Index: include/llvm/IR/DataLayout.h
===================================================================
--- include/llvm/IR/DataLayout.h
+++ include/llvm/IR/DataLayout.h
@@ -375,6 +375,15 @@
   /// [*] The alloc size depends on the alignment, and thus on the target.
   ///     These values are for x86-32 linux.
 
+  /// \brief Returns true if the number of bits necessary to hold the specified
+  /// type is a multiple of the byte size.
+  ///
+  /// The type passed must have a size (Type::isSized() must return true).
+  bool isByteSized(Type *Ty) const {
+    uint64_t TySize = getTypeSizeInBits(Ty);
+    return (TySize % 8) == 0;
+  }
+
   /// \brief Returns the number of bits necessary to hold the specified type.
   ///
   /// For example, returns 36 for i36 and 80 for x86_fp80. The type passed must
Index: lib/Transforms/Vectorize/LoadStoreVectorizer.cpp
===================================================================
--- lib/Transforms/Vectorize/LoadStoreVectorizer.cpp
+++ lib/Transforms/Vectorize/LoadStoreVectorizer.cpp
@@ -612,13 +612,13 @@
 
       // Skip weird non-byte sizes. They probably aren't worth the effort of
       // handling correctly.
-      unsigned TySize = DL.getTypeSizeInBits(Ty);
-      if (TySize < 8)
+      if (!DL.isByteSized(Ty))
         continue;
 
       Value *Ptr = LI->getPointerOperand();
       unsigned AS = Ptr->getType()->getPointerAddressSpace();
       unsigned VecRegSize = TTI.getLoadStoreVecRegBitWidth(AS);
+      unsigned TySize = DL.getTypeSizeInBits(Ty);
 
       // No point in looking at these if they're too big to vectorize.
       if (TySize > VecRegSize / 2)
@@ -648,13 +648,15 @@
 
       // Skip weird non-byte sizes. They probably aren't worth the effort of
       // handling correctly.
-      unsigned TySize = DL.getTypeSizeInBits(Ty);
-      if (TySize < 8)
+      if (!DL.isByteSized(Ty))
         continue;
 
       Value *Ptr = SI->getPointerOperand();
       unsigned AS = Ptr->getType()->getPointerAddressSpace();
       unsigned VecRegSize = TTI.getLoadStoreVecRegBitWidth(AS);
+      unsigned TySize = DL.getTypeSizeInBits(Ty);
+
+      // No point in looking at these if they're too big to vectorize.
       if (TySize > VecRegSize / 2)
         continue;
 
Index: test/Transforms/LoadStoreVectorizer/X86/non-byte-size.ll
===================================================================
--- /dev/null
+++ test/Transforms/LoadStoreVectorizer/X86/non-byte-size.ll
@@ -0,0 +1,30 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -load-store-vectorizer -S -mtriple=x86_64-unknown-linux-gnu | FileCheck %s
+
+%rec = type { i32, i28 }
+
+; We currently do not optimize this scenario.
+; But we verify that we no longer crash when compiling this.
+define void @test1(%rec* %out, %rec* %in) {
+; CHECK-LABEL: @test1(
+; CHECK-NEXT:    [[IN1:%.*]] = getelementptr [[REC:%.*]], %rec* [[IN:%.*]], i16 0, i32 0
+; CHECK-NEXT:    [[IN2:%.*]] = getelementptr [[REC]], %rec* [[IN]], i16 0, i32 1
+; CHECK-NEXT:    [[VAL1:%.*]] = load i32, i32* [[IN1]], align 8
+; CHECK-NEXT:    [[VAL2:%.*]] = load i28, i28* [[IN2]]
+; CHECK-NEXT:    [[OUT1:%.*]] = getelementptr [[REC]], %rec* [[OUT:%.*]], i16 0, i32 0
+; CHECK-NEXT:    [[OUT2:%.*]] = getelementptr [[REC]], %rec* [[OUT]], i16 0, i32 1
+; CHECK-NEXT:    store i32 [[VAL1]], i32* [[OUT1]], align 8
+; CHECK-NEXT:    store i28 [[VAL2]], i28* [[OUT2]]
+; CHECK-NEXT:    ret void
+;
+  %in1 = getelementptr %rec, %rec* %in, i16 0, i32 0
+  %in2 = getelementptr %rec, %rec* %in, i16 0, i32 1
+  %val1 = load i32, i32* %in1, align 8
+  %val2 = load i28, i28* %in2
+  %out1 = getelementptr %rec, %rec* %out, i16 0, i32 0
+  %out2 = getelementptr %rec, %rec* %out, i16 0, i32 1
+  store i32 %val1, i32* %out1, align 8
+  store i28 %val2, i28* %out2
+  ret void
+}
+