[clang] [llvm] [HLSL] Add load overload with status (PR #166449)
Joshua Batista via llvm-commits
llvm-commits at lists.llvm.org
Tue Nov 4 13:36:15 PST 2025
https://github.com/bob80905 created https://github.com/llvm/llvm-project/pull/166449
This PR adds a new overload for resources, which takes an additional parameter by reference, status. It fills the status parameter with a 1 or 0, depending on whether or not the resource access was mapped. CheckAccessFullyMapped is also added as an intrinsic, and called in the production of this status bit.
>From 99c97887389d5255905394052a766b7dee2129fd Mon Sep 17 00:00:00 2001
From: Joshua Batista <jbatista at microsoft.com>
Date: Thu, 30 Oct 2025 17:06:11 -0700
Subject: [PATCH 1/3] 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 <jbatista at microsoft.com>
Date: Tue, 4 Nov 2025 12:03:27 -0800
Subject: [PATCH 2/3] 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 6d0741dbac11ddb3136b83eafebbfe2dc08f98d5 Mon Sep 17 00:00:00 2001
From: Joshua Batista <jbatista at microsoft.com>
Date: Tue, 4 Nov 2025 13:09:09 -0800
Subject: [PATCH 3/3] use cafm
---
clang/lib/CodeGen/CGHLSLBuiltins.cpp | 18 ++++++++++++++----
.../StructuredBuffers-methods-lib.hlsl | 12 ++++++++----
.../StructuredBuffers-methods-ps.hlsl | 16 ++++++++++------
.../resources/TypedBuffers-methods.hlsl | 12 ++++++++----
llvm/include/llvm/IR/IntrinsicsDirectX.td | 5 ++---
llvm/lib/Target/DirectX/DXILOpLowering.cpp | 11 -----------
6 files changed, 42 insertions(+), 32 deletions(-)
diff --git a/clang/lib/CodeGen/CGHLSLBuiltins.cpp b/clang/lib/CodeGen/CGHLSLBuiltins.cpp
index 607cf523ddf78..ff3d906d4bf11 100644
--- a/clang/lib/CodeGen/CGHLSLBuiltins.cpp
+++ b/clang/lib/CodeGen/CGHLSLBuiltins.cpp
@@ -392,13 +392,23 @@ Value *CodeGenFunction::EmitHLSLBuiltinExpr(unsigned BuiltinID,
// 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
+ // Extend the 1-bit status to 32-bit, because the check access fully mapped
+ // intrinsic expects i32 input
+ Value *StatusInt =
+ Builder.CreateZExt(StatusBit, Builder.getInt32Ty(), "ld.status.i32");
+
+ // Call CheckAccessFullyMapped(i32)
+ llvm::Function *CheckAccessFn =
+ CGM.getIntrinsic(llvm::Intrinsic::dx_check_access_fully_mapped);
+
+ Value *StatusBool =
+ Builder.CreateCall(CheckAccessFn, {StatusInt}, "ld.status.checked");
+
+ // Extend the boolean to 32-bit uint for storing in user�s var
Value *ExtendedStatus =
- Builder.CreateZExt(StatusBit, Builder.getInt32Ty(), "ld.status.ext");
+ Builder.CreateZExt(StatusBool, 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: {
diff --git a/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-lib.hlsl b/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-lib.hlsl
index 969586055b1d5..e692a14ecc168 100644
--- a/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-lib.hlsl
+++ b/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-lib.hlsl
@@ -127,7 +127,9 @@ export float TestLoadWithStatus() {
// 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: %[[STATUS_CHECKED:.*]] = call i1 @llvm.dx.check.access.fully.mapped(i32 %[[STATUS_EXT:.*]])
+// CHECK-NEXT: %[[STATUS_REEXT:.*]] = zext i1 %[[STATUS_CHECKED]] to i32
+// CHECK-NEXT: store i32 %[[STATUS_REEXT]], ptr %2, align 4
// CHECK-NEXT: %[[RETVAL:.*]] = load float, ptr %[[VALUE]]
// CHECK-NEXT: ret float %[[RETVAL]]
@@ -138,9 +140,11 @@ export float TestLoadWithStatus() {
// 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: %[[STATUS_TEMP:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 1
+// CHECK-NEXT: %[[STATUS_EXT:.*]] = zext i1 %[[STATUS_TEMP]] to i32
+// CHECK-NEXT: %[[STATUS_CHECKED:.*]] = call i1 @llvm.dx.check.access.fully.mapped(i32 %[[STATUS_EXT:.*]])
+// CHECK-NEXT: %[[STATUS_REEXT:.*]] = zext i1 %[[STATUS_CHECKED]] to i32
+// CHECK-NEXT: store i32 %[[STATUS_REEXT]], ptr %2, align 4
// CHECK-NEXT: %[[RETVAL:.*]] = load float, ptr %[[VALUE]]
// CHECK-NEXT: ret float %[[RETVAL]]
diff --git a/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-ps.hlsl b/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-ps.hlsl
index 38bb5ae7bb871..77aaf281fbc39 100644
--- a/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-ps.hlsl
+++ b/clang/test/CodeGenHLSL/resources/StructuredBuffers-methods-ps.hlsl
@@ -86,7 +86,9 @@ export float TestLoadWithStatus() {
// 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: %[[STATUS_CHECKED:.*]] = call i1 @llvm.dx.check.access.fully.mapped(i32 %[[STATUS_EXT:.*]])
+// CHECK-NEXT: %[[STATUS_REEXT:.*]] = zext i1 %[[STATUS_CHECKED]] to i32
+// CHECK-NEXT: store i32 %[[STATUS_REEXT]], ptr %2, align 4
// CHECK-NEXT: %[[RETVAL:.*]] = load float, ptr %[[VALUE]]
// CHECK-NEXT: ret float %[[RETVAL]]
@@ -97,11 +99,13 @@ export float TestLoadWithStatus() {
// 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]]
+// CHECK-NEXT: %[[STATUS_TEMP:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 1
+// CHECK-NEXT: %[[STATUS_EXT:.*]] = zext i1 %[[STATUS_TEMP]] to i32
+// CHECK-NEXT: %[[STATUS_CHECKED:.*]] = call i1 @llvm.dx.check.access.fully.mapped(i32 %[[STATUS_EXT:.*]])
+// CHECK-NEXT: %[[STATUS_REEXT:.*]] = zext i1 %[[STATUS_CHECKED]] to i32
+// CHECK-NEXT: store i32 %[[STATUS_REEXT]], ptr %2, align 4
+// CHECK-NEXT: %[[RETVAL:.*]] = load float, ptr %[[VALUE]]
+// CHECK-NEXT: ret float %[[RETVAL]]
export uint TestGetDimensions() {
diff --git a/clang/test/CodeGenHLSL/resources/TypedBuffers-methods.hlsl b/clang/test/CodeGenHLSL/resources/TypedBuffers-methods.hlsl
index c884b857f59bf..14607b58c67d9 100644
--- a/clang/test/CodeGenHLSL/resources/TypedBuffers-methods.hlsl
+++ b/clang/test/CodeGenHLSL/resources/TypedBuffers-methods.hlsl
@@ -61,7 +61,9 @@ export float TestLoadWithStatus() {
// 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: %[[STATUS_CHECKED:.*]] = call i1 @llvm.dx.check.access.fully.mapped(i32 %[[STATUS_EXT:.*]])
+// CHECK-NEXT: %[[STATUS_REEXT:.*]] = zext i1 %[[STATUS_CHECKED]] to i32
+// CHECK-NEXT: store i32 %[[STATUS_REEXT]], ptr %2, align 4
// CHECK-NEXT: %[[RETVAL:.*]] = load float, ptr %[[VALUE]]
// CHECK-NEXT: ret float %[[RETVAL]]
@@ -72,9 +74,11 @@ export float TestLoadWithStatus() {
// 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: %[[STATUS_TEMP:.*]] = extractvalue { ptr, i1 } %[[STRUCT]], 1
+// CHECK-NEXT: %[[STATUS_EXT:.*]] = zext i1 %[[STATUS_TEMP]] to i32
+// CHECK-NEXT: %[[STATUS_CHECKED:.*]] = call i1 @llvm.dx.check.access.fully.mapped(i32 %[[STATUS_EXT:.*]])
+// CHECK-NEXT: %[[STATUS_REEXT:.*]] = zext i1 %[[STATUS_CHECKED]] to i32
+// CHECK-NEXT: store i32 %[[STATUS_REEXT]], ptr %2, align 4
// CHECK-NEXT: %[[RETVAL:.*]] = load <4 x i32>, ptr %[[VALUE]]
// CHECK-NEXT: ret <4 x i32> %[[RETVAL]]
diff --git a/llvm/include/llvm/IR/IntrinsicsDirectX.td b/llvm/include/llvm/IR/IntrinsicsDirectX.td
index 6c2d4e33881ee..6959978678540 100644
--- a/llvm/include/llvm/IR/IntrinsicsDirectX.td
+++ b/llvm/include/llvm/IR/IntrinsicsDirectX.td
@@ -40,9 +40,8 @@ def int_dx_resource_getpointer
: DefaultAttrsIntrinsic<[llvm_anyptr_ty], [llvm_any_ty, llvm_i32_ty],
[IntrNoMem]>;
-def int_dx_resource_load_with_status
- : DefaultAttrsIntrinsic<[llvm_anyptr_ty], [llvm_any_ty, llvm_i32_ty, llvm_i32_ty],
- [IntrNoMem]>;
+def int_dx_check_access_fully_mapped
+ : DefaultAttrsIntrinsic<[llvm_i1_ty], [llvm_i32_ty], [IntrNoMem]>;
def int_dx_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 bb1cc4f098b6e..8720460cceb20 100644
--- a/llvm/lib/Target/DirectX/DXILOpLowering.cpp
+++ b/llvm/lib/Target/DirectX/DXILOpLowering.cpp
@@ -657,14 +657,6 @@ class OpLowerer {
return false;
}
- [[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");
- F.eraseFromParent();
- return false;
- }
-
[[nodiscard]] bool lowerBufferStore(Function &F, bool IsRaw) {
const DataLayout &DL = F.getDataLayout();
IRBuilder<> &IRB = OpBuilder.getIRB();
@@ -941,9 +933,6 @@ class OpLowerer {
case Intrinsic::dx_resource_getpointer:
HasErrors |= lowerGetPointer(F);
break;
- case Intrinsic::dx_resource_load_with_status:
- HasErrors |= lowerLoadWithStatus(F);
- break;
case Intrinsic::dx_resource_nonuniformindex:
assert(!CleanupNURI &&
"overloaded llvm.dx.resource.nonuniformindex intrinsics?");
More information about the llvm-commits
mailing list