Support arbitrary addrspace pointers in masked load/store intrinsics

This patch fixes the problem which occurs when loop-vectorize tries to use @llvm.masked.load/store intrinsic for a non-default addrspace pointer. It fails with "Calling a function with a bad signature!" assertion in CallInst constructor because it tries to pass a non-default addrspace pointer to the pointer argument which has default addrspace.

The fix is to add pointer type as another overloaded type to @llvm.masked.load/store intrinsics.

Reviewed By: reames

Differential Revision: http://reviews.llvm.org/D17270

llvm-svn: 263158

llvm/docs/LangRef.rst

@@ -11342,12 +11342,12 @@ This is an overloaded intrinsic. The loaded data is a vector of any integer, flo
 
 ::
 
-      declare <16 x float>  @llvm.masked.load.v16f32 (<16 x float>* <ptr>, i32 <alignment>, <16 x i1> <mask>, <16 x float> <passthru>)
+      declare <16 x float>  @llvm.masked.load.v16f32.p0v16f32 (<16 x float>* <ptr>, i32 <alignment>, <16 x i1> <mask>, <16 x float> <passthru>)
-      declare <2 x double>  @llvm.masked.load.v2f64  (<2 x double>* <ptr>, i32 <alignment>, <2 x i1>  <mask>, <2 x double> <passthru>)
+      declare <2 x double>  @llvm.masked.load.v2f64.p0v2f64  (<2 x double>* <ptr>, i32 <alignment>, <2 x i1>  <mask>, <2 x double> <passthru>)
       ;; The data is a vector of pointers to double
-      declare <8 x double*> @llvm.masked.load.v8p0f64    (<8 x double*>* <ptr>, i32 <alignment>, <8 x i1> <mask>, <8 x double*> <passthru>)
+      declare <8 x double*> @llvm.masked.load.v8p0f64.p0v8p0f64    (<8 x double*>* <ptr>, i32 <alignment>, <8 x i1> <mask>, <8 x double*> <passthru>)
       ;; The data is a vector of function pointers
-      declare <8 x i32 ()*> @llvm.masked.load.v8p0f_i32f (<8 x i32 ()*>* <ptr>, i32 <alignment>, <8 x i1> <mask>, <8 x i32 ()*> <passthru>)
+      declare <8 x i32 ()*> @llvm.masked.load.v8p0f_i32f.p0v8p0f_i32f (<8 x i32 ()*>* <ptr>, i32 <alignment>, <8 x i1> <mask>, <8 x i32 ()*> <passthru>)
 
 Overview:
 """""""""
@@ -11370,7 +11370,7 @@ The result of this operation is equivalent to a regular vector load instruction
 
 ::
 
-       %res = call <16 x float> @llvm.masked.load.v16f32 (<16 x float>* %ptr, i32 4, <16 x i1>%mask, <16 x float> %passthru)
+       %res = call <16 x float> @llvm.masked.load.v16f32.p0v16f32 (<16 x float>* %ptr, i32 4, <16 x i1>%mask, <16 x float> %passthru)
 
        ;; The result of the two following instructions is identical aside from potential memory access exception
        %loadlal = load <16 x float>, <16 x float>* %ptr, align 4
@@ -11387,12 +11387,12 @@ This is an overloaded intrinsic. The data stored in memory is a vector of any in
 
 ::
 
-       declare void @llvm.masked.store.v8i32  (<8  x i32>   <value>, <8  x i32>*   <ptr>, i32 <alignment>,  <8  x i1> <mask>)
+       declare void @llvm.masked.store.v8i32.p0v8i32  (<8  x i32>   <value>, <8  x i32>*   <ptr>, i32 <alignment>,  <8  x i1> <mask>)
-       declare void @llvm.masked.store.v16f32 (<16 x float> <value>, <16 x float>* <ptr>, i32 <alignment>,  <16 x i1> <mask>)
+       declare void @llvm.masked.store.v16f32.p0v16f32 (<16 x float> <value>, <16 x float>* <ptr>, i32 <alignment>,  <16 x i1> <mask>)
        ;; The data is a vector of pointers to double
-       declare void @llvm.masked.store.v8p0f64    (<8 x double*> <value>, <8 x double*>* <ptr>, i32 <alignment>, <8 x i1> <mask>)
+       declare void @llvm.masked.store.v8p0f64.p0v8p0f64    (<8 x double*> <value>, <8 x double*>* <ptr>, i32 <alignment>, <8 x i1> <mask>)
        ;; The data is a vector of function pointers
-       declare void @llvm.masked.store.v4p0f_i32f (<4 x i32 ()*> <value>, <4 x i32 ()*>* <ptr>, i32 <alignment>, <4 x i1> <mask>)
+       declare void @llvm.masked.store.v4p0f_i32f.p0v4p0f_i32f (<4 x i32 ()*> <value>, <4 x i32 ()*>* <ptr>, i32 <alignment>, <4 x i1> <mask>)
 
 Overview:
 """""""""
@@ -11413,7 +11413,7 @@ The result of this operation is equivalent to a load-modify-store sequence. Howe
 
 ::
 
-       call void @llvm.masked.store.v16f32(<16 x float> %value, <16 x float>* %ptr, i32 4,  <16 x i1> %mask)
+       call void @llvm.masked.store.v16f32.p0v16f32(<16 x float> %value, <16 x float>* %ptr, i32 4,  <16 x i1> %mask)
 
        ;; The result of the following instructions is identical aside from potential data races and memory access exceptions
        %oldval = load <16 x float>, <16 x float>* %ptr, align 4

llvm/include/llvm/IR/IRBuilder.h

@@ -520,9 +520,9 @@ public:
 
 private:
   /// \brief Create a call to a masked intrinsic with given Id.
-  /// Masked intrinsic has only one overloaded type - data type.
   CallInst *CreateMaskedIntrinsic(Intrinsic::ID Id, ArrayRef<Value *> Ops,
-                                  Type *DataTy, const Twine &Name = "");
+                                  ArrayRef<Type *> OverloadedTypes,
+                                  const Twine &Name = "");
 
   Value *getCastedInt8PtrValue(Value *Ptr);
 };

llvm/include/llvm/IR/Intrinsics.td

@@ -632,13 +632,14 @@ def int_clear_cache : Intrinsic<[], [llvm_ptr_ty, llvm_ptr_ty],
 
 //===-------------------------- Masked Intrinsics -------------------------===//
 //
-def int_masked_store : Intrinsic<[], [llvm_anyvector_ty, LLVMPointerTo<0>,
+def int_masked_store : Intrinsic<[], [llvm_anyvector_ty,
+                                      LLVMAnyPointerType<LLVMMatchType<0>>,
                                       llvm_i32_ty,
                                       LLVMVectorSameWidth<0, llvm_i1_ty>],
                                  [IntrReadWriteArgMem]>;
 
 def int_masked_load  : Intrinsic<[llvm_anyvector_ty],
-                                 [LLVMPointerTo<0>, llvm_i32_ty,
+                                 [LLVMAnyPointerType<LLVMMatchType<0>>, llvm_i32_ty,
                                   LLVMVectorSameWidth<0, llvm_i1_ty>, LLVMMatchType<0>],
                                  [IntrReadArgMem]>;
 

llvm/lib/IR/AutoUpgrade.cpp

@@ -145,6 +145,31 @@ static bool UpgradeIntrinsicFunction1(Function *F, Function *&NewFn) {
     break;
   }
 
+  case 'm': {
+    if (Name.startswith("masked.load.")) {
+      Type *Tys[] = { F->getReturnType(), F->arg_begin()->getType() };
+      if (F->getName() != Intrinsic::getName(Intrinsic::masked_load, Tys)) {
+        F->setName(Name + ".old");
+        NewFn = Intrinsic::getDeclaration(F->getParent(),
+                                          Intrinsic::masked_load,
+                                          Tys);
+        return true;
+      }
+    }
+    if (Name.startswith("masked.store.")) {
+      auto Args = F->getFunctionType()->params();
+      Type *Tys[] = { Args[0], Args[1] };
+      if (F->getName() != Intrinsic::getName(Intrinsic::masked_store, Tys)) {
+        F->setName(Name + ".old");
+        NewFn = Intrinsic::getDeclaration(F->getParent(),
+                                          Intrinsic::masked_store,
+                                          Tys);
+        return true;
+      }
+    }
+    break;
+  }
+
   case 'o':
     // We only need to change the name to match the mangling including the
     // address space.
@@ -790,6 +815,15 @@ void llvm::UpgradeIntrinsicCall(CallInst *CI, Function *NewFn) {
     CI->eraseFromParent();
     return;
   }
+
+  case Intrinsic::masked_load:
+  case Intrinsic::masked_store: {
+    SmallVector<Value *, 4> Args(CI->arg_operands().begin(),
+                                 CI->arg_operands().end());
+    CI->replaceAllUsesWith(Builder.CreateCall(NewFn, Args));
+    CI->eraseFromParent();
+    return;
+  }
   }
 }
 

llvm/lib/IR/IRBuilder.cpp

@@ -212,13 +212,15 @@ CallInst *IRBuilderBase::CreateAssumption(Value *Cond) {
 CallInst *IRBuilderBase::CreateMaskedLoad(Value *Ptr, unsigned Align,
                                           Value *Mask, Value *PassThru,
                                           const Twine &Name) {
-  // DataTy is the overloaded type
+  PointerType *PtrTy = cast<PointerType>(Ptr->getType());
-  Type *DataTy = cast<PointerType>(Ptr->getType())->getElementType();
+  Type *DataTy = PtrTy->getElementType();
   assert(DataTy->isVectorTy() && "Ptr should point to a vector");
   if (!PassThru)
     PassThru = UndefValue::get(DataTy);
+  Type *OverloadedTypes[] = { DataTy, PtrTy };
   Value *Ops[] = { Ptr, getInt32(Align), Mask,  PassThru};
-  return CreateMaskedIntrinsic(Intrinsic::masked_load, Ops, DataTy, Name);
+  return CreateMaskedIntrinsic(Intrinsic::masked_load, Ops,
+                               OverloadedTypes, Name);
 }
 
 /// \brief Create a call to a Masked Store intrinsic.
@@ -229,19 +231,22 @@ CallInst *IRBuilderBase::CreateMaskedLoad(Value *Ptr, unsigned Align,
 ///            be accessed in memory
 CallInst *IRBuilderBase::CreateMaskedStore(Value *Val, Value *Ptr,
                                            unsigned Align, Value *Mask) {
+  PointerType *PtrTy = cast<PointerType>(Ptr->getType());
+  Type *DataTy = PtrTy->getElementType();
+  assert(DataTy->isVectorTy() && "Ptr should point to a vector");
+  Type *OverloadedTypes[] = { DataTy, PtrTy };
   Value *Ops[] = { Val, Ptr, getInt32(Align), Mask };
-  // Type of the data to be stored - the only one overloaded type
+  return CreateMaskedIntrinsic(Intrinsic::masked_store, Ops, OverloadedTypes);
-  return CreateMaskedIntrinsic(Intrinsic::masked_store, Ops, Val->getType());
 }
 
 /// Create a call to a Masked intrinsic, with given intrinsic Id,
-/// an array of operands - Ops, and one overloaded type - DataTy
+/// an array of operands - Ops, and an array of overloaded types -
+/// OverloadedTypes.
 CallInst *IRBuilderBase::CreateMaskedIntrinsic(Intrinsic::ID Id,
                                                ArrayRef<Value *> Ops,
-                                               Type *DataTy,
+                                               ArrayRef<Type *> OverloadedTypes,
                                                const Twine &Name) {
   Module *M = BB->getParent()->getParent();
-  Type *OverloadedTypes[] = { DataTy };
   Value *TheFn = Intrinsic::getDeclaration(M, Id, OverloadedTypes);
   return createCallHelper(TheFn, Ops, this, Name);
 }
@@ -270,7 +275,7 @@ CallInst *IRBuilderBase::CreateMaskedGather(Value *Ptrs, unsigned Align,
 
   // We specify only one type when we create this intrinsic. Types of other
   // arguments are derived from this type.
-  return CreateMaskedIntrinsic(Intrinsic::masked_gather, Ops, DataTy, Name);
+  return CreateMaskedIntrinsic(Intrinsic::masked_gather, Ops, { DataTy }, Name);
 }
 
 /// \brief Create a call to a Masked Scatter intrinsic.
@@ -300,7 +305,7 @@ CallInst *IRBuilderBase::CreateMaskedScatter(Value *Data, Value *Ptrs,
 
   // We specify only one type when we create this intrinsic. Types of other
   // arguments are derived from this type.
-  return CreateMaskedIntrinsic(Intrinsic::masked_scatter, Ops, DataTy);
+  return CreateMaskedIntrinsic(Intrinsic::masked_scatter, Ops, { DataTy });
 }
 
 template <typename T0, typename T1, typename T2, typename T3>

llvm/test/Analysis/CostModel/X86/masked-intrinsic-cost.ll

@@ -7,7 +7,7 @@
 ; AVX2: Found an estimated cost of 4 {{.*}}.masked
 define <2 x double> @test1(<2 x i64> %trigger, <2 x double>* %addr, <2 x double> %dst) {
   %mask = icmp eq <2 x i64> %trigger, zeroinitializer
-  %res = call <2 x double> @llvm.masked.load.v2f64(<2 x double>* %addr, i32 4, <2 x i1>%mask, <2 x double>%dst)
+  %res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %addr, i32 4, <2 x i1>%mask, <2 x double>%dst)
   ret <2 x double> %res
 }
 
@@ -15,7 +15,7 @@ define <2 x double> @test1(<2 x i64> %trigger, <2 x double>* %addr, <2 x double>
 ; AVX2: Found an estimated cost of 4 {{.*}}.masked
 define <4 x i32> @test2(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %dst) {
   %mask = icmp eq <4 x i32> %trigger, zeroinitializer
-  %res = call <4 x i32> @llvm.masked.load.v4i32(<4 x i32>* %addr, i32 4, <4 x i1>%mask, <4 x i32>%dst)
+  %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr, i32 4, <4 x i1>%mask, <4 x i32>%dst)
   ret <4 x i32> %res
 }
 
@@ -23,7 +23,7 @@ define <4 x i32> @test2(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %dst) {
 ; AVX2: Found an estimated cost of 4 {{.*}}.masked
 define void @test3(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %val) {
   %mask = icmp eq <4 x i32> %trigger, zeroinitializer
-  call void @llvm.masked.store.v4i32(<4 x i32>%val, <4 x i32>* %addr, i32 4, <4 x i1>%mask)
+  call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>%val, <4 x i32>* %addr, i32 4, <4 x i1>%mask)
   ret void
 }
 
@@ -31,7 +31,7 @@ define void @test3(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %val) {
 ; AVX2: Found an estimated cost of 4 {{.*}}.masked
 define <8 x float> @test4(<8 x i32> %trigger, <8 x float>* %addr, <8 x float> %dst) {
   %mask = icmp eq <8 x i32> %trigger, zeroinitializer
-  %res = call <8 x float> @llvm.masked.load.v8f32(<8 x float>* %addr, i32 4, <8 x i1>%mask, <8 x float>%dst)
+  %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1>%mask, <8 x float>%dst)
   ret <8 x float> %res
 }
 
@@ -39,7 +39,7 @@ define <8 x float> @test4(<8 x i32> %trigger, <8 x float>* %addr, <8 x float> %d
 ; AVX2: Found an estimated cost of 5 {{.*}}.masked
 define void @test5(<2 x i32> %trigger, <2 x float>* %addr, <2 x float> %val) {
   %mask = icmp eq <2 x i32> %trigger, zeroinitializer
-  call void @llvm.masked.store.v2f32(<2 x float>%val, <2 x float>* %addr, i32 4, <2 x i1>%mask)
+  call void @llvm.masked.store.v2f32.p0v2f32(<2 x float>%val, <2 x float>* %addr, i32 4, <2 x i1>%mask)
   ret void
 }
 
@@ -47,7 +47,7 @@ define void @test5(<2 x i32> %trigger, <2 x float>* %addr, <2 x float> %val) {
 ; AVX2: Found an estimated cost of 6 {{.*}}.masked
 define void @test6(<2 x i32> %trigger, <2 x i32>* %addr, <2 x i32> %val) {
   %mask = icmp eq <2 x i32> %trigger, zeroinitializer
-  call void @llvm.masked.store.v2i32(<2 x i32>%val, <2 x i32>* %addr, i32 4, <2 x i1>%mask)
+  call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32>%val, <2 x i32>* %addr, i32 4, <2 x i1>%mask)
   ret void
 }
 
@@ -55,7 +55,7 @@ define void @test6(<2 x i32> %trigger, <2 x i32>* %addr, <2 x i32> %val) {
 ; AVX2: Found an estimated cost of 5 {{.*}}.masked
 define <2 x float> @test7(<2 x i32> %trigger, <2 x float>* %addr, <2 x float> %dst) {
   %mask = icmp eq <2 x i32> %trigger, zeroinitializer
-  %res = call <2 x float> @llvm.masked.load.v2f32(<2 x float>* %addr, i32 4, <2 x i1>%mask, <2 x float>%dst)
+  %res = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* %addr, i32 4, <2 x i1>%mask, <2 x float>%dst)
   ret <2 x float> %res
 }
 
@@ -63,7 +63,7 @@ define <2 x float> @test7(<2 x i32> %trigger, <2 x float>* %addr, <2 x float> %d
 ; AVX2: Found an estimated cost of 6 {{.*}}.masked
 define <2 x i32> @test8(<2 x i32> %trigger, <2 x i32>* %addr, <2 x i32> %dst) {
   %mask = icmp eq <2 x i32> %trigger, zeroinitializer
-  %res = call <2 x i32> @llvm.masked.load.v2i32(<2 x i32>* %addr, i32 4, <2 x i1>%mask, <2 x i32>%dst)
+  %res = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* %addr, i32 4, <2 x i1>%mask, <2 x i32>%dst)
   ret <2 x i32> %res
 }
 
@@ -279,24 +279,22 @@ declare void @llvm.masked.scatter.v4i32(<4 x i32> %a1, <4 x i32*> %ptr, i32, <4
 declare void @llvm.masked.scatter.v16i32(<16 x i32>%val, <16 x i32*> %gep.random, i32, <16 x i1> %imask)
 declare <16 x float> @llvm.masked.gather.v16f32(<16 x float*> %gep.v, i32, <16 x i1> %mask, <16 x float>)
 
-declare <16 x i32> @llvm.masked.load.v16i32(<16 x i32>*, i32, <16 x i1>, <16 x i32>)
+declare <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>*, i32, <16 x i1>, <16 x i32>)
-declare <4 x i32> @llvm.masked.load.v4i32(<4 x i32>*, i32, <4 x i1>, <4 x i32>)
+declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32, <4 x i1>, <4 x i32>)
-declare <2 x i32> @llvm.masked.load.v2i32(<2 x i32>*, i32, <2 x i1>, <2 x i32>)
+declare <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>*, i32, <2 x i1>, <2 x i32>)
-declare void @llvm.masked.store.v16i32(<16 x i32>, <16 x i32>*, i32, <16 x i1>)
+declare void @llvm.masked.store.v16i32.p0v16i32(<16 x i32>, <16 x i32>*, i32, <16 x i1>)
-declare void @llvm.masked.store.v8i32(<8 x i32>, <8 x i32>*, i32, <8 x i1>)
+declare void @llvm.masked.store.v8i32.p0v8i32(<8 x i32>, <8 x i32>*, i32, <8 x i1>)
-declare void @llvm.masked.store.v4i32(<4 x i32>, <4 x i32>*, i32, <4 x i1>)
+declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32, <4 x i1>)
-declare void @llvm.masked.store.v2f32(<2 x float>, <2 x float>*, i32, <2 x i1>)
+declare void @llvm.masked.store.v2f32.p0v2f32(<2 x float>, <2 x float>*, i32, <2 x i1>)
-declare void @llvm.masked.store.v2i32(<2 x i32>, <2 x i32>*, i32, <2 x i1>)
+declare void @llvm.masked.store.v2i32.p0v2i32(<2 x i32>, <2 x i32>*, i32, <2 x i1>)
-declare void @llvm.masked.store.v16f32(<16 x float>, <16 x float>*, i32, <16 x i1>)
+declare void @llvm.masked.store.v16f32.p0v16f32(<16 x float>, <16 x float>*, i32, <16 x i1>)
-declare void @llvm.masked.store.v16f32p(<16 x float>*, <16 x float>**, i32, <16 x i1>)
+declare <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>*, i32, <16 x i1>, <16 x float>)
-declare <16 x float> @llvm.masked.load.v16f32(<16 x float>*, i32, <16 x i1>, <16 x float>)
+declare <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>*, i32, <8 x i1>, <8 x float>)
-declare <8 x float> @llvm.masked.load.v8f32(<8 x float>*, i32, <8 x i1>, <8 x float>)
+declare <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>*, i32, <4 x i1>, <4 x float>)
-declare <4 x float> @llvm.masked.load.v4f32(<4 x float>*, i32, <4 x i1>, <4 x float>)
+declare <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>*, i32, <2 x i1>, <2 x float>)
-declare <2 x float> @llvm.masked.load.v2f32(<2 x float>*, i32, <2 x i1>, <2 x float>)
+declare <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>*, i32, <8 x i1>, <8 x double>)
-declare <8 x double> @llvm.masked.load.v8f64(<8 x double>*, i32, <8 x i1>, <8 x double>)
+declare <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>*, i32, <4 x i1>, <4 x double>)
-declare <4 x double> @llvm.masked.load.v4f64(<4 x double>*, i32, <4 x i1>, <4 x double>)
+declare <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>*, i32, <2 x i1>, <2 x double>)
-declare <2 x double> @llvm.masked.load.v2f64(<2 x double>*, i32, <2 x i1>, <2 x double>)
+declare void @llvm.masked.store.v8f64.p0v8f64(<8 x double>, <8 x double>*, i32, <8 x i1>)
-declare void @llvm.masked.store.v8f64(<8 x double>, <8 x double>*, i32, <8 x i1>)
+declare void @llvm.masked.store.v2f64.p0v2f64(<2 x double>, <2 x double>*, i32, <2 x i1>)
-declare void @llvm.masked.store.v2f64(<2 x double>, <2 x double>*, i32, <2 x i1>)
+declare void @llvm.masked.store.v2i64.p0v2i64(<2 x i64>, <2 x i64>*, i32, <2 x i1>)
-declare void @llvm.masked.store.v2i64(<2 x i64>, <2 x i64>*, i32, <2 x i1>)
-

llvm/test/Assembler/auto_upgrade_intrinsics.ll

@@ -54,7 +54,24 @@ entry:
 define i32 @test.objectsize() {
 ; CHECK-LABEL: @test.objectsize(
 ; CHECK: @llvm.objectsize.i32.p0i8
-; CHECK-DAG: declare i32 @llvm.objectsize.i32.p0i8
   %s = call i32 @llvm.objectsize.i32(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i1 false)
   ret i32 %s
 }
+
+declare <2 x double> @llvm.masked.load.v2f64(<2 x double>* %ptrs, i32, <2 x i1> %mask, <2 x double> %src0)
+
+define <2 x double> @tests.masked.load(<2 x double>* %ptr, <2 x i1> %mask, <2 x double> %passthru)  {
+; CHECK-LABEL: @tests.masked.load(
+; CHECK: @llvm.masked.load.v2f64.p0v2f64
+  %res = call <2 x double> @llvm.masked.load.v2f64(<2 x double>* %ptr, i32 1, <2 x i1> %mask, <2 x double> %passthru)
+  ret <2 x double> %res
+}
+
+declare void @llvm.masked.store.v2f64(<2 x double> %val, <2 x double>* %ptrs, i32, <2 x i1> %mask)
+
+define void @tests.masked.store(<2 x double>* %ptr, <2 x i1> %mask, <2 x double> %val)  {
+; CHECK-LABEL: @tests.masked.store(
+; CHECK: @llvm.masked.store.v2f64.p0v2f64
+  call void @llvm.masked.store.v2f64(<2 x double> %val, <2 x double>* %ptr, i32 3, <2 x i1> %mask)
+  ret void
+}

llvm/test/CodeGen/X86/avx512-bugfix-26264.ll

@@ -18,7 +18,7 @@ define <32 x double> @test_load_32f64(<32 x double>* %ptrs, <32 x i1> %mask, <32
 ; AVX512BW-NEXT:    vmovaps %zmm3, %zmm2
 ; AVX512BW-NEXT:    vmovaps %zmm4, %zmm3
 ; AVX512BW-NEXT:    retq
-  %res = call <32 x double> @llvm.masked.load.v32f64(<32 x double>* %ptrs, i32 4, <32 x i1> %mask, <32 x double> %src0)
+  %res = call <32 x double> @llvm.masked.load.v32f64.p0v32f64(<32 x double>* %ptrs, i32 4, <32 x i1> %mask, <32 x double> %src0)
   ret <32 x double> %res
 }
 
@@ -39,9 +39,9 @@ define <32 x i64> @test_load_32i64(<32 x i64>* %ptrs, <32 x i1> %mask, <32 x i64
 ; AVX512BW-NEXT:    vmovaps %zmm3, %zmm2
 ; AVX512BW-NEXT:    vmovaps %zmm4, %zmm3
 ; AVX512BW-NEXT:    retq
-  %res = call <32 x i64> @llvm.masked.load.v32i64(<32 x i64>* %ptrs, i32 4, <32 x i1> %mask, <32 x i64> %src0)
+  %res = call <32 x i64> @llvm.masked.load.v32i64.p0v32i64(<32 x i64>* %ptrs, i32 4, <32 x i1> %mask, <32 x i64> %src0)
   ret <32 x i64> %res
 }
 
-declare <32 x i64> @llvm.masked.load.v32i64(<32 x i64>* %ptrs, i32, <32 x i1> %mask, <32 x i64> %src0)
+declare <32 x i64> @llvm.masked.load.v32i64.p0v32i64(<32 x i64>* %ptrs, i32, <32 x i1> %mask, <32 x i64> %src0)
-declare <32 x double> @llvm.masked.load.v32f64(<32 x double>* %ptrs, i32, <32 x i1> %mask, <32 x double> %src0)
+declare <32 x double> @llvm.masked.load.v32f64.p0v32f64(<32 x double>* %ptrs, i32, <32 x i1> %mask, <32 x double> %src0)

llvm/test/CodeGen/X86/masked_memop.ll

@@ -40,7 +40,7 @@ define <16 x i32> @test1(<16 x i32> %trigger, <16 x i32>* %addr) {
 ; AVX512-NEXT:    vmovdqu32 (%rdi), %zmm0 {%k1} {z}
 ; AVX512-NEXT:    retq
   %mask = icmp eq <16 x i32> %trigger, zeroinitializer
-  %res = call <16 x i32> @llvm.masked.load.v16i32(<16 x i32>* %addr, i32 4, <16 x i1>%mask, <16 x i32>undef)
+  %res = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* %addr, i32 4, <16 x i1>%mask, <16 x i32>undef)
   ret <16 x i32> %res
 }
 
@@ -76,7 +76,7 @@ define <16 x i32> @test2(<16 x i32> %trigger, <16 x i32>* %addr) {
 ; AVX512-NEXT:    vmovdqu32 (%rdi), %zmm0 {%k1} {z}
 ; AVX512-NEXT:    retq
   %mask = icmp eq <16 x i32> %trigger, zeroinitializer
-  %res = call <16 x i32> @llvm.masked.load.v16i32(<16 x i32>* %addr, i32 4, <16 x i1>%mask, <16 x i32>zeroinitializer)
+  %res = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* %addr, i32 4, <16 x i1>%mask, <16 x i32>zeroinitializer)
   ret <16 x i32> %res
 }
 
@@ -114,7 +114,7 @@ define void @test3(<16 x i32> %trigger, <16 x i32>* %addr, <16 x i32> %val) {
 ; AVX512-NEXT:    vmovdqu32 %zmm1, (%rdi) {%k1}
 ; AVX512-NEXT:    retq
   %mask = icmp eq <16 x i32> %trigger, zeroinitializer
-  call void @llvm.masked.store.v16i32(<16 x i32>%val, <16 x i32>* %addr, i32 4, <16 x i1>%mask)
+  call void @llvm.masked.store.v16i32.p0v16i32(<16 x i32>%val, <16 x i32>* %addr, i32 4, <16 x i1>%mask)
   ret void
 }
 
@@ -155,7 +155,7 @@ define <16 x float> @test4(<16 x i32> %trigger, <16 x float>* %addr, <16 x float
 ; AVX512-NEXT:    vmovaps %zmm1, %zmm0
 ; AVX512-NEXT:    retq
   %mask = icmp eq <16 x i32> %trigger, zeroinitializer
-  %res = call <16 x float> @llvm.masked.load.v16f32(<16 x float>* %addr, i32 4, <16 x i1>%mask, <16 x float> %dst)
+  %res = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>* %addr, i32 4, <16 x i1>%mask, <16 x float> %dst)
   ret <16 x float> %res
 }
 
@@ -210,7 +210,7 @@ define <8 x double> @test5(<8 x i32> %trigger, <8 x double>* %addr, <8 x double>
 ; SKX-NEXT:    vmovaps %zmm1, %zmm0
 ; SKX-NEXT:    retq
   %mask = icmp eq <8 x i32> %trigger, zeroinitializer
-  %res = call <8 x double> @llvm.masked.load.v8f64(<8 x double>* %addr, i32 4, <8 x i1>%mask, <8 x double>%dst)
+  %res = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* %addr, i32 4, <8 x i1>%mask, <8 x double>%dst)
   ret <8 x double> %res
 }
 
@@ -239,7 +239,7 @@ define <2 x double> @test6(<2 x i64> %trigger, <2 x double>* %addr, <2 x double>
 ; SKX-NEXT:    vmovaps %zmm1, %zmm0
 ; SKX-NEXT:    retq
   %mask = icmp eq <2 x i64> %trigger, zeroinitializer
-  %res = call <2 x double> @llvm.masked.load.v2f64(<2 x double>* %addr, i32 4, <2 x i1>%mask, <2 x double>%dst)
+  %res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %addr, i32 4, <2 x i1>%mask, <2 x double>%dst)
   ret <2 x double> %res
 }
 
@@ -268,7 +268,7 @@ define <4 x float> @test7(<4 x i32> %trigger, <4 x float>* %addr, <4 x float> %d
 ; SKX-NEXT:    vmovaps %zmm1, %zmm0
 ; SKX-NEXT:    retq
   %mask = icmp eq <4 x i32> %trigger, zeroinitializer
-  %res = call <4 x float> @llvm.masked.load.v4f32(<4 x float>* %addr, i32 4, <4 x i1>%mask, <4 x float>%dst)
+  %res = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %addr, i32 4, <4 x i1>%mask, <4 x float>%dst)
   ret <4 x float> %res
 }
 
@@ -305,7 +305,7 @@ define <4 x i32> @test8(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %dst) {
 ; SKX-NEXT:    vmovaps %zmm1, %zmm0
 ; SKX-NEXT:    retq
   %mask = icmp eq <4 x i32> %trigger, zeroinitializer
-  %res = call <4 x i32> @llvm.masked.load.v4i32(<4 x i32>* %addr, i32 4, <4 x i1>%mask, <4 x i32>%dst)
+  %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr, i32 4, <4 x i1>%mask, <4 x i32>%dst)
   ret <4 x i32> %res
 }
 
@@ -338,7 +338,7 @@ define void @test9(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %val) {
 ; SKX-NEXT:    vmovdqu32 %xmm1, (%rdi) {%k1}
 ; SKX-NEXT:    retq
   %mask = icmp eq <4 x i32> %trigger, zeroinitializer
-  call void @llvm.masked.store.v4i32(<4 x i32>%val, <4 x i32>* %addr, i32 4, <4 x i1>%mask)
+  call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>%val, <4 x i32>* %addr, i32 4, <4 x i1>%mask)
   ret void
 }
 
@@ -381,7 +381,7 @@ define <4 x double> @test10(<4 x i32> %trigger, <4 x double>* %addr, <4 x double
 ; SKX-NEXT:    vmovaps %zmm1, %zmm0
 ; SKX-NEXT:    retq
   %mask = icmp eq <4 x i32> %trigger, zeroinitializer
-  %res = call <4 x double> @llvm.masked.load.v4f64(<4 x double>* %addr, i32 32, <4 x i1>%mask, <4 x double>%dst)
+  %res = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* %addr, i32 32, <4 x i1>%mask, <4 x double>%dst)
   ret <4 x double> %res
 }
 
@@ -420,7 +420,7 @@ define <4 x double> @test10b(<4 x i32> %trigger, <4 x double>* %addr, <4 x doubl
 ; SKX-NEXT:    vmovapd (%rdi), %ymm0 {%k1} {z}
 ; SKX-NEXT:    retq
   %mask = icmp eq <4 x i32> %trigger, zeroinitializer
-  %res = call <4 x double> @llvm.masked.load.v4f64(<4 x double>* %addr, i32 32, <4 x i1>%mask, <4 x double>zeroinitializer)
+  %res = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* %addr, i32 32, <4 x i1>%mask, <4 x double>zeroinitializer)
   ret <4 x double> %res
 }
 
@@ -462,7 +462,7 @@ define <8 x float> @test11a(<8 x i32> %trigger, <8 x float>* %addr, <8 x float>
 ; SKX-NEXT:    vmovaps %zmm1, %zmm0
 ; SKX-NEXT:    retq
   %mask = icmp eq <8 x i32> %trigger, zeroinitializer
-  %res = call <8 x float> @llvm.masked.load.v8f32(<8 x float>* %addr, i32 32, <8 x i1>%mask, <8 x float>%dst)
+  %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 32, <8 x i1>%mask, <8 x float>%dst)
   ret <8 x float> %res
 }
 
@@ -507,7 +507,7 @@ define <8 x i32> @test11b(<8 x i1> %mask, <8 x i32>* %addr, <8 x i32> %dst) {
 ; SKX-NEXT:    vmovdqu32 (%rdi), %ymm1 {%k1}
 ; SKX-NEXT:    vmovaps %zmm1, %zmm0
 ; SKX-NEXT:    retq
-  %res = call <8 x i32> @llvm.masked.load.v8i32(<8 x i32>* %addr, i32 4, <8 x i1>%mask, <8 x i32>%dst)
+  %res = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* %addr, i32 4, <8 x i1>%mask, <8 x i32>%dst)
   ret <8 x i32> %res
 }
 
@@ -548,7 +548,7 @@ define <8 x float> @test11c(<8 x i1> %mask, <8 x float>* %addr) {
 ; SKX-NEXT:    vpmovw2m %xmm0, %k1
 ; SKX-NEXT:    vmovaps (%rdi), %ymm0 {%k1} {z}
 ; SKX-NEXT:    retq
-  %res = call <8 x float> @llvm.masked.load.v8f32(<8 x float>* %addr, i32 32, <8 x i1> %mask, <8 x float> zeroinitializer)
+  %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 32, <8 x i1> %mask, <8 x float> zeroinitializer)
   ret <8 x float> %res
 }
 
@@ -589,7 +589,7 @@ define <8 x i32> @test11d(<8 x i1> %mask, <8 x i32>* %addr) {
 ; SKX-NEXT:    vpmovw2m %xmm0, %k1
 ; SKX-NEXT:    vmovdqu32 (%rdi), %ymm0 {%k1} {z}
 ; SKX-NEXT:    retq
-  %res = call <8 x i32> @llvm.masked.load.v8i32(<8 x i32>* %addr, i32 4, <8 x i1> %mask, <8 x i32> zeroinitializer)
+  %res = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* %addr, i32 4, <8 x i1> %mask, <8 x i32> zeroinitializer)
   ret <8 x i32> %res
 }
 
@@ -629,7 +629,7 @@ define void @test12(<8 x i32> %trigger, <8 x i32>* %addr, <8 x i32> %val) {
 ; SKX-NEXT:    vmovdqu32 %ymm1, (%rdi) {%k1}
 ; SKX-NEXT:    retq
   %mask = icmp eq <8 x i32> %trigger, zeroinitializer
-  call void @llvm.masked.store.v8i32(<8 x i32>%val, <8 x i32>* %addr, i32 4, <8 x i1>%mask)
+  call void @llvm.masked.store.v8i32.p0v8i32(<8 x i32>%val, <8 x i32>* %addr, i32 4, <8 x i1>%mask)
   ret void
 }
 
@@ -667,7 +667,7 @@ define void @test13(<16 x i32> %trigger, <16 x float>* %addr, <16 x float> %val)
 ; AVX512-NEXT:    vmovups %zmm1, (%rdi) {%k1}
 ; AVX512-NEXT:    retq
   %mask = icmp eq <16 x i32> %trigger, zeroinitializer
-  call void @llvm.masked.store.v16f32(<16 x float>%val, <16 x float>* %addr, i32 4, <16 x i1>%mask)
+  call void @llvm.masked.store.v16f32.p0v16f32(<16 x float>%val, <16 x float>* %addr, i32 4, <16 x i1>%mask)
   ret void
 }
 
@@ -712,7 +712,7 @@ define void @test14(<2 x i32> %trigger, <2 x float>* %addr, <2 x float> %val) {
 ; SKX-NEXT:    vmovups %xmm1, (%rdi) {%k1}
 ; SKX-NEXT:    retq
   %mask = icmp eq <2 x i32> %trigger, zeroinitializer
-  call void @llvm.masked.store.v2f32(<2 x float>%val, <2 x float>* %addr, i32 4, <2 x i1>%mask)
+  call void @llvm.masked.store.v2f32.p0v2f32(<2 x float>%val, <2 x float>* %addr, i32 4, <2 x i1>%mask)
   ret void
 }
 
@@ -758,7 +758,7 @@ define void @test15(<2 x i32> %trigger, <2 x i32>* %addr, <2 x i32> %val) {
 ; SKX-NEXT:    vpmovqd %xmm1, (%rdi) {%k1}
 ; SKX-NEXT:    retq
   %mask = icmp eq <2 x i32> %trigger, zeroinitializer
-  call void @llvm.masked.store.v2i32(<2 x i32>%val, <2 x i32>* %addr, i32 4, <2 x i1>%mask)
+  call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32>%val, <2 x i32>* %addr, i32 4, <2 x i1>%mask)
   ret void
 }
 
@@ -807,7 +807,7 @@ define <2 x float> @test16(<2 x i32> %trigger, <2 x float>* %addr, <2 x float> %
 ; SKX-NEXT:    vmovaps %zmm1, %zmm0
 ; SKX-NEXT:    retq
   %mask = icmp eq <2 x i32> %trigger, zeroinitializer
-  %res = call <2 x float> @llvm.masked.load.v2f32(<2 x float>* %addr, i32 4, <2 x i1>%mask, <2 x float>%dst)
+  %res = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* %addr, i32 4, <2 x i1>%mask, <2 x float>%dst)
   ret <2 x float> %res
 }
 
@@ -863,7 +863,7 @@ define <2 x i32> @test17(<2 x i32> %trigger, <2 x i32>* %addr, <2 x i32> %dst) {
 ; SKX-NEXT:    vpmovsxdq %xmm0, %xmm0
 ; SKX-NEXT:    retq
   %mask = icmp eq <2 x i32> %trigger, zeroinitializer
-  %res = call <2 x i32> @llvm.masked.load.v2i32(<2 x i32>* %addr, i32 4, <2 x i1>%mask, <2 x i32>%dst)
+  %res = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* %addr, i32 4, <2 x i1>%mask, <2 x i32>%dst)
   ret <2 x i32> %res
 }
 
@@ -908,7 +908,7 @@ define <2 x float> @test18(<2 x i32> %trigger, <2 x float>* %addr) {
 ; SKX-NEXT:    vmovups (%rdi), %xmm0 {%k1} {z}
 ; SKX-NEXT:    retq
   %mask = icmp eq <2 x i32> %trigger, zeroinitializer
-  %res = call <2 x float> @llvm.masked.load.v2f32(<2 x float>* %addr, i32 4, <2 x i1>%mask, <2 x float>undef)
+  %res = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* %addr, i32 4, <2 x i1>%mask, <2 x float>undef)
   ret <2 x float> %res
 }
 
@@ -931,7 +931,7 @@ define <4 x float> @load_all(<4 x i32> %trigger, <4 x float>* %addr) {
 ; SKX-NEXT:    vmovups (%rdi), %xmm0 {%k1} {z}
 ; SKX-NEXT:    retq
   %mask = icmp eq <4 x i32> %trigger, zeroinitializer
-  %res = call <4 x float> @llvm.masked.load.v4f32(<4 x float>* %addr, i32 4, <4 x i1><i1 true, i1 true, i1 true, i1 true>, <4 x float>undef)
+  %res = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %addr, i32 4, <4 x i1><i1 true, i1 true, i1 true, i1 true>, <4 x float>undef)
   ret <4 x float> %res
 }
 
@@ -960,7 +960,7 @@ define <4 x float> @mload_constmask_v4f32(<4 x float>* %addr, <4 x float> %dst)
 ; SKX-NEXT:    kmovw %eax, %k1
 ; SKX-NEXT:    vmovups (%rdi), %xmm0 {%k1}
 ; SKX-NEXT:    retq
-  %res = call <4 x float> @llvm.masked.load.v4f32(<4 x float>* %addr, i32 4, <4 x i1> <i1 1, i1 0, i1 1, i1 1>, <4 x float> %dst)
+  %res = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %addr, i32 4, <4 x i1> <i1 1, i1 0, i1 1, i1 1>, <4 x float> %dst)
   ret <4 x float> %res
 }
 
@@ -994,7 +994,7 @@ define <4 x i32> @mload_constmask_v4i32(<4 x i32>* %addr, <4 x i32> %dst) {
 ; SKX-NEXT:    kmovw %eax, %k1
 ; SKX-NEXT:    vmovdqu32 (%rdi), %xmm0 {%k1}
 ; SKX-NEXT:    retq
-  %res = call <4 x i32> @llvm.masked.load.v4i32(<4 x i32>* %addr, i32 4, <4 x i1> <i1 0, i1 1, i1 1, i1 1>, <4 x i32> %dst)
+  %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr, i32 4, <4 x i1> <i1 0, i1 1, i1 1, i1 1>, <4 x i32> %dst)
   ret <4 x i32> %res
 }
 
@@ -1021,7 +1021,7 @@ define <8 x float> @mload_constmask_v8f32(<8 x float>* %addr, <8 x float> %dst)
 ; SKX-NEXT:    kmovw %eax, %k1
 ; SKX-NEXT:    vmovups (%rdi), %ymm0 {%k1}
 ; SKX-NEXT:    retq
-  %res = call <8 x float> @llvm.masked.load.v8f32(<8 x float>* %addr, i32 4, <8 x i1> <i1 1, i1 1, i1 1, i1 0, i1 0, i1 0, i1 0, i1 0>, <8 x float> %dst)
+  %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1> <i1 1, i1 1, i1 1, i1 0, i1 0, i1 0, i1 0, i1 0>, <8 x float> %dst)
   ret <8 x float> %res
 }
 
@@ -1046,7 +1046,7 @@ define <4 x double> @mload_constmask_v4f64(<4 x double>* %addr, <4 x double> %ds
 ; SKX-NEXT:    kmovw %eax, %k1
 ; SKX-NEXT:    vmovupd (%rdi), %ymm0 {%k1}
 ; SKX-NEXT:    retq
-  %res = call <4 x double> @llvm.masked.load.v4f64(<4 x double>* %addr, i32 4, <4 x i1> <i1 1, i1 1, i1 1, i1 0>, <4 x double> %dst)
+  %res = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* %addr, i32 4, <4 x i1> <i1 1, i1 1, i1 1, i1 0>, <4 x double> %dst)
   ret <4 x double> %res
 }
 
@@ -1080,7 +1080,7 @@ define <8 x i32> @mload_constmask_v8i32(<8 x i32>* %addr, <8 x i32> %dst) {
 ; SKX-NEXT:    kmovw %eax, %k1
 ; SKX-NEXT:    vmovdqu32 (%rdi), %ymm0 {%k1}
 ; SKX-NEXT:    retq
-  %res = call <8 x i32> @llvm.masked.load.v8i32(<8 x i32>* %addr, i32 4, <8 x i1> <i1 1, i1 1, i1 1, i1 0, i1 0, i1 0, i1 0, i1 1>, <8 x i32> %dst)
+  %res = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* %addr, i32 4, <8 x i1> <i1 1, i1 1, i1 1, i1 0, i1 0, i1 0, i1 0, i1 1>, <8 x i32> %dst)
   ret <8 x i32> %res
 }
 
@@ -1112,7 +1112,7 @@ define <4 x i64> @mload_constmask_v4i64(<4 x i64>* %addr, <4 x i64> %dst) {
 ; SKX-NEXT:    kmovw %eax, %k1
 ; SKX-NEXT:    vmovdqu64 (%rdi), %ymm0 {%k1}
 ; SKX-NEXT:    retq
-  %res = call <4 x i64> @llvm.masked.load.v4i64(<4 x i64>* %addr, i32 4, <4 x i1> <i1 1, i1 0, i1 0, i1 1>, <4 x i64> %dst)
+  %res = call <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>* %addr, i32 4, <4 x i1> <i1 1, i1 0, i1 0, i1 1>, <4 x i64> %dst)
   ret <4 x i64> %res
 }
 
@@ -1135,7 +1135,7 @@ define <8 x double> @mload_constmask_v8f64(<8 x double>* %addr, <8 x double> %ds
 ; AVX512-NEXT:    kmovw %eax, %k1
 ; AVX512-NEXT:    vmovupd (%rdi), %zmm0 {%k1}
 ; AVX512-NEXT:    retq
-  %res = call <8 x double> @llvm.masked.load.v8f64(<8 x double>* %addr, i32 4, <8 x i1> <i1 1, i1 1, i1 1, i1 0, i1 0, i1 0, i1 0, i1 1>, <8 x double> %dst)
+  %res = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* %addr, i32 4, <8 x i1> <i1 1, i1 1, i1 1, i1 0, i1 0, i1 0, i1 0, i1 1>, <8 x double> %dst)
   ret <8 x double> %res
 }
 
@@ -1160,7 +1160,7 @@ define <4 x double> @mload_constmask_v4f64_undef_passthrough(<4 x double>* %addr
 ; SKX-NEXT:    kmovw %eax, %k1
 ; SKX-NEXT:    vmovupd (%rdi), %ymm0 {%k1} {z}
 ; SKX-NEXT:    retq
-  %res = call <4 x double> @llvm.masked.load.v4f64(<4 x double>* %addr, i32 4, <4 x i1> <i1 1, i1 1, i1 1, i1 0>, <4 x double> undef)
+  %res = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* %addr, i32 4, <4 x i1> <i1 1, i1 1, i1 1, i1 0>, <4 x double> undef)
   ret <4 x double> %res
 }
 
@@ -1189,7 +1189,7 @@ define <4 x i64> @mload_constmask_v4i64_undef_passthrough(<4 x i64>* %addr) {
 ; SKX-NEXT:    kmovw %eax, %k1
 ; SKX-NEXT:    vmovdqu64 (%rdi), %ymm0 {%k1} {z}
 ; SKX-NEXT:    retq
-  %res = call <4 x i64> @llvm.masked.load.v4i64(<4 x i64>* %addr, i32 4, <4 x i1> <i1 0, i1 1, i1 1, i1 0>, <4 x i64> undef)
+  %res = call <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>* %addr, i32 4, <4 x i1> <i1 0, i1 1, i1 1, i1 0>, <4 x i64> undef)
   ret <4 x i64> %res
 }
 
@@ -1218,7 +1218,7 @@ define void @test21(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %val) {
 ; SKX-NEXT:    vmovdqu32 %xmm1, (%rdi) {%k1}
 ; SKX-NEXT:    retq
   %mask = icmp eq <4 x i32> %trigger, zeroinitializer
-  call void @llvm.masked.store.v4i32(<4 x i32>%val, <4 x i32>* %addr, i32 4, <4 x i1><i1 true, i1 true, i1 true, i1 true>)
+  call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>%val, <4 x i32>* %addr, i32 4, <4 x i1><i1 true, i1 true, i1 true, i1 true>)
   ret void
 }
 
@@ -1234,7 +1234,7 @@ define void @one_mask_bit_set1(<4 x i32>* %addr, <4 x i32> %val) {
 ; AVX512:       ## BB#0:
 ; AVX512-NEXT:    vmovd %xmm0, (%rdi)
 ; AVX512-NEXT:    retq
-  call void @llvm.masked.store.v4i32(<4 x i32> %val, <4 x i32>* %addr, i32 4, <4 x i1><i1 true, i1 false, i1 false, i1 false>)
+  call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %val, <4 x i32>* %addr, i32 4, <4 x i1><i1 true, i1 false, i1 false, i1 false>)
   ret void
 }
 
@@ -1250,7 +1250,7 @@ define void @one_mask_bit_set2(<4 x float>* %addr, <4 x float> %val) {
 ; AVX512:       ## BB#0:
 ; AVX512-NEXT:    vextractps $2, %xmm0, 8(%rdi)
 ; AVX512-NEXT:    retq
-  call void @llvm.masked.store.v4f32(<4 x float> %val, <4 x float>* %addr, i32 4, <4 x i1><i1 false, i1 false, i1 true, i1 false>)
+  call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> %val, <4 x float>* %addr, i32 4, <4 x i1><i1 false, i1 false, i1 true, i1 false>)
   ret void
 }
 
@@ -1269,7 +1269,7 @@ define void @one_mask_bit_set3(<4 x i64>* %addr, <4 x i64> %val) {
 ; AVX512-NEXT:    vextractf128 $1, %ymm0, %xmm0
 ; AVX512-NEXT:    vmovq %xmm0, 16(%rdi)
 ; AVX512-NEXT:    retq
-  call void @llvm.masked.store.v4i64(<4 x i64> %val, <4 x i64>* %addr, i32 4, <4 x i1><i1 false, i1 false, i1 true, i1 false>)
+  call void @llvm.masked.store.v4i64.p0v4i64(<4 x i64> %val, <4 x i64>* %addr, i32 4, <4 x i1><i1 false, i1 false, i1 true, i1 false>)
   ret void
 }
 
@@ -1288,7 +1288,7 @@ define void @one_mask_bit_set4(<4 x double>* %addr, <4 x double> %val) {
 ; AVX512-NEXT:    vextractf128 $1, %ymm0, %xmm0
 ; AVX512-NEXT:    vmovhpd %xmm0, 24(%rdi)
 ; AVX512-NEXT:    retq
-  call void @llvm.masked.store.v4f64(<4 x double> %val, <4 x double>* %addr, i32 4, <4 x i1><i1 false, i1 false, i1 false, i1 true>)
+  call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> %val, <4 x double>* %addr, i32 4, <4 x i1><i1 false, i1 false, i1 false, i1 true>)
   ret void
 }
 
@@ -1307,7 +1307,7 @@ define void @one_mask_bit_set5(<8 x double>* %addr, <8 x double> %val) {
 ; AVX512-NEXT:    vextractf32x4 $3, %zmm0, %xmm0
 ; AVX512-NEXT:    vmovlpd %xmm0, 48(%rdi)
 ; AVX512-NEXT:    retq
-  call void @llvm.masked.store.v8f64(<8 x double> %val, <8 x double>* %addr, i32 4, <8 x i1><i1 false, i1 false, i1 false, i1 false, i1 false, i1 false, i1 true, i1 false>)
+  call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> %val, <8 x double>* %addr, i32 4, <8 x i1><i1 false, i1 false, i1 false, i1 false, i1 false, i1 false, i1 true, i1 false>)
   ret void
 }
 
@@ -1323,7 +1323,7 @@ define <4 x i32> @load_one_mask_bit_set1(<4 x i32>* %addr, <4 x i32> %val) {
 ; AVX512:       ## BB#0:
 ; AVX512-NEXT:    vpinsrd $0, (%rdi), %xmm0, %xmm0
 ; AVX512-NEXT:    retq
-  %res = call <4 x i32> @llvm.masked.load.v4i32(<4 x i32>* %addr, i32 4, <4 x i1><i1 true, i1 false, i1 false, i1 false>, <4 x i32> %val)
+  %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr, i32 4, <4 x i1><i1 true, i1 false, i1 false, i1 false>, <4 x i32> %val)
   ret <4 x i32> %res
 }
 
@@ -1339,7 +1339,7 @@ define <4 x float> @load_one_mask_bit_set2(<4 x float>* %addr, <4 x float> %val)
 ; AVX512:       ## BB#0:
 ; AVX512-NEXT:    vinsertps $32, 8(%rdi), %xmm0, %xmm0 ## xmm0 = xmm0[0,1],mem[0],xmm0[3]
 ; AVX512-NEXT:    retq
-  %res = call <4 x float> @llvm.masked.load.v4f32(<4 x float>* %addr, i32 4, <4 x i1><i1 false, i1 false, i1 true, i1 false>, <4 x float> %val)
+  %res = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %addr, i32 4, <4 x i1><i1 false, i1 false, i1 true, i1 false>, <4 x float> %val)
   ret <4 x float> %res
 }
 
@@ -1373,7 +1373,7 @@ define <4 x i64> @load_one_mask_bit_set3(<4 x i64>* %addr, <4 x i64> %val) {
 ; SKX-NEXT:    vpinsrq $0, 16(%rdi), %xmm1, %xmm1
 ; SKX-NEXT:    vinserti32x4 $1, %xmm1, %ymm0, %ymm0
 ; SKX-NEXT:    retq
-  %res = call <4 x i64> @llvm.masked.load.v4i64(<4 x i64>* %addr, i32 4, <4 x i1><i1 false, i1 false, i1 true, i1 false>, <4 x i64> %val)
+  %res = call <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>* %addr, i32 4, <4 x i1><i1 false, i1 false, i1 true, i1 false>, <4 x i64> %val)
   ret <4 x i64> %res
 }
 
@@ -1400,7 +1400,7 @@ define <4 x double> @load_one_mask_bit_set4(<4 x double>* %addr, <4 x double> %v
 ; SKX-NEXT:    vmovhpd 24(%rdi), %xmm1, %xmm1  ## xmm1 = xmm1[0],mem[0]
 ; SKX-NEXT:    vinsertf32x4 $1, %xmm1, %ymm0, %ymm0
 ; SKX-NEXT:    retq
-  %res = call <4 x double> @llvm.masked.load.v4f64(<4 x double>* %addr, i32 4, <4 x i1><i1 false, i1 false, i1 false, i1 true>, <4 x double> %val)
+  %res = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* %addr, i32 4, <4 x i1><i1 false, i1 false, i1 false, i1 true>, <4 x double> %val)
   ret <4 x double> %res
 }
 
@@ -1421,37 +1421,36 @@ define <8 x double> @load_one_mask_bit_set5(<8 x double>* %addr, <8 x double> %v
 ; AVX512-NEXT:    vmovhpd {{.*#+}} xmm1 = xmm1[0],mem[0]
 ; AVX512-NEXT:    vinsertf32x4 $3, %xmm1, %zmm0, %zmm0
 ; AVX512-NEXT:    retq
-  %res = call <8 x double> @llvm.masked.load.v8f64(<8 x double>* %addr, i32 4, <8 x i1><i1 false, i1 false, i1 false, i1 false, i1 false, i1 false, i1 false, i1 true>, <8 x double> %val)
+  %res = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* %addr, i32 4, <8 x i1><i1 false, i1 false, i1 false, i1 false, i1 false, i1 false, i1 false, i1 true>, <8 x double> %val)
   ret <8 x double> %res
 }
 
-declare <16 x i32> @llvm.masked.load.v16i32(<16 x i32>*, i32, <16 x i1>, <16 x i32>)
+declare <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>*, i32, <16 x i1>, <16 x i32>)
-declare <4 x i32> @llvm.masked.load.v4i32(<4 x i32>*, i32, <4 x i1>, <4 x i32>)
+declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32, <4 x i1>, <4 x i32>)
-declare <2 x i32> @llvm.masked.load.v2i32(<2 x i32>*, i32, <2 x i1>, <2 x i32>)
+declare <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>*, i32, <2 x i1>, <2 x i32>)
-declare <4 x i64> @llvm.masked.load.v4i64(<4 x i64>*, i32, <4 x i1>, <4 x i64>)
+declare <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>*, i32, <4 x i1>, <4 x i64>)
-declare void @llvm.masked.store.v16i32(<16 x i32>, <16 x i32>*, i32, <16 x i1>)
+declare void @llvm.masked.store.v16i32.p0v16i32(<16 x i32>, <16 x i32>*, i32, <16 x i1>)
-declare void @llvm.masked.store.v8i32(<8 x i32>, <8 x i32>*, i32, <8 x i1>)
+declare void @llvm.masked.store.v8i32.p0v8i32(<8 x i32>, <8 x i32>*, i32, <8 x i1>)
-declare void @llvm.masked.store.v4i32(<4 x i32>, <4 x i32>*, i32, <4 x i1>)
+declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32, <4 x i1>)
-declare void @llvm.masked.store.v4i64(<4 x i64>, <4 x i64>*, i32, <4 x i1>)
+declare void @llvm.masked.store.v4i64.p0v4i64(<4 x i64>, <4 x i64>*, i32, <4 x i1>)
-declare void @llvm.masked.store.v2f32(<2 x float>, <2 x float>*, i32, <2 x i1>)
+declare void @llvm.masked.store.v2f32.p0v2f32(<2 x float>, <2 x float>*, i32, <2 x i1>)
-declare void @llvm.masked.store.v2i32(<2 x i32>, <2 x i32>*, i32, <2 x i1>)
+declare void @llvm.masked.store.v2i32.p0v2i32(<2 x i32>, <2 x i32>*, i32, <2 x i1>)
-declare void @llvm.masked.store.v4f32(<4 x float>, <4 x float>*, i32, <4 x i1>)
+declare void @llvm.masked.store.v4f32.p0v4f32(<4 x float>, <4 x float>*, i32, <4 x i1>)
-declare void @llvm.masked.store.v16f32(<16 x float>, <16 x float>*, i32, <16 x i1>)
+declare void @llvm.masked.store.v16f32.p0v16f32(<16 x float>, <16 x float>*, i32, <16 x i1>)
-declare void @llvm.masked.store.v16f32p(<16 x float>*, <16 x float>**, i32, <16 x i1>)
+declare <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>*, i32, <16 x i1>, <16 x float>)
-declare <16 x float> @llvm.masked.load.v16f32(<16 x float>*, i32, <16 x i1>, <16 x float>)
+declare <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>*, i32, <8 x i1>, <8 x float>)
-declare <8 x float> @llvm.masked.load.v8f32(<8 x float>*, i32, <8 x i1>, <8 x float>)
+declare <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>*, i32, <8 x i1>, <8 x i32>)
-declare <8 x i32> @llvm.masked.load.v8i32(<8 x i32>*, i32, <8 x i1>, <8 x i32>)
+declare <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>*, i32, <4 x i1>, <4 x float>)
-declare <4 x float> @llvm.masked.load.v4f32(<4 x float>*, i32, <4 x i1>, <4 x float>)
+declare <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>*, i32, <2 x i1>, <2 x float>)
-declare <2 x float> @llvm.masked.load.v2f32(<2 x float>*, i32, <2 x i1>, <2 x float>)
+declare <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>*, i32, <8 x i1>, <8 x double>)
-declare <8 x double> @llvm.masked.load.v8f64(<8 x double>*, i32, <8 x i1>, <8 x double>)
+declare <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>*, i32, <4 x i1>, <4 x double>)
-declare <4 x double> @llvm.masked.load.v4f64(<4 x double>*, i32, <4 x i1>, <4 x double>)
+declare <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>*, i32, <2 x i1>, <2 x double>)
-declare <2 x double> @llvm.masked.load.v2f64(<2 x double>*, i32, <2 x i1>, <2 x double>)
+declare void @llvm.masked.store.v8f64.p0v8f64(<8 x double>, <8 x double>*, i32, <8 x i1>)
-declare void @llvm.masked.store.v8f64(<8 x double>, <8 x double>*, i32, <8 x i1>)
+declare void @llvm.masked.store.v4f64.p0v4f64(<4 x double>, <4 x double>*, i32, <4 x i1>)
-declare void @llvm.masked.store.v4f64(<4 x double>, <4 x double>*, i32, <4 x i1>)
+declare void @llvm.masked.store.v2f64.p0v2f64(<2 x double>, <2 x double>*, i32, <2 x i1>)
-declare void @llvm.masked.store.v2f64(<2 x double>, <2 x double>*, i32, <2 x i1>)
+declare void @llvm.masked.store.v2i64.p0v2i64(<2 x i64>, <2 x i64>*, i32, <2 x i1>)
-declare void @llvm.masked.store.v2i64(<2 x i64>, <2 x i64>*, i32, <2 x i1>)
 
-declare <16 x i32*> @llvm.masked.load.v16p0i32(<16 x i32*>*, i32, <16 x i1>, <16 x i32*>)
+declare <16 x i32*> @llvm.masked.load.v16p0i32.p0v16p0i32(<16 x i32*>*, i32, <16 x i1>, <16 x i32*>)
 
 define <16 x i32*> @test23(<16 x i32*> %trigger, <16 x i32*>* %addr) {
 ; AVX1-LABEL: test23:
@@ -1501,13 +1500,13 @@ define <16 x i32*> @test23(<16 x i32*> %trigger, <16 x i32*>* %addr) {
 ; AVX512-NEXT:    vmovdqu64 (%rdi), %zmm0 {%k1} {z}
 ; AVX512-NEXT:    retq
   %mask = icmp eq <16 x i32*> %trigger, zeroinitializer
-  %res = call <16 x i32*> @llvm.masked.load.v16p0i32(<16 x i32*>* %addr, i32 4, <16 x i1>%mask, <16 x i32*>zeroinitializer)
+  %res = call <16 x i32*> @llvm.masked.load.v16p0i32.p0v16p0i32(<16 x i32*>* %addr, i32 4, <16 x i1>%mask, <16 x i32*>zeroinitializer)
   ret <16 x i32*> %res
 }
 
 %mystruct = type { i16, i16, [1 x i8*] }
 
-declare <16 x %mystruct*> @llvm.masked.load.v16p0mystruct(<16 x %mystruct*>*, i32, <16 x i1>, <16 x %mystruct*>)
+declare <16 x %mystruct*> @llvm.masked.load.v16p0mystruct.p0v16p0mystruct(<16 x %mystruct*>*, i32, <16 x i1>, <16 x %mystruct*>)
 
 define <16 x %mystruct*> @test24(<16 x i1> %mask, <16 x %mystruct*>* %addr) {
 ; AVX1-LABEL: test24:
@@ -1596,7 +1595,7 @@ define <16 x %mystruct*> @test24(<16 x i1> %mask, <16 x %mystruct*>* %addr) {
 ; SKX-NEXT:    kshiftrw $8, %k1, %k1
 ; SKX-NEXT:    vmovdqu64 64(%rdi), %zmm1 {%k1} {z}
 ; SKX-NEXT:    retq
-  %res = call <16 x %mystruct*> @llvm.masked.load.v16p0mystruct(<16 x %mystruct*>* %addr, i32 4, <16 x i1>%mask, <16 x %mystruct*>zeroinitializer)
+  %res = call <16 x %mystruct*> @llvm.masked.load.v16p0mystruct.p0v16p0mystruct(<16 x %mystruct*>* %addr, i32 4, <16 x i1>%mask, <16 x %mystruct*>zeroinitializer)
   ret <16 x %mystruct*> %res
 }
 
@@ -1687,10 +1686,10 @@ define void @test_store_16i64(<16 x i64>* %ptrs, <16 x i1> %mask, <16 x i64> %sr
 ; SKX-NEXT:    kshiftrw $8, %k1, %k1
 ; SKX-NEXT:    vmovdqu64 %zmm2, 64(%rdi) {%k1}
 ; SKX-NEXT:    retq
-  call void @llvm.masked.store.v16i64(<16 x i64> %src0, <16 x i64>* %ptrs, i32 4, <16 x i1> %mask)
+  call void @llvm.masked.store.v16i64.p0v16i64(<16 x i64> %src0, <16 x i64>* %ptrs, i32 4, <16 x i1> %mask)
   ret void
 }
-declare void @llvm.masked.store.v16i64(<16 x i64> %src0, <16 x i64>* %ptrs, i32, <16 x i1> %mask)
+declare void @llvm.masked.store.v16i64.p0v16i64(<16 x i64> %src0, <16 x i64>* %ptrs, i32, <16 x i1> %mask)
 
 define void @test_store_16f64(<16 x double>* %ptrs, <16 x i1> %mask, <16 x double> %src0)  {
 ; AVX1-LABEL: test_store_16f64:
@@ -1779,10 +1778,10 @@ define void @test_store_16f64(<16 x double>* %ptrs, <16 x i1> %mask, <16 x doubl
 ; SKX-NEXT:    kshiftrw $8, %k1, %k1
 ; SKX-NEXT:    vmovupd %zmm2, 64(%rdi) {%k1}
 ; SKX-NEXT:    retq
-  call void @llvm.masked.store.v16f64(<16 x double> %src0, <16 x double>* %ptrs, i32 4, <16 x i1> %mask)
+  call void @llvm.masked.store.v16f64.p0v16f64(<16 x double> %src0, <16 x double>* %ptrs, i32 4, <16 x i1> %mask)
   ret void
 }
-declare void @llvm.masked.store.v16f64(<16 x double> %src0, <16 x double>* %ptrs, i32, <16 x i1> %mask)
+declare void @llvm.masked.store.v16f64.p0v16f64(<16 x double> %src0, <16 x double>* %ptrs, i32, <16 x i1> %mask)
 
 define <16 x i64> @test_load_16i64(<16 x i64>* %ptrs, <16 x i1> %mask, <16 x i64> %src0)  {
 ; AVX1-LABEL: test_load_16i64:
@@ -1883,10 +1882,10 @@ define <16 x i64> @test_load_16i64(<16 x i64>* %ptrs, <16 x i1> %mask, <16 x i64
 ; SKX-NEXT:    vmovaps %zmm1, %zmm0
 ; SKX-NEXT:    vmovaps %zmm2, %zmm1
 ; SKX-NEXT:    retq
-  %res = call <16 x i64> @llvm.masked.load.v16i64(<16 x i64>* %ptrs, i32 4, <16 x i1> %mask, <16 x i64> %src0)
+  %res = call <16 x i64> @llvm.masked.load.v16i64.p0v16i64(<16 x i64>* %ptrs, i32 4, <16 x i1> %mask, <16 x i64> %src0)
   ret <16 x i64> %res
 }
-declare <16 x i64> @llvm.masked.load.v16i64(<16 x i64>* %ptrs, i32, <16 x i1> %mask, <16 x i64> %src0)
+declare <16 x i64> @llvm.masked.load.v16i64.p0v16i64(<16 x i64>* %ptrs, i32, <16 x i1> %mask, <16 x i64> %src0)
 
 define <16 x double> @test_load_16f64(<16 x double>* %ptrs, <16 x i1> %mask, <16 x double> %src0)  {
 ; AVX1-LABEL: test_load_16f64:
@@ -1987,10 +1986,10 @@ define <16 x double> @test_load_16f64(<16 x double>* %ptrs, <16 x i1> %mask, <16
 ; SKX-NEXT:    vmovaps %zmm1, %zmm0
 ; SKX-NEXT:    vmovaps %zmm2, %zmm1
 ; SKX-NEXT:    retq
-  %res = call <16 x double> @llvm.masked.load.v16f64(<16 x double>* %ptrs, i32 4, <16 x i1> %mask, <16 x double> %src0)
+  %res = call <16 x double> @llvm.masked.load.v16f64.p0v16f64(<16 x double>* %ptrs, i32 4, <16 x i1> %mask, <16 x double> %src0)
   ret <16 x double> %res
 }
-declare <16 x double> @llvm.masked.load.v16f64(<16 x double>* %ptrs, i32, <16 x i1> %mask, <16 x double> %src0)
+declare <16 x double> @llvm.masked.load.v16f64.p0v16f64(<16 x double>* %ptrs, i32, <16 x i1> %mask, <16 x double> %src0)
 
 define <32 x double> @test_load_32f64(<32 x double>* %ptrs, <32 x i1> %mask, <32 x double> %src0)  {
 ; AVX1-LABEL: test_load_32f64:
@@ -2218,10 +2217,11 @@ define <32 x double> @test_load_32f64(<32 x double>* %ptrs, <32 x i1> %mask, <32
 ; SKX-NEXT:    vmovaps %zmm3, %zmm2
 ; SKX-NEXT:    vmovaps %zmm4, %zmm3
 ; SKX-NEXT:    retq
-  %res = call <32 x double> @llvm.masked.load.v32f64(<32 x double>* %ptrs, i32 4, <32 x i1> %mask, <32 x double> %src0)
+  %res = call <32 x double> @llvm.masked.load.v32f64.p0v32f64(<32 x double>* %ptrs, i32 4, <32 x i1> %mask, <32 x double> %src0)
   ret <32 x double> %res
 }
-declare <32 x double> @llvm.masked.load.v32f64(<32 x double>* %ptrs, i32, <32 x i1> %mask, <32 x double> %src0)
+
+declare <32 x double> @llvm.masked.load.v32f64.p0v32f64(<32 x double>* %ptrs, i32, <32 x i1> %mask, <32 x double> %src0)
 
 define <16 x i8> @test_mask_load_16xi8(<16 x i1> %mask, <16 x i8>* %addr, <16 x i8> %val) {
 ; SKX-LABEL: test_mask_load_16xi8:
@@ -2230,10 +2230,10 @@ define <16 x i8> @test_mask_load_16xi8(<16 x i1> %mask, <16 x i8>* %addr, <16 x
 ; SKX-NEXT:    vpmovb2m %xmm0, %k1
 ; SKX-NEXT:    vmovdqu8 (%rdi), %xmm0 {%k1} {z}
 ; SKX-NEXT:    retq
-  %res = call <16 x i8> @llvm.masked.load.v16i8(<16 x i8>* %addr, i32 4, <16 x i1>%mask, <16 x i8> undef)
+  %res = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* %addr, i32 4, <16 x i1>%mask, <16 x i8> undef)
   ret <16 x i8> %res
 }
-declare <16 x i8> @llvm.masked.load.v16i8(<16 x i8>*, i32, <16 x i1>, <16 x i8>)
+declare <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>*, i32, <16 x i1>, <16 x i8>)
 
 define <32 x i8> @test_mask_load_32xi8(<32 x i1> %mask, <32 x i8>* %addr, <32 x i8> %val) {
 ; SKX-LABEL: test_mask_load_32xi8:
@@ -2242,10 +2242,10 @@ define <32 x i8> @test_mask_load_32xi8(<32 x i1> %mask, <32 x i8>* %addr, <32 x
 ; SKX-NEXT:    vpmovb2m %ymm0, %k1
 ; SKX-NEXT:    vmovdqu8 (%rdi), %ymm0 {%k1} {z}
 ; SKX-NEXT:    retq
-  %res = call <32 x i8> @llvm.masked.load.v32i8(<32 x i8>* %addr, i32 4, <32 x i1>%mask, <32 x i8> zeroinitializer)
+  %res = call <32 x i8> @llvm.masked.load.v32i8.p0v32i8(<32 x i8>* %addr, i32 4, <32 x i1>%mask, <32 x i8> zeroinitializer)
   ret <32 x i8> %res
 }
-declare <32 x i8> @llvm.masked.load.v32i8(<32 x i8>*, i32, <32 x i1>, <32 x i8>)
+declare <32 x i8> @llvm.masked.load.v32i8.p0v32i8(<32 x i8>*, i32, <32 x i1>, <32 x i8>)
 
 define <64 x i8> @test_mask_load_64xi8(<64 x i1> %mask, <64 x i8>* %addr, <64 x i8> %val) {
 ; SKX-LABEL: test_mask_load_64xi8:
@@ -2255,10 +2255,10 @@ define <64 x i8> @test_mask_load_64xi8(<64 x i1> %mask, <64 x i8>* %addr, <64 x
 ; SKX-NEXT:    vmovdqu8 (%rdi), %zmm1 {%k1}
 ; SKX-NEXT:    vmovaps %zmm1, %zmm0
 ; SKX-NEXT:    retq
-  %res = call <64 x i8> @llvm.masked.load.v64i8(<64 x i8>* %addr, i32 4, <64 x i1>%mask, <64 x i8> %val)
+  %res = call <64 x i8> @llvm.masked.load.v64i8.p0v64i8(<64 x i8>* %addr, i32 4, <64 x i1>%mask, <64 x i8> %val)
   ret <64 x i8> %res
 }
-declare <64 x i8> @llvm.masked.load.v64i8(<64 x i8>*, i32, <64 x i1>, <64 x i8>)
+declare <64 x i8> @llvm.masked.load.v64i8.p0v64i8(<64 x i8>*, i32, <64 x i1>, <64 x i8>)
 
 define <8 x i16> @test_mask_load_8xi16(<8 x i1> %mask, <8 x i16>* %addr, <8 x i16> %val) {
 ; SKX-LABEL: test_mask_load_8xi16:
@@ -2267,10 +2267,10 @@ define <8 x i16> @test_mask_load_8xi16(<8 x i1> %mask, <8 x i16>* %addr, <8 x i1
 ; SKX-NEXT:    vpmovw2m %xmm0, %k1
 ; SKX-NEXT:    vmovdqu16 (%rdi), %xmm0 {%k1} {z}
 ; SKX-NEXT:    retq
-  %res = call <8 x i16> @llvm.masked.load.v8i16(<8 x i16>* %addr, i32 4, <8 x i1>%mask, <8 x i16> undef)
+  %res = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* %addr, i32 4, <8 x i1>%mask, <8 x i16> undef)
   ret <8 x i16> %res
 }
-declare <8 x i16> @llvm.masked.load.v8i16(<8 x i16>*, i32, <8 x i1>, <8 x i16>)
+declare <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>*, i32, <8 x i1>, <8 x i16>)
 
 define <16 x i16> @test_mask_load_16xi16(<16 x i1> %mask, <16 x i16>* %addr, <16 x i16> %val) {
 ; SKX-LABEL: test_mask_load_16xi16:
@@ -2279,10 +2279,10 @@ define <16 x i16> @test_mask_load_16xi16(<16 x i1> %mask, <16 x i16>* %addr, <16
 ; SKX-NEXT:    vpmovb2m %xmm0, %k1
 ; SKX-NEXT:    vmovdqu16 (%rdi), %ymm0 {%k1} {z}
 ; SKX-NEXT:    retq
-  %res = call <16 x i16> @llvm.masked.load.v16i16(<16 x i16>* %addr, i32 4, <16 x i1>%mask, <16 x i16> zeroinitializer)
+  %res = call <16 x i16> @llvm.masked.load.v16i16.p0v16i16(<16 x i16>* %addr, i32 4, <16 x i1>%mask, <16 x i16> zeroinitializer)
   ret <16 x i16> %res
 }
-declare <16 x i16> @llvm.masked.load.v16i16(<16 x i16>*, i32, <16 x i1>, <16 x i16>)
+declare <16 x i16> @llvm.masked.load.v16i16.p0v16i16(<16 x i16>*, i32, <16 x i1>, <16 x i16>)
 
 define <32 x i16> @test_mask_load_32xi16(<32 x i1> %mask, <32 x i16>* %addr, <32 x i16> %val) {
 ; SKX-LABEL: test_mask_load_32xi16:
@@ -2292,10 +2292,10 @@ define <32 x i16> @test_mask_load_32xi16(<32 x i1> %mask, <32 x i16>* %addr, <32
 ; SKX-NEXT:    vmovdqu16 (%rdi), %zmm1 {%k1}
 ; SKX-NEXT:    vmovaps %zmm1, %zmm0
 ; SKX-NEXT:    retq
-  %res = call <32 x i16> @llvm.masked.load.v32i16(<32 x i16>* %addr, i32 4, <32 x i1>%mask, <32 x i16> %val)
+  %res = call <32 x i16> @llvm.masked.load.v32i16.p0v32i16(<32 x i16>* %addr, i32 4, <32 x i1>%mask, <32 x i16> %val)
   ret <32 x i16> %res
 }
-declare <32 x i16> @llvm.masked.load.v32i16(<32 x i16>*, i32, <32 x i1>, <32 x i16>)
+declare <32 x i16> @llvm.masked.load.v32i16.p0v32i16(<32 x i16>*, i32, <32 x i1>, <32 x i16>)
 
 define void @test_mask_store_16xi8(<16 x i1> %mask, <16 x i8>* %addr, <16 x i8> %val) {
 ; SKX-LABEL: test_mask_store_16xi8:
@@ -2304,10 +2304,10 @@ define void @test_mask_store_16xi8(<16 x i1> %mask, <16 x i8>* %addr, <16 x i8>
 ; SKX-NEXT:    vpmovb2m %xmm0, %k1
 ; SKX-NEXT:    vmovdqu8 %xmm1, (%rdi) {%k1}
 ; SKX-NEXT:    retq
-  call void @llvm.masked.store.v16i8(<16 x i8> %val, <16 x i8>* %addr, i32 4, <16 x i1>%mask)
+  call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> %val, <16 x i8>* %addr, i32 4, <16 x i1>%mask)
   ret void
 }
-declare void @llvm.masked.store.v16i8(<16 x i8>, <16 x i8>*, i32, <16 x i1>)
+declare void @llvm.masked.store.v16i8.p0v16i8(<16 x i8>, <16 x i8>*, i32, <16 x i1>)
 
 define void @test_mask_store_32xi8(<32 x i1> %mask, <32 x i8>* %addr, <32 x i8> %val) {
 ; SKX-LABEL: test_mask_store_32xi8:
@@ -2316,10 +2316,10 @@ define void @test_mask_store_32xi8(<32 x i1> %mask, <32 x i8>* %addr, <32 x i8>
 ; SKX-NEXT:    vpmovb2m %ymm0, %k1
 ; SKX-NEXT:    vmovdqu8 %ymm1, (%rdi) {%k1}
 ; SKX-NEXT:    retq
-  call void @llvm.masked.store.v32i8(<32 x i8> %val, <32 x i8>* %addr, i32 4, <32 x i1>%mask)
+  call void @llvm.masked.store.v32i8.p0v32i8(<32 x i8> %val, <32 x i8>* %addr, i32 4, <32 x i1>%mask)
   ret void
 }
-declare void @llvm.masked.store.v32i8(<32 x i8>, <32 x i8>*, i32, <32 x i1>)
+declare void @llvm.masked.store.v32i8.p0v32i8(<32 x i8>, <32 x i8>*, i32, <32 x i1>)
 
 define void @test_mask_store_64xi8(<64 x i1> %mask, <64 x i8>* %addr, <64 x i8> %val) {
 ; SKX-LABEL: test_mask_store_64xi8:
@@ -2328,10 +2328,10 @@ define void @test_mask_store_64xi8(<64 x i1> %mask, <64 x i8>* %addr, <64 x i8>
 ; SKX-NEXT:    vpmovb2m %zmm0, %k1
 ; SKX-NEXT:    vmovdqu8 %zmm1, (%rdi) {%k1}
 ; SKX-NEXT:    retq
-  call void @llvm.masked.store.v64i8(<64 x i8> %val, <64 x i8>* %addr, i32 4, <64 x i1>%mask)
+  call void @llvm.masked.store.v64i8.p0v64i8(<64 x i8> %val, <64 x i8>* %addr, i32 4, <64 x i1>%mask)
   ret void
 }
-declare void @llvm.masked.store.v64i8(<64 x i8>, <64 x i8>*, i32, <64 x i1>)
+declare void @llvm.masked.store.v64i8.p0v64i8(<64 x i8>, <64 x i8>*, i32, <64 x i1>)
 
 define void @test_mask_store_8xi16(<8 x i1> %mask, <8 x i16>* %addr, <8 x i16> %val) {
 ; SKX-LABEL: test_mask_store_8xi16:
@@ -2340,10 +2340,10 @@ define void @test_mask_store_8xi16(<8 x i1> %mask, <8 x i16>* %addr, <8 x i16> %
 ; SKX-NEXT:    vpmovw2m %xmm0, %k1
 ; SKX-NEXT:    vmovdqu16 %xmm1, (%rdi) {%k1}
 ; SKX-NEXT:    retq
-  call void @llvm.masked.store.v8i16(<8 x i16> %val, <8 x i16>* %addr, i32 4, <8 x i1>%mask)
+  call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> %val, <8 x i16>* %addr, i32 4, <8 x i1>%mask)
   ret void
 }
-declare void @llvm.masked.store.v8i16(<8 x i16>, <8 x i16>*, i32, <8 x i1>)
+declare void @llvm.masked.store.v8i16.p0v8i16(<8 x i16>, <8 x i16>*, i32, <8 x i1>)
 
 define void @test_mask_store_16xi16(<16 x i1> %mask, <16 x i16>* %addr, <16 x i16> %val) {
 ; SKX-LABEL: test_mask_store_16xi16:
@@ -2352,10 +2352,10 @@ define void @test_mask_store_16xi16(<16 x i1> %mask, <16 x i16>* %addr, <16 x i1
 ; SKX-NEXT:    vpmovb2m %xmm0, %k1
 ; SKX-NEXT:    vmovdqu16 %ymm1, (%rdi) {%k1}
 ; SKX-NEXT:    retq
-  call void @llvm.masked.store.v16i16(<16 x i16> %val, <16 x i16>* %addr, i32 4, <16 x i1>%mask)
+  call void @llvm.masked.store.v16i16.p0v16i16(<16 x i16> %val, <16 x i16>* %addr, i32 4, <16 x i1>%mask)
   ret void
 }
-declare void @llvm.masked.store.v16i16(<16 x i16>, <16 x i16>*, i32, <16 x i1>)
+declare void @llvm.masked.store.v16i16.p0v16i16(<16 x i16>, <16 x i16>*, i32, <16 x i1>)
 
 define void @test_mask_store_32xi16(<32 x i1> %mask, <32 x i16>* %addr, <32 x i16> %val) {
 ; SKX-LABEL: test_mask_store_32xi16:
@@ -2364,7 +2364,8 @@ define void @test_mask_store_32xi16(<32 x i1> %mask, <32 x i16>* %addr, <32 x i1
 ; SKX-NEXT:    vpmovb2m %ymm0, %k1
 ; SKX-NEXT:    vmovdqu16 %zmm1, (%rdi) {%k1}
 ; SKX-NEXT:    retq
-  call void @llvm.masked.store.v32i16(<32 x i16> %val, <32 x i16>* %addr, i32 4, <32 x i1>%mask)
+  call void @llvm.masked.store.v32i16.p0v32i16(<32 x i16> %val, <32 x i16>* %addr, i32 4, <32 x i1>%mask)
   ret void
 }
-declare void @llvm.masked.store.v32i16(<32 x i16>, <32 x i16>*, i32, <32 x i1>)
+
+declare void @llvm.masked.store.v32i16.p0v32i16(<32 x i16>, <32 x i16>*, i32, <32 x i1>)

llvm/test/Transforms/InstCombine/masked_intrinsics.ll

@@ -1,12 +1,12 @@
 ; RUN: opt -instcombine -S < %s | FileCheck %s
 
-declare <2 x double> @llvm.masked.load.v2f64(<2 x double>* %ptrs, i32, <2 x i1> %mask, <2 x double> %src0)
+declare <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %ptrs, i32, <2 x i1> %mask, <2 x double> %src0)
-declare void @llvm.masked.store.v2f64(<2 x double> %val, <2 x double>* %ptrs, i32, <2 x i1> %mask)
+declare void @llvm.masked.store.v2f64.p0v2f64(<2 x double> %val, <2 x double>* %ptrs, i32, <2 x i1> %mask)
 declare <2 x double> @llvm.masked.gather.v2f64(<2 x double*> %ptrs, i32, <2 x i1> %mask, <2 x double> %passthru)
 declare void @llvm.masked.scatter.v2f64(<2 x double> %val, <2 x double*> %ptrs, i32, <2 x i1> %mask)
 
 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)
+  %res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %ptr, i32 1, <2 x i1> zeroinitializer, <2 x double> %passthru)
   ret <2 x double> %res
 
 ; CHECK-LABEL: @load_zeromask(
@@ -14,7 +14,7 @@ define <2 x double> @load_zeromask(<2 x double>* %ptr, <2 x double> %passthru)
 }
 
 define <2 x double> @load_onemask(<2 x double>* %ptr, <2 x double> %passthru)  {
-  %res = call <2 x double> @llvm.masked.load.v2f64(<2 x double>* %ptr, i32 2, <2 x i1> <i1 1, i1 1>, <2 x double> %passthru)
+  %res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %ptr, i32 2, <2 x i1> <i1 1, i1 1>, <2 x double> %passthru)
   ret <2 x double> %res
 
 ; CHECK-LABEL: @load_onemask(
@@ -23,7 +23,7 @@ define <2 x double> @load_onemask(<2 x double>* %ptr, <2 x double> %passthru)  {
 }
 
 define void @store_zeromask(<2 x double>* %ptr, <2 x double> %val)  {
-  call void @llvm.masked.store.v2f64(<2 x double> %val, <2 x double>* %ptr, i32 3, <2 x i1> zeroinitializer)
+  call void @llvm.masked.store.v2f64.p0v2f64(<2 x double> %val, <2 x double>* %ptr, i32 3, <2 x i1> zeroinitializer)
   ret void
 
 ; CHECK-LABEL: @store_zeromask(
@@ -31,7 +31,7 @@ define void @store_zeromask(<2 x double>* %ptr, <2 x double> %val)  {
 }
 
 define void @store_onemask(<2 x double>* %ptr, <2 x double> %val)  {
-  call void @llvm.masked.store.v2f64(<2 x double> %val, <2 x double>* %ptr, i32 4, <2 x i1> <i1 1, i1 1>)
+  call void @llvm.masked.store.v2f64.p0v2f64(<2 x double> %val, <2 x double>* %ptr, i32 4, <2 x i1> <i1 1, i1 1>)
   ret void
 
 ; CHECK-LABEL: @store_onemask(

llvm/test/Transforms/InstCombine/x86-masked-memops.ll

@@ -53,7 +53,7 @@ define <4 x float> @mload_one_one(i8* %f) {
 
 ; CHECK-LABEL: @mload_one_one(
 ; CHECK-NEXT:  %castvec = bitcast i8* %f to <4 x float>*
-; CHECK-NEXT:  %1 = call <4 x float> @llvm.masked.load.v4f32(<4 x float>* %castvec, i32 1, <4 x i1> <i1 false, i1 false, i1 false, i1 true>, <4 x float> undef)
+; CHECK-NEXT:  %1 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %castvec, i32 1, <4 x i1> <i1 false, i1 false, i1 false, i1 true>, <4 x float> undef)
 ; CHECK-NEXT:  ret <4 x float> %1
 }
 
@@ -65,7 +65,7 @@ define <2 x double> @mload_one_one_double(i8* %f) {
 
 ; CHECK-LABEL: @mload_one_one_double(
 ; CHECK-NEXT:  %castvec = bitcast i8* %f to <2 x double>*
-; CHECK-NEXT:  %1 = call <2 x double> @llvm.masked.load.v2f64(<2 x double>* %castvec, i32 1, <2 x i1> <i1 true, i1 false>, <2 x double> undef)
+; CHECK-NEXT:  %1 = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %castvec, i32 1, <2 x i1> <i1 true, i1 false>, <2 x double> undef)
 ; CHECK-NEXT:  ret <2 x double> %1
 }
 
@@ -77,7 +77,7 @@ define <8 x float> @mload_v8f32(i8* %f) {
 
 ; CHECK-LABEL: @mload_v8f32(
 ; CHECK-NEXT:  %castvec = bitcast i8* %f to <8 x float>*
-; CHECK-NEXT:  %1 = call <8 x float> @llvm.masked.load.v8f32(<8 x float>* %castvec, i32 1, <8 x i1> <i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false, i1 false>, <8 x float> undef)
+; CHECK-NEXT:  %1 = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %castvec, i32 1, <8 x i1> <i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false, i1 false>, <8 x float> undef)
 ; CHECK-NEXT:  ret <8 x float> %1
 }
 
@@ -87,7 +87,7 @@ define <4 x double> @mload_v4f64(i8* %f) {
 
 ; CHECK-LABEL: @mload_v4f64(
 ; CHECK-NEXT:  %castvec = bitcast i8* %f to <4 x double>*
-; CHECK-NEXT:  %1 = call <4 x double> @llvm.masked.load.v4f64(<4 x double>* %castvec, i32 1, <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x double> undef)
+; CHECK-NEXT:  %1 = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* %castvec, i32 1, <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x double> undef)
 ; CHECK-NEXT:  ret <4 x double> %1
 }
 
@@ -99,7 +99,7 @@ define <4 x i32> @mload_v4i32(i8* %f) {
 
 ; CHECK-LABEL: @mload_v4i32(
 ; CHECK-NEXT:  %castvec = bitcast i8* %f to <4 x i32>*
-; CHECK-NEXT:  %1 = call <4 x i32> @llvm.masked.load.v4i32(<4 x i32>* %castvec, i32 1, <4 x i1> <i1 false, i1 false, i1 false, i1 true>, <4 x i32> undef)
+; CHECK-NEXT:  %1 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %castvec, i32 1, <4 x i1> <i1 false, i1 false, i1 false, i1 true>, <4 x i32> undef)
 ; CHECK-NEXT:  ret <4 x i32> %1
 }
 
@@ -109,7 +109,7 @@ define <2 x i64> @mload_v2i64(i8* %f) {
 
 ; CHECK-LABEL: @mload_v2i64(
 ; CHECK-NEXT:  %castvec = bitcast i8* %f to <2 x i64>*
-; CHECK-NEXT:  %1 = call <2 x i64> @llvm.masked.load.v2i64(<2 x i64>* %castvec, i32 1, <2 x i1> <i1 true, i1 false>, <2 x i64> undef)
+; CHECK-NEXT:  %1 = call <2 x i64> @llvm.masked.load.v2i64.p0v2i64(<2 x i64>* %castvec, i32 1, <2 x i1> <i1 true, i1 false>, <2 x i64> undef)
 ; CHECK-NEXT:  ret <2 x i64> %1
 }
 
@@ -119,7 +119,7 @@ define <8 x i32> @mload_v8i32(i8* %f) {
 
 ; CHECK-LABEL: @mload_v8i32(
 ; CHECK-NEXT:  %castvec = bitcast i8* %f to <8 x i32>*
-; CHECK-NEXT:  %1 = call <8 x i32> @llvm.masked.load.v8i32(<8 x i32>* %castvec, i32 1, <8 x i1> <i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false, i1 false>, <8 x i32> undef)
+; CHECK-NEXT:  %1 = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* %castvec, i32 1, <8 x i1> <i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false, i1 false>, <8 x i32> undef)
 ; CHECK-NEXT:  ret <8 x i32> %1
 }
 
@@ -129,7 +129,7 @@ define <4 x i64> @mload_v4i64(i8* %f) {
 
 ; CHECK-LABEL: @mload_v4i64(
 ; CHECK-NEXT:  %castvec = bitcast i8* %f to <4 x i64>*
-; CHECK-NEXT:  %1 = call <4 x i64> @llvm.masked.load.v4i64(<4 x i64>* %castvec, i32 1, <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x i64> undef)
+; CHECK-NEXT:  %1 = call <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>* %castvec, i32 1, <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x i64> undef)
 ; CHECK-NEXT:  ret <4 x i64> %1
 }
 
@@ -187,7 +187,7 @@ define void @mstore_one_one(i8* %f, <4 x float> %v) {
 
 ; CHECK-LABEL: @mstore_one_one(
 ; CHECK-NEXT:  %castvec = bitcast i8* %f to <4 x float>*
-; CHECK-NEXT:  call void @llvm.masked.store.v4f32(<4 x float> %v, <4 x float>* %castvec, i32 1, <4 x i1> <i1 false, i1 false, i1 false, i1 true>)
+; CHECK-NEXT:  call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> %v, <4 x float>* %castvec, i32 1, <4 x i1> <i1 false, i1 false, i1 false, i1 true>)
 ; CHECK-NEXT:  ret void
 }
 
@@ -199,7 +199,7 @@ define void @mstore_one_one_double(i8* %f, <2 x double> %v) {
 
 ; CHECK-LABEL: @mstore_one_one_double(
 ; CHECK-NEXT:  %castvec = bitcast i8* %f to <2 x double>*
-; CHECK-NEXT:  call void @llvm.masked.store.v2f64(<2 x double> %v, <2 x double>* %castvec, i32 1, <2 x i1> <i1 true, i1 false>)
+; CHECK-NEXT:  call void @llvm.masked.store.v2f64.p0v2f64(<2 x double> %v, <2 x double>* %castvec, i32 1, <2 x i1> <i1 true, i1 false>)
 ; CHECK-NEXT:  ret void
 }
 
@@ -211,7 +211,7 @@ define void @mstore_v8f32(i8* %f, <8 x float> %v) {
 
 ; CHECK-LABEL: @mstore_v8f32(
 ; CHECK-NEXT:  %castvec = bitcast i8* %f to <8 x float>*
-; CHECK-NEXT:  call void @llvm.masked.store.v8f32(<8 x float> %v, <8 x float>* %castvec, i32 1, <8 x i1> <i1 false, i1 false, i1 false, i1 false, i1 true, i1 true, i1 true, i1 true>)
+; CHECK-NEXT:  call void @llvm.masked.store.v8f32.p0v8f32(<8 x float> %v, <8 x float>* %castvec, i32 1, <8 x i1> <i1 false, i1 false, i1 false, i1 false, i1 true, i1 true, i1 true, i1 true>)
 ; CHECK-NEXT:  ret void
 }
 
@@ -221,7 +221,7 @@ define void @mstore_v4f64(i8* %f, <4 x double> %v) {
 
 ; CHECK-LABEL: @mstore_v4f64(
 ; CHECK-NEXT:  %castvec = bitcast i8* %f to <4 x double>*
-; CHECK-NEXT:  call void @llvm.masked.store.v4f64(<4 x double> %v, <4 x double>* %castvec, i32 1, <4 x i1> <i1 true, i1 false, i1 false, i1 false>)
+; CHECK-NEXT:  call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> %v, <4 x double>* %castvec, i32 1, <4 x i1> <i1 true, i1 false, i1 false, i1 false>)
 ; CHECK-NEXT:  ret void
 }
 
@@ -233,7 +233,7 @@ define void @mstore_v4i32(i8* %f, <4 x i32> %v) {
 
 ; CHECK-LABEL: @mstore_v4i32(
 ; CHECK-NEXT:  %castvec = bitcast i8* %f to <4 x i32>*
-; CHECK-NEXT:  call void @llvm.masked.store.v4i32(<4 x i32> %v, <4 x i32>* %castvec, i32 1, <4 x i1> <i1 false, i1 false, i1 true, i1 true>)
+; CHECK-NEXT:  call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %v, <4 x i32>* %castvec, i32 1, <4 x i1> <i1 false, i1 false, i1 true, i1 true>)
 ; CHECK-NEXT:  ret void
 }
 
@@ -243,7 +243,7 @@ define void @mstore_v2i64(i8* %f, <2 x i64> %v) {
 
 ; CHECK-LABEL: @mstore_v2i64(
 ; CHECK-NEXT:  %castvec = bitcast i8* %f to <2 x i64>*
-; CHECK-NEXT:  call void @llvm.masked.store.v2i64(<2 x i64> %v, <2 x i64>* %castvec, i32 1, <2 x i1> <i1 true, i1 false>)
+; CHECK-NEXT:  call void @llvm.masked.store.v2i64.p0v2i64(<2 x i64> %v, <2 x i64>* %castvec, i32 1, <2 x i1> <i1 true, i1 false>)
 ; CHECK-NEXT:  ret void
 }
 
@@ -253,7 +253,7 @@ define void @mstore_v8i32(i8* %f, <8 x i32> %v) {
 
 ; CHECK-LABEL: @mstore_v8i32(
 ; CHECK-NEXT:  %castvec = bitcast i8* %f to <8 x i32>*
-; CHECK-NEXT:  call void @llvm.masked.store.v8i32(<8 x i32> %v, <8 x i32>* %castvec, i32 1, <8 x i1> <i1 false, i1 false, i1 false, i1 false, i1 true, i1 true, i1 true, i1 true>)
+; CHECK-NEXT:  call void @llvm.masked.store.v8i32.p0v8i32(<8 x i32> %v, <8 x i32>* %castvec, i32 1, <8 x i1> <i1 false, i1 false, i1 false, i1 false, i1 true, i1 true, i1 true, i1 true>)
 ; CHECK-NEXT:  ret void
 }
 
@@ -263,7 +263,7 @@ define void @mstore_v4i64(i8* %f, <4 x i64> %v) {
 
 ; CHECK-LABEL: @mstore_v4i64(
 ; CHECK-NEXT:  %castvec = bitcast i8* %f to <4 x i64>*
-; CHECK-NEXT:  call void @llvm.masked.store.v4i64(<4 x i64> %v, <4 x i64>* %castvec, i32 1, <4 x i1> <i1 true, i1 false, i1 false, i1 false>)
+; CHECK-NEXT:  call void @llvm.masked.store.v4i64.p0v4i64(<4 x i64> %v, <4 x i64>* %castvec, i32 1, <4 x i1> <i1 true, i1 false, i1 false, i1 false>)
 ; CHECK-NEXT:  ret void
 }
 

llvm/test/Transforms/LoopVectorize/X86/masked_load_store.ll

@@ -18,16 +18,16 @@ target triple = "x86_64-pc_linux"
 
 ;AVX-LABEL: @foo1
 ;AVX: icmp slt <8 x i32> %wide.load, <i32 100, i32 100, i32 100
-;AVX: call <8 x i32> @llvm.masked.load.v8i32
+;AVX: call <8 x i32> @llvm.masked.load.v8i32.p0v8i32
 ;AVX: add nsw <8 x i32>
-;AVX: call void @llvm.masked.store.v8i32
+;AVX: call void @llvm.masked.store.v8i32.p0v8i32
 ;AVX: ret void
 
 ;AVX512-LABEL: @foo1
 ;AVX512: icmp slt <16 x i32> %wide.load, <i32 100, i32 100, i32 100
-;AVX512: call <16 x i32> @llvm.masked.load.v16i32
+;AVX512: call <16 x i32> @llvm.masked.load.v16i32.p0v16i32
 ;AVX512: add nsw <16 x i32>
-;AVX512: call void @llvm.masked.store.v16i32
+;AVX512: call void @llvm.masked.store.v16i32.p0v16i32
 ;AVX512: ret void
 
 ; Function Attrs: nounwind uwtable
@@ -89,6 +89,81 @@ for.end:                                          ; preds = %for.cond
   ret void
 }
 
+; The same as @foo1 but all the pointers are address space 1 pointers.
+
+;AVX-LABEL: @foo1_addrspace1
+;AVX: icmp slt <8 x i32> %wide.load, <i32 100, i32 100, i32 100
+;AVX: call <8 x i32> @llvm.masked.load.v8i32.p1v8i32
+;AVX: add nsw <8 x i32>
+;AVX: call void @llvm.masked.store.v8i32.p1v8i32
+;AVX: ret void
+
+;AVX512-LABEL: @foo1_addrspace1
+;AVX512: icmp slt <16 x i32> %wide.load, <i32 100, i32 100, i32 100
+;AVX512: call <16 x i32> @llvm.masked.load.v16i32.p1v16i32
+;AVX512: add nsw <16 x i32>
+;AVX512: call void @llvm.masked.store.v16i32.p1v16i32
+;AVX512: ret void
+
+; Function Attrs: nounwind uwtable
+define void @foo1_addrspace1(i32 addrspace(1)*  %A, i32 addrspace(1)* %B, i32 addrspace(1)* %trigger) {
+entry:
+  %A.addr = alloca i32 addrspace(1)*, align 8
+  %B.addr = alloca i32 addrspace(1)*, align 8
+  %trigger.addr = alloca i32 addrspace(1)*, align 8
+  %i = alloca i32, align 4
+  store i32 addrspace(1)* %A, i32 addrspace(1)** %A.addr, align 8
+  store i32 addrspace(1)* %B, i32 addrspace(1)** %B.addr, align 8
+  store i32 addrspace(1)* %trigger, i32 addrspace(1)** %trigger.addr, align 8
+  store i32 0, i32* %i, align 4
+  br label %for.cond
+
+for.cond:                                         ; preds = %for.inc, %entry
+  %0 = load i32, i32* %i, align 4
+  %cmp = icmp slt i32 %0, 10000
+  br i1 %cmp, label %for.body, label %for.end
+
+for.body:                                         ; preds = %for.cond
+  %1 = load i32, i32* %i, align 4
+  %idxprom = sext i32 %1 to i64
+  %2 = load i32 addrspace(1)*, i32 addrspace(1)** %trigger.addr, align 8
+  %arrayidx = getelementptr inbounds i32, i32 addrspace(1)* %2, i64 %idxprom
+  %3 = load i32, i32 addrspace(1)* %arrayidx, align 4
+  %cmp1 = icmp slt i32 %3, 100
+  br i1 %cmp1, label %if.then, label %if.end
+
+if.then:                                          ; preds = %for.body
+  %4 = load i32, i32* %i, align 4
+  %idxprom2 = sext i32 %4 to i64
+  %5 = load i32 addrspace(1)*, i32 addrspace(1)** %B.addr, align 8
+  %arrayidx3 = getelementptr inbounds i32, i32 addrspace(1)* %5, i64 %idxprom2
+  %6 = load i32, i32 addrspace(1)* %arrayidx3, align 4
+  %7 = load i32, i32* %i, align 4
+  %idxprom4 = sext i32 %7 to i64
+  %8 = load i32 addrspace(1)*, i32 addrspace(1)** %trigger.addr, align 8
+  %arrayidx5 = getelementptr inbounds i32, i32 addrspace(1)* %8, i64 %idxprom4
+  %9 = load i32, i32 addrspace(1)* %arrayidx5, align 4
+  %add = add nsw i32 %6, %9
+  %10 = load i32, i32* %i, align 4
+  %idxprom6 = sext i32 %10 to i64
+  %11 = load i32 addrspace(1)*, i32 addrspace(1)** %A.addr, align 8
+  %arrayidx7 = getelementptr inbounds i32, i32 addrspace(1)* %11, i64 %idxprom6
+  store i32 %add, i32 addrspace(1)* %arrayidx7, align 4
+  br label %if.end
+
+if.end:                                           ; preds = %if.then, %for.body
+  br label %for.inc
+
+for.inc:                                          ; preds = %if.end
+  %12 = load i32, i32* %i, align 4
+  %inc = add nsw i32 %12, 1
+  store i32 %inc, i32* %i, align 4
+  br label %for.cond
+
+for.end:                                          ; preds = %for.cond
+  ret void
+}
+
 ; The source code:
 ;
 ;void foo2(float *A, float *B, int *trigger) {
@@ -102,16 +177,16 @@ for.end:                                          ; preds = %for.cond
 
 ;AVX-LABEL: @foo2
 ;AVX: icmp slt <8 x i32> %wide.load, <i32 100, i32 100, i32 100
-;AVX: call <8 x float> @llvm.masked.load.v8f32
+;AVX: call <8 x float> @llvm.masked.load.v8f32.p0v8f32
 ;AVX: fadd <8 x float>
-;AVX: call void @llvm.masked.store.v8f32
+;AVX: call void @llvm.masked.store.v8f32.p0v8f32
 ;AVX: ret void
 
 ;AVX512-LABEL: @foo2
 ;AVX512: icmp slt <16 x i32> %wide.load, <i32 100, i32 100, i32 100
-;AVX512: call <16 x float> @llvm.masked.load.v16f32
+;AVX512: call <16 x float> @llvm.masked.load.v16f32.p0v16f32
 ;AVX512: fadd <16 x float>
-;AVX512: call void @llvm.masked.store.v16f32
+;AVX512: call void @llvm.masked.store.v16f32.p0v16f32
 ;AVX512: ret void
 
 ; Function Attrs: nounwind uwtable
@@ -187,18 +262,18 @@ for.end:                                          ; preds = %for.cond
 
 ;AVX-LABEL: @foo3
 ;AVX: icmp slt <4 x i32> %wide.load, <i32 100, i32 100,
-;AVX: call <4 x double> @llvm.masked.load.v4f64
+;AVX: call <4 x double> @llvm.masked.load.v4f64.p0v4f64
 ;AVX: sitofp <4 x i32> %wide.load to <4 x double>
 ;AVX: fadd <4 x double>
-;AVX: call void @llvm.masked.store.v4f64
+;AVX: call void @llvm.masked.store.v4f64.p0v4f64
 ;AVX: ret void
 
 ;AVX512-LABEL: @foo3
 ;AVX512: icmp slt <8 x i32> %wide.load, <i32 100, i32 100,
-;AVX512: call <8 x double> @llvm.masked.load.v8f64
+;AVX512: call <8 x double> @llvm.masked.load.v8f64.p0v8f64
 ;AVX512: sitofp <8 x i32> %wide.load to <8 x double>
 ;AVX512: fadd <8 x double>
-;AVX512: call void @llvm.masked.store.v8f64
+;AVX512: call void @llvm.masked.store.v8f64.p0v8f64
 ;AVX512: ret void
 
 
@@ -429,17 +504,17 @@ for.end:                                          ; preds = %for.cond
 ;AVX2-LABEL: @foo6
 ;AVX2: icmp sgt <4 x i32> %reverse, zeroinitializer
 ;AVX2: shufflevector <4 x i1>{{.*}}<4 x i32> <i32 3, i32 2, i32 1, i32 0>
-;AVX2: call <4 x double> @llvm.masked.load.v4f64
+;AVX2: call <4 x double> @llvm.masked.load.v4f64.p0v4f64
 ;AVX2: fadd <4 x double>
-;AVX2: call void @llvm.masked.store.v4f64
+;AVX2: call void @llvm.masked.store.v4f64.p0v4f64
 ;AVX2: ret void
 
 ;AVX512-LABEL: @foo6
 ;AVX512: icmp sgt <8 x i32> %reverse, zeroinitializer
 ;AVX512: shufflevector <8 x i1>{{.*}}<8 x i32> <i32 7, i32 6, i32 5, i32 4
-;AVX512: call <8 x double> @llvm.masked.load.v8f64
+;AVX512: call <8 x double> @llvm.masked.load.v8f64.p0v8f64
 ;AVX512: fadd <8 x double>
-;AVX512: call void @llvm.masked.store.v8f64
+;AVX512: call void @llvm.masked.store.v8f64.p0v8f64
 ;AVX512: ret void
 
 
@@ -507,8 +582,8 @@ for.end:                                          ; preds = %for.cond
 ; }
 
 ;AVX512-LABEL: @foo7
-;AVX512: call <8 x double*> @llvm.masked.load.v8p0f64(<8 x double*>*
+;AVX512: call <8 x double*> @llvm.masked.load.v8p0f64.p0v8p0f64(<8 x double*>*
-;AVX512: call void @llvm.masked.store.v8f64
+;AVX512: call void @llvm.masked.store.v8f64.p0v8f64
 ;AVX512: ret void
 
 define void @foo7(double* noalias %out, double** noalias %in, i8* noalias %trigger, i32 %size) #0 {
@@ -579,8 +654,8 @@ for.end:                                          ; preds = %for.cond
 ;}
 
 ;AVX512-LABEL: @foo8
-;AVX512: call <8 x i32 ()*> @llvm.masked.load.v8p0f_i32f(<8 x i32 ()*>* %
+;AVX512: call <8 x i32 ()*> @llvm.masked.load.v8p0f_i32f.p0v8p0f_i32f(<8 x i32 ()*>* %
-;AVX512: call void @llvm.masked.store.v8f64
+;AVX512: call void @llvm.masked.store.v8f64.p0v8f64
 ;AVX512: ret void
 
 define void @foo8(double* noalias %out, i32 ()** noalias %in, i8* noalias %trigger, i32 %size) #0 {