Index: lib/Transforms/InstCombine/InstCombineCalls.cpp
===================================================================
--- lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -1899,14 +1899,30 @@
     }
     break;
   }
-  case Intrinsic::masked_load:
+  case Intrinsic::masked_load: {
+    auto VWidth = II->getType()->getVectorNumElements();
+    APInt UndefElts(VWidth, 0);
+    APInt AllOnesEltMask(APInt::getAllOnesValue(VWidth));
+    if (Value *V = SimplifyDemandedVectorElts(II, AllOnesEltMask, UndefElts))
+      if (V != II)
+        return replaceInstUsesWith(*II, V);
+
     if (Value *SimplifiedMaskedOp = simplifyMaskedLoad(*II, Builder))
       return replaceInstUsesWith(CI, SimplifiedMaskedOp);
     break;
+  }
   case Intrinsic::masked_store:
     return simplifyMaskedStore(*II, *this);
-  case Intrinsic::masked_gather:
+  case Intrinsic::masked_gather: {
+    auto VWidth = II->getType()->getVectorNumElements();
+    APInt UndefElts(VWidth, 0);
+    APInt AllOnesEltMask(APInt::getAllOnesValue(VWidth));
+    if (Value *V = SimplifyDemandedVectorElts(II, AllOnesEltMask, UndefElts))
+      if (V != II)
+        return replaceInstUsesWith(*II, V);
+
     return simplifyMaskedGather(*II, *this);
+  }
   case Intrinsic::masked_scatter:
     return simplifyMaskedScatter(*II, *this);
   case Intrinsic::launder_invariant_group:
Index: lib/Transforms/InstCombine/InstCombineSimplifyDemanded.cpp
===================================================================
--- lib/Transforms/InstCombine/InstCombineSimplifyDemanded.cpp
+++ lib/Transforms/InstCombine/InstCombineSimplifyDemanded.cpp
@@ -1441,6 +1441,29 @@
     IntrinsicInst *II = dyn_cast<IntrinsicInst>(I);
     if (!II) break;
     switch (II->getIntrinsicID()) {
+    case Intrinsic::masked_gather: // fallthrough
+    case Intrinsic::masked_load: {
+      // Subtle - We *can't* simplify the zero bits of the mask just because
+      // they're unused because that might introduce a fault.
+      // TODO: but we can fold them to zero in a constant mask
+      APInt DemandedLoad(DemandedElts), DemandedPassThrough(DemandedElts);
+      if (auto *CV = dyn_cast<ConstantVector>(II->getOperand(2)))
+        for (unsigned i = 0; i < VWidth; i++) {
+          Constant *CElt = CV->getAggregateElement(i);
+          if (CElt->isNullValue())
+            DemandedLoad.clearBit(i);
+          else if (CElt->isAllOnesValue())
+            DemandedPassThrough.clearBit(i);
+        }
+      if (II->getIntrinsicID() == Intrinsic::masked_gather)
+        simplifyAndSetOp(II, 0, DemandedLoad, UndefElts2);
+      simplifyAndSetOp(II, 3, DemandedPassThrough, UndefElts3);
+      
+      // Output elements are undefined if the element from both sources are.
+      // TODO: can strengthen via mask as well.
+      UndefElts = UndefElts2 & UndefElts3;
+      break;
+    }
     case Intrinsic::x86_xop_vfrcz_ss:
     case Intrinsic::x86_xop_vfrcz_sd:
       // The instructions for these intrinsics are speced to zero upper bits not
Index: test/Transforms/InstCombine/masked_intrinsics.ll
===================================================================
--- test/Transforms/InstCombine/masked_intrinsics.ll
+++ test/Transforms/InstCombine/masked_intrinsics.ll
@@ -37,8 +37,7 @@
 
 define <2 x double> @load_lane0(<2 x double>* %ptr, double %pt)  {
 ; CHECK-LABEL: @load_lane0(
-; 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:    [[PTV2:%.*]] = insertelement <2 x double> undef, double [[PT:%.*]], i64 1
 ; CHECK-NEXT:    [[RES:%.*]] = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* [[PTR:%.*]], i32 2, <2 x i1> <i1 true, i1 false>, <2 x double> [[PTV2]])
 ; CHECK-NEXT:    ret <2 x double> [[RES]]
 ;
@@ -81,7 +80,7 @@
 
 define <2 x double> @gather_onemask(<2 x double*> %ptrs, <2 x double> %passthru)  {
 ; CHECK-LABEL: @gather_onemask(
-; CHECK-NEXT:    [[RES:%.*]] = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> [[PTRS:%.*]], i32 5, <2 x i1> <i1 true, i1 true>, <2 x double> [[PASSTHRU:%.*]])
+; CHECK-NEXT:    [[RES:%.*]] = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> [[PTRS:%.*]], i32 5, <2 x i1> <i1 true, i1 true>, <2 x double> undef)
 ; CHECK-NEXT:    ret <2 x double> [[RES]]
 ;
   %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 5, <2 x i1> <i1 true, i1 true>, <2 x double> %passthru)
@@ -91,9 +90,8 @@
 
 define <2 x double> @gather_lane0(double* %base, double %pt)  {
 ; CHECK-LABEL: @gather_lane0(
-; CHECK-NEXT:    [[PTRS:%.*]] = getelementptr double, double* [[BASE:%.*]], <2 x i64> <i64 0, i64 1>
-; CHECK-NEXT:    [[PT_V1:%.*]] = insertelement <2 x double> undef, double [[PT:%.*]], i64 0
-; CHECK-NEXT:    [[PT_V2:%.*]] = shufflevector <2 x double> [[PT_V1]], <2 x double> undef, <2 x i32> zeroinitializer
+; CHECK-NEXT:    [[PTRS:%.*]] = getelementptr double, double* [[BASE:%.*]], <2 x i64> <i64 0, i64 undef>
+; CHECK-NEXT:    [[PT_V2:%.*]] = insertelement <2 x double> undef, double [[PT:%.*]], i64 1
 ; CHECK-NEXT:    [[RES:%.*]] = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> [[PTRS]], i32 5, <2 x i1> <i1 true, i1 false>, <2 x double> [[PT_V2]])
 ; CHECK-NEXT:    ret <2 x double> [[RES]]
 ;