2 files changed, 45 insertions, 30 deletions

diff --git a/llvm/lib/Analysis/TargetTransformInfo.cpp b/llvm/lib/Analysis/TargetTransformInfo.cpp
index 424bb7b..dc06609 100644
--- a/llvm/lib/Analysis/TargetTransformInfo.cpp
+++ b/llvm/lib/Analysis/TargetTransformInfo.cpp
@@ -1153,6 +1153,15 @@ InstructionCost TargetTransformInfo::getGatherScatterOpCost(
   return Cost;
 }
 
+InstructionCost TargetTransformInfo::getExpandCompressMemoryOpCost(
+    unsigned Opcode, Type *DataTy, bool VariableMask, Align Alignment,
+    TTI::TargetCostKind CostKind, const Instruction *I) const {
+  InstructionCost Cost = TTIImpl->getExpandCompressMemoryOpCost(
+      Opcode, DataTy, VariableMask, Alignment, CostKind, I);
+  assert(Cost >= 0 && "TTI should not produce negative costs!");
+  return Cost;
+}
+
 InstructionCost TargetTransformInfo::getStridedMemoryOpCost(
     unsigned Opcode, Type *DataTy, const Value *Ptr, bool VariableMask,
     Align Alignment, TTI::TargetCostKind CostKind, const Instruction *I) const {
diff --git a/llvm/lib/Analysis/ValueTracking.cpp b/llvm/lib/Analysis/ValueTracking.cpp
index 6b61a35..55feb15 100644
--- a/llvm/lib/Analysis/ValueTracking.cpp
+++ b/llvm/lib/Analysis/ValueTracking.cpp
@@ -1426,7 +1426,22 @@ static void computeKnownBitsFromOperator(const Operator *I,
     computeKnownBits(I->getOperand(0), Known, Depth + 1, Q);
     // Accumulate the constant indices in a separate variable
     // to minimize the number of calls to computeForAddSub.
-    APInt AccConstIndices(BitWidth, 0, /*IsSigned*/ true);
+    unsigned IndexWidth = Q.DL.getIndexTypeSizeInBits(I->getType());
+    APInt AccConstIndices(IndexWidth, 0);
+
+    auto AddIndexToKnown = [&](KnownBits IndexBits) {
+      if (IndexWidth == BitWidth) {
+        // Note that inbounds does *not* guarantee nsw for the addition, as only
+        // the offset is signed, while the base address is unsigned.
+        Known = KnownBits::add(Known, IndexBits);
+      } else {
+        // If the index width is smaller than the pointer width, only add the
+        // value to the low bits.
+        assert(IndexWidth < BitWidth &&
+               "Index width can't be larger than pointer width");
+        Known.insertBits(KnownBits::add(Known.trunc(IndexWidth), IndexBits), 0);
+      }
+    };
 
     gep_type_iterator GTI = gep_type_begin(I);
     for (unsigned i = 1, e = I->getNumOperands(); i != e; ++i, ++GTI) {
@@ -1464,43 +1479,34 @@ static void computeKnownBitsFromOperator(const Operator *I,
         break;
       }
 
-      unsigned IndexBitWidth = Index->getType()->getScalarSizeInBits();
-      KnownBits IndexBits(IndexBitWidth);
-      computeKnownBits(Index, IndexBits, Depth + 1, Q);
-      TypeSize IndexTypeSize = GTI.getSequentialElementStride(Q.DL);
-      uint64_t TypeSizeInBytes = IndexTypeSize.getKnownMinValue();
-      KnownBits ScalingFactor(IndexBitWidth);
+      TypeSize Stride = GTI.getSequentialElementStride(Q.DL);
+      uint64_t StrideInBytes = Stride.getKnownMinValue();
+      if (!Stride.isScalable()) {
+        // Fast path for constant offset.
+        if (auto *CI = dyn_cast<ConstantInt>(Index)) {
+          AccConstIndices +=
+              CI->getValue().sextOrTrunc(IndexWidth) * StrideInBytes;
+          continue;
+        }
+      }
+
+      KnownBits IndexBits =
+          computeKnownBits(Index, Depth + 1, Q).sextOrTrunc(IndexWidth);
+      KnownBits ScalingFactor(IndexWidth);
       // Multiply by current sizeof type.
       // &A[i] == A + i * sizeof(*A[i]).
-      if (IndexTypeSize.isScalable()) {
+      if (Stride.isScalable()) {
         // For scalable types the only thing we know about sizeof is
         // that this is a multiple of the minimum size.
-        ScalingFactor.Zero.setLowBits(llvm::countr_zero(TypeSizeInBytes));
-      } else if (IndexBits.isConstant()) {
-        APInt IndexConst = IndexBits.getConstant();
-        APInt ScalingFactor(IndexBitWidth, TypeSizeInBytes);
-        IndexConst *= ScalingFactor;
-        AccConstIndices += IndexConst.sextOrTrunc(BitWidth);
-        continue;
+        ScalingFactor.Zero.setLowBits(llvm::countr_zero(StrideInBytes));
       } else {
         ScalingFactor =
-            KnownBits::makeConstant(APInt(IndexBitWidth, TypeSizeInBytes));
+            KnownBits::makeConstant(APInt(IndexWidth, StrideInBytes));
       }
-      IndexBits = KnownBits::mul(IndexBits, ScalingFactor);
-
-      // If the offsets have a different width from the pointer, according
-      // to the language reference we need to sign-extend or truncate them
-      // to the width of the pointer.
-      IndexBits = IndexBits.sextOrTrunc(BitWidth);
-
-      // Note that inbounds does *not* guarantee nsw for the addition, as only
-      // the offset is signed, while the base address is unsigned.
-      Known = KnownBits::add(Known, IndexBits);
-    }
-    if (!Known.isUnknown() && !AccConstIndices.isZero()) {
-      KnownBits Index = KnownBits::makeConstant(AccConstIndices);
-      Known = KnownBits::add(Known, Index);
+      AddIndexToKnown(KnownBits::mul(IndexBits, ScalingFactor));
     }
+    if (!Known.isUnknown() && !AccConstIndices.isZero())
+      AddIndexToKnown(KnownBits::makeConstant(AccConstIndices));
     break;
   }
   case Instruction::PHI: {