Index: llvm/trunk/lib/Transforms/Vectorize/SLPVectorizer.cpp
===================================================================
--- llvm/trunk/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ llvm/trunk/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -1158,6 +1158,23 @@
       return;
     }
     case Instruction::Load: {
+      // Check that a vectorized load would load the same memory as a scalar
+      // load.
+      // For example we don't want vectorize loads that are smaller than 8 bit.
+      // Even though we have a packed struct {<i2, i2, i2, i2>} LLVM treats
+      // loading/storing it as an i8 struct. If we vectorize loads/stores from
+      // such a struct we read/write packed bits disagreeing with the
+      // unvectorized version.
+      const DataLayout &DL = F->getParent()->getDataLayout();
+      Type *ScalarTy = VL[0]->getType();
+
+      if (DL.getTypeSizeInBits(ScalarTy) !=
+          DL.getTypeAllocSizeInBits(ScalarTy)) {
+        BS.cancelScheduling(VL);
+        newTreeEntry(VL, false);
+        DEBUG(dbgs() << "SLP: Gathering loads of non-packed type.\n");
+        return;
+      }
       // Check if the loads are consecutive or of we need to swizzle them.
       for (unsigned i = 0, e = VL.size() - 1; i < e; ++i) {
         LoadInst *L = cast<LoadInst>(VL[i]);
@@ -1167,7 +1184,7 @@
           DEBUG(dbgs() << "SLP: Gathering non-simple loads.\n");
           return;
         }
-        const DataLayout &DL = F->getParent()->getDataLayout();
+
         if (!isConsecutiveAccess(VL[i], VL[i + 1], DL)) {
           if (VL.size() == 2 && isConsecutiveAccess(VL[1], VL[0], DL)) {
             ++NumLoadsWantToChangeOrder;
Index: llvm/trunk/test/Transforms/SLPVectorizer/X86/bad_types.ll
===================================================================
--- llvm/trunk/test/Transforms/SLPVectorizer/X86/bad_types.ll
+++ llvm/trunk/test/Transforms/SLPVectorizer/X86/bad_types.ll
@@ -47,4 +47,30 @@
   ret void
 }
 
+define i8 @test3(i8 *%addr) {
+; Check that we do not vectorize types that are padded to a bigger ones.
+;
+; CHECK-LABEL: @test3
+; CHECK-NOT:   <4 x i2>
+; CHECK:       ret i8
+entry:
+  %a = bitcast i8* %addr to i2*
+  %a0 = getelementptr inbounds i2, i2* %a, i64 0
+  %a1 = getelementptr inbounds i2, i2* %a, i64 1
+  %a2 = getelementptr inbounds i2, i2* %a, i64 2
+  %a3 = getelementptr inbounds i2, i2* %a, i64 3
+  %l0 = load i2, i2* %a0, align 1
+  %l1 = load i2, i2* %a1, align 1
+  %l2 = load i2, i2* %a2, align 1
+  %l3 = load i2, i2* %a3, align 1
+  br label %bb1
+bb1:                                              ; preds = %entry
+  %p0 = phi i2 [ %l0, %entry ]
+  %p1 = phi i2 [ %l1, %entry ]
+  %p2 = phi i2 [ %l2, %entry ]
+  %p3 = phi i2 [ %l3, %entry ]
+  %r  = zext i2 %p2 to i8
+  ret i8 %r
+}
+
 declare void @f(i64, i64)