Index: llvm/trunk/lib/Transforms/InstCombine/InstCombineCalls.cpp
===================================================================
--- llvm/trunk/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ llvm/trunk/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -753,6 +753,26 @@
   return nullptr;
 }
 
+static Value *simplifyMaskedLoad(const IntrinsicInst &II,
+                                 InstCombiner::BuilderTy &Builder) {
+  auto *ConstMask = dyn_cast<Constant>(II.getArgOperand(2));
+  if (!ConstMask)
+    return nullptr;
+
+  // If the mask is all zeros, the "passthru" argument is the result.
+  if (ConstMask->isNullValue())
+    return II.getArgOperand(3);
+
+  // If the mask is all ones, this is a plain vector load of the 1st argument.
+  if (ConstMask->isAllOnesValue()) {
+    Value *LoadPtr = II.getArgOperand(0);
+    unsigned Alignment = cast<ConstantInt>(II.getArgOperand(1))->getZExtValue();
+    return Builder.CreateAlignedLoad(LoadPtr, Alignment, "unmaskedload");
+  }
+
+  return nullptr;
+}
+
 /// CallInst simplification. This mostly only handles folding of intrinsic
 /// instructions. For normal calls, it allows visitCallSite to do the heavy
 /// lifting.
@@ -877,6 +897,16 @@
     break;
   }
 
+  case Intrinsic::masked_load:
+    if (Value *SimplifiedMaskedOp = simplifyMaskedLoad(*II, *Builder))
+      return ReplaceInstUsesWith(CI, SimplifiedMaskedOp);
+    break;
+
+  // TODO: Handle the other masked ops.
+  // case Intrinsic::masked_store:
+  // case Intrinsic::masked_gather:
+  // case Intrinsic::masked_scatter:
+
   case Intrinsic::powi:
     if (ConstantInt *Power = dyn_cast<ConstantInt>(II->getArgOperand(1))) {
       // powi(x, 0) -> 1.0
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
@@ -2,15 +2,13 @@
 
 declare <2 x double> @llvm.masked.load.v2f64(<2 x double>* %ptrs, i32, <2 x i1> %mask, <2 x double> %src0)
 
-; FIXME: All of these could be simplified.
 
 define <2 x double> @load_zeromask(<2 x double>* %ptr, <2 x double> %passthru)  {
   %res = call <2 x double> @llvm.masked.load.v2f64(<2 x double>* %ptr, i32 1, <2 x i1> zeroinitializer, <2 x double> %passthru)
   ret <2 x double> %res
 
 ; CHECK-LABEL: @load_zeromask(
-; CHECK-NEXT:  %res = call <2 x double> @llvm.masked.load.v2f64(<2 x double>* %ptr, i32 1, <2 x i1> zeroinitializer, <2 x double> %passthru)
-; CHECK-NEXT   ret <2 x double> %res
+; CHECK-NEXT   ret <2 x double> %passthru
 }
 
 define <2 x double> @load_onemask(<2 x double>* %ptr, <2 x double> %passthru)  {
@@ -18,24 +16,7 @@
   ret <2 x double> %res
 
 ; CHECK-LABEL: @load_onemask(
-; CHECK-NEXT:  %res = call <2 x double> @llvm.masked.load.v2f64(<2 x double>* %ptr, i32 2, <2 x i1> <i1 true, i1 true>, <2 x double> %passthru)
-; CHECK-NEXT   ret <2 x double> %res
-}
-
-define <2 x double> @load_onesetbitmask1(<2 x double>* %ptr, <2 x double> %passthru)  {
-  %res = call <2 x double> @llvm.masked.load.v2f64(<2 x double>* %ptr, i32 3, <2 x i1> <i1 0, i1 1>, <2 x double> %passthru)
-  ret <2 x double> %res
-
-; CHECK-LABEL: @load_onesetbitmask1(
-; CHECK-NEXT:  %res = call <2 x double> @llvm.masked.load.v2f64(<2 x double>* %ptr, i32 3, <2 x i1> <i1 false, i1 true>, <2 x double> %passthru)
+; CHECK-NEXT:  %unmaskedload = load <2 x double>, <2 x double>* %ptr, align 2
 ; CHECK-NEXT   ret <2 x double> %res
 }
 
-define <2 x double> @load_onesetbitmask2(<2 x double>* %ptr, <2 x double> %passthru)  {
-  %res = call <2 x double> @llvm.masked.load.v2f64(<2 x double>* %ptr, i32 4, <2 x i1> <i1 1, i1 0>, <2 x double> %passthru)
-  ret <2 x double> %res
-
-; CHECK-LABEL: @load_onesetbitmask2(
-; CHECK-NEXT:  %res = call <2 x double> @llvm.masked.load.v2f64(<2 x double>* %ptr, i32 4, <2 x i1> <i1 true, i1 false>, <2 x double> %passthru)
-; CHECK-NEXT   ret <2 x double> %res
-}