Index: llvm/trunk/lib/Transforms/InstCombine/InstCombineCalls.cpp
===================================================================
--- llvm/trunk/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ llvm/trunk/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -21,6 +21,7 @@
 #include "llvm/ADT/Statistic.h"
 #include "llvm/ADT/Twine.h"
 #include "llvm/Analysis/AssumptionCache.h"
+#include "llvm/Analysis/Loads.h"
 #include "llvm/Analysis/InstructionSimplify.h"
 #include "llvm/Analysis/MemoryBuiltins.h"
 #include "llvm/Transforms/Utils/Local.h"
@@ -1183,17 +1184,26 @@
 }
 
 // TODO, Obvious Missing Transforms:
-// * Dereferenceable address -> speculative load/select
 // * Narrow width by halfs excluding zero/undef lanes
 static Value *simplifyMaskedLoad(const IntrinsicInst &II,
                                  InstCombiner::BuilderTy &Builder) {
+  Value *LoadPtr = II.getArgOperand(0);
+  unsigned Alignment = cast<ConstantInt>(II.getArgOperand(1))->getZExtValue();
+
   // If the mask is all ones or undefs, this is a plain vector load of the 1st
   // argument.
-  if (maskIsAllOneOrUndef(II.getArgOperand(2))) {
-    Value *LoadPtr = II.getArgOperand(0);
-    unsigned Alignment = cast<ConstantInt>(II.getArgOperand(1))->getZExtValue();
+  if (maskIsAllOneOrUndef(II.getArgOperand(2)))
     return Builder.CreateAlignedLoad(II.getType(), LoadPtr, Alignment,
                                      "unmaskedload");
+
+  // If we can unconditionally load from this address, replace with a
+  // load/select idiom. TODO: use DT for context sensitive query
+  if (isDereferenceableAndAlignedPointer(LoadPtr, Alignment,
+                                         II.getModule()->getDataLayout(),
+                                         &II, nullptr)) {
+    Value *LI = Builder.CreateAlignedLoad(II.getType(), LoadPtr, Alignment,
+                                         "unmaskedload");
+    return Builder.CreateSelect(II.getArgOperand(2), LI, II.getArgOperand(3));
   }
 
   return nullptr;
Index: llvm/trunk/test/Transforms/InstCombine/masked_intrinsics.ll
===================================================================
--- llvm/trunk/test/Transforms/InstCombine/masked_intrinsics.ll
+++ llvm/trunk/test/Transforms/InstCombine/masked_intrinsics.ll
@@ -87,8 +87,9 @@
 ; CHECK-LABEL: @load_speculative(
 ; CHECK-NEXT:    [[PTV1:%.*]] = insertelement <2 x double> undef, double [[PT:%.*]], i64 0
 ; CHECK-NEXT:    [[PTV2:%.*]] = shufflevector <2 x double> [[PTV1]], <2 x double> undef, <2 x i32> zeroinitializer
-; CHECK-NEXT:    [[RES:%.*]] = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* nonnull [[PTR:%.*]], i32 4, <2 x i1> [[MASK:%.*]], <2 x double> [[PTV2]])
-; CHECK-NEXT:    ret <2 x double> [[RES]]
+; CHECK-NEXT:    [[UNMASKEDLOAD:%.*]] = load <2 x double>, <2 x double>* [[PTR:%.*]], align 4
+; CHECK-NEXT:    [[TMP1:%.*]] = select <2 x i1> [[MASK:%.*]], <2 x double> [[UNMASKEDLOAD]], <2 x double> [[PTV2]]
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
 ;
   double %pt, <2 x i1> %mask)  {
   %ptv1 = insertelement <2 x double> undef, double %pt, i64 0