https://github.com/bob80905 updated 
https://github.com/llvm/llvm-project/pull/166449

>From 99c97887389d5255905394052a766b7dee2129fd Mon Sep 17 00:00:00 2001
From: Joshua Batista <[email protected]>
Date: Thu, 30 Oct 2025 17:06:11 -0700
Subject: [PATCH 1/5] as far as I can go without adding CAFM

---
 clang/include/clang/Basic/Builtins.td         |  6 ++++
 clang/lib/CodeGen/CGHLSLBuiltins.cpp          | 11 ++++++
 clang/lib/CodeGen/CGHLSLRuntime.h             |  2 ++
 clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.cpp | 36 +++++++++++++++++++
 clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.h   |  3 ++
 clang/lib/Sema/SemaHLSL.cpp                   | 21 +++++++++++
 .../StructuredBuffers-methods-lib.hlsl        | 30 ++++++++++++++++
 .../StructuredBuffers-methods-ps.hlsl         | 33 +++++++++++++++++
 llvm/include/llvm/IR/IntrinsicsDirectX.td     |  4 +++
 llvm/include/llvm/IR/IntrinsicsSPIRV.td       |  3 ++
 llvm/lib/Target/DirectX/DXILOpLowering.cpp    | 11 ++++++
 11 files changed, 160 insertions(+)

diff --git a/clang/include/clang/Basic/Builtins.td 
b/clang/include/clang/Basic/Builtins.td
index 2b400b012d6ed..58f4b2ec0fb94 100644
--- a/clang/include/clang/Basic/Builtins.td
+++ b/clang/include/clang/Basic/Builtins.td
@@ -4934,6 +4934,12 @@ def HLSLResourceGetPointer : LangBuiltin<"HLSL_LANG"> {
   let Prototype = "void(...)";
 }
 
+def HLSLResourceGetPointerWithStatus : LangBuiltin<"HLSL_LANG"> {
+  let Spellings = ["__builtin_hlsl_resource_getpointer_with_status"];
+  let Attributes = [NoThrow];
+  let Prototype = "void(...)";
+}
+
 def HLSLResourceUninitializedHandle : LangBuiltin<"HLSL_LANG"> {
   let Spellings = ["__builtin_hlsl_resource_uninitializedhandle"];
   let Attributes = [NoThrow];
diff --git a/clang/lib/CodeGen/CGHLSLBuiltins.cpp 
b/clang/lib/CodeGen/CGHLSLBuiltins.cpp
index fbf4a5722caed..69f9877a2bc1c 100644
--- a/clang/lib/CodeGen/CGHLSLBuiltins.cpp
+++ b/clang/lib/CodeGen/CGHLSLBuiltins.cpp
@@ -353,6 +353,17 @@ Value *CodeGenFunction::EmitHLSLBuiltinExpr(unsigned 
BuiltinID,
         RetTy, CGM.getHLSLRuntime().getCreateResourceGetPointerIntrinsic(),
         ArrayRef<Value *>{HandleOp, IndexOp});
   }
+  case Builtin::BI__builtin_hlsl_resource_getpointer_with_status: {
+    Value *HandleOp = EmitScalarExpr(E->getArg(0));
+    Value *IndexOp = EmitScalarExpr(E->getArg(1));
+    Value *StatusOp = EmitScalarExpr(E->getArg(2));
+
+    llvm::Type *RetTy = ConvertType(E->getType());
+    return Builder.CreateIntrinsic(
+        RetTy,
+        CGM.getHLSLRuntime().getCreateResourceGetPointerWithStatusIntrinsic(),
+        ArrayRef<Value *>{HandleOp, IndexOp, StatusOp});
+  }
   case Builtin::BI__builtin_hlsl_resource_uninitializedhandle: {
     llvm::Type *HandleTy = CGM.getTypes().ConvertType(E->getType());
     return llvm::PoisonValue::get(HandleTy);
diff --git a/clang/lib/CodeGen/CGHLSLRuntime.h 
b/clang/lib/CodeGen/CGHLSLRuntime.h
index d35df524fdc84..f965390d1e6fb 100644
--- a/clang/lib/CodeGen/CGHLSLRuntime.h
+++ b/clang/lib/CodeGen/CGHLSLRuntime.h
@@ -126,6 +126,8 @@ class CGHLSLRuntime {
 
   GENERATE_HLSL_INTRINSIC_FUNCTION(CreateResourceGetPointer,
                                    resource_getpointer)
+  GENERATE_HLSL_INTRINSIC_FUNCTION(CreateResourceGetPointerWithStatus,
+                                   resource_getpointer_with_status)
   GENERATE_HLSL_INTRINSIC_FUNCTION(CreateHandleFromBinding,
                                    resource_handlefrombinding)
   GENERATE_HLSL_INTRINSIC_FUNCTION(CreateHandleFromImplicitBinding,
diff --git a/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.cpp 
b/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.cpp
index 066acf6f01a90..e3fbf11d862ae 100644
--- a/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.cpp
+++ b/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.cpp
@@ -1140,6 +1140,7 @@ BuiltinTypeDeclBuilder 
&BuiltinTypeDeclBuilder::addLoadMethods() {
   DeclarationName Load(&II);
   // TODO: We also need versions with status for CheckAccessFullyMapped.
   addHandleAccessFunction(Load, /*IsConst=*/false, /*IsRef=*/false);
+  addHandleAccessFunctionWithStatus(Load, /*IsConst=*/false, /*IsRef=*/false);
 
   return *this;
 }
@@ -1232,6 +1233,41 @@ BuiltinTypeDeclBuilder 
&BuiltinTypeDeclBuilder::addDecrementCounterMethod() {
       .finalize();
 }
 
+BuiltinTypeDeclBuilder &
+BuiltinTypeDeclBuilder::addHandleAccessFunctionWithStatus(DeclarationName 
&Name,
+                                                          bool IsConst,
+                                                          bool IsRef) {
+  assert(!Record->isCompleteDefinition() && "record is already complete");
+  ASTContext &AST = SemaRef.getASTContext();
+  using PH = BuiltinTypeMethodBuilder::PlaceHolder;
+
+  QualType ElemTy = getHandleElementType();
+  QualType AddrSpaceElemTy =
+      AST.getAddrSpaceQualType(ElemTy, LangAS::hlsl_device);
+  QualType ElemPtrTy = AST.getPointerType(AddrSpaceElemTy);
+  QualType ReturnTy;
+
+  if (IsRef) {
+    ReturnTy = AddrSpaceElemTy;
+    if (IsConst)
+      ReturnTy.addConst();
+    ReturnTy = AST.getLValueReferenceType(ReturnTy);
+  } else {
+    ReturnTy = ElemTy;
+    if (IsConst)
+      ReturnTy.addConst();
+  }
+
+  QualType StatusRefTy = AST.getLValueReferenceType(AST.UnsignedIntTy);
+  return BuiltinTypeMethodBuilder(*this, Name, ReturnTy, IsConst)
+      .addParam("Index", AST.UnsignedIntTy)
+      .addParam("Status", StatusRefTy)
+      .callBuiltin("__builtin_hlsl_resource_getpointer_with_status", ElemPtrTy,
+                   PH::Handle, PH::_0, PH::_1)
+      .dereference(PH::LastStmt)
+      .finalize();
+}
+
 BuiltinTypeDeclBuilder &
 BuiltinTypeDeclBuilder::addHandleAccessFunction(DeclarationName &Name,
                                                 bool IsConst, bool IsRef) {
diff --git a/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.h 
b/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.h
index 95e3a6c4fb2f1..07305ad19dc5d 100644
--- a/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.h
+++ b/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.h
@@ -91,6 +91,9 @@ class BuiltinTypeDeclBuilder {
   BuiltinTypeDeclBuilder &addDecrementCounterMethod();
   BuiltinTypeDeclBuilder &addHandleAccessFunction(DeclarationName &Name,
                                                   bool IsConst, bool IsRef);
+  BuiltinTypeDeclBuilder &
+  addHandleAccessFunctionWithStatus(DeclarationName &Name, bool IsConst,
+                                    bool IsRef);
   BuiltinTypeDeclBuilder &addAppendMethod();
   BuiltinTypeDeclBuilder &addConsumeMethod();
 
diff --git a/clang/lib/Sema/SemaHLSL.cpp b/clang/lib/Sema/SemaHLSL.cpp
index 94a490a8f68dc..2e402deb25a01 100644
--- a/clang/lib/Sema/SemaHLSL.cpp
+++ b/clang/lib/Sema/SemaHLSL.cpp
@@ -3010,6 +3010,27 @@ bool SemaHLSL::CheckBuiltinFunctionCall(unsigned 
BuiltinID, CallExpr *TheCall) {
 
     break;
   }
+  case Builtin::BI__builtin_hlsl_resource_getpointer_with_status: {
+    if (SemaRef.checkArgCount(TheCall, 3) ||
+        CheckResourceHandle(&SemaRef, TheCall, 0) ||
+        CheckArgTypeMatches(&SemaRef, TheCall->getArg(1),
+                            SemaRef.getASTContext().UnsignedIntTy) ||
+        CheckArgTypeMatches(&SemaRef, TheCall->getArg(2),
+                            SemaRef.getASTContext().UnsignedIntTy))
+      return true;
+
+    auto *ResourceTy =
+        TheCall->getArg(0)->getType()->castAs<HLSLAttributedResourceType>();
+    QualType ContainedTy = ResourceTy->getContainedType();
+    auto ReturnType =
+        SemaRef.Context.getAddrSpaceQualType(ContainedTy, LangAS::hlsl_device);
+    ReturnType = SemaRef.Context.getPointerType(ReturnType);
+    TheCall->setType(ReturnType);
+    TheCall->setValueKind(VK_LValue);
+
+    break;
+  }
+
   case Builtin::BI__builtin_hlsl_resource_uninitializedhandle: {
     if (SemaRef.checkArgCount(TheCall, 1) ||
         CheckResourceHandle(&SemaRef, TheCall, 0))
diff --git 
a/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-lib.hlsl 
b/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-lib.hlsl
index 1f248d0560006..f7d7371650320 100644
--- a/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-lib.hlsl
+++ b/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-lib.hlsl
@@ -104,6 +104,36 @@ export float TestLoad() {
 // CHECK-NEXT: %[[VAL:.*]] = load float, ptr %[[PTR]]
 // CHECK-NEXT: ret float %[[VAL]]
 
+export float TestLoadWithStatus() {
+    uint s1;
+    uint s2;
+    float ret = RWSB1.Load(1, s) + SB1.Load(2, s2);
+    ret += float(s1 + s2);
+    return ret;
+}
+
+// CHECK: define noundef nofpclass(nan inf) float @TestLoad()()
+// CHECK: call {{.*}} float @hlsl::RWStructuredBuffer<float>::Load(unsigned 
int)(ptr {{.*}} @RWSB1, i32 noundef 1)
+// CHECK: call {{.*}} float @hlsl::StructuredBuffer<float>::Load(unsigned 
int)(ptr {{.*}} @SB1, i32 noundef 2)
+// CHECK: add
+// CHECK: ret float
+
+// CHECK: define {{.*}} float @hlsl::RWStructuredBuffer<float>::Load(unsigned 
int)(ptr {{.*}} %this, i32 noundef %Index)
+// CHECK: %__handle = getelementptr inbounds nuw 
%"class.hlsl::RWStructuredBuffer", ptr %{{.*}}, i32 0, i32 0
+// DXIL-NEXT: %[[HANDLE:.*]] = load target("dx.RawBuffer", float, 1, 0), ptr 
%__handle
+// CHECK-NEXT: %[[INDEX:.*]] = load i32, ptr %Index.addr
+// DXIL-NEXT: %[[PTR:.*]] = call ptr 
@llvm.dx.resource.getpointer.p0.tdx.RawBuffer_f32_1_0t(target("dx.RawBuffer", 
float, 1, 0) %[[HANDLE]], i32 %[[INDEX]])
+// CHECK-NEXT: %[[VAL:.*]] = load float, ptr %[[PTR]]
+// CHECK-NEXT: ret float %[[VAL]]
+
+// CHECK: define {{.*}} float @hlsl::StructuredBuffer<float>::Load(unsigned 
int)(ptr {{.*}} %this, i32 noundef %Index)
+// CHECK: %__handle = getelementptr inbounds nuw 
%"class.hlsl::StructuredBuffer", ptr %{{.*}}, i32 0, i32 0
+// DXIL-NEXT: %[[HANDLE:.*]] = load target("dx.RawBuffer", float, 0, 0), ptr 
%__handle
+// CHECK-NEXT: %[[INDEX:.*]] = load i32, ptr %Index.addr
+// DXIL-NEXT: %[[PTR:.*]] = call ptr 
@llvm.dx.resource.getpointer.p0.tdx.RawBuffer_f32_0_0t(target("dx.RawBuffer", 
float, 0, 0) %[[HANDLE]], i32 %[[INDEX]])
+// CHECK-NEXT: %[[VAL:.*]] = load float, ptr %[[PTR]]
+// CHECK-NEXT: ret float %[[VAL]]
+
 export uint TestGetDimensions() {
     uint dim1, dim2, dim3, stride1, stride2, stride3;
     SB1.GetDimensions(dim1, stride1);
diff --git a/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-ps.hlsl 
b/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-ps.hlsl
index 25fa75965d686..2c90604ef7ce2 100644
--- a/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-ps.hlsl
+++ b/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-ps.hlsl
@@ -65,6 +65,39 @@ export float TestLoad() {
 // CHECK-NEXT: %[[VAL:.*]] = load <2 x i32>, ptr %[[BUFPTR]]
 // CHECK-NEXT: ret <2 x i32> %[[VAL]]
 
+export float TestLoadWithStatus() {
+    uint status;
+    uint status2;
+    float val = ROSB1.Load(10, status).x + ROSB2.Load(20, status2).x;
+    return val + float(status + status2);
+}
+
+// CHECK: define {{.*}} float @TestLoadWithStatus()()
+// CHECK: call {{.*}} float 
@hlsl::RasterizerOrderedStructuredBuffer<float>::Load(unsigned int, unsigned 
int&)(ptr {{.*}} @ROSB1, i32 noundef 10, ptr noundef nonnull align 4 
dereferenceable(4) %status)
+// CHECK: call {{.*}} <2 x i32> @hlsl::RasterizerOrderedStructuredBuffer<int 
vector[2]>::Load(unsigned int, unsigned int&)(ptr {{.*}} @ROSB2, i32 noundef 
20, ptr noundef nonnull align 4 dereferenceable(4) %status2)
+// CHECK: ret
+
+// CHECK: define {{.*}} float 
@hlsl::RasterizerOrderedStructuredBuffer<float>::Load(unsigned int, unsigned 
int&)(ptr {{.*}} %Index, ptr noundef nonnull align 4 dereferenceable(4) %Status)
+// CHECK: %__handle = getelementptr inbounds nuw 
%"class.hlsl::RasterizerOrderedStructuredBuffer", ptr {{.*}}, i32 0, i32 0
+// CHECK-NEXT: %[[HANDLE:.*]] = load target("dx.RawBuffer", float, 1, 1), ptr 
%__handle
+// CHECK-NEXT: %[[INDEX:.*]] = load i32, ptr %Index.addr
+// CHECK-NEXT: %[[STATUS_HANDLE:.*]] = load ptr, ptr %Status.addr, align 4, 
!nonnull !3, !align !4
+// CHECK-NEXT: %[[STATUS:.*]] = load i32, ptr %[[STATUS_HANDLE]], align 4
+// DXIL-NEXT: %[[BUFPTR:.*]] = call ptr 
@llvm.dx.resource.getpointer.with.status.p0.tdx.RawBuffer_f32_1_1t(target("dx.RawBuffer",
 float, 1, 1) %[[HANDLE]], i32 %[[INDEX]], i32 %[[STATUS]])
+// CHECK-NEXT: %[[VAL:.*]] = load float, ptr %[[BUFPTR]]
+// CHECK-NEXT: ret float %[[VAL]]
+
+// CHECK: define {{.*}} <2 x i32> @hlsl::RasterizerOrderedStructuredBuffer<int 
vector[2]>::Load(unsigned int, unsigned int&)(ptr {{.*}} %Index, ptr noundef 
nonnull align 4 dereferenceable(4) %Status)
+// CHECK: %__handle = getelementptr inbounds nuw 
%"class.hlsl::RasterizerOrderedStructuredBuffer.0", ptr {{.*}}, i32 0, i32 0
+// CHECK-NEXT: %[[HANDLE:.*]] = load target("dx.RawBuffer", <2 x i32>, 1, 1), 
ptr %__handle
+// CHECK-NEXT: %[[INDEX:.*]] = load i32, ptr %Index.addr
+// CHECK-NEXT: %[[STATUS_HANDLE:.*]] = load ptr, ptr %Status.addr, align 4, 
!nonnull !3, !align !4
+// CHECK-NEXT: %[[STATUS:.*]] = load i32, ptr %[[STATUS_HANDLE]], align 4
+// DXIL-NEXT: %[[BUFPTR:.*]] = call ptr 
@llvm.dx.resource.getpointer.with.status.p0.tdx.RawBuffer_v2i32_1_1t(target("dx.RawBuffer",
 <2 x i32>, 1, 1) %[[HANDLE]], i32 %[[INDEX]], i32 %[[STATUS]])
+// CHECK-NEXT: %[[VAL:.*]] = load <2 x i32>, ptr %[[BUFPTR]]
+// CHECK-NEXT: ret <2 x i32> %[[VAL]]
+
+
 export uint TestGetDimensions() {
     uint dim1, dim2, stride1, stride2;
     ROSB1.GetDimensions(dim1, stride1);
diff --git a/llvm/include/llvm/IR/IntrinsicsDirectX.td 
b/llvm/include/llvm/IR/IntrinsicsDirectX.td
index d6b85630eb979..3dfefc8a0eda5 100644
--- a/llvm/include/llvm/IR/IntrinsicsDirectX.td
+++ b/llvm/include/llvm/IR/IntrinsicsDirectX.td
@@ -40,6 +40,10 @@ def int_dx_resource_getpointer
     : DefaultAttrsIntrinsic<[llvm_anyptr_ty], [llvm_any_ty, llvm_i32_ty],
                             [IntrNoMem]>;
 
+def int_dx_resource_getpointer_with_status
+    : DefaultAttrsIntrinsic<[llvm_anyptr_ty], [llvm_any_ty, llvm_i32_ty, 
llvm_i32_ty],
+                            [IntrNoMem]>;
+
 def int_dx_resource_nonuniformindex
     : DefaultAttrsIntrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoMem]>;
 
diff --git a/llvm/include/llvm/IR/IntrinsicsSPIRV.td 
b/llvm/include/llvm/IR/IntrinsicsSPIRV.td
index bc51fb639fd75..36d7aa24d864e 100644
--- a/llvm/include/llvm/IR/IntrinsicsSPIRV.td
+++ b/llvm/include/llvm/IR/IntrinsicsSPIRV.td
@@ -175,6 +175,9 @@ def int_spv_rsqrt : 
DefaultAttrsIntrinsic<[LLVMMatchType<0>], [llvm_anyfloat_ty]
   def int_spv_resource_getpointer
       : DefaultAttrsIntrinsic<[llvm_anyptr_ty], [llvm_any_ty, llvm_i32_ty],
                               [IntrNoMem]>;
+  def int_spv_resource_getpointer_with_status
+      : DefaultAttrsIntrinsic<[llvm_anyptr_ty], [llvm_any_ty, llvm_i32_ty, 
llvm_i32_ty],
+                              [IntrNoMem]>;
 
 def int_spv_resource_nonuniformindex
       : DefaultAttrsIntrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoMem]>;
diff --git a/llvm/lib/Target/DirectX/DXILOpLowering.cpp 
b/llvm/lib/Target/DirectX/DXILOpLowering.cpp
index 8720460cceb20..f46e066c2dbb3 100644
--- a/llvm/lib/Target/DirectX/DXILOpLowering.cpp
+++ b/llvm/lib/Target/DirectX/DXILOpLowering.cpp
@@ -657,6 +657,14 @@ class OpLowerer {
     return false;
   }
 
+  [[nodiscard]] bool lowerGetPointerWithStatus(Function &F) {
+    // These should have already been handled in DXILResourceAccess, so we can
+    // just clean up the dead prototype.
+    assert(F.user_empty() && "getpointer operations should have been removed");
+    F.eraseFromParent();
+    return false;
+  }
+
   [[nodiscard]] bool lowerBufferStore(Function &F, bool IsRaw) {
     const DataLayout &DL = F.getDataLayout();
     IRBuilder<> &IRB = OpBuilder.getIRB();
@@ -933,6 +941,9 @@ class OpLowerer {
       case Intrinsic::dx_resource_getpointer:
         HasErrors |= lowerGetPointer(F);
         break;
+      case Intrinsic::dx_resource_getpointer_with_status:
+        HasErrors |= lowerGetPointerWithStatus(F);
+        break;
       case Intrinsic::dx_resource_nonuniformindex:
         assert(!CleanupNURI &&
                "overloaded llvm.dx.resource.nonuniformindex intrinsics?");

>From 06ad11a6df118dbbcf9441a63a3eca0750fe0c0c Mon Sep 17 00:00:00 2001
From: Joshua Batista <[email protected]>
Date: Tue, 4 Nov 2025 12:03:27 -0800
Subject: [PATCH 2/5] works without cafm

---
 clang/include/clang/Basic/Builtins.td         |  4 +-
 clang/lib/CodeGen/CGHLSLBuiltins.cpp          | 51 ++++++++++++++++---
 clang/lib/CodeGen/CGHLSLRuntime.h             |  5 +-
 clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.cpp |  9 ++--
 clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.h   |  5 +-
 clang/lib/Sema/SemaHLSL.cpp                   |  2 +-
 .../StructuredBuffers-methods-lib.hlsl        | 36 ++++++++-----
 .../StructuredBuffers-methods-ps.hlsl         | 24 +++++----
 .../resources/TypedBuffers-methods.hlsl       | 40 +++++++++++++++
 llvm/include/llvm/IR/IntrinsicsDirectX.td     |  2 +-
 llvm/include/llvm/IR/IntrinsicsSPIRV.td       |  2 +-
 llvm/lib/Target/DirectX/DXILOpLowering.cpp    |  6 +--
 12 files changed, 139 insertions(+), 47 deletions(-)

diff --git a/clang/include/clang/Basic/Builtins.td 
b/clang/include/clang/Basic/Builtins.td
index 58f4b2ec0fb94..f2b4c54a5ba6b 100644
--- a/clang/include/clang/Basic/Builtins.td
+++ b/clang/include/clang/Basic/Builtins.td
@@ -4934,8 +4934,8 @@ def HLSLResourceGetPointer : LangBuiltin<"HLSL_LANG"> {
   let Prototype = "void(...)";
 }
 
-def HLSLResourceGetPointerWithStatus : LangBuiltin<"HLSL_LANG"> {
-  let Spellings = ["__builtin_hlsl_resource_getpointer_with_status"];
+def HLSLResourceLoadWithStatus : LangBuiltin<"HLSL_LANG"> {
+  let Spellings = ["__builtin_hlsl_resource_load_with_status"];
   let Attributes = [NoThrow];
   let Prototype = "void(...)";
 }
diff --git a/clang/lib/CodeGen/CGHLSLBuiltins.cpp 
b/clang/lib/CodeGen/CGHLSLBuiltins.cpp
index 69f9877a2bc1c..607cf523ddf78 100644
--- a/clang/lib/CodeGen/CGHLSLBuiltins.cpp
+++ b/clang/lib/CodeGen/CGHLSLBuiltins.cpp
@@ -353,16 +353,53 @@ Value *CodeGenFunction::EmitHLSLBuiltinExpr(unsigned 
BuiltinID,
         RetTy, CGM.getHLSLRuntime().getCreateResourceGetPointerIntrinsic(),
         ArrayRef<Value *>{HandleOp, IndexOp});
   }
-  case Builtin::BI__builtin_hlsl_resource_getpointer_with_status: {
+  case Builtin::BI__builtin_hlsl_resource_load_with_status: {
     Value *HandleOp = EmitScalarExpr(E->getArg(0));
     Value *IndexOp = EmitScalarExpr(E->getArg(1));
-    Value *StatusOp = EmitScalarExpr(E->getArg(2));
 
-    llvm::Type *RetTy = ConvertType(E->getType());
-    return Builder.CreateIntrinsic(
-        RetTy,
-        CGM.getHLSLRuntime().getCreateResourceGetPointerWithStatusIntrinsic(),
-        ArrayRef<Value *>{HandleOp, IndexOp, StatusOp});
+    // Get the *address* of the status argument (since it's a reference)
+    LValue StatusLVal = EmitLValue(E->getArg(2));
+    Address StatusAddr = StatusLVal.getAddress();
+
+    QualType HandleTy = E->getArg(0)->getType();
+    const HLSLAttributedResourceType *RT =
+        HandleTy->getAs<HLSLAttributedResourceType>();
+    assert(RT && "Expected a resource type as first parameter");
+
+    Intrinsic::ID IntrID = RT->getAttrs().RawBuffer
+                               ? llvm::Intrinsic::dx_resource_load_rawbuffer
+                               : llvm::Intrinsic::dx_resource_load_typedbuffer;
+
+    llvm::Type *DataTy = ConvertType(E->getType());
+    llvm::Type *RetTy = llvm::StructType::get(Builder.getContext(),
+                                              {DataTy, Builder.getInt1Ty()});
+
+    SmallVector<Value *, 3> Args;
+    Args.push_back(HandleOp);
+    Args.push_back(IndexOp);
+
+    if (RT->getAttrs().RawBuffer) {
+      Args.push_back(Builder.getInt32(0)); // dummy offset
+    }
+
+    // Call the intrinsic (returns a struct)
+    Value *ResRet =
+        Builder.CreateIntrinsic(RetTy, IntrID, Args, {}, "ld.struct");
+
+    // Extract the loaded data (first element of the struct)
+    Value *LoadedValue = Builder.CreateExtractValue(ResRet, {0}, "ld.value");
+
+    // Extract the status bit (second element of the struct)
+    Value *StatusBit = Builder.CreateExtractValue(ResRet, {1}, "ld.status");
+
+    // Extend the status bit to a 32-bit integer
+    Value *ExtendedStatus =
+        Builder.CreateZExt(StatusBit, Builder.getInt32Ty(), "ld.status.ext");
+
+    // Store the extended status into the user's reference variable
+    Builder.CreateStore(ExtendedStatus, StatusAddr);
+
+    return LoadedValue;
   }
   case Builtin::BI__builtin_hlsl_resource_uninitializedhandle: {
     llvm::Type *HandleTy = CGM.getTypes().ConvertType(E->getType());
diff --git a/clang/lib/CodeGen/CGHLSLRuntime.h 
b/clang/lib/CodeGen/CGHLSLRuntime.h
index f965390d1e6fb..f6c654bd61ff5 100644
--- a/clang/lib/CodeGen/CGHLSLRuntime.h
+++ b/clang/lib/CodeGen/CGHLSLRuntime.h
@@ -126,8 +126,9 @@ class CGHLSLRuntime {
 
   GENERATE_HLSL_INTRINSIC_FUNCTION(CreateResourceGetPointer,
                                    resource_getpointer)
-  GENERATE_HLSL_INTRINSIC_FUNCTION(CreateResourceGetPointerWithStatus,
-                                   resource_getpointer_with_status)
+
+  GENERATE_HLSL_INTRINSIC_FUNCTION(CreateResourceLoadTypedBuffer,
+                                   resource_load_typedbuffer)
   GENERATE_HLSL_INTRINSIC_FUNCTION(CreateHandleFromBinding,
                                    resource_handlefrombinding)
   GENERATE_HLSL_INTRINSIC_FUNCTION(CreateHandleFromImplicitBinding,
diff --git a/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.cpp 
b/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.cpp
index e3fbf11d862ae..bdbc2d4ce87b3 100644
--- a/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.cpp
+++ b/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.cpp
@@ -1140,7 +1140,7 @@ BuiltinTypeDeclBuilder 
&BuiltinTypeDeclBuilder::addLoadMethods() {
   DeclarationName Load(&II);
   // TODO: We also need versions with status for CheckAccessFullyMapped.
   addHandleAccessFunction(Load, /*IsConst=*/false, /*IsRef=*/false);
-  addHandleAccessFunctionWithStatus(Load, /*IsConst=*/false, /*IsRef=*/false);
+  addLoadWithStatusFunction(Load, /*IsConst=*/false, /*IsRef=*/false);
 
   return *this;
 }
@@ -1234,9 +1234,8 @@ BuiltinTypeDeclBuilder 
&BuiltinTypeDeclBuilder::addDecrementCounterMethod() {
 }
 
 BuiltinTypeDeclBuilder &
-BuiltinTypeDeclBuilder::addHandleAccessFunctionWithStatus(DeclarationName 
&Name,
-                                                          bool IsConst,
-                                                          bool IsRef) {
+BuiltinTypeDeclBuilder::addLoadWithStatusFunction(DeclarationName &Name,
+                                                  bool IsConst, bool IsRef) {
   assert(!Record->isCompleteDefinition() && "record is already complete");
   ASTContext &AST = SemaRef.getASTContext();
   using PH = BuiltinTypeMethodBuilder::PlaceHolder;
@@ -1262,7 +1261,7 @@ 
BuiltinTypeDeclBuilder::addHandleAccessFunctionWithStatus(DeclarationName &Name,
   return BuiltinTypeMethodBuilder(*this, Name, ReturnTy, IsConst)
       .addParam("Index", AST.UnsignedIntTy)
       .addParam("Status", StatusRefTy)
-      .callBuiltin("__builtin_hlsl_resource_getpointer_with_status", ElemPtrTy,
+      .callBuiltin("__builtin_hlsl_resource_load_with_status", ElemPtrTy,
                    PH::Handle, PH::_0, PH::_1)
       .dereference(PH::LastStmt)
       .finalize();
diff --git a/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.h 
b/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.h
index 07305ad19dc5d..4941b8b7952a2 100644
--- a/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.h
+++ b/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.h
@@ -91,9 +91,8 @@ class BuiltinTypeDeclBuilder {
   BuiltinTypeDeclBuilder &addDecrementCounterMethod();
   BuiltinTypeDeclBuilder &addHandleAccessFunction(DeclarationName &Name,
                                                   bool IsConst, bool IsRef);
-  BuiltinTypeDeclBuilder &
-  addHandleAccessFunctionWithStatus(DeclarationName &Name, bool IsConst,
-                                    bool IsRef);
+  BuiltinTypeDeclBuilder &addLoadWithStatusFunction(DeclarationName &Name,
+                                                    bool IsConst, bool IsRef);
   BuiltinTypeDeclBuilder &addAppendMethod();
   BuiltinTypeDeclBuilder &addConsumeMethod();
 
diff --git a/clang/lib/Sema/SemaHLSL.cpp b/clang/lib/Sema/SemaHLSL.cpp
index 2e402deb25a01..f95a647b5679f 100644
--- a/clang/lib/Sema/SemaHLSL.cpp
+++ b/clang/lib/Sema/SemaHLSL.cpp
@@ -3010,7 +3010,7 @@ bool SemaHLSL::CheckBuiltinFunctionCall(unsigned 
BuiltinID, CallExpr *TheCall) {
 
     break;
   }
-  case Builtin::BI__builtin_hlsl_resource_getpointer_with_status: {
+  case Builtin::BI__builtin_hlsl_resource_load_with_status: {
     if (SemaRef.checkArgCount(TheCall, 3) ||
         CheckResourceHandle(&SemaRef, TheCall, 0) ||
         CheckArgTypeMatches(&SemaRef, TheCall->getArg(1),
diff --git 
a/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-lib.hlsl 
b/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-lib.hlsl
index f7d7371650320..969586055b1d5 100644
--- a/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-lib.hlsl
+++ b/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-lib.hlsl
@@ -107,32 +107,42 @@ export float TestLoad() {
 export float TestLoadWithStatus() {
     uint s1;
     uint s2;
-    float ret = RWSB1.Load(1, s) + SB1.Load(2, s2);
+    float ret = RWSB1.Load(1, s1) + SB1.Load(2, s2);
     ret += float(s1 + s2);
     return ret;
 }
 
-// CHECK: define noundef nofpclass(nan inf) float @TestLoad()()
-// CHECK: call {{.*}} float @hlsl::RWStructuredBuffer<float>::Load(unsigned 
int)(ptr {{.*}} @RWSB1, i32 noundef 1)
-// CHECK: call {{.*}} float @hlsl::StructuredBuffer<float>::Load(unsigned 
int)(ptr {{.*}} @SB1, i32 noundef 2)
+// CHECK: define noundef nofpclass(nan inf) float @TestLoadWithStatus()()
+// CHECK: call {{.*}} float @hlsl::RWStructuredBuffer<float>::Load(unsigned 
int, unsigned int&)(ptr {{.*}} @RWSB1, i32 noundef 1, ptr noundef nonnull align 
4 dereferenceable(4) %s1)
+// CHECK: call {{.*}} float @hlsl::StructuredBuffer<float>::Load(unsigned int, 
unsigned int&)(ptr {{.*}} @SB1, i32 noundef 2, ptr noundef nonnull align 4 
dereferenceable(4) %s2)
 // CHECK: add
 // CHECK: ret float
 
-// CHECK: define {{.*}} float @hlsl::RWStructuredBuffer<float>::Load(unsigned 
int)(ptr {{.*}} %this, i32 noundef %Index)
+// CHECK: define {{.*}} float @hlsl::RWStructuredBuffer<float>::Load(unsigned 
int, unsigned int&)(ptr {{.*}} %this, i32 noundef %Index, ptr noundef nonnull 
align 4 dereferenceable(4) %Status)
 // CHECK: %__handle = getelementptr inbounds nuw 
%"class.hlsl::RWStructuredBuffer", ptr %{{.*}}, i32 0, i32 0
 // DXIL-NEXT: %[[HANDLE:.*]] = load target("dx.RawBuffer", float, 1, 0), ptr 
%__handle
 // CHECK-NEXT: %[[INDEX:.*]] = load i32, ptr %Index.addr
-// DXIL-NEXT: %[[PTR:.*]] = call ptr 
@llvm.dx.resource.getpointer.p0.tdx.RawBuffer_f32_1_0t(target("dx.RawBuffer", 
float, 1, 0) %[[HANDLE]], i32 %[[INDEX]])
-// CHECK-NEXT: %[[VAL:.*]] = load float, ptr %[[PTR]]
-// CHECK-NEXT: ret float %[[VAL]]
-
-// CHECK: define {{.*}} float @hlsl::StructuredBuffer<float>::Load(unsigned 
int)(ptr {{.*}} %this, i32 noundef %Index)
+// CHECK-NEXT: %[[STATUS:.*]] = load ptr, ptr %Status.addr,
+// DXIL-NEXT: %[[STRUCT:.*]] = call { ptr, i1 } 
@llvm.dx.resource.load.rawbuffer.p0.tdx.RawBuffer_f32_1_0t(target("dx.RawBuffer",
 float, 1, 0) %[[HANDLE]], i32 %[[INDEX]], i32 0)
+// CHECK-NEXT: %[[VALUE:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 0
+// CHECK-NEXT: %[[STATUS_TEMP:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 1
+// CHECK-NEXT: %[[STATUS_EXT:.*]] = zext i1 %[[STATUS_TEMP]] to i32
+// CHECK-NEXT: store i32 %[[STATUS_EXT]], ptr %2, align 4
+// CHECK-NEXT: %[[RETVAL:.*]] = load float, ptr %[[VALUE]]
+// CHECK-NEXT: ret float %[[RETVAL]]
+
+// CHECK: define {{.*}} float @hlsl::StructuredBuffer<float>::Load(unsigned 
int, unsigned int&)(ptr {{.*}} %this, i32 noundef %Index, ptr noundef nonnull 
align 4 dereferenceable(4) %Status)
 // CHECK: %__handle = getelementptr inbounds nuw 
%"class.hlsl::StructuredBuffer", ptr %{{.*}}, i32 0, i32 0
 // DXIL-NEXT: %[[HANDLE:.*]] = load target("dx.RawBuffer", float, 0, 0), ptr 
%__handle
 // CHECK-NEXT: %[[INDEX:.*]] = load i32, ptr %Index.addr
-// DXIL-NEXT: %[[PTR:.*]] = call ptr 
@llvm.dx.resource.getpointer.p0.tdx.RawBuffer_f32_0_0t(target("dx.RawBuffer", 
float, 0, 0) %[[HANDLE]], i32 %[[INDEX]])
-// CHECK-NEXT: %[[VAL:.*]] = load float, ptr %[[PTR]]
-// CHECK-NEXT: ret float %[[VAL]]
+// CHECK-NEXT: %[[STATUS_HANDLE:.*]] = load ptr, ptr %Status.addr, align 4, 
!nonnull !3, !align !4
+// DXIL-NEXT: %[[STRUCT:.*]] = call { ptr, i1 } 
@llvm.dx.resource.load.rawbuffer.p0.tdx.RawBuffer_f32_0_0t(target("dx.RawBuffer",
 float, 0, 0) %0, i32 %1, i32 0)
+// CHECK-NEXT: %[[VALUE:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 0
+// CHECK-NEXT: %[[STATUS:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 1
+// CHECK-NEXT: %[[STATUS_EXT:.*]] = zext i1 %[[STATUS]] to i32
+// CHECK-NEXT: store i32 %[[STATUS_EXT]], ptr %2, align 4
+// CHECK-NEXT: %[[RETVAL:.*]] = load float, ptr %[[VALUE]]
+// CHECK-NEXT: ret float %[[RETVAL]]
 
 export uint TestGetDimensions() {
     uint dim1, dim2, dim3, stride1, stride2, stride3;
diff --git a/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-ps.hlsl 
b/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-ps.hlsl
index 2c90604ef7ce2..38bb5ae7bb871 100644
--- a/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-ps.hlsl
+++ b/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-ps.hlsl
@@ -81,21 +81,27 @@ export float TestLoadWithStatus() {
 // CHECK: %__handle = getelementptr inbounds nuw 
%"class.hlsl::RasterizerOrderedStructuredBuffer", ptr {{.*}}, i32 0, i32 0
 // CHECK-NEXT: %[[HANDLE:.*]] = load target("dx.RawBuffer", float, 1, 1), ptr 
%__handle
 // CHECK-NEXT: %[[INDEX:.*]] = load i32, ptr %Index.addr
-// CHECK-NEXT: %[[STATUS_HANDLE:.*]] = load ptr, ptr %Status.addr, align 4, 
!nonnull !3, !align !4
-// CHECK-NEXT: %[[STATUS:.*]] = load i32, ptr %[[STATUS_HANDLE]], align 4
-// DXIL-NEXT: %[[BUFPTR:.*]] = call ptr 
@llvm.dx.resource.getpointer.with.status.p0.tdx.RawBuffer_f32_1_1t(target("dx.RawBuffer",
 float, 1, 1) %[[HANDLE]], i32 %[[INDEX]], i32 %[[STATUS]])
-// CHECK-NEXT: %[[VAL:.*]] = load float, ptr %[[BUFPTR]]
-// CHECK-NEXT: ret float %[[VAL]]
+// CHECK-NEXT: %[[STATUS:.*]] = load ptr, ptr %Status.addr,
+// DXIL-NEXT: %[[STRUCT:.*]] = call { ptr, i1 } 
@llvm.dx.resource.load.rawbuffer.p0.tdx.RawBuffer_f32_1_1t(target("dx.RawBuffer",
 float, 1, 1) %[[HANDLE]], i32 %[[INDEX]], i32 0)
+// CHECK-NEXT: %[[VALUE:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 0
+// CHECK-NEXT: %[[STATUS_TEMP:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 1
+// CHECK-NEXT: %[[STATUS_EXT:.*]] = zext i1 %[[STATUS_TEMP]] to i32
+// CHECK-NEXT: store i32 %[[STATUS_EXT]], ptr %2, align 4
+// CHECK-NEXT: %[[RETVAL:.*]] = load float, ptr %[[VALUE]]
+// CHECK-NEXT: ret float %[[RETVAL]]
 
 // CHECK: define {{.*}} <2 x i32> @hlsl::RasterizerOrderedStructuredBuffer<int 
vector[2]>::Load(unsigned int, unsigned int&)(ptr {{.*}} %Index, ptr noundef 
nonnull align 4 dereferenceable(4) %Status)
 // CHECK: %__handle = getelementptr inbounds nuw 
%"class.hlsl::RasterizerOrderedStructuredBuffer.0", ptr {{.*}}, i32 0, i32 0
 // CHECK-NEXT: %[[HANDLE:.*]] = load target("dx.RawBuffer", <2 x i32>, 1, 1), 
ptr %__handle
 // CHECK-NEXT: %[[INDEX:.*]] = load i32, ptr %Index.addr
 // CHECK-NEXT: %[[STATUS_HANDLE:.*]] = load ptr, ptr %Status.addr, align 4, 
!nonnull !3, !align !4
-// CHECK-NEXT: %[[STATUS:.*]] = load i32, ptr %[[STATUS_HANDLE]], align 4
-// DXIL-NEXT: %[[BUFPTR:.*]] = call ptr 
@llvm.dx.resource.getpointer.with.status.p0.tdx.RawBuffer_v2i32_1_1t(target("dx.RawBuffer",
 <2 x i32>, 1, 1) %[[HANDLE]], i32 %[[INDEX]], i32 %[[STATUS]])
-// CHECK-NEXT: %[[VAL:.*]] = load <2 x i32>, ptr %[[BUFPTR]]
-// CHECK-NEXT: ret <2 x i32> %[[VAL]]
+// DXIL-NEXT: %[[STRUCT:.*]] = call { ptr, i1 } 
@llvm.dx.resource.load.rawbuffer.p0.tdx.RawBuffer_v2i32_1_1t(target("dx.RawBuffer",
 <2 x i32>, 1, 1) %0, i32 %1, i32 0)
+// CHECK-NEXT: %[[VALUE:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 0
+// CHECK-NEXT: %[[STATUS:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 1
+// CHECK-NEXT: %[[STATUS_EXT:.*]] = zext i1 %[[STATUS]] to i32
+// CHECK-NEXT: store i32 %[[STATUS_EXT]], ptr %2, align 4
+// CHECK-NEXT: %[[RETVAL:.*]] = load <2 x i32>, ptr %[[VALUE]]
+// CHECK-NEXT: ret <2 x i32> %[[RETVAL]]
 
 
 export uint TestGetDimensions() {
diff --git a/clang/test/CodeGenHLSL/resources/TypedBuffers-methods.hlsl 
b/clang/test/CodeGenHLSL/resources/TypedBuffers-methods.hlsl
index fdc1ef08b7c2c..c884b857f59bf 100644
--- a/clang/test/CodeGenHLSL/resources/TypedBuffers-methods.hlsl
+++ b/clang/test/CodeGenHLSL/resources/TypedBuffers-methods.hlsl
@@ -38,6 +38,46 @@ export float TestLoad() {
 // CHECK-NEXT: %[[VEC:.*]] = load <4 x i32>, ptr %[[PTR]]
 // CHECK-NEXT: ret <4 x i32> %[[VEC]]
 
+export float TestLoadWithStatus() {
+    uint s1;
+    uint s2;
+    float ret = Buf.Load(1, s1) + float(RWBuf.Load(2, s2).y);
+    ret += float(s1 + s2);
+    return ret;
+}
+
+// CHECK: define noundef nofpclass(nan inf) float @TestLoadWithStatus()()
+// CHECK: call {{.*}} float @hlsl::Buffer<float>::Load(unsigned int, unsigned 
int&)(ptr {{.*}} @Buf, i32 noundef 1, ptr noundef nonnull align 4 
dereferenceable(4) %s1)
+// CHECK: call {{.*}} <4 x i32> @hlsl::RWBuffer<unsigned int 
vector[4]>::Load(unsigned int, unsigned int&)(ptr {{.*}} @RWBuf, i32 noundef 2, 
ptr noundef nonnull align 4 dereferenceable(4) %s2)
+// CHECK: add
+// CHECK: ret float
+
+// CHECK: define {{.*}} float @hlsl::Buffer<float>::Load(unsigned int, 
unsigned int&)(ptr {{.*}} %this, i32 noundef %Index, ptr noundef nonnull align 
4 dereferenceable(4) %Status)
+// CHECK: %__handle = getelementptr inbounds nuw %"class.hlsl::Buffer", ptr 
%{{.*}}, i32 0, i32 0
+// DXIL-NEXT: %[[HANDLE:.*]] = load target("dx.TypedBuffer", float, 0, 0, 0), 
ptr %__handle
+// CHECK-NEXT: %[[INDEX:.*]] = load i32, ptr %Index.addr
+// CHECK-NEXT: %[[STATUS:.*]] = load ptr, ptr %Status.addr,
+// DXIL-NEXT: %[[STRUCT:.*]] = call { ptr, i1 } 
@llvm.dx.resource.load.typedbuffer.p0.tdx.TypedBuffer_f32_0_0_0t(target("dx.TypedBuffer",
 float, 0, 0, 0) %[[HANDLE]], i32 %[[INDEX]])
+// CHECK-NEXT: %[[VALUE:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 0
+// CHECK-NEXT: %[[STATUS_TEMP:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 1
+// CHECK-NEXT: %[[STATUS_EXT:.*]] = zext i1 %[[STATUS_TEMP]] to i32
+// CHECK-NEXT: store i32 %[[STATUS_EXT]], ptr %2, align 4
+// CHECK-NEXT: %[[RETVAL:.*]] = load float, ptr %[[VALUE]]
+// CHECK-NEXT: ret float %[[RETVAL]]
+
+// CHECK: define {{.*}}  <4 x i32> @hlsl::RWBuffer<unsigned int 
vector[4]>::Load(unsigned int, unsigned int&)(ptr {{.*}} %this, i32 noundef 
%Index, ptr noundef nonnull align 4 dereferenceable(4) %Status)
+// CHECK: %__handle = getelementptr inbounds nuw %"class.hlsl::RWBuffer", ptr 
%{{.*}}, i32 0, i32 0
+// DXIL-NEXT: %[[HANDLE:.*]] = load target("dx.TypedBuffer", <4 x i32>, 1, 0, 
0), ptr %__handle
+// CHECK-NEXT: %[[INDEX:.*]] = load i32, ptr %Index.addr
+// CHECK-NEXT: %[[STATUS_HANDLE:.*]] = load ptr, ptr %Status.addr, align 4, 
!nonnull !3, !align !4
+// DXIL-NEXT: %[[STRUCT:.*]] = call { ptr, i1 } 
@llvm.dx.resource.load.typedbuffer.p0.tdx.TypedBuffer_v4i32_1_0_0t(target("dx.TypedBuffer",
 <4 x i32>, 1, 0, 0) %0, i32 %1)
+// CHECK-NEXT: %[[VALUE:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 0
+// CHECK-NEXT: %[[STATUS:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 1
+// CHECK-NEXT: %[[STATUS_EXT:.*]] = zext i1 %[[STATUS]] to i32
+// CHECK-NEXT: store i32 %[[STATUS_EXT]], ptr %2, align 4
+// CHECK-NEXT: %[[RETVAL:.*]] = load <4 x i32>, ptr %[[VALUE]]
+// CHECK-NEXT: ret <4 x i32> %[[RETVAL]]
+
 export uint TestGetDimensions() {
     uint dim1, dim2;
     Buf.GetDimensions(dim1);
diff --git a/llvm/include/llvm/IR/IntrinsicsDirectX.td 
b/llvm/include/llvm/IR/IntrinsicsDirectX.td
index 3dfefc8a0eda5..6c2d4e33881ee 100644
--- a/llvm/include/llvm/IR/IntrinsicsDirectX.td
+++ b/llvm/include/llvm/IR/IntrinsicsDirectX.td
@@ -40,7 +40,7 @@ def int_dx_resource_getpointer
     : DefaultAttrsIntrinsic<[llvm_anyptr_ty], [llvm_any_ty, llvm_i32_ty],
                             [IntrNoMem]>;
 
-def int_dx_resource_getpointer_with_status
+def int_dx_resource_load_with_status
     : DefaultAttrsIntrinsic<[llvm_anyptr_ty], [llvm_any_ty, llvm_i32_ty, 
llvm_i32_ty],
                             [IntrNoMem]>;
 
diff --git a/llvm/include/llvm/IR/IntrinsicsSPIRV.td 
b/llvm/include/llvm/IR/IntrinsicsSPIRV.td
index 36d7aa24d864e..53ec4c3f5274d 100644
--- a/llvm/include/llvm/IR/IntrinsicsSPIRV.td
+++ b/llvm/include/llvm/IR/IntrinsicsSPIRV.td
@@ -175,7 +175,7 @@ def int_spv_rsqrt : 
DefaultAttrsIntrinsic<[LLVMMatchType<0>], [llvm_anyfloat_ty]
   def int_spv_resource_getpointer
       : DefaultAttrsIntrinsic<[llvm_anyptr_ty], [llvm_any_ty, llvm_i32_ty],
                               [IntrNoMem]>;
-  def int_spv_resource_getpointer_with_status
+  def int_spv_resource_load_with_status
       : DefaultAttrsIntrinsic<[llvm_anyptr_ty], [llvm_any_ty, llvm_i32_ty, 
llvm_i32_ty],
                               [IntrNoMem]>;
 
diff --git a/llvm/lib/Target/DirectX/DXILOpLowering.cpp 
b/llvm/lib/Target/DirectX/DXILOpLowering.cpp
index f46e066c2dbb3..bb1cc4f098b6e 100644
--- a/llvm/lib/Target/DirectX/DXILOpLowering.cpp
+++ b/llvm/lib/Target/DirectX/DXILOpLowering.cpp
@@ -657,7 +657,7 @@ class OpLowerer {
     return false;
   }
 
-  [[nodiscard]] bool lowerGetPointerWithStatus(Function &F) {
+  [[nodiscard]] bool lowerLoadWithStatus(Function &F) {
     // These should have already been handled in DXILResourceAccess, so we can
     // just clean up the dead prototype.
     assert(F.user_empty() && "getpointer operations should have been removed");
@@ -941,8 +941,8 @@ class OpLowerer {
       case Intrinsic::dx_resource_getpointer:
         HasErrors |= lowerGetPointer(F);
         break;
-      case Intrinsic::dx_resource_getpointer_with_status:
-        HasErrors |= lowerGetPointerWithStatus(F);
+      case Intrinsic::dx_resource_load_with_status:
+        HasErrors |= lowerLoadWithStatus(F);
         break;
       case Intrinsic::dx_resource_nonuniformindex:
         assert(!CleanupNURI &&

>From ec4e3a94c44b2b36f80137ad7528f75315991bb4 Mon Sep 17 00:00:00 2001
From: Joshua Batista <[email protected]>
Date: Thu, 6 Nov 2025 12:48:51 -0800
Subject: [PATCH 3/5] furthest checkpoint yet

---
 clang/lib/CodeGen/CGHLSLBuiltins.cpp          | 10 +++++----
 clang/lib/CodeGen/CGHLSLRuntime.h             |  3 ---
 clang/lib/Headers/hlsl/hlsl_intrinsics.h      |  2 ++
 clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.cpp | 17 +++++----------
 clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.h   |  2 +-
 .../test/AST/HLSL/StructuredBuffers-AST.hlsl  | 21 +++++++++++++++++++
 clang/test/AST/HLSL/TypedBuffers-AST.hlsl     | 20 ++++++++++++++++++
 7 files changed, 55 insertions(+), 20 deletions(-)

diff --git a/clang/lib/CodeGen/CGHLSLBuiltins.cpp 
b/clang/lib/CodeGen/CGHLSLBuiltins.cpp
index 607cf523ddf78..a7aed9229f2c9 100644
--- a/clang/lib/CodeGen/CGHLSLBuiltins.cpp
+++ b/clang/lib/CodeGen/CGHLSLBuiltins.cpp
@@ -370,9 +370,11 @@ Value *CodeGenFunction::EmitHLSLBuiltinExpr(unsigned 
BuiltinID,
                                ? llvm::Intrinsic::dx_resource_load_rawbuffer
                                : llvm::Intrinsic::dx_resource_load_typedbuffer;
 
-    llvm::Type *DataTy = ConvertType(E->getType());
-    llvm::Type *RetTy = llvm::StructType::get(Builder.getContext(),
-                                              {DataTy, Builder.getInt1Ty()});
+    QualType BuiltinRetTy = E->getType();
+    llvm::Type *DataTy = ConvertType(BuiltinRetTy->getPointeeType());
+
+    llvm::Type *IntrinsicRetTy = llvm::StructType::get(
+        Builder.getContext(), {DataTy, Builder.getInt1Ty()});
 
     SmallVector<Value *, 3> Args;
     Args.push_back(HandleOp);
@@ -384,7 +386,7 @@ Value *CodeGenFunction::EmitHLSLBuiltinExpr(unsigned 
BuiltinID,
 
     // Call the intrinsic (returns a struct)
     Value *ResRet =
-        Builder.CreateIntrinsic(RetTy, IntrID, Args, {}, "ld.struct");
+        Builder.CreateIntrinsic(IntrinsicRetTy, IntrID, Args, {}, "ld.struct");
 
     // Extract the loaded data (first element of the struct)
     Value *LoadedValue = Builder.CreateExtractValue(ResRet, {0}, "ld.value");
diff --git a/clang/lib/CodeGen/CGHLSLRuntime.h 
b/clang/lib/CodeGen/CGHLSLRuntime.h
index f6c654bd61ff5..d35df524fdc84 100644
--- a/clang/lib/CodeGen/CGHLSLRuntime.h
+++ b/clang/lib/CodeGen/CGHLSLRuntime.h
@@ -126,9 +126,6 @@ class CGHLSLRuntime {
 
   GENERATE_HLSL_INTRINSIC_FUNCTION(CreateResourceGetPointer,
                                    resource_getpointer)
-
-  GENERATE_HLSL_INTRINSIC_FUNCTION(CreateResourceLoadTypedBuffer,
-                                   resource_load_typedbuffer)
   GENERATE_HLSL_INTRINSIC_FUNCTION(CreateHandleFromBinding,
                                    resource_handlefrombinding)
   GENERATE_HLSL_INTRINSIC_FUNCTION(CreateHandleFromImplicitBinding,
diff --git a/clang/lib/Headers/hlsl/hlsl_intrinsics.h 
b/clang/lib/Headers/hlsl/hlsl_intrinsics.h
index 5ba5bfb9abde0..6663ae9e0d762 100644
--- a/clang/lib/Headers/hlsl/hlsl_intrinsics.h
+++ b/clang/lib/Headers/hlsl/hlsl_intrinsics.h
@@ -605,5 +605,7 @@ smoothstep(__detail::HLSL_FIXED_VECTOR<float, N> Min,
   return __detail::smoothstep_vec_impl(Min, Max, X);
 }
 
+bool CheckAccessFullyMapped(uint Status) { return static_cast<bool>(Status); }
+
 } // namespace hlsl
 #endif //_HLSL_HLSL_INTRINSICS_H_
diff --git a/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.cpp 
b/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.cpp
index bdbc2d4ce87b3..ced93c5b220b5 100644
--- a/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.cpp
+++ b/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.cpp
@@ -1140,7 +1140,7 @@ BuiltinTypeDeclBuilder 
&BuiltinTypeDeclBuilder::addLoadMethods() {
   DeclarationName Load(&II);
   // TODO: We also need versions with status for CheckAccessFullyMapped.
   addHandleAccessFunction(Load, /*IsConst=*/false, /*IsRef=*/false);
-  addLoadWithStatusFunction(Load, /*IsConst=*/false, /*IsRef=*/false);
+  addLoadWithStatusFunction(Load, /*IsConst=*/false);
 
   return *this;
 }
@@ -1235,7 +1235,7 @@ BuiltinTypeDeclBuilder 
&BuiltinTypeDeclBuilder::addDecrementCounterMethod() {
 
 BuiltinTypeDeclBuilder &
 BuiltinTypeDeclBuilder::addLoadWithStatusFunction(DeclarationName &Name,
-                                                  bool IsConst, bool IsRef) {
+                                                  bool IsConst) {
   assert(!Record->isCompleteDefinition() && "record is already complete");
   ASTContext &AST = SemaRef.getASTContext();
   using PH = BuiltinTypeMethodBuilder::PlaceHolder;
@@ -1246,16 +1246,9 @@ 
BuiltinTypeDeclBuilder::addLoadWithStatusFunction(DeclarationName &Name,
   QualType ElemPtrTy = AST.getPointerType(AddrSpaceElemTy);
   QualType ReturnTy;
 
-  if (IsRef) {
-    ReturnTy = AddrSpaceElemTy;
-    if (IsConst)
-      ReturnTy.addConst();
-    ReturnTy = AST.getLValueReferenceType(ReturnTy);
-  } else {
-    ReturnTy = ElemTy;
-    if (IsConst)
-      ReturnTy.addConst();
-  }
+  ReturnTy = ElemTy;
+  if (IsConst)
+    ReturnTy.addConst();
 
   QualType StatusRefTy = AST.getLValueReferenceType(AST.UnsignedIntTy);
   return BuiltinTypeMethodBuilder(*this, Name, ReturnTy, IsConst)
diff --git a/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.h 
b/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.h
index 4941b8b7952a2..47c8b0e225612 100644
--- a/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.h
+++ b/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.h
@@ -92,7 +92,7 @@ class BuiltinTypeDeclBuilder {
   BuiltinTypeDeclBuilder &addHandleAccessFunction(DeclarationName &Name,
                                                   bool IsConst, bool IsRef);
   BuiltinTypeDeclBuilder &addLoadWithStatusFunction(DeclarationName &Name,
-                                                    bool IsConst, bool IsRef);
+                                                    bool IsConst);
   BuiltinTypeDeclBuilder &addAppendMethod();
   BuiltinTypeDeclBuilder &addConsumeMethod();
 
diff --git a/clang/test/AST/HLSL/StructuredBuffers-AST.hlsl 
b/clang/test/AST/HLSL/StructuredBuffers-AST.hlsl
index 7a8c57c59643d..8f8208c40bc33 100644
--- a/clang/test/AST/HLSL/StructuredBuffers-AST.hlsl
+++ b/clang/test/AST/HLSL/StructuredBuffers-AST.hlsl
@@ -326,6 +326,27 @@ RESOURCE<float> Buffer;
 // CHECK-LOAD-NEXT: DeclRefExpr {{.*}} 'unsigned int' ParmVar {{.*}} 'Index' 
'unsigned int'
 // CHECK-LOAD-NEXT: AlwaysInlineAttr {{.*}} Implicit always_inline
 
+// Load with status method
+
+// CHECK-LOAD: CXXMethodDecl {{.*}} Load 'element_type (unsigned int, unsigned 
int &)'
+// CHECK-LOAD-NEXT: ParmVarDecl {{.*}} Index 'unsigned int'
+// CHECK-LOAD-NEXT: ParmVarDecl {{.*}} Status 'unsigned int &'
+// CHECK-LOAD-NEXT: CompoundStmt
+// CHECK-LOAD-NEXT: ReturnStmt
+// CHECK-LOAD-NEXT: UnaryOperator {{.*}} 'hlsl_device element_type' prefix '*' 
cannot overflow
+// CHECK-LOAD-NEXT: CallExpr {{.*}} 'hlsl_device element_type *'
+// CHECK-LOAD-NEXT: ImplicitCastExpr {{.*}} <BuiltinFnToFnPtr>
+// CHECK-LOAD-NEXT: DeclRefExpr {{.*}} '<builtin fn type>' Function {{.*}} 
'__builtin_hlsl_resource_load_with_status' 'void (...) noexcept'
+// CHECK-LOAD-NEXT: MemberExpr {{.*}} '__hlsl_resource_t
+// CHECK-LOAD-UAV-SAME{LITERAL}: [[hlsl::resource_class(UAV)]]
+// CHECK-LOAD-SRV-SAME{LITERAL}: [[hlsl::resource_class(SRV)]]
+// CHECK-LOAD-SAME{LITERAL}: [[hlsl::contained_type(element_type)]]
+// CHECK-LOAD-SAME: lvalue .__handle {{.*}}
+// CHECK-LOAD-NEXT: CXXThisExpr {{.*}} 'hlsl::[[RESOURCE]]<element_type>' 
lvalue implicit this
+// CHECK-LOAD-NEXT: DeclRefExpr {{.*}} 'unsigned int' ParmVar {{.*}} 'Index' 
'unsigned int'
+// CHECK-LOAD-NEXT: DeclRefExpr {{.*}} 'unsigned int' ParmVar {{.*}} 'Status' 
'unsigned int &'
+// CHECK-LOAD-NEXT: AlwaysInlineAttr {{.*}} Implicit always_inline
+
 // IncrementCounter method
 
 // CHECK-COUNTER: CXXMethodDecl {{.*}} IncrementCounter 'unsigned int ()'
diff --git a/clang/test/AST/HLSL/TypedBuffers-AST.hlsl 
b/clang/test/AST/HLSL/TypedBuffers-AST.hlsl
index 14e274d3855ed..bd81b87b72e9c 100644
--- a/clang/test/AST/HLSL/TypedBuffers-AST.hlsl
+++ b/clang/test/AST/HLSL/TypedBuffers-AST.hlsl
@@ -214,6 +214,26 @@ RESOURCE<float> Buffer;
 // CHECK-NEXT: DeclRefExpr {{.*}} 'unsigned int' ParmVar {{.*}}  'Index' 
'unsigned int'
 // CHECK-NEXT: AlwaysInlineAttr {{.*}} Implicit always_inline
 
+// Load with status method
+// CHECK-NEXT: CXXMethodDecl {{.*}} Load 'element_type (unsigned int, unsigned 
int &)'
+// CHECK-NEXT: ParmVarDecl {{.*}} Index 'unsigned int'
+// CHECK-NEXT: ParmVarDecl {{.*}} Status 'unsigned int &'
+// CHECK-NEXT: CompoundStmt
+// CHECK-NEXT: ReturnStmt
+// CHECK-NEXT: UnaryOperator {{.*}} 'hlsl_device element_type' prefix '*' 
cannot overflow
+// CHECK-NEXT: CallExpr {{.*}} 'hlsl_device element_type *'
+// CHECK-NEXT: ImplicitCastExpr {{.*}} <BuiltinFnToFnPtr>
+// CHECK-NEXT: DeclRefExpr {{.*}} '<builtin fn type>' Function {{.*}} 
'__builtin_hlsl_resource_load_with_status' 'void (...) noexcept'
+// CHECK-NEXT: MemberExpr {{.*}} '__hlsl_resource_t
+// CHECK-UAV-SAME{LITERAL}: [[hlsl::resource_class(UAV)]]
+// CHECK-SRV-SAME{LITERAL}: [[hlsl::resource_class(SRV)]]
+// CHECK-SAME{LITERAL}: [[hlsl::contained_type(element_type)]]
+// CHECK-SAME: lvalue .__handle {{.*}}
+// CHECK-NEXT: CXXThisExpr {{.*}} 'hlsl::[[RESOURCE]]<element_type>' lvalue 
implicit this
+// CHECK-NEXT: DeclRefExpr {{.*}} 'unsigned int' ParmVar {{.*}} 'Index' 
'unsigned int'
+// CHECK-NEXT: DeclRefExpr {{.*}} 'unsigned int' ParmVar {{.*}} 'Status' 
'unsigned int &'
+// CHECK-NEXT: AlwaysInlineAttr {{.*}} Implicit always_inline
+
 // GetDimensions method
 
 // CHECK-NEXT: CXXMethodDecl {{.*}} GetDimensions 'void (out unsigned int)'

>From 2a49c36987b1e4af875c8da9bed6c865c00e8da0 Mon Sep 17 00:00:00 2001
From: Joshua Batista <[email protected]>
Date: Mon, 10 Nov 2025 14:28:26 -0800
Subject: [PATCH 4/5] fix up function definition, add TiledResources shader
 flag

---
 clang/lib/CodeGen/CGHLSLBuiltins.cpp          | 12 ++++----
 clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.cpp | 29 +++++++++----------
 clang/lib/Sema/SemaHLSL.cpp                   |  8 ++---
 .../resources/TypedBuffers-methods.hlsl       |  6 ++--
 llvm/lib/Target/DirectX/DXILShaderFlags.cpp   | 28 ++++++++++++++++++
 5 files changed, 51 insertions(+), 32 deletions(-)

diff --git a/clang/lib/CodeGen/CGHLSLBuiltins.cpp 
b/clang/lib/CodeGen/CGHLSLBuiltins.cpp
index a7aed9229f2c9..6256b3d3d3760 100644
--- a/clang/lib/CodeGen/CGHLSLBuiltins.cpp
+++ b/clang/lib/CodeGen/CGHLSLBuiltins.cpp
@@ -357,7 +357,7 @@ Value *CodeGenFunction::EmitHLSLBuiltinExpr(unsigned 
BuiltinID,
     Value *HandleOp = EmitScalarExpr(E->getArg(0));
     Value *IndexOp = EmitScalarExpr(E->getArg(1));
 
-    // Get the *address* of the status argument (since it's a reference)
+    // Get the *address* of the status argument to write to it by reference
     LValue StatusLVal = EmitLValue(E->getArg(2));
     Address StatusAddr = StatusLVal.getAddress();
 
@@ -370,11 +370,9 @@ Value *CodeGenFunction::EmitHLSLBuiltinExpr(unsigned 
BuiltinID,
                                ? llvm::Intrinsic::dx_resource_load_rawbuffer
                                : llvm::Intrinsic::dx_resource_load_typedbuffer;
 
-    QualType BuiltinRetTy = E->getType();
-    llvm::Type *DataTy = ConvertType(BuiltinRetTy->getPointeeType());
-
-    llvm::Type *IntrinsicRetTy = llvm::StructType::get(
-        Builder.getContext(), {DataTy, Builder.getInt1Ty()});
+    llvm::Type *DataTy = ConvertType(E->getType());
+    llvm::Type *RetTy = llvm::StructType::get(Builder.getContext(),
+                                              {DataTy, Builder.getInt1Ty()});
 
     SmallVector<Value *, 3> Args;
     Args.push_back(HandleOp);
@@ -386,7 +384,7 @@ Value *CodeGenFunction::EmitHLSLBuiltinExpr(unsigned 
BuiltinID,
 
     // Call the intrinsic (returns a struct)
     Value *ResRet =
-        Builder.CreateIntrinsic(IntrinsicRetTy, IntrID, Args, {}, "ld.struct");
+        Builder.CreateIntrinsic(RetTy, IntrID, Args, {}, "ld.struct");
 
     // Extract the loaded data (first element of the struct)
     Value *LoadedValue = Builder.CreateExtractValue(ResRet, {0}, "ld.value");
diff --git a/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.cpp 
b/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.cpp
index ced93c5b220b5..284d5ff0177e9 100644
--- a/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.cpp
+++ b/clang/lib/Sema/HLSLBuiltinTypeDeclBuilder.cpp
@@ -202,7 +202,7 @@ struct BuiltinTypeMethodBuilder {
   BuiltinTypeMethodBuilder &declareLocalVar(LocalVar &Var);
   template <typename... Ts>
   BuiltinTypeMethodBuilder &callBuiltin(StringRef BuiltinName,
-                                        QualType ReturnType, Ts... ArgSpecs);
+                                        QualType ReturnType, Ts &&...ArgSpecs);
   template <typename TLHS, typename TRHS>
   BuiltinTypeMethodBuilder &assign(TLHS LHS, TRHS RHS);
   template <typename T> BuiltinTypeMethodBuilder &dereference(T Ptr);
@@ -572,7 +572,7 @@ BuiltinTypeMethodBuilder 
&BuiltinTypeMethodBuilder::returnThis() {
 template <typename... Ts>
 BuiltinTypeMethodBuilder &
 BuiltinTypeMethodBuilder::callBuiltin(StringRef BuiltinName,
-                                      QualType ReturnType, Ts... ArgSpecs) {
+                                      QualType ReturnType, Ts &&...ArgSpecs) {
   ensureCompleteDecl();
 
   std::array<Expr *, sizeof...(ArgSpecs)> Args{
@@ -1240,23 +1240,20 @@ 
BuiltinTypeDeclBuilder::addLoadWithStatusFunction(DeclarationName &Name,
   ASTContext &AST = SemaRef.getASTContext();
   using PH = BuiltinTypeMethodBuilder::PlaceHolder;
 
-  QualType ElemTy = getHandleElementType();
-  QualType AddrSpaceElemTy =
-      AST.getAddrSpaceQualType(ElemTy, LangAS::hlsl_device);
-  QualType ElemPtrTy = AST.getPointerType(AddrSpaceElemTy);
-  QualType ReturnTy;
-
-  ReturnTy = ElemTy;
-  if (IsConst)
-    ReturnTy.addConst();
+  QualType ReturnTy = getHandleElementType();
+  BuiltinTypeMethodBuilder::LocalVar ResultVar("Result", ReturnTy);
+  BuiltinTypeMethodBuilder::LocalVar StatusVar("StatusBool", AST.BoolTy);
 
-  QualType StatusRefTy = AST.getLValueReferenceType(AST.UnsignedIntTy);
   return BuiltinTypeMethodBuilder(*this, Name, ReturnTy, IsConst)
       .addParam("Index", AST.UnsignedIntTy)
-      .addParam("Status", StatusRefTy)
-      .callBuiltin("__builtin_hlsl_resource_load_with_status", ElemPtrTy,
-                   PH::Handle, PH::_0, PH::_1)
-      .dereference(PH::LastStmt)
+      .addParam("Status", AST.UnsignedIntTy, 
HLSLParamModifierAttr::Keyword_out)
+      .declareLocalVar(ResultVar)
+      .declareLocalVar(StatusVar)
+      .callBuiltin("__builtin_hlsl_resource_load_with_status", ReturnTy,
+                   PH::Handle, PH::_0, StatusVar)
+      .assign(ResultVar, PH::LastStmt)
+      .assign(PH::_1, StatusVar)
+      .returnValue(ResultVar)
       .finalize();
 }
 
diff --git a/clang/lib/Sema/SemaHLSL.cpp b/clang/lib/Sema/SemaHLSL.cpp
index f95a647b5679f..8cc737d83376c 100644
--- a/clang/lib/Sema/SemaHLSL.cpp
+++ b/clang/lib/Sema/SemaHLSL.cpp
@@ -3016,17 +3016,13 @@ bool SemaHLSL::CheckBuiltinFunctionCall(unsigned 
BuiltinID, CallExpr *TheCall) {
         CheckArgTypeMatches(&SemaRef, TheCall->getArg(1),
                             SemaRef.getASTContext().UnsignedIntTy) ||
         CheckArgTypeMatches(&SemaRef, TheCall->getArg(2),
-                            SemaRef.getASTContext().UnsignedIntTy))
+                            SemaRef.getASTContext().BoolTy))
       return true;
 
     auto *ResourceTy =
         TheCall->getArg(0)->getType()->castAs<HLSLAttributedResourceType>();
-    QualType ContainedTy = ResourceTy->getContainedType();
-    auto ReturnType =
-        SemaRef.Context.getAddrSpaceQualType(ContainedTy, LangAS::hlsl_device);
-    ReturnType = SemaRef.Context.getPointerType(ReturnType);
+    QualType ReturnType = ResourceTy->getContainedType();
     TheCall->setType(ReturnType);
-    TheCall->setValueKind(VK_LValue);
 
     break;
   }
diff --git a/clang/test/CodeGenHLSL/resources/TypedBuffers-methods.hlsl 
b/clang/test/CodeGenHLSL/resources/TypedBuffers-methods.hlsl
index c884b857f59bf..5960a1c406fc4 100644
--- a/clang/test/CodeGenHLSL/resources/TypedBuffers-methods.hlsl
+++ b/clang/test/CodeGenHLSL/resources/TypedBuffers-methods.hlsl
@@ -47,12 +47,12 @@ export float TestLoadWithStatus() {
 }
 
 // CHECK: define noundef nofpclass(nan inf) float @TestLoadWithStatus()()
-// CHECK: call {{.*}} float @hlsl::Buffer<float>::Load(unsigned int, unsigned 
int&)(ptr {{.*}} @Buf, i32 noundef 1, ptr noundef nonnull align 4 
dereferenceable(4) %s1)
-// CHECK: call {{.*}} <4 x i32> @hlsl::RWBuffer<unsigned int 
vector[4]>::Load(unsigned int, unsigned int&)(ptr {{.*}} @RWBuf, i32 noundef 2, 
ptr noundef nonnull align 4 dereferenceable(4) %s2)
+// CHECK: call {{.*}} float @hlsl::Buffer<float>::Load(unsigned int, unsigned 
int&)(ptr {{.*}} @Buf, i32 noundef 1, ptr noalias noundef nonnull align 4 
dereferenceable(4) %tmp)
+// CHECK: call {{.*}} <4 x i32> @hlsl::RWBuffer<unsigned int 
vector[4]>::Load(unsigned int, unsigned int&)(ptr {{.*}} @RWBuf, i32 noundef 2, 
ptr noalias noundef nonnull align 4 dereferenceable(4) %tmp1)
 // CHECK: add
 // CHECK: ret float
 
-// CHECK: define {{.*}} float @hlsl::Buffer<float>::Load(unsigned int, 
unsigned int&)(ptr {{.*}} %this, i32 noundef %Index, ptr noundef nonnull align 
4 dereferenceable(4) %Status)
+// CHECK: define {{.*}} float @hlsl::Buffer<float>::Load(unsigned int, 
unsigned int&)(ptr {{.*}} %this, i32 noundef %Index, ptr noalias noundef 
nonnull align 4 dereferenceable(4) %Status)
 // CHECK: %__handle = getelementptr inbounds nuw %"class.hlsl::Buffer", ptr 
%{{.*}}, i32 0, i32 0
 // DXIL-NEXT: %[[HANDLE:.*]] = load target("dx.TypedBuffer", float, 0, 0, 0), 
ptr %__handle
 // CHECK-NEXT: %[[INDEX:.*]] = load i32, ptr %Index.addr
diff --git a/llvm/lib/Target/DirectX/DXILShaderFlags.cpp 
b/llvm/lib/Target/DirectX/DXILShaderFlags.cpp
index ce6e8121b9d94..4b08b019e52f0 100644
--- a/llvm/lib/Target/DirectX/DXILShaderFlags.cpp
+++ b/llvm/lib/Target/DirectX/DXILShaderFlags.cpp
@@ -100,6 +100,27 @@ static bool checkWaveOps(Intrinsic::ID IID) {
   }
 }
 
+// Checks to see if the status bit from a load with status
+// instruction is ever extracted.
+// This is our proof that the module requires TiledResources
+// to be set, as if check access fully mapped was used.
+bool checkIfStatusIsExtracted(const Instruction &I) {
+  // Iterate over all uses of the instruction
+  for (const Use &U : I.uses()) {
+    const User *UserInst = U.getUser();
+
+    // Check if the user is an ExtractValue instruction
+    if (const ExtractValueInst *EVI = dyn_cast<ExtractValueInst>(UserInst)) {
+      // ExtractValueInst has a list of indices; check if it extracts index 1
+      if (EVI->getNumIndices() == 1 && EVI->getIndices()[0] == 1) {
+        return true;
+      }
+    }
+  }
+
+  return false;
+}
+
 /// Update the shader flags mask based on the given instruction.
 /// \param CSF Shader flags mask to update.
 /// \param I Instruction to check.
@@ -192,6 +213,13 @@ void 
ModuleShaderFlags::updateFunctionFlags(ComputedShaderFlags &CSF,
           DRTM[cast<TargetExtType>(II->getArgOperand(0)->getType())];
       if (RTI.isTyped())
         CSF.TypedUAVLoadAdditionalFormats |= RTI.getTyped().ElementCount > 1;
+      if (!CSF.TiledResources && checkIfStatusIsExtracted(I))
+        CSF.TiledResources = true;
+      break;
+    }
+    case Intrinsic::dx_resource_load_rawbuffer: {
+      if (!CSF.TiledResources && checkIfStatusIsExtracted(I))
+        CSF.TiledResources = true;
       break;
     }
     }

>From 0d0b79f224b13585c385d82736c6f737837c9106 Mon Sep 17 00:00:00 2001
From: Joshua Batista <[email protected]>
Date: Mon, 10 Nov 2025 19:13:18 -0800
Subject: [PATCH 5/5] update tests, make checkaccess inline so it doesn't get
 auto-emitted into every IR output

---
 clang/lib/Headers/hlsl/hlsl_intrinsics.h      |  4 +-
 .../test/AST/HLSL/StructuredBuffers-AST.hlsl  | 23 ++++++---
 clang/test/AST/HLSL/TypedBuffers-AST.hlsl     | 23 ++++++---
 .../StructuredBuffers-methods-lib.hlsl        | 50 +++++++++++--------
 .../StructuredBuffers-methods-ps.hlsl         | 50 +++++++++++--------
 .../resources/TypedBuffers-methods.hlsl       | 44 +++++++++-------
 6 files changed, 122 insertions(+), 72 deletions(-)

diff --git a/clang/lib/Headers/hlsl/hlsl_intrinsics.h 
b/clang/lib/Headers/hlsl/hlsl_intrinsics.h
index 6663ae9e0d762..c6bb4d2ca8cc5 100644
--- a/clang/lib/Headers/hlsl/hlsl_intrinsics.h
+++ b/clang/lib/Headers/hlsl/hlsl_intrinsics.h
@@ -605,7 +605,9 @@ smoothstep(__detail::HLSL_FIXED_VECTOR<float, N> Min,
   return __detail::smoothstep_vec_impl(Min, Max, X);
 }
 
-bool CheckAccessFullyMapped(uint Status) { return static_cast<bool>(Status); }
+inline bool CheckAccessFullyMapped(uint Status) {
+  return static_cast<bool>(Status);
+}
 
 } // namespace hlsl
 #endif //_HLSL_HLSL_INTRINSICS_H_
diff --git a/clang/test/AST/HLSL/StructuredBuffers-AST.hlsl 
b/clang/test/AST/HLSL/StructuredBuffers-AST.hlsl
index 8f8208c40bc33..b7111fe53eb23 100644
--- a/clang/test/AST/HLSL/StructuredBuffers-AST.hlsl
+++ b/clang/test/AST/HLSL/StructuredBuffers-AST.hlsl
@@ -328,23 +328,32 @@ RESOURCE<float> Buffer;
 
 // Load with status method
 
-// CHECK-LOAD: CXXMethodDecl {{.*}} Load 'element_type (unsigned int, unsigned 
int &)'
+// CHECK-LOAD: CXXMethodDecl {{.*}} Load 'element_type (unsigned int, out 
unsigned int)'
 // CHECK-LOAD-NEXT: ParmVarDecl {{.*}} Index 'unsigned int'
-// CHECK-LOAD-NEXT: ParmVarDecl {{.*}} Status 'unsigned int &'
+// CHECK-LOAD-NEXT: ParmVarDecl {{.*}} Status 'unsigned int &__restrict'
+// CHECK-LOAD-NEXT: HLSLParamModifierAttr {{.*}} out
 // CHECK-LOAD-NEXT: CompoundStmt
-// CHECK-LOAD-NEXT: ReturnStmt
-// CHECK-LOAD-NEXT: UnaryOperator {{.*}} 'hlsl_device element_type' prefix '*' 
cannot overflow
-// CHECK-LOAD-NEXT: CallExpr {{.*}} 'hlsl_device element_type *'
+// CHECK-LOAD-NEXT: DeclStmt
+// CHECK-LOAD-NEXT: VarDecl {{.*}} Result 'element_type'
+// CHECK-LOAD-NEXT: DeclStmt
+// CHECK-LOAD-NEXT: VarDecl {{.*}} StatusBool 'bool'
+// CHECK-LOAD-NEXT: BinaryOperator {{.*}} 'element_type' '='
+// CHECK-LOAD-NEXT: DeclRefExpr {{.*}} 'element_type' lvalue Var {{.*}} 
'Result' 'element_type'
+// CHECK-LOAD-NEXT: CallExpr {{.*}} 'element_type'
 // CHECK-LOAD-NEXT: ImplicitCastExpr {{.*}} <BuiltinFnToFnPtr>
 // CHECK-LOAD-NEXT: DeclRefExpr {{.*}} '<builtin fn type>' Function {{.*}} 
'__builtin_hlsl_resource_load_with_status' 'void (...) noexcept'
 // CHECK-LOAD-NEXT: MemberExpr {{.*}} '__hlsl_resource_t
 // CHECK-LOAD-UAV-SAME{LITERAL}: [[hlsl::resource_class(UAV)]]
 // CHECK-LOAD-SRV-SAME{LITERAL}: [[hlsl::resource_class(SRV)]]
 // CHECK-LOAD-SAME{LITERAL}: [[hlsl::contained_type(element_type)]]
-// CHECK-LOAD-SAME: lvalue .__handle {{.*}}
 // CHECK-LOAD-NEXT: CXXThisExpr {{.*}} 'hlsl::[[RESOURCE]]<element_type>' 
lvalue implicit this
 // CHECK-LOAD-NEXT: DeclRefExpr {{.*}} 'unsigned int' ParmVar {{.*}} 'Index' 
'unsigned int'
-// CHECK-LOAD-NEXT: DeclRefExpr {{.*}} 'unsigned int' ParmVar {{.*}} 'Status' 
'unsigned int &'
+// CHECK-LOAD-NEXT: DeclRefExpr {{.*}} 'bool' lvalue Var {{.*}} 'StatusBool' 
'bool'
+// CHECK-LOAD-NEXT: BinaryOperator {{.*}} 'unsigned int' '='
+// CHECK-LOAD-NEXT: DeclRefExpr {{.*}} 'unsigned int' ParmVar {{.*}} 'Status' 
'unsigned int &__restrict'
+// CHECK-LOAD-NEXT: DeclRefExpr {{.*}} 'bool' lvalue Var {{.*}} 'StatusBool' 
'bool'
+// CHECK-LOAD-NEXT: ReturnStmt
+// CHECK-LOAD-NEXT: DeclRefExpr {{.*}} 'element_type' lvalue Var {{.*}} 
'Result' 'element_type'
 // CHECK-LOAD-NEXT: AlwaysInlineAttr {{.*}} Implicit always_inline
 
 // IncrementCounter method
diff --git a/clang/test/AST/HLSL/TypedBuffers-AST.hlsl 
b/clang/test/AST/HLSL/TypedBuffers-AST.hlsl
index bd81b87b72e9c..8fb30eea7eb5b 100644
--- a/clang/test/AST/HLSL/TypedBuffers-AST.hlsl
+++ b/clang/test/AST/HLSL/TypedBuffers-AST.hlsl
@@ -215,23 +215,32 @@ RESOURCE<float> Buffer;
 // CHECK-NEXT: AlwaysInlineAttr {{.*}} Implicit always_inline
 
 // Load with status method
-// CHECK-NEXT: CXXMethodDecl {{.*}} Load 'element_type (unsigned int, unsigned 
int &)'
+// CHECK: CXXMethodDecl {{.*}} Load 'element_type (unsigned int, out unsigned 
int)'
 // CHECK-NEXT: ParmVarDecl {{.*}} Index 'unsigned int'
-// CHECK-NEXT: ParmVarDecl {{.*}} Status 'unsigned int &'
+// CHECK-NEXT: ParmVarDecl {{.*}} Status 'unsigned int &__restrict'
+// CHECK-NEXT: HLSLParamModifierAttr {{.*}} out
 // CHECK-NEXT: CompoundStmt
-// CHECK-NEXT: ReturnStmt
-// CHECK-NEXT: UnaryOperator {{.*}} 'hlsl_device element_type' prefix '*' 
cannot overflow
-// CHECK-NEXT: CallExpr {{.*}} 'hlsl_device element_type *'
+// CHECK-NEXT: DeclStmt
+// CHECK-NEXT: VarDecl {{.*}} Result 'element_type'
+// CHECK-NEXT: DeclStmt
+// CHECK-NEXT: VarDecl {{.*}} StatusBool 'bool'
+// CHECK-NEXT: BinaryOperator {{.*}} 'element_type' '='
+// CHECK-NEXT: DeclRefExpr {{.*}} 'element_type' lvalue Var {{.*}} 'Result' 
'element_type'
+// CHECK-NEXT: CallExpr {{.*}} 'element_type'
 // CHECK-NEXT: ImplicitCastExpr {{.*}} <BuiltinFnToFnPtr>
 // CHECK-NEXT: DeclRefExpr {{.*}} '<builtin fn type>' Function {{.*}} 
'__builtin_hlsl_resource_load_with_status' 'void (...) noexcept'
 // CHECK-NEXT: MemberExpr {{.*}} '__hlsl_resource_t
 // CHECK-UAV-SAME{LITERAL}: [[hlsl::resource_class(UAV)]]
 // CHECK-SRV-SAME{LITERAL}: [[hlsl::resource_class(SRV)]]
 // CHECK-SAME{LITERAL}: [[hlsl::contained_type(element_type)]]
-// CHECK-SAME: lvalue .__handle {{.*}}
 // CHECK-NEXT: CXXThisExpr {{.*}} 'hlsl::[[RESOURCE]]<element_type>' lvalue 
implicit this
 // CHECK-NEXT: DeclRefExpr {{.*}} 'unsigned int' ParmVar {{.*}} 'Index' 
'unsigned int'
-// CHECK-NEXT: DeclRefExpr {{.*}} 'unsigned int' ParmVar {{.*}} 'Status' 
'unsigned int &'
+// CHECK-NEXT: DeclRefExpr {{.*}} 'bool' lvalue Var {{.*}} 'StatusBool' 'bool'
+// CHECK-NEXT: BinaryOperator {{.*}} 'unsigned int' '='
+// CHECK-NEXT: DeclRefExpr {{.*}} 'unsigned int' ParmVar {{.*}} 'Status' 
'unsigned int &__restrict'
+// CHECK-NEXT: DeclRefExpr {{.*}} 'bool' lvalue Var {{.*}} 'StatusBool' 'bool'
+// CHECK-NEXT: ReturnStmt
+// CHECK-NEXT: DeclRefExpr {{.*}} 'element_type' lvalue Var {{.*}} 'Result' 
'element_type'
 // CHECK-NEXT: AlwaysInlineAttr {{.*}} Implicit always_inline
 
 // GetDimensions method
diff --git 
a/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-lib.hlsl 
b/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-lib.hlsl
index 969586055b1d5..2c48cf7e35346 100644
--- a/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-lib.hlsl
+++ b/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-lib.hlsl
@@ -113,36 +113,46 @@ export float TestLoadWithStatus() {
 }
 
 // CHECK: define noundef nofpclass(nan inf) float @TestLoadWithStatus()()
-// CHECK: call {{.*}} float @hlsl::RWStructuredBuffer<float>::Load(unsigned 
int, unsigned int&)(ptr {{.*}} @RWSB1, i32 noundef 1, ptr noundef nonnull align 
4 dereferenceable(4) %s1)
-// CHECK: call {{.*}} float @hlsl::StructuredBuffer<float>::Load(unsigned int, 
unsigned int&)(ptr {{.*}} @SB1, i32 noundef 2, ptr noundef nonnull align 4 
dereferenceable(4) %s2)
+// CHECK: call {{.*}} float @hlsl::RWStructuredBuffer<float>::Load(unsigned 
int, unsigned int&)(ptr {{.*}} @RWSB1, i32 noundef 1, ptr noalias noundef 
nonnull align 4 dereferenceable(4) %tmp)
+// CHECK: call {{.*}} float @hlsl::StructuredBuffer<float>::Load(unsigned int, 
unsigned int&)(ptr {{.*}} @SB1, i32 noundef 2, ptr noalias noundef nonnull 
align 4 dereferenceable(4) %tmp1)
 // CHECK: add
 // CHECK: ret float
 
-// CHECK: define {{.*}} float @hlsl::RWStructuredBuffer<float>::Load(unsigned 
int, unsigned int&)(ptr {{.*}} %this, i32 noundef %Index, ptr noundef nonnull 
align 4 dereferenceable(4) %Status)
+// CHECK: define {{.*}} float @hlsl::RWStructuredBuffer<float>::Load(unsigned 
int, unsigned int&)(ptr {{.*}} %this, i32 noundef %Index, ptr noalias noundef 
nonnull align 4 dereferenceable(4) %Status)
 // CHECK: %__handle = getelementptr inbounds nuw 
%"class.hlsl::RWStructuredBuffer", ptr %{{.*}}, i32 0, i32 0
 // DXIL-NEXT: %[[HANDLE:.*]] = load target("dx.RawBuffer", float, 1, 0), ptr 
%__handle
 // CHECK-NEXT: %[[INDEX:.*]] = load i32, ptr %Index.addr
-// CHECK-NEXT: %[[STATUS:.*]] = load ptr, ptr %Status.addr,
-// DXIL-NEXT: %[[STRUCT:.*]] = call { ptr, i1 } 
@llvm.dx.resource.load.rawbuffer.p0.tdx.RawBuffer_f32_1_0t(target("dx.RawBuffer",
 float, 1, 0) %[[HANDLE]], i32 %[[INDEX]], i32 0)
-// CHECK-NEXT: %[[VALUE:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 0
-// CHECK-NEXT: %[[STATUS_TEMP:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 1
+// DXIL-NEXT: %[[STRUCT:.*]] = call { float, i1 } 
@llvm.dx.resource.load.rawbuffer.f32.tdx.RawBuffer_f32_1_0t(target("dx.RawBuffer",
 float, 1, 0) %[[HANDLE]], i32 %[[INDEX]], i32 0)
+// CHECK-NEXT: %[[VALUE:.*]] = extractvalue { float, i1 } %[[STRUCT]], 0
+// CHECK-NEXT: %[[STATUS_TEMP:.*]] = extractvalue { float, i1 } %[[STRUCT]], 1
 // CHECK-NEXT: %[[STATUS_EXT:.*]] = zext i1 %[[STATUS_TEMP]] to i32
-// CHECK-NEXT: store i32 %[[STATUS_EXT]], ptr %2, align 4
-// CHECK-NEXT: %[[RETVAL:.*]] = load float, ptr %[[VALUE]]
-// CHECK-NEXT: ret float %[[RETVAL]]
-
-// CHECK: define {{.*}} float @hlsl::StructuredBuffer<float>::Load(unsigned 
int, unsigned int&)(ptr {{.*}} %this, i32 noundef %Index, ptr noundef nonnull 
align 4 dereferenceable(4) %Status)
+// CHECK-NEXT: store i32 %[[STATUS_EXT]], ptr %StatusBool, align 4
+// CHECK-NEXT: store float %ld.value, ptr %Result, align 4
+// CHECK-NEXT: %[[STATUS_INT:.*]] = load i32, ptr %StatusBool, align 4
+// CHECK-NEXT: %[[LOADED_VALUE:.*]] = trunc i32 %[[STATUS_INT]] to i1
+// CHECK-NEXT: %[[ZEXT_VALUE:.*]] = zext i1 %[[LOADED_VALUE]] to i32
+// CHECK-NEXT: %[[LOADED_STATUS_ADDR:.*]] = load ptr, ptr %Status.addr, align 4
+// CHECK-NEXT: store i32 %[[ZEXT_VALUE]], ptr %[[LOADED_STATUS_ADDR]], align 4
+// CHECK-NEXT: %[[RETURN_VALUE:.*]] = load float, ptr %Result, align 4
+// CHECK-NEXT: ret float %[[RETURN_VALUE]]
+
+// CHECK: define {{.*}} float @hlsl::StructuredBuffer<float>::Load(unsigned 
int, unsigned int&)(ptr {{.*}} %this, i32 noundef %Index, ptr noalias noundef 
nonnull align 4 dereferenceable(4) %Status)
 // CHECK: %__handle = getelementptr inbounds nuw 
%"class.hlsl::StructuredBuffer", ptr %{{.*}}, i32 0, i32 0
 // DXIL-NEXT: %[[HANDLE:.*]] = load target("dx.RawBuffer", float, 0, 0), ptr 
%__handle
 // CHECK-NEXT: %[[INDEX:.*]] = load i32, ptr %Index.addr
-// CHECK-NEXT: %[[STATUS_HANDLE:.*]] = load ptr, ptr %Status.addr, align 4, 
!nonnull !3, !align !4
-// DXIL-NEXT: %[[STRUCT:.*]] = call { ptr, i1 } 
@llvm.dx.resource.load.rawbuffer.p0.tdx.RawBuffer_f32_0_0t(target("dx.RawBuffer",
 float, 0, 0) %0, i32 %1, i32 0)
-// CHECK-NEXT: %[[VALUE:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 0
-// CHECK-NEXT: %[[STATUS:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 1
-// CHECK-NEXT: %[[STATUS_EXT:.*]] = zext i1 %[[STATUS]] to i32
-// CHECK-NEXT: store i32 %[[STATUS_EXT]], ptr %2, align 4
-// CHECK-NEXT: %[[RETVAL:.*]] = load float, ptr %[[VALUE]]
-// CHECK-NEXT: ret float %[[RETVAL]]
+// DXIL-NEXT: %[[STRUCT:.*]] = call { float, i1 } 
@llvm.dx.resource.load.rawbuffer.f32.tdx.RawBuffer_f32_0_0t(target("dx.RawBuffer",
 float, 0, 0) %[[HANDLE]], i32 %[[INDEX]], i32 0)
+// CHECK-NEXT: %[[VALUE:.*]] = extractvalue { float, i1 } %[[STRUCT]], 0
+// CHECK-NEXT: %[[STATUS_TEMP:.*]] = extractvalue { float, i1 } %[[STRUCT]], 1
+// CHECK-NEXT: %[[STATUS_EXT:.*]] = zext i1 %[[STATUS_TEMP]] to i32
+// CHECK-NEXT: store i32 %[[STATUS_EXT]], ptr %StatusBool, align 4
+// CHECK-NEXT: store float %ld.value, ptr %Result, align 4
+// CHECK-NEXT: %[[STATUS_INT:.*]] = load i32, ptr %StatusBool, align 4
+// CHECK-NEXT: %[[LOADED_VALUE:.*]] = trunc i32 %[[STATUS_INT]] to i1
+// CHECK-NEXT: %[[ZEXT_VALUE:.*]] = zext i1 %[[LOADED_VALUE]] to i32
+// CHECK-NEXT: %[[LOADED_STATUS_ADDR:.*]] = load ptr, ptr %Status.addr, align 4
+// CHECK-NEXT: store i32 %[[ZEXT_VALUE]], ptr %[[LOADED_STATUS_ADDR]], align 4
+// CHECK-NEXT: %[[RETURN_VALUE:.*]] = load float, ptr %Result, align 4
+// CHECK-NEXT: ret float %[[RETURN_VALUE]]
 
 export uint TestGetDimensions() {
     uint dim1, dim2, dim3, stride1, stride2, stride3;
diff --git a/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-ps.hlsl 
b/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-ps.hlsl
index 38bb5ae7bb871..58c18940b81ca 100644
--- a/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-ps.hlsl
+++ b/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-ps.hlsl
@@ -73,35 +73,45 @@ export float TestLoadWithStatus() {
 }
 
 // CHECK: define {{.*}} float @TestLoadWithStatus()()
-// CHECK: call {{.*}} float 
@hlsl::RasterizerOrderedStructuredBuffer<float>::Load(unsigned int, unsigned 
int&)(ptr {{.*}} @ROSB1, i32 noundef 10, ptr noundef nonnull align 4 
dereferenceable(4) %status)
-// CHECK: call {{.*}} <2 x i32> @hlsl::RasterizerOrderedStructuredBuffer<int 
vector[2]>::Load(unsigned int, unsigned int&)(ptr {{.*}} @ROSB2, i32 noundef 
20, ptr noundef nonnull align 4 dereferenceable(4) %status2)
+// CHECK: call {{.*}} float 
@hlsl::RasterizerOrderedStructuredBuffer<float>::Load(unsigned int, unsigned 
int&)(ptr {{.*}} @ROSB1, i32 noundef 10, ptr noalias noundef nonnull align 4 
dereferenceable(4) %tmp)
+// CHECK: call {{.*}} <2 x i32> @hlsl::RasterizerOrderedStructuredBuffer<int 
vector[2]>::Load(unsigned int, unsigned int&)(ptr {{.*}} @ROSB2, i32 noundef 
20, ptr noalias noundef nonnull align 4 dereferenceable(4) %tmp2)
 // CHECK: ret
 
-// CHECK: define {{.*}} float 
@hlsl::RasterizerOrderedStructuredBuffer<float>::Load(unsigned int, unsigned 
int&)(ptr {{.*}} %Index, ptr noundef nonnull align 4 dereferenceable(4) %Status)
+// CHECK: define {{.*}} float 
@hlsl::RasterizerOrderedStructuredBuffer<float>::Load(unsigned int, unsigned 
int&)(ptr {{.*}} %this, i32 noundef %Index, ptr noalias noundef nonnull align 4 
dereferenceable(4) %Status)
 // CHECK: %__handle = getelementptr inbounds nuw 
%"class.hlsl::RasterizerOrderedStructuredBuffer", ptr {{.*}}, i32 0, i32 0
 // CHECK-NEXT: %[[HANDLE:.*]] = load target("dx.RawBuffer", float, 1, 1), ptr 
%__handle
 // CHECK-NEXT: %[[INDEX:.*]] = load i32, ptr %Index.addr
-// CHECK-NEXT: %[[STATUS:.*]] = load ptr, ptr %Status.addr,
-// DXIL-NEXT: %[[STRUCT:.*]] = call { ptr, i1 } 
@llvm.dx.resource.load.rawbuffer.p0.tdx.RawBuffer_f32_1_1t(target("dx.RawBuffer",
 float, 1, 1) %[[HANDLE]], i32 %[[INDEX]], i32 0)
-// CHECK-NEXT: %[[VALUE:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 0
-// CHECK-NEXT: %[[STATUS_TEMP:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 1
+// DXIL-NEXT: %[[STRUCT:.*]] = call { float, i1 } 
@llvm.dx.resource.load.rawbuffer.f32.tdx.RawBuffer_f32_1_1t(target("dx.RawBuffer",
 float, 1, 1) %[[HANDLE]], i32 %[[INDEX]], i32 0)
+// CHECK-NEXT: %[[VALUE:.*]] = extractvalue { float, i1 } %[[STRUCT]], 0
+// CHECK-NEXT: %[[STATUS_TEMP:.*]] = extractvalue { float, i1 } %[[STRUCT]], 1
 // CHECK-NEXT: %[[STATUS_EXT:.*]] = zext i1 %[[STATUS_TEMP]] to i32
-// CHECK-NEXT: store i32 %[[STATUS_EXT]], ptr %2, align 4
-// CHECK-NEXT: %[[RETVAL:.*]] = load float, ptr %[[VALUE]]
-// CHECK-NEXT: ret float %[[RETVAL]]
-
-// CHECK: define {{.*}} <2 x i32> @hlsl::RasterizerOrderedStructuredBuffer<int 
vector[2]>::Load(unsigned int, unsigned int&)(ptr {{.*}} %Index, ptr noundef 
nonnull align 4 dereferenceable(4) %Status)
+// CHECK-NEXT: store i32 %[[STATUS_EXT]], ptr %StatusBool, align 4
+// CHECK-NEXT: store float %ld.value, ptr %Result, align 4
+// CHECK-NEXT: %[[STATUS_INT:.*]] = load i32, ptr %StatusBool, align 4
+// CHECK-NEXT: %[[LOADED_VALUE:.*]] = trunc i32 %[[STATUS_INT]] to i1
+// CHECK-NEXT: %[[ZEXT_VALUE:.*]] = zext i1 %[[LOADED_VALUE]] to i32
+// CHECK-NEXT: %[[LOADED_STATUS_ADDR:.*]] = load ptr, ptr %Status.addr, align 4
+// CHECK-NEXT: store i32 %[[ZEXT_VALUE]], ptr %[[LOADED_STATUS_ADDR]], align 4
+// CHECK-NEXT: %[[RETURN_VALUE:.*]] = load float, ptr %Result, align 4
+// CHECK-NEXT: ret float %[[RETURN_VALUE]]
+
+// CHECK: define {{.*}} <2 x i32> @hlsl::RasterizerOrderedStructuredBuffer<int 
vector[2]>::Load(unsigned int, unsigned int&)(ptr {{.*}} %this, i32 noundef 
%Index, ptr noalias noundef nonnull align 4 dereferenceable(4) %Status)
 // CHECK: %__handle = getelementptr inbounds nuw 
%"class.hlsl::RasterizerOrderedStructuredBuffer.0", ptr {{.*}}, i32 0, i32 0
 // CHECK-NEXT: %[[HANDLE:.*]] = load target("dx.RawBuffer", <2 x i32>, 1, 1), 
ptr %__handle
 // CHECK-NEXT: %[[INDEX:.*]] = load i32, ptr %Index.addr
-// CHECK-NEXT: %[[STATUS_HANDLE:.*]] = load ptr, ptr %Status.addr, align 4, 
!nonnull !3, !align !4
-// DXIL-NEXT: %[[STRUCT:.*]] = call { ptr, i1 } 
@llvm.dx.resource.load.rawbuffer.p0.tdx.RawBuffer_v2i32_1_1t(target("dx.RawBuffer",
 <2 x i32>, 1, 1) %0, i32 %1, i32 0)
-// CHECK-NEXT: %[[VALUE:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 0
-// CHECK-NEXT: %[[STATUS:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 1
-// CHECK-NEXT: %[[STATUS_EXT:.*]] = zext i1 %[[STATUS]] to i32
-// CHECK-NEXT: store i32 %[[STATUS_EXT]], ptr %2, align 4
-// CHECK-NEXT: %[[RETVAL:.*]] = load <2 x i32>, ptr %[[VALUE]]
-// CHECK-NEXT: ret <2 x i32> %[[RETVAL]]
+// DXIL-NEXT: %[[STRUCT:.*]] = call { <2 x i32>, i1 } 
@llvm.dx.resource.load.rawbuffer.v2i32.tdx.RawBuffer_v2i32_1_1t(target("dx.RawBuffer",
 <2 x i32>, 1, 1) %[[HANDLE]], i32 %[[INDEX]], i32 0)
+// CHECK-NEXT: %[[VALUE:.*]] = extractvalue { <2 x i32>, i1 } %[[STRUCT]], 0
+// CHECK-NEXT: %[[STATUS_TEMP:.*]] = extractvalue { <2 x i32>, i1 } 
%[[STRUCT]], 1
+// CHECK-NEXT: %[[STATUS_EXT:.*]] = zext i1 %[[STATUS_TEMP]] to i32
+// CHECK-NEXT: store i32 %[[STATUS_EXT]], ptr %StatusBool, align 4
+// CHECK-NEXT: store <2 x i32> %ld.value, ptr %Result, align 8
+// CHECK-NEXT: %[[STATUS_INT:.*]] = load i32, ptr %StatusBool, align 4
+// CHECK-NEXT: %[[LOADED_VALUE:.*]] = trunc i32 %[[STATUS_INT]] to i1
+// CHECK-NEXT: %[[ZEXT_VALUE:.*]] = zext i1 %[[LOADED_VALUE]] to i32
+// CHECK-NEXT: %[[LOADED_STATUS_ADDR:.*]] = load ptr, ptr %Status.addr, align 4
+// CHECK-NEXT: store i32 %[[ZEXT_VALUE]], ptr %[[LOADED_STATUS_ADDR]], align 4
+// CHECK-NEXT: %[[RETURN_VALUE:.*]] = load <2 x i32>, ptr %Result, align 8
+// CHECK-NEXT: ret <2 x i32> %[[RETURN_VALUE]]
 
 
 export uint TestGetDimensions() {
diff --git a/clang/test/CodeGenHLSL/resources/TypedBuffers-methods.hlsl 
b/clang/test/CodeGenHLSL/resources/TypedBuffers-methods.hlsl
index 5960a1c406fc4..5d28a01d4839f 100644
--- a/clang/test/CodeGenHLSL/resources/TypedBuffers-methods.hlsl
+++ b/clang/test/CodeGenHLSL/resources/TypedBuffers-methods.hlsl
@@ -56,27 +56,37 @@ export float TestLoadWithStatus() {
 // CHECK: %__handle = getelementptr inbounds nuw %"class.hlsl::Buffer", ptr 
%{{.*}}, i32 0, i32 0
 // DXIL-NEXT: %[[HANDLE:.*]] = load target("dx.TypedBuffer", float, 0, 0, 0), 
ptr %__handle
 // CHECK-NEXT: %[[INDEX:.*]] = load i32, ptr %Index.addr
-// CHECK-NEXT: %[[STATUS:.*]] = load ptr, ptr %Status.addr,
-// DXIL-NEXT: %[[STRUCT:.*]] = call { ptr, i1 } 
@llvm.dx.resource.load.typedbuffer.p0.tdx.TypedBuffer_f32_0_0_0t(target("dx.TypedBuffer",
 float, 0, 0, 0) %[[HANDLE]], i32 %[[INDEX]])
-// CHECK-NEXT: %[[VALUE:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 0
-// CHECK-NEXT: %[[STATUS_TEMP:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 1
+// DXIL-NEXT: %[[STRUCT:.*]] = call { float, i1 } 
@llvm.dx.resource.load.typedbuffer.f32.tdx.TypedBuffer_f32_0_0_0t(target("dx.TypedBuffer",
 float, 0, 0, 0) %[[HANDLE]], i32 %[[INDEX]])
+// CHECK-NEXT: %[[VALUE:.*]] = extractvalue { float, i1 } %[[STRUCT]], 0
+// CHECK-NEXT: %[[STATUS_TEMP:.*]] = extractvalue { float, i1 } %[[STRUCT]], 1
 // CHECK-NEXT: %[[STATUS_EXT:.*]] = zext i1 %[[STATUS_TEMP]] to i32
-// CHECK-NEXT: store i32 %[[STATUS_EXT]], ptr %2, align 4
-// CHECK-NEXT: %[[RETVAL:.*]] = load float, ptr %[[VALUE]]
-// CHECK-NEXT: ret float %[[RETVAL]]
-
-// CHECK: define {{.*}}  <4 x i32> @hlsl::RWBuffer<unsigned int 
vector[4]>::Load(unsigned int, unsigned int&)(ptr {{.*}} %this, i32 noundef 
%Index, ptr noundef nonnull align 4 dereferenceable(4) %Status)
+// CHECK-NEXT: store i32 %[[STATUS_EXT]], ptr %StatusBool, align 4
+// CHECK-NEXT: store float %ld.value, ptr %Result, align 4
+// CHECK-NEXT: %[[STATUS_INT:.*]] = load i32, ptr %StatusBool, align 4
+// CHECK-NEXT: %[[LOADED_VALUE:.*]] = trunc i32 %[[STATUS_INT]] to i1
+// CHECK-NEXT: %[[ZEXT_VALUE:.*]] = zext i1 %[[LOADED_VALUE]] to i32
+// CHECK-NEXT: %[[LOADED_STATUS_ADDR:.*]] = load ptr, ptr %Status.addr, align 4
+// CHECK-NEXT: store i32 %[[ZEXT_VALUE]], ptr %[[LOADED_STATUS_ADDR]], align 4
+// CHECK-NEXT: %[[RETURN_VALUE:.*]] = load float, ptr %Result, align 4
+// CHECK-NEXT: ret float %[[RETURN_VALUE]]
+
+// CHECK: define {{.*}}  <4 x i32> @hlsl::RWBuffer<unsigned int 
vector[4]>::Load(unsigned int, unsigned int&)(ptr {{.*}} %this, i32 noundef 
%Index, ptr noalias noundef nonnull align 4 dereferenceable(4) %Status)
 // CHECK: %__handle = getelementptr inbounds nuw %"class.hlsl::RWBuffer", ptr 
%{{.*}}, i32 0, i32 0
 // DXIL-NEXT: %[[HANDLE:.*]] = load target("dx.TypedBuffer", <4 x i32>, 1, 0, 
0), ptr %__handle
 // CHECK-NEXT: %[[INDEX:.*]] = load i32, ptr %Index.addr
-// CHECK-NEXT: %[[STATUS_HANDLE:.*]] = load ptr, ptr %Status.addr, align 4, 
!nonnull !3, !align !4
-// DXIL-NEXT: %[[STRUCT:.*]] = call { ptr, i1 } 
@llvm.dx.resource.load.typedbuffer.p0.tdx.TypedBuffer_v4i32_1_0_0t(target("dx.TypedBuffer",
 <4 x i32>, 1, 0, 0) %0, i32 %1)
-// CHECK-NEXT: %[[VALUE:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 0
-// CHECK-NEXT: %[[STATUS:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 1
-// CHECK-NEXT: %[[STATUS_EXT:.*]] = zext i1 %[[STATUS]] to i32
-// CHECK-NEXT: store i32 %[[STATUS_EXT]], ptr %2, align 4
-// CHECK-NEXT: %[[RETVAL:.*]] = load <4 x i32>, ptr %[[VALUE]]
-// CHECK-NEXT: ret <4 x i32> %[[RETVAL]]
+// DXIL-NEXT: %[[STRUCT:.*]] = call { <4 x i32>, i1 } 
@llvm.dx.resource.load.typedbuffer.v4i32.tdx.TypedBuffer_v4i32_1_0_0t(target("dx.TypedBuffer",
 <4 x i32>, 1, 0, 0) %[[HANDLE]], i32 %[[INDEX]])
+// CHECK-NEXT: %[[VALUE:.*]] = extractvalue { <4 x i32>, i1 } %[[STRUCT]], 0
+// CHECK-NEXT: %[[STATUS_TEMP:.*]] = extractvalue { <4 x i32>, i1 } 
%[[STRUCT]], 1
+// CHECK-NEXT: %[[STATUS_EXT:.*]] = zext i1 %[[STATUS_TEMP]] to i32
+// CHECK-NEXT: store i32 %[[STATUS_EXT]], ptr %StatusBool, align 4
+// CHECK-NEXT: store <4 x i32> %ld.value, ptr %Result, align 16
+// CHECK-NEXT: %[[STATUS_INT:.*]] = load i32, ptr %StatusBool, align 4
+// CHECK-NEXT: %[[LOADED_VALUE:.*]] = trunc i32 %[[STATUS_INT]] to i1
+// CHECK-NEXT: %[[ZEXT_VALUE:.*]] = zext i1 %[[LOADED_VALUE]] to i32
+// CHECK-NEXT: %[[LOADED_STATUS_ADDR:.*]] = load ptr, ptr %Status.addr, align 4
+// CHECK-NEXT: store i32 %[[ZEXT_VALUE]], ptr %[[LOADED_STATUS_ADDR]], align 4
+// CHECK-NEXT: %[[RETURN_VALUE:.*]] = load <4 x i32>, ptr %Result, align 16
+// CHECK-NEXT: ret <4 x i32> %[[RETURN_VALUE]]
 
 export uint TestGetDimensions() {
     uint dim1, dim2;

_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

Reply via email to