diff --git a/lib/AST/ByteCode/Context.cpp b/lib/AST/ByteCode/Context.cpp
index 9e683d7..12b8ab5 100644
--- a/lib/AST/ByteCode/Context.cpp
+++ b/lib/AST/ByteCode/Context.cpp
@@ -254,7 +254,7 @@
     Result = 0;
     for (unsigned I = Ptr.getIndex(); I != N; ++I) {
       INT_TYPE_SWITCH(ElemT, {
-        auto Elem = Ptr.atIndex(I).deref<T>();
+        auto Elem = Ptr.elem<T>(I);
         if (Elem.isZero())
           return true;
         ++Result;
diff --git a/lib/AST/ByteCode/EvaluationResult.cpp b/lib/AST/ByteCode/EvaluationResult.cpp
index f59612b..b11531f 100644
--- a/lib/AST/ByteCode/EvaluationResult.cpp
+++ b/lib/AST/ByteCode/EvaluationResult.cpp
@@ -204,7 +204,7 @@
 
   } else if (Desc->isPrimitiveArray() && Desc->getPrimType() == PT_Ptr) {
     for (unsigned I = 0; I != Desc->getNumElems(); ++I) {
-      const Pointer &ElemPointee = Ptr.atIndex(I).deref<Pointer>();
+      const Pointer &ElemPointee = Ptr.elem<Pointer>(I);
       if (isUsefulPtr(ElemPointee) && !Blocks.contains(ElemPointee.block()))
         collectBlocks(ElemPointee, Blocks);
     }
diff --git a/lib/AST/ByteCode/Interp.h b/lib/AST/ByteCode/Interp.h
index 7ba6e21..7f29200 100644
--- a/lib/AST/ByteCode/Interp.h
+++ b/lib/AST/ByteCode/Interp.h
@@ -468,10 +468,10 @@
   const Pointer &Result = S.Stk.peek<Pointer>();
 
   if constexpr (std::is_same_v<T, Floating>) {
-    APFloat A = LHS.atIndex(0).deref<Floating>().getAPFloat();
-    APFloat B = LHS.atIndex(1).deref<Floating>().getAPFloat();
-    APFloat C = RHS.atIndex(0).deref<Floating>().getAPFloat();
-    APFloat D = RHS.atIndex(1).deref<Floating>().getAPFloat();
+    APFloat A = LHS.elem<Floating>(0).getAPFloat();
+    APFloat B = LHS.elem<Floating>(1).getAPFloat();
+    APFloat C = RHS.elem<Floating>(0).getAPFloat();
+    APFloat D = RHS.elem<Floating>(1).getAPFloat();
 
     APFloat ResR(A.getSemantics());
     APFloat ResI(A.getSemantics());
@@ -480,20 +480,20 @@
     // Copy into the result.
     Floating RA = S.allocFloat(A.getSemantics());
     RA.copy(ResR);
-    Result.atIndex(0).deref<Floating>() = RA; // Floating(ResR);
+    Result.elem<Floating>(0) = RA; // Floating(ResR);
     Result.atIndex(0).initialize();
 
     Floating RI = S.allocFloat(A.getSemantics());
     RI.copy(ResI);
-    Result.atIndex(1).deref<Floating>() = RI; // Floating(ResI);
+    Result.elem<Floating>(1) = RI; // Floating(ResI);
     Result.atIndex(1).initialize();
     Result.initialize();
   } else {
     // Integer element type.
-    const T &LHSR = LHS.atIndex(0).deref<T>();
-    const T &LHSI = LHS.atIndex(1).deref<T>();
-    const T &RHSR = RHS.atIndex(0).deref<T>();
-    const T &RHSI = RHS.atIndex(1).deref<T>();
+    const T &LHSR = LHS.elem<T>(0);
+    const T &LHSI = LHS.elem<T>(1);
+    const T &RHSR = RHS.elem<T>(0);
+    const T &RHSI = RHS.elem<T>(1);
     unsigned Bits = LHSR.bitWidth();
 
     // real(Result) = (real(LHS) * real(RHS)) - (imag(LHS) * imag(RHS))
@@ -503,7 +503,7 @@
     T B;
     if (T::mul(LHSI, RHSI, Bits, &B))
       return false;
-    if (T::sub(A, B, Bits, &Result.atIndex(0).deref<T>()))
+    if (T::sub(A, B, Bits, &Result.elem<T>(0)))
       return false;
     Result.atIndex(0).initialize();
 
@@ -512,7 +512,7 @@
       return false;
     if (T::mul(LHSI, RHSR, Bits, &B))
       return false;
-    if (T::add(A, B, Bits, &Result.atIndex(1).deref<T>()))
+    if (T::add(A, B, Bits, &Result.elem<T>(1)))
       return false;
     Result.atIndex(1).initialize();
     Result.initialize();
@@ -528,10 +528,10 @@
   const Pointer &Result = S.Stk.peek<Pointer>();
 
   if constexpr (std::is_same_v<T, Floating>) {
-    APFloat A = LHS.atIndex(0).deref<Floating>().getAPFloat();
-    APFloat B = LHS.atIndex(1).deref<Floating>().getAPFloat();
-    APFloat C = RHS.atIndex(0).deref<Floating>().getAPFloat();
-    APFloat D = RHS.atIndex(1).deref<Floating>().getAPFloat();
+    APFloat A = LHS.elem<Floating>(0).getAPFloat();
+    APFloat B = LHS.elem<Floating>(1).getAPFloat();
+    APFloat C = RHS.elem<Floating>(0).getAPFloat();
+    APFloat D = RHS.elem<Floating>(1).getAPFloat();
 
     APFloat ResR(A.getSemantics());
     APFloat ResI(A.getSemantics());
@@ -540,21 +540,21 @@
     // Copy into the result.
     Floating RA = S.allocFloat(A.getSemantics());
     RA.copy(ResR);
-    Result.atIndex(0).deref<Floating>() = RA; // Floating(ResR);
+    Result.elem<Floating>(0) = RA; // Floating(ResR);
     Result.atIndex(0).initialize();
 
     Floating RI = S.allocFloat(A.getSemantics());
     RI.copy(ResI);
-    Result.atIndex(1).deref<Floating>() = RI; // Floating(ResI);
+    Result.elem<Floating>(1) = RI; // Floating(ResI);
     Result.atIndex(1).initialize();
 
     Result.initialize();
   } else {
     // Integer element type.
-    const T &LHSR = LHS.atIndex(0).deref<T>();
-    const T &LHSI = LHS.atIndex(1).deref<T>();
-    const T &RHSR = RHS.atIndex(0).deref<T>();
-    const T &RHSI = RHS.atIndex(1).deref<T>();
+    const T &LHSR = LHS.elem<T>(0);
+    const T &LHSI = LHS.elem<T>(1);
+    const T &RHSR = RHS.elem<T>(0);
+    const T &RHSI = RHS.elem<T>(1);
     unsigned Bits = LHSR.bitWidth();
     const T Zero = T::from(0, Bits);
 
@@ -581,8 +581,8 @@
     }
 
     // real(Result) = ((real(LHS) * real(RHS)) + (imag(LHS) * imag(RHS))) / Den
-    T &ResultR = Result.atIndex(0).deref<T>();
-    T &ResultI = Result.atIndex(1).deref<T>();
+    T &ResultR = Result.elem<T>(0);
+    T &ResultI = Result.elem<T>(1);
 
     if (T::mul(LHSR, RHSR, Bits, &A) || T::mul(LHSI, RHSI, Bits, &B))
       return false;
@@ -3103,7 +3103,7 @@
     return false;
 
   assert(Ptr.atIndex(Index).getFieldDesc()->getPrimType() == Name);
-  S.Stk.push<T>(Ptr.atIndex(Index).deref<T>());
+  S.Stk.push<T>(Ptr.elem<T>(Index));
   return true;
 }
 
@@ -3115,7 +3115,7 @@
     return false;
 
   assert(Ptr.atIndex(Index).getFieldDesc()->getPrimType() == Name);
-  S.Stk.push<T>(Ptr.atIndex(Index).deref<T>());
+  S.Stk.push<T>(Ptr.elem<T>(Index));
   return true;
 }
 
diff --git a/lib/AST/ByteCode/InterpBuiltin.cpp b/lib/AST/ByteCode/InterpBuiltin.cpp
index 462b9a1..f86d26e 100644
--- a/lib/AST/ByteCode/InterpBuiltin.cpp
+++ b/lib/AST/ByteCode/InterpBuiltin.cpp
@@ -1098,9 +1098,9 @@
   const Floating &Arg1 = S.Stk.pop<Floating>();
   Pointer &Result = S.Stk.peek<Pointer>();
 
-  Result.atIndex(0).deref<Floating>() = Arg1;
+  Result.elem<Floating>(0) = Arg1;
   Result.atIndex(0).initialize();
-  Result.atIndex(1).deref<Floating>() = Arg2;
+  Result.elem<Floating>(1) = Arg2;
   Result.atIndex(1).initialize();
   Result.initialize();
 
@@ -1644,10 +1644,10 @@
   unsigned NumElems = Arg.getNumElems();
 
   INT_TYPE_SWITCH_NO_BOOL(ElemT, {
-    T Result = Arg.atIndex(0).deref<T>();
+    T Result = Arg.elem<T>(0);
     unsigned BitWidth = Result.bitWidth();
     for (unsigned I = 1; I != NumElems; ++I) {
-      T Elem = Arg.atIndex(I).deref<T>();
+      T Elem = Arg.elem<T>(I);
       T PrevResult = Result;
 
       if (ID == Builtin::BI__builtin_reduce_add) {
@@ -1723,11 +1723,10 @@
   for (unsigned I = 0; I != NumElems; ++I) {
     INT_TYPE_SWITCH_NO_BOOL(ElemT, {
       if (BuiltinID == Builtin::BI__builtin_elementwise_popcount) {
-        Dst.atIndex(I).deref<T>() =
-            T::from(Arg.atIndex(I).deref<T>().toAPSInt().popcount());
+        Dst.elem<T>(I) = T::from(Arg.elem<T>(I).toAPSInt().popcount());
       } else {
-        Dst.atIndex(I).deref<T>() = T::from(
-            Arg.atIndex(I).deref<T>().toAPSInt().reverseBits().getZExtValue());
+        Dst.elem<T>(I) =
+            T::from(Arg.elem<T>(I).toAPSInt().reverseBits().getZExtValue());
       }
       Dst.atIndex(I).initialize();
     });
@@ -2296,8 +2295,8 @@
     APSInt Elem1;
     APSInt Elem2;
     INT_TYPE_SWITCH_NO_BOOL(ElemT, {
-      Elem1 = LHS.atIndex(I).deref<T>().toAPSInt();
-      Elem2 = RHS.atIndex(I).deref<T>().toAPSInt();
+      Elem1 = LHS.elem<T>(I).toAPSInt();
+      Elem2 = RHS.elem<T>(I).toAPSInt();
     });
 
     APSInt Result;
@@ -2942,7 +2941,7 @@
     for (unsigned I = 0, N = DestDesc->getNumElems(); I != N; ++I) {
       Pointer DestElem = Dest.atIndex(I);
       TYPE_SWITCH(ET, {
-        DestElem.deref<T>() = Src.atIndex(I).deref<T>();
+        DestElem.deref<T>() = Src.elem<T>(I);
         DestElem.initialize();
       });
     }
diff --git a/lib/AST/ByteCode/Pointer.cpp b/lib/AST/ByteCode/Pointer.cpp
index 2f9ecf9..c4d06d6 100644
--- a/lib/AST/ByteCode/Pointer.cpp
+++ b/lib/AST/ByteCode/Pointer.cpp
@@ -760,14 +760,14 @@
         std::optional<PrimType> ElemT = Ctx.classify(ElemTy);
         assert(ElemT);
         INT_TYPE_SWITCH(*ElemT, {
-          auto V1 = Ptr.atIndex(0).deref<T>();
-          auto V2 = Ptr.atIndex(1).deref<T>();
+          auto V1 = Ptr.elem<T>(0);
+          auto V2 = Ptr.elem<T>(1);
           R = APValue(V1.toAPSInt(), V2.toAPSInt());
           return true;
         });
       } else if (ElemTy->isFloatingType()) {
-        R = APValue(Ptr.atIndex(0).deref<Floating>().getAPFloat(),
-                    Ptr.atIndex(1).deref<Floating>().getAPFloat());
+        R = APValue(Ptr.elem<Floating>(0).getAPFloat(),
+                    Ptr.elem<Floating>(1).getAPFloat());
         return true;
       }
       return false;
@@ -782,9 +782,8 @@
       SmallVector<APValue> Values;
       Values.reserve(VT->getNumElements());
       for (unsigned I = 0; I != VT->getNumElements(); ++I) {
-        TYPE_SWITCH(ElemT, {
-          Values.push_back(Ptr.atIndex(I).deref<T>().toAPValue(ASTCtx));
-        });
+        TYPE_SWITCH(ElemT,
+                    { Values.push_back(Ptr.elem<T>(I).toAPValue(ASTCtx)); });
       }
 
       assert(Values.size() == VT->getNumElements());
diff --git a/lib/AST/ByteCode/Pointer.h b/lib/AST/ByteCode/Pointer.h
index da74013..d17eba5 100644
--- a/lib/AST/ByteCode/Pointer.h
+++ b/lib/AST/ByteCode/Pointer.h
@@ -693,6 +693,25 @@
     return *reinterpret_cast<T *>(asBlockPointer().Pointee->rawData() + Offset);
   }
 
+  /// Dereferences the element at index \p I.
+  /// This is equivalent to atIndex(I).deref<T>().
+  template <typename T> T &elem(unsigned I) const {
+    assert(isLive() && "Invalid pointer");
+    assert(isBlockPointer());
+    assert(asBlockPointer().Pointee);
+    assert(isDereferencable());
+    assert(getFieldDesc()->isPrimitiveArray());
+
+    unsigned ElemByteOffset = I * getFieldDesc()->getElemSize();
+    if (isArrayRoot())
+      return *reinterpret_cast<T *>(asBlockPointer().Pointee->rawData() +
+                                    asBlockPointer().Base + sizeof(InitMapPtr) +
+                                    ElemByteOffset);
+
+    return *reinterpret_cast<T *>(asBlockPointer().Pointee->rawData() + Offset +
+                                  ElemByteOffset);
+  }
+
   /// Whether this block can be read from at all. This is only true for
   /// block pointers that point to a valid location inside that block.
   bool isDereferencable() const {
diff --git a/lib/AST/ByteCode/Program.cpp b/lib/AST/ByteCode/Program.cpp
index 5ac0f59..af6d7c7 100644
--- a/lib/AST/ByteCode/Program.cpp
+++ b/lib/AST/ByteCode/Program.cpp
@@ -74,27 +74,25 @@
 
   const Pointer Ptr(G->block());
   if (CharWidth == 1) {
-    std::memcpy(&Ptr.atIndex(0).deref<char>(), S->getString().data(),
-                StringLength);
+    std::memcpy(&Ptr.elem<char>(0), S->getString().data(), StringLength);
   } else {
     // Construct the string in storage.
     for (unsigned I = 0; I <= StringLength; ++I) {
-      Pointer Field = Ptr.atIndex(I);
       const uint32_t CodePoint = I == StringLength ? 0 : S->getCodeUnit(I);
       switch (CharType) {
       case PT_Sint8: {
         using T = PrimConv<PT_Sint8>::T;
-        Field.deref<T>() = T::from(CodePoint, BitWidth);
+        Ptr.elem<T>(I) = T::from(CodePoint, BitWidth);
         break;
       }
       case PT_Uint16: {
         using T = PrimConv<PT_Uint16>::T;
-        Field.deref<T>() = T::from(CodePoint, BitWidth);
+        Ptr.elem<T>(I) = T::from(CodePoint, BitWidth);
         break;
       }
       case PT_Uint32: {
         using T = PrimConv<PT_Uint32>::T;
-        Field.deref<T>() = T::from(CodePoint, BitWidth);
+        Ptr.elem<T>(I) = T::from(CodePoint, BitWidth);
         break;
       }
       default: