diff --git a/llvm/include/llvm/Analysis/ValueTracking.h b/llvm/include/llvm/Analysis/ValueTracking.h
--- a/llvm/include/llvm/Analysis/ValueTracking.h
+++ b/llvm/include/llvm/Analysis/ValueTracking.h
@@ -463,6 +463,28 @@
                                     const DominatorTree *DT = nullptr,
                                     const TargetLibraryInfo *TLI = nullptr);
 
+  /// This returns the same result as isSafeToSpeculativelyExecute if Opcode is
+  /// the actual opcode of Inst. If the provided and actual opcode differ, the
+  /// function (virtually) overrides the opcode of Inst with the provided
+  /// Opcode. There are come constraints in this case:
+  /// * If Opcode has a fixed number of operands (eg, as binary operators do),
+  ///   then Inst has to have at least as many leading operands. The function
+  ///   will ignore all trailing operands beyond that number.
+  /// * If Opcode allows for an arbitrary number of operands (eg, as CallInsts
+  ///   do), then all operands are considered.
+  /// * The virtual instruction has to satisfy all typing rules of the provided
+  ///   Opcode.
+  /// * This function is pessimistic in the following sense: If one actually
+  ///   materialized the virtual instruction, then isSafeToSpeculativelyExecute
+  ///   may say that the materialized instruction is speculatable whereas this
+  ///   function may have said that the instruction wouldn't be speculatable.
+  ///   This behavior is a shortcoming in the current implementation and not
+  ///   intentional.
+  bool isSafeToSpeculativelyExecuteWithOpcode(
+      unsigned Opcode, const Operator *Inst, const Instruction *CtxI = nullptr,
+      const DominatorTree *DT = nullptr,
+      const TargetLibraryInfo *TLI = nullptr);
+
   /// Returns true if the result or effects of the given instructions \p I
   /// depend values not reachable through the def use graph.
   /// * Memory dependence arises for example if the instruction reads from
diff --git a/llvm/include/llvm/IR/Intrinsics.td b/llvm/include/llvm/IR/Intrinsics.td
--- a/llvm/include/llvm/IR/Intrinsics.td
+++ b/llvm/include/llvm/IR/Intrinsics.td
@@ -1415,11 +1415,11 @@
                              [ IntrReadMem, IntrNoSync, IntrWillReturn, IntrArgMemOnly ]>;
 
 def int_vp_scatter: DefaultAttrsIntrinsic<[],
-                              [ llvm_anyvector_ty,
-                                LLVMVectorOfAnyPointersToElt<0>,
-                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                llvm_i32_ty],
-                              [ IntrArgMemOnly, IntrNoSync, IntrWillReturn ]>; // TODO allow IntrNoCapture for vectors of pointers
+                             [ llvm_anyvector_ty,
+                               LLVMVectorOfAnyPointersToElt<0>,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty],
+                             [ IntrArgMemOnly, IntrNoSync, IntrWillReturn ]>; // TODO allow IntrNoCapture for vectors of pointers
 
 // Experimental strided memory accesses
 def int_experimental_vp_strided_store : DefaultAttrsIntrinsic<[],
@@ -1437,8 +1437,9 @@
                                llvm_i32_ty],
                              [ NoCapture<ArgIndex<0>>, IntrNoSync, IntrReadMem, IntrWillReturn, IntrArgMemOnly ]>;
 
-// Speculatable Binary operators
-let IntrProperties = [IntrSpeculatable, IntrNoMem, IntrNoSync, IntrWillReturn] in {
+// Operators
+let IntrProperties = [IntrNoMem, IntrNoSync, IntrWillReturn] in {
+  // Integer arithmetic
   def int_vp_add : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
                              [ LLVMMatchType<0>,
                                LLVMMatchType<0>,
@@ -1450,30 +1451,30 @@
                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
                                llvm_i32_ty]>;
   def int_vp_mul  : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                              [ LLVMMatchType<0>,
-                                LLVMMatchType<0>,
-                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                llvm_i32_ty]>;
+                             [ LLVMMatchType<0>,
+                               LLVMMatchType<0>,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_ashr : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                              [ LLVMMatchType<0>,
-                                LLVMMatchType<0>,
-                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                llvm_i32_ty]>;
+                             [ LLVMMatchType<0>,
+                               LLVMMatchType<0>,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_lshr : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                              [ LLVMMatchType<0>,
-                                LLVMMatchType<0>,
-                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                llvm_i32_ty]>;
+                             [ LLVMMatchType<0>,
+                               LLVMMatchType<0>,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_shl : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
                              [ LLVMMatchType<0>,
                                LLVMMatchType<0>,
                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
                                llvm_i32_ty]>;
   def int_vp_or : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                            [ LLVMMatchType<0>,
-                              LLVMMatchType<0>,
-                              LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                              llvm_i32_ty]>;
+                             [ LLVMMatchType<0>,
+                               LLVMMatchType<0>,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_and : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
                              [ LLVMMatchType<0>,
                                LLVMMatchType<0>,
@@ -1484,35 +1485,28 @@
                                LLVMMatchType<0>,
                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
                                llvm_i32_ty]>;
-}
-
-// Non-speculatable binary operators.
-let IntrProperties = [IntrNoMem, IntrNoSync, IntrWillReturn] in {
   def int_vp_sdiv : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                              [ LLVMMatchType<0>,
-                                LLVMMatchType<0>,
-                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                llvm_i32_ty]>;
+                             [ LLVMMatchType<0>,
+                               LLVMMatchType<0>,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_udiv : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                              [ LLVMMatchType<0>,
-                                LLVMMatchType<0>,
-                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                llvm_i32_ty]>;
+                             [ LLVMMatchType<0>,
+                               LLVMMatchType<0>,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_srem : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                              [ LLVMMatchType<0>,
-                                LLVMMatchType<0>,
-                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                llvm_i32_ty]>;
+                             [ LLVMMatchType<0>,
+                               LLVMMatchType<0>,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_urem : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                              [ LLVMMatchType<0>,
-                                LLVMMatchType<0>,
-                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                llvm_i32_ty]>;
-}
+                             [ LLVMMatchType<0>,
+                               LLVMMatchType<0>,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
 
-// Floating-point arithmetic.
-let IntrProperties =
-    [IntrSpeculatable, IntrNoMem, IntrNoSync, IntrWillReturn] in {
+  // Floating-point arithmetic
   def int_vp_fadd : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
                              [ LLVMMatchType<0>,
                                LLVMMatchType<0>,
@@ -1524,177 +1518,169 @@
                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
                                llvm_i32_ty]>;
   def int_vp_fmul  : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                              [ LLVMMatchType<0>,
-                                LLVMMatchType<0>,
-                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                llvm_i32_ty]>;
+                             [ LLVMMatchType<0>,
+                               LLVMMatchType<0>,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_fdiv : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                              [ LLVMMatchType<0>,
-                                LLVMMatchType<0>,
-                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                llvm_i32_ty]>;
+                             [ LLVMMatchType<0>,
+                               LLVMMatchType<0>,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_frem : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                              [ LLVMMatchType<0>,
-                                LLVMMatchType<0>,
-                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                llvm_i32_ty]>;
-
+                             [ LLVMMatchType<0>,
+                               LLVMMatchType<0>,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_fneg : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                              [ LLVMMatchType<0>,
-                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                llvm_i32_ty]>;
-
+                             [ LLVMMatchType<0>,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_fma : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                              [ LLVMMatchType<0>,
-                                LLVMMatchType<0>,
-                                LLVMMatchType<0>,
-                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                llvm_i32_ty]>;
-}
+                             [ LLVMMatchType<0>,
+                               LLVMMatchType<0>,
+                               LLVMMatchType<0>,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
 
-// Casts.
-def int_vp_trunc : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                            [ llvm_anyvector_ty,
-                              LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                              llvm_i32_ty]>;
-def int_vp_zext : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                            [ llvm_anyvector_ty,
-                              LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                              llvm_i32_ty]>;
-def int_vp_sext : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                            [ llvm_anyvector_ty,
-                              LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                              llvm_i32_ty]>;
-def int_vp_fptrunc : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                            [ llvm_anyvector_ty,
-                              LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                              llvm_i32_ty]>;
-def int_vp_fpext : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                            [ llvm_anyvector_ty,
-                              LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                              llvm_i32_ty]>;
-def int_vp_fptoui : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                            [ llvm_anyvector_ty,
-                              LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                              llvm_i32_ty]>;
-def int_vp_fptosi : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                            [ llvm_anyvector_ty,
-                              LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                              llvm_i32_ty]>;
-def int_vp_uitofp : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                            [ llvm_anyvector_ty,
-                              LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                              llvm_i32_ty]>;
-def int_vp_sitofp : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                            [ llvm_anyvector_ty,
-                              LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                              llvm_i32_ty]>;
-def int_vp_ptrtoint : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                            [ llvm_anyvector_ty,
-                              LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                              llvm_i32_ty]>;
-def int_vp_inttoptr : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                            [ llvm_anyvector_ty,
-                              LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                              llvm_i32_ty]>;
-
-// Shuffles.
-def int_vp_select : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                              [ LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                LLVMMatchType<0>,
-                                LLVMMatchType<0>,
-                                llvm_i32_ty]>;
-
-def int_vp_merge : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
-                              [ LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                LLVMMatchType<0>,
-                                LLVMMatchType<0>,
-                                llvm_i32_ty]>;
-
-// Comparisons.
-let IntrProperties = [IntrNoMem, IntrNoSync, IntrWillReturn] in {
-  def int_vp_fcmp : DefaultAttrsIntrinsic<[ LLVMScalarOrSameVectorWidth<0, llvm_i1_ty> ],
-                                [ llvm_anyvector_ty,
-                                  LLVMMatchType<0>,
-                                  llvm_metadata_ty,
-                                  LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                  llvm_i32_ty]>;
+  // Casts
+  def int_vp_trunc : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
+                             [ llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
+  def int_vp_zext : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
+                             [ llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
+  def int_vp_sext : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
+                             [ llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
+  def int_vp_fptrunc : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
+                             [ llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
+  def int_vp_fpext : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
+                             [ llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
+  def int_vp_fptoui : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
+                             [ llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
+  def int_vp_fptosi : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
+                             [ llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
+  def int_vp_uitofp : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
+                             [ llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
+  def int_vp_sitofp : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
+                             [ llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
+  def int_vp_ptrtoint : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
+                             [ llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
+  def int_vp_inttoptr : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
+                             [ llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
 
+  // Shuffles
+  def int_vp_select : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
+                             [ LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               LLVMMatchType<0>,
+                               LLVMMatchType<0>,
+                               llvm_i32_ty]>;
+  def int_vp_merge : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
+                             [ LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               LLVMMatchType<0>,
+                               LLVMMatchType<0>,
+                               llvm_i32_ty]>;
+
+  // Comparisons
+  def int_vp_fcmp : DefaultAttrsIntrinsic<[ LLVMScalarOrSameVectorWidth<0, llvm_i1_ty> ],
+                             [ llvm_anyvector_ty,
+                               LLVMMatchType<0>,
+                               llvm_metadata_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_icmp : DefaultAttrsIntrinsic<[ LLVMScalarOrSameVectorWidth<0, llvm_i1_ty> ],
-                                [ llvm_anyvector_ty,
-                                  LLVMMatchType<0>,
-                                  llvm_metadata_ty,
-                                  LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                  llvm_i32_ty]>;
-}
+                             [ llvm_anyvector_ty,
+                               LLVMMatchType<0>,
+                               llvm_metadata_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
 
-// Reductions
-let IntrProperties = [IntrSpeculatable, IntrNoMem, IntrNoSync, IntrWillReturn] in {
+  // Reductions
   def int_vp_reduce_fadd : DefaultAttrsIntrinsic<[LLVMVectorElementType<0>],
-                                    [LLVMVectorElementType<0>,
-                                     llvm_anyvector_ty,
-                                     LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                     llvm_i32_ty]>;
+                             [ LLVMVectorElementType<0>,
+                               llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_reduce_fmul : DefaultAttrsIntrinsic<[LLVMVectorElementType<0>],
-                                    [LLVMVectorElementType<0>,
-                                     llvm_anyvector_ty,
-                                     LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                     llvm_i32_ty]>;
+                             [ LLVMVectorElementType<0>,
+                               llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_reduce_add  : DefaultAttrsIntrinsic<[LLVMVectorElementType<0>],
-                                    [LLVMVectorElementType<0>,
-                                     llvm_anyvector_ty,
-                                     LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                     llvm_i32_ty]>;
+                             [ LLVMVectorElementType<0>,
+                               llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_reduce_mul : DefaultAttrsIntrinsic<[LLVMVectorElementType<0>],
-                                    [LLVMVectorElementType<0>,
-                                     llvm_anyvector_ty,
-                                     LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                     llvm_i32_ty]>;
+                             [ LLVMVectorElementType<0>,
+                               llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_reduce_and : DefaultAttrsIntrinsic<[LLVMVectorElementType<0>],
-                                    [LLVMVectorElementType<0>,
-                                     llvm_anyvector_ty,
-                                     LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                     llvm_i32_ty]>;
+                             [ LLVMVectorElementType<0>,
+                               llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_reduce_or : DefaultAttrsIntrinsic<[LLVMVectorElementType<0>],
-                                    [LLVMVectorElementType<0>,
-                                     llvm_anyvector_ty,
-                                     LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                     llvm_i32_ty]>;
+                             [ LLVMVectorElementType<0>,
+                               llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_reduce_xor : DefaultAttrsIntrinsic<[LLVMVectorElementType<0>],
-                                    [LLVMVectorElementType<0>,
-                                     llvm_anyvector_ty,
-                                     LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                     llvm_i32_ty]>;
+                             [ LLVMVectorElementType<0>,
+                               llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_reduce_smax : DefaultAttrsIntrinsic<[LLVMVectorElementType<0>],
-                                    [LLVMVectorElementType<0>,
-                                     llvm_anyvector_ty,
-                                     LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                     llvm_i32_ty]>;
+                             [ LLVMVectorElementType<0>,
+                               llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_reduce_smin : DefaultAttrsIntrinsic<[LLVMVectorElementType<0>],
-                                    [LLVMVectorElementType<0>,
-                                     llvm_anyvector_ty,
-                                     LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                     llvm_i32_ty]>;
+                             [ LLVMVectorElementType<0>,
+                               llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_reduce_umax : DefaultAttrsIntrinsic<[LLVMVectorElementType<0>],
-                                    [LLVMVectorElementType<0>,
-                                     llvm_anyvector_ty,
-                                     LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                     llvm_i32_ty]>;
+                             [ LLVMVectorElementType<0>,
+                               llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_reduce_umin : DefaultAttrsIntrinsic<[LLVMVectorElementType<0>],
-                                    [LLVMVectorElementType<0>,
-                                     llvm_anyvector_ty,
-                                     LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                     llvm_i32_ty]>;
+                             [ LLVMVectorElementType<0>,
+                               llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_reduce_fmax : DefaultAttrsIntrinsic<[LLVMVectorElementType<0>],
-                                    [LLVMVectorElementType<0>,
-                                     llvm_anyvector_ty,
-                                     LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                     llvm_i32_ty]>;
+                             [ LLVMVectorElementType<0>,
+                               llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_reduce_fmin : DefaultAttrsIntrinsic<[LLVMVectorElementType<0>],
-                                    [LLVMVectorElementType<0>,
-                                     llvm_anyvector_ty,
-                                     LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
-                                     llvm_i32_ty]>;
+                             [ LLVMVectorElementType<0>,
+                               llvm_anyvector_ty,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
 }
 
 def int_get_active_lane_mask:
diff --git a/llvm/lib/Analysis/ValueTracking.cpp b/llvm/lib/Analysis/ValueTracking.cpp
--- a/llvm/lib/Analysis/ValueTracking.cpp
+++ b/llvm/lib/Analysis/ValueTracking.cpp
@@ -4599,13 +4599,38 @@
   const Operator *Inst = dyn_cast<Operator>(V);
   if (!Inst)
     return false;
+  return isSafeToSpeculativelyExecuteWithOpcode(Inst->getOpcode(), Inst, CtxI, DT, TLI);
+}
+
+bool llvm::isSafeToSpeculativelyExecuteWithOpcode(unsigned Opcode,
+                                        const Operator *Inst,
+                                        const Instruction *CtxI,
+                                        const DominatorTree *DT,
+                                        const TargetLibraryInfo *TLI) {
+  if (Inst->getOpcode() != Opcode) {
+    // Check that the operands are actually compatible with the Opcode override.
+    auto hasEqualReturnAndLeadingOperandTypes =
+        [](const Operator *Inst, unsigned NumLeadingOperands) {
+          if (Inst->getNumOperands() < NumLeadingOperands)
+            return false;
+          const Type *ExpectedType = Inst->getType();
+          for (unsigned ItOp = 0; ItOp < NumLeadingOperands; ++ItOp)
+            if (Inst->getOperand(ItOp)->getType() != ExpectedType)
+              return false;
+          return true;
+        };
+    assert(!Instruction::isBinaryOp(Opcode) ||
+           hasEqualReturnAndLeadingOperandTypes(Inst, 2));
+    assert(!Instruction::isUnaryOp(Opcode) ||
+           hasEqualReturnAndLeadingOperandTypes(Inst, 1));
+  }
 
   for (unsigned i = 0, e = Inst->getNumOperands(); i != e; ++i)
     if (Constant *C = dyn_cast<Constant>(Inst->getOperand(i)))
       if (C->canTrap())
         return false;
 
-  switch (Inst->getOpcode()) {
+  switch (Opcode) {
   default:
     return true;
   case Instruction::UDiv:
@@ -4636,7 +4661,9 @@
     return false;
   }
   case Instruction::Load: {
-    const LoadInst *LI = cast<LoadInst>(Inst);
+    const LoadInst *LI = dyn_cast<LoadInst>(Inst);
+    if (!LI)
+      return false;
     if (mustSuppressSpeculation(*LI))
       return false;
     const DataLayout &DL = LI->getModule()->getDataLayout();
@@ -4645,7 +4672,9 @@
         TLI);
   }
   case Instruction::Call: {
-    auto *CI = cast<const CallInst>(Inst);
+    auto *CI = dyn_cast<const CallInst>(Inst);
+    if (!CI)
+      return false;
     const Function *Callee = CI->getCalledFunction();
 
     // The called function could have undefined behavior or side-effects, even
diff --git a/llvm/lib/CodeGen/ExpandVectorPredication.cpp b/llvm/lib/CodeGen/ExpandVectorPredication.cpp
--- a/llvm/lib/CodeGen/ExpandVectorPredication.cpp
+++ b/llvm/lib/CodeGen/ExpandVectorPredication.cpp
@@ -118,10 +118,10 @@
   if (isa<VPReductionIntrinsic>(VPI))
     return false;
   // Fallback to whether the intrinsic is speculatable.
-  // FIXME: Check whether the replacing non-VP code will be speculatable
-  //        instead. VP intrinsics themselves are never speculatable because of
-  //        UB if %evl is greater than the runtime vector length.
-  return isSafeToSpeculativelyExecute(cast<Operator>(&VPI));
+  Optional<unsigned> OpcOpt = VPI.getFunctionalOpcode();
+  unsigned FunctionalOpc = OpcOpt.getValueOr((unsigned)Instruction::Call);
+  return isSafeToSpeculativelyExecuteWithOpcode(FunctionalOpc,
+                                                cast<Operator>(&VPI));
 }
 
 //// } Helpers
@@ -481,7 +481,7 @@
 };
 
 void sanitizeStrategy(VPIntrinsic &VPI, VPLegalization &LegalizeStrat) {
-  // Speculatable instructions do not strictly need predication.
+  // Operations with speculatable lanes do not strictly need predication.
   if (maySpeculateLanes(VPI)) {
     // Converting a speculatable VP intrinsic means dropping %mask and %evl.
     // No need to expand %evl into the %mask only to ignore that code.