[llvm] [IA]: Construct (de)interleave4 out of (de)interleave2 (PR #89276)

[Paul Walker via llvm-commits]

================
@@ -16958,40 +17085,96 @@ bool AArch64TargetLowering::lowerDeinterleaveIntrinsicToLoad(
         LdN = Builder.CreateCall(LdNFunc, {Pred, Address}, "ldN");
       else
         LdN = Builder.CreateCall(LdNFunc, Address, "ldN");
-
       Value *Idx =
           Builder.getInt64(I * LdTy->getElementCount().getKnownMinValue());
-      Left = Builder.CreateInsertVector(
-          VTy, Left, Builder.CreateExtractValue(LdN, 0), Idx);
-      Right = Builder.CreateInsertVector(
-          VTy, Right, Builder.CreateExtractValue(LdN, 1), Idx);
+      for (unsigned J = 0; J < Factor; ++J) {
+        ExtractedLdValues[J] = Builder.CreateInsertVector(
+            VTy, ExtractedLdValues[J], Builder.CreateExtractValue(LdN, J), Idx);
+      }
+      LLVM_DEBUG(dbgs() << "LdN4 res: "; LdN->dump());
     }
-
-    Result = PoisonValue::get(DI->getType());
-    Result = Builder.CreateInsertValue(Result, Left, 0);
-    Result = Builder.CreateInsertValue(Result, Right, 1);
+    // Replace output of deinterleave2 intrinsic by output of ldN2/ldN4
+    for (unsigned J = 0; J < Factor; ++J)
+      DeinterleavedValues[J]->replaceAllUsesWith(ExtractedLdValues[J]);
   } else {
+    Value *Result;
     if (UseScalable)
       Result = Builder.CreateCall(LdNFunc, {Pred, BaseAddr}, "ldN");
     else
       Result = Builder.CreateCall(LdNFunc, BaseAddr, "ldN");
+    // Replace output of deinterleave2 intrinsic by output of ldN2/ldN4
+    for (unsigned I = 0; I < DeinterleavedValues.size(); I++) {
----------------
paulwalker-arm wrote:

Can you use `Factor` here instead of `DeinterleavedValues.size()`? since it's already cached.

https://github.com/llvm/llvm-project/pull/89276