ExternalUser(ScalarPtr, cast<User>(VecPtr), FoundLane));
+        ExternalUses.push_back(ExternalUser(
+            ScalarPtr, ScalarPtr != VecPtr ? cast<User>(VecPtr) : ST,
+            FoundLane));
       }
 
       Value *V = propagateMetadata(ST, E->Scalars);

llvm/test/Transforms/SLPVectorizer/X86/opaque-ptr.ll

@@ -55,3 +55,30 @@ define void @test(ptr %r, ptr %p, ptr %q) #0 {
   %g3 = getelementptr inbounds i32, ptr %r, i64 %sub3
   ret void
 }
+
+define void @test2(i64* %a, i64* %b) {
+; CHECK-LABEL: @test2(
+; CHECK-NEXT:    [[A2:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 2
+; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x ptr> poison, ptr [[A]], i32 0
+; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <2 x ptr> [[TMP1]], ptr [[B:%.*]], i32 1
+; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr i64, <2 x ptr> [[TMP2]], <2 x i64> <i64 1, i64 3>
+; CHECK-NEXT:    [[TMP4:%.*]] = ptrtoint <2 x ptr> [[TMP3]] to <2 x i64>
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <2 x ptr> [[TMP3]], i32 0
+; CHECK-NEXT:    [[TMP6:%.*]] = load <2 x i64>, ptr [[TMP5]], align 8
+; CHECK-NEXT:    [[TMP7:%.*]] = add <2 x i64> [[TMP4]], [[TMP6]]
+; CHECK-NEXT:    store <2 x i64> [[TMP7]], ptr [[TMP5]], align 8
+; CHECK-NEXT:    ret void
+;
+  %a1 = getelementptr inbounds i64, i64* %a, i64 1
+  %a2 = getelementptr inbounds i64, i64* %a, i64 2
+  %i1 = ptrtoint i64* %a1 to i64
+  %b3 = getelementptr inbounds i64, i64* %b, i64 3
+  %i2 = ptrtoint i64* %b3 to i64
+  %v1 = load i64, i64* %a1, align 8
+  %v2 = load i64, i64* %a2, align 8
+  %add1 = add i64 %i1, %v1
+  %add2 = add i64 %i2, %v2
+  store i64 %add1, i64* %a1, align 8
+  store i64 %add2, i64* %a2, align 8
+  ret void
+}