[X86][SelectionDAG] Fix the Gather's base and index by modifying the Scale value

llvm/lib/Target/X86/X86ISelLowering.cpp

@@ -56578,13 +56578,49 @@ static SDValue combineGatherScatter(SDNode *N, SelectionDAG &DAG,
   const TargetLowering &TLI = DAG.getTargetLoweringInfo();
 
   if (DCI.isBeforeLegalize()) {
+    // Attempt to move shifted index into the address scale, allows further
+    // index truncation below.
+    if (Index.getOpcode() == ISD::SHL && isa<ConstantSDNode>(Scale)) {
+      unsigned BitWidth = Index.getScalarValueSizeInBits();
+      unsigned MaskBits = BitWidth - Log2_32(Scale->getAsZExtVal());
+      APInt DemandedBits = APInt::getLowBitsSet(BitWidth, MaskBits);
+      if (TLI.SimplifyDemandedBits(Index, DemandedBits, DCI)) {
+        if (N->getOpcode() != ISD::DELETED_NODE)
+          DCI.AddToWorklist(N);
+        return SDValue(N, 0);
+      }
+      uint64_t ScaleAmt = Scale->getAsZExtVal();
+      if (auto MinShAmt = DAG.getValidMinimumShiftAmount(Index)) {
+        if (*MinShAmt >= 1 && (*MinShAmt + Log2_64(ScaleAmt)) < 4 &&
+            DAG.ComputeNumSignBits(Index.getOperand(0)) > 1) {
+          SDValue ShAmt = Index.getOperand(1);
+          SDValue NewShAmt =
+              DAG.getNode(ISD::SUB, DL, ShAmt.getValueType(), ShAmt,
+                          DAG.getConstant(1, DL, ShAmt.getValueType()));
+          SDValue NewIndex = DAG.getNode(ISD::SHL, DL, Index.getValueType(),
+                                         Index.getOperand(0), NewShAmt);
+          SDValue NewScale =
+              DAG.getConstant(ScaleAmt * 2, DL, Scale.getValueType());
+          return rebuildGatherScatter(GorS, NewIndex, Base, NewScale, DAG);
+        }
+      }
+    }
     unsigned IndexWidth = Index.getScalarValueSizeInBits();
 
     // Shrink indices if they are larger than 32-bits.
     // Only do this before legalize types since v2i64 could become v2i32.
     // FIXME: We could check that the type is legal if we're after legalize
     // types, but then we would need to construct test cases where that happens.
-    if (IndexWidth > 32 && DAG.ComputeNumSignBits(Index) > (IndexWidth - 32)) {
+    unsigned ComputeNumSignBits = DAG.ComputeNumSignBits(Index);
+    if (Index.getOpcode() == ISD::SHL) {
+      if (auto MinShAmt = DAG.getValidMinimumShiftAmount(Index)) {
+        if (DAG.ComputeNumSignBits(Index.getOperand(0)) > 1) {
+          ComputeNumSignBits += *MinShAmt;
+        }
+      }
+    }
+
+    if (IndexWidth > 32 && ComputeNumSignBits > (IndexWidth - 32)) {
       EVT NewVT = IndexVT.changeVectorElementType(MVT::i32);
 
       // FIXME: We could support more than just constant fold, but we need to
@@ -56604,11 +56640,25 @@ static SDValue combineGatherScatter(SDNode *N, SelectionDAG &DAG,
         Index = DAG.getNode(ISD::TRUNCATE, DL, NewVT, Index);
         return rebuildGatherScatter(GorS, Index, Base, Scale, DAG);
       }
+
+      // Shrink if we remove an illegal type.
+      if (!TLI.isTypeLegal(Index.getValueType()) && TLI.isTypeLegal(NewVT)) {
+        Index = DAG.getNode(ISD::TRUNCATE, DL, NewVT, Index);
+        return rebuildGatherScatter(GorS, Index, Base, Scale, DAG);
+      }
     }
   }
 
   EVT PtrVT = TLI.getPointerTy(DAG.getDataLayout());
 
+  // if (Index.getOpcode() == ISD::SHL) {
+  //   unsigned BitWidth = Index.getScalarValueSizeInBits();
+  //   unsigned MaskBits = BitWidth - Log2_32(Scale->getAsZExtVal());
+  //   APInt DemandedBits = APInt::getLowBitsSet(BitWidth, MaskBits);
+  //   if (TLI.SimplifyDemandedBits(Index, DemandedBits, DCI)) {
+  //     return SDValue(N, 0);
+  //   }
+  // }
   // Try to move splat adders from the index operand to the base
   // pointer operand. Taking care to multiply by the scale. We can only do
   // this when index element type is the same as the pointer type.