diff --git a/llvm/lib/Transforms/Scalar/LoopLoadElimination.cpp b/llvm/lib/Transforms/Scalar/LoopLoadElimination.cpp
--- a/llvm/lib/Transforms/Scalar/LoopLoadElimination.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopLoadElimination.cpp
@@ -101,7 +101,8 @@
 
     assert(LoadPtr->getType()->getPointerAddressSpace() ==
                StorePtr->getType()->getPointerAddressSpace() &&
-           LoadType == getLoadStoreType(Store) &&
+           LoadType->getScalarSizeInBits() ==
+               getLoadStoreType(Store)->getScalarSizeInBits() &&
            "Should be a known dependence");
 
     // Currently we only support accesses with unit stride.  FIXME: we should be
@@ -211,9 +212,9 @@
       if (!Load)
         continue;
 
-      // Only progagate the value if they are of the same type.
-      if (Store->getPointerOperandType() != Load->getPointerOperandType() ||
-          getLoadStoreType(Store) != getLoadStoreType(Load))
+      // Only progagate the value if the pointees are the same size.
+      if (getLoadStoreType(Store)->getScalarSizeInBits() !=
+          getLoadStoreType(Load)->getScalarSizeInBits())
         continue;
 
       Candidates.emplace_front(Load, Store);
@@ -438,7 +439,25 @@
     PHINode *PHI = PHINode::Create(Initial->getType(), 2, "store_forwarded",
                                    &L->getHeader()->front());
     PHI->addIncoming(Initial, PH);
-    PHI->addIncoming(Cand.Store->getOperand(0), L->getLoopLatch());
+
+    Value *StoreValue;
+
+    Type *LoadType = Initial->getType();
+    Type *StoreType = Cand.Store->getOperand(0)->getType();
+
+    assert(LoadType->getScalarSizeInBits() ==
+               StoreType->getScalarSizeInBits() &&
+           "The type sizes should match!");
+
+    if (LoadType != StoreType) {
+      // Need a bitcast to convert to the loaded type
+      StoreValue =
+          CastInst::Create(Instruction::BitCast, Cand.Store->getOperand(0),
+                           LoadType, "store_forward_cast", Cand.Store);
+    } else
+      StoreValue = Cand.Store->getOperand(0);
+
+    PHI->addIncoming(StoreValue, L->getLoopLatch());
 
     Cand.Load->replaceAllUsesWith(PHI);
   }
diff --git a/llvm/test/Transforms/LoopLoadElim/type-mismatch-opaque-ptr.ll b/llvm/test/Transforms/LoopLoadElim/type-mismatch-opaque-ptr.ll
--- a/llvm/test/Transforms/LoopLoadElim/type-mismatch-opaque-ptr.ll
+++ b/llvm/test/Transforms/LoopLoadElim/type-mismatch-opaque-ptr.ll
@@ -1,6 +1,7 @@
 ; RUN: opt --opaque-pointers -loop-load-elim -S < %s | FileCheck %s
 
-; Don't crash if the store and the load use different types.
+; If the store and the load use different types, but have the same
+; size then we should still be able to forward the value.
 ;
 ;   for (unsigned i = 0; i < 100; i++) {
 ;     A[i+1] = B[i] + 2;
@@ -30,7 +31,7 @@
 
 ; CHECK: %a = load float, ptr %Aidx, align 4
   %a = load float, ptr %Aidx, align 4
-; CHECK-NEXT: %c = fmul float %a, 2.0
+; CHECK-NEXT: %c = fmul float %store_forwarded, 2.0
   %c = fmul float %a, 2.0
   %c.int = fptosi float %c to i32
   store i32 %c.int, ptr %Cidx, align 4
@@ -42,7 +43,8 @@
   ret void
 }
 
-; Don't crash if the store and the load use different types.
+; If the store and the load use different types, but have the same
+; size then we should still be able to forward the value.
 ;
 ;   for (unsigned i = 0; i < 100; i++) {
 ;     A[i+1] = B[i] + 2;
@@ -74,7 +76,7 @@
 
 ; CHECK: %a = load float, ptr %Aidx, align 4
   %a = load float, ptr %Aidx, align 4
-; CHECK-NEXT: %c = fmul float %a, 2.0
+; CHECK-NEXT: %c = fmul float %store_forwarded, 2.0
   %c = fmul float %a, 2.0
   %c.int = fptosi float %c to i32
   store i32 %c.int, ptr %Cidx, align 4
diff --git a/llvm/test/Transforms/LoopLoadElim/type-mismatch.ll b/llvm/test/Transforms/LoopLoadElim/type-mismatch.ll
--- a/llvm/test/Transforms/LoopLoadElim/type-mismatch.ll
+++ b/llvm/test/Transforms/LoopLoadElim/type-mismatch.ll
@@ -1,6 +1,7 @@
 ; RUN: opt -loop-load-elim -S < %s | FileCheck %s
 
-; Don't crash if the store and the load use different types.
+; If the store and the load use different types, but have the same
+; size then we should still be able to forward the value.
 ;
 ;   for (unsigned i = 0; i < 100; i++) {
 ;     A[i+1] = B[i] + 2;
@@ -27,11 +28,12 @@
 
   %b = load i32, i32* %Bidx, align 4
   %a_p1 = add i32 %b, 2
+; CHECK: %store_forward_cast = bitcast i32 %a_p1 to float
   store i32 %a_p1, i32* %Aidx_next, align 4
 
 ; CHECK: %a = load float, float* %Aidx.float, align 4
   %a = load float, float* %Aidx.float, align 4
-; CHECK-NEXT: %c = fmul float %a, 2.0
+; CHECK-NEXT: %c = fmul float %store_forwarded, 2.0
   %c = fmul float %a, 2.0
   %c.int = fptosi float %c to i32
   store i32 %c.int, i32* %Cidx, align 4
@@ -43,7 +45,8 @@
   ret void
 }
 
-; Don't crash if the store and the load use different types.
+; If the store and the load use different types, but have the same
+; size then we should still be able to forward the value.
 ;
 ;   for (unsigned i = 0; i < 100; i++) {
 ;     A[i+1] = B[i] + 2;
@@ -69,6 +72,7 @@
 
   %b = load i32, i32* %Bidx, align 4
   %a_p2 = add i32 %b, 2
+; CHECK: %store_forward_cast = bitcast i32 %a_p3 to float
   store i32 %a_p2, i32* %Aidx_next, align 4
 
   %a_p3 = add i32 %b, 3
@@ -76,7 +80,7 @@
 
 ; CHECK: %a = load float, float* %Aidx.float, align 4
   %a = load float, float* %Aidx.float, align 4
-; CHECK-NEXT: %c = fmul float %a, 2.0
+; CHECK-NEXT: %c = fmul float %store_forwarded, 2.0
   %c = fmul float %a, 2.0
   %c.int = fptosi float %c to i32
   store i32 %c.int, i32* %Cidx, align 4
@@ -87,3 +91,40 @@
 for.end:                                          ; preds = %for.body
   ret void
 }
+
+; Check that we don't forward between pointer-sized integers and actual
+; pointers; We could potentially do this in future but in IR pointers are
+; considered to have a size of 0.
+; CHECK-LABEL: @f3(
+; CHECK-NOT: store_forwarded
+define void @f3(i64* noalias %A, i64* noalias %B, i64* noalias %C, i64 %N) {
+
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+
+  %Aidx_next = getelementptr inbounds i64, i64* %A, i64 %indvars.iv.next
+  %Bidx = getelementptr inbounds i64, i64* %B, i64 %indvars.iv
+  %Cidx = getelementptr inbounds i64, i64* %C, i64 %indvars.iv
+  %Aidx = getelementptr inbounds i64, i64* %A, i64 %indvars.iv
+  %Aidx.i8p = bitcast i64* %Aidx to i8**
+
+  %b = load i64, i64* %Bidx, align 8
+  %a_p1 = add i64 %b, 2
+  store i64 %a_p1, i64* %Aidx_next, align 8
+
+  %a = load i8*, i8** %Aidx.i8p, align 8
+  %c = getelementptr i8, i8* %a, i64 57
+  %c.i64p = ptrtoint i8* %c to i64
+  store i64 %c.i64p, i64* %Cidx, align 8
+
+  %exitcond = icmp eq i64 %indvars.iv.next, %N
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+