Index: lib/Transforms/InstCombine/InstructionCombining.cpp
===================================================================
--- lib/Transforms/InstCombine/InstructionCombining.cpp
+++ lib/Transforms/InstCombine/InstructionCombining.cpp
@@ -939,9 +939,14 @@
       // `TrueVInPred`.
       if (InC && !isa<ConstantExpr>(InC) && isa<ConstantInt>(InC))
         InV = InC->isNullValue() ? FalseVInPred : TrueVInPred;
-      else
+      else {
+        // Generate the select in the same block as PN's current incoming block.
+        // Note: ThisBB need not be the NonConstBB because vector constants
+        // which are constants by definition are handled here.
+        Builder->SetInsertPoint(ThisBB->getTerminator());
         InV = Builder->CreateSelect(PN->getIncomingValue(i),
                                     TrueVInPred, FalseVInPred, "phitmp");
+      }
       NewPN->addIncoming(InV, ThisBB);
     }
   } else if (CmpInst *CI = dyn_cast<CmpInst>(&I)) {
Index: test/Transforms/InstCombine/phi-select-constant.ll
===================================================================
--- test/Transforms/InstCombine/phi-select-constant.ll
+++ test/Transforms/InstCombine/phi-select-constant.ll
@@ -55,3 +55,47 @@
  %sel = select <4 x i1> %phinode, <4 x i64> zeroinitializer, <4 x i64> <i64 124, i64 125, i64 126, i64 127>
  ret <4 x i64> %sel
 }
+
+; Test PR33364
+; Insert the generated select into the same block as the incoming phi value.
+; The select for loadA (generated through foldOpIntoPhi) should be inserted
+; into bb itself. Later passes of instcombine correctly converts this select 
+; to an insert in the zero'th element of loadA.
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py and modified.
+@globalA = global <2 x i8> <i8 42, i8 24>, align 2
+@globalB = global <2 x i8> zeroinitializer, align 2
+define i8 @vec3(i1 %cond) {
+; CHECK-LABEL: vec3
+; CHECK-LABEL: bb:
+; CHECK-NEXT:    [[LOADA:%.*]] = load <2 x i8>, <2 x i8>* @globalA,
+; CHECK-NEXT:    [[PHITMP23:%.*]] = insertelement <2 x i8> [[LOADA]], i8 0, i32 0
+; CHECK-NEXT:    br i1 %cond, label %bb13_crit_edge, label %bb13
+bb:
+  %loadA = load <2 x i8>, <2 x i8>* @globalA, align 2
+  br i1 %cond, label %bb13_crit_edge, label %bb13
+
+; CHECK:       bb13_crit_edge:
+; CHECK-NEXT:    [[LOADB:%.*]] = load <2 x i8>, <2 x i8>* @globalB
+; CHECK-NEXT:    [[PHITMP:%.*]] = icmp slt <2 x i8> [[LOADB]], <i8 1, i8 1>
+; CHECK-NEXT:    [[PHITMP1:%.*]] = select <2 x i1> [[PHITMP]], <2 x i8> [[LOADA]], <2 x i8> zeroinitializer
+; CHECK-NEXT:    br label %bb13
+bb13_crit_edge:                               ; preds = %bb15
+  %loadB = load <2 x i8>, <2 x i8>* @globalB, align 2
+  br label %bb13
+
+
+; CHECK:       bb13:
+; CHECK-NEXT:    [[PHI:%.*]] = phi <2 x i8> [ [[PHITMP1]], [[BB13_CRIT_EDGE]] ], [ [[PHITMP23]], [[BB:%.*]] ]
+; CHECK-NEXT:    [[EX1:%.*]] = extractelement <2 x i8> [[PHI]], i32 0
+; CHECK-NEXT:    [[EX2:%.*]] = extractelement <2 x i8> [[PHI]], i32 1
+; CHECK-NEXT:    [[SUM:%.*]] = add nsw i8 [[EX1]], [[EX2]]
+; CHECK-NEXT:    ret i8 [[SUM]]
+bb13:                                             ; preds = %bb13_crit_edge, %bb
+  %phi = phi <2 x i8> [ %loadB, %bb13_crit_edge ], [ <i8 1, i8 0>, %bb ]
+  %cmp = icmp slt <2 x i8> %phi, <i8 1, i8 1>
+  %sel = select <2 x i1> %cmp, <2 x i8> %loadA, <2 x i8> zeroinitializer
+  %ex1 = extractelement <2 x i8> %sel, i32 0
+  %ex2 = extractelement <2 x i8> %sel, i32 1
+  %sum = add nsw i8  %ex1, %ex2
+  ret i8 %sum
+}