[clang] [HLSL] Enable unbounded resource arrays at global scope (PR #155053)
Helena Kotas via cfe-commits
cfe-commits at lists.llvm.org
Thu Sep 4 21:14:30 PDT 2025
https://github.com/hekota updated https://github.com/llvm/llvm-project/pull/155053
>From 75a7511da94a609d7b2c944d3719a60057f9fa53 Mon Sep 17 00:00:00 2001
From: Helena Kotas <hekotas at microsoft.com>
Date: Thu, 14 Aug 2025 23:32:05 -0700
Subject: [PATCH 1/3] [HLSL] Codegen for indexing of sub-arrays of
multi-dimensional resource arrays
Closes #145426
---
clang/lib/CodeGen/CGHLSLRuntime.cpp | 134 ++++++++++++++----
.../res-array-global-subarray-many.hlsl | 102 +++++++++++++
.../res-array-global-subarray-one.hlsl | 62 ++++++++
3 files changed, 270 insertions(+), 28 deletions(-)
create mode 100644 clang/test/CodeGenHLSL/resources/res-array-global-subarray-many.hlsl
create mode 100644 clang/test/CodeGenHLSL/resources/res-array-global-subarray-one.hlsl
diff --git a/clang/lib/CodeGen/CGHLSLRuntime.cpp b/clang/lib/CodeGen/CGHLSLRuntime.cpp
index 12ece217ba563..c41601159dd2c 100644
--- a/clang/lib/CodeGen/CGHLSLRuntime.cpp
+++ b/clang/lib/CodeGen/CGHLSLRuntime.cpp
@@ -18,6 +18,7 @@
#include "CodeGenModule.h"
#include "TargetInfo.h"
#include "clang/AST/ASTContext.h"
+#include "clang/AST/Attrs.inc"
#include "clang/AST/Decl.h"
#include "clang/AST/RecursiveASTVisitor.h"
#include "clang/AST/Type.h"
@@ -36,6 +37,7 @@
#include "llvm/Support/Alignment.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/FormatVariadic.h"
+#include <cstdint>
using namespace clang;
using namespace CodeGen;
@@ -190,6 +192,71 @@ static void createResourceCtorArgs(CodeGenModule &CGM, CXXConstructorDecl *CD,
Args.add(RValue::get(NameStr), AST.getPointerType(AST.CharTy.withConst()));
}
+// Initializes local resource array variable. For multi-dimensional arrays it
+// calls itself recursively to initialize its sub-arrays. The Index used in the
+// resource constructor calls will begin at StartIndex and will be incremented
+// for each array element. The last last used resource Index is returned to the
+// caller.
+static Value *initializeLocalResourceArray(
+ CodeGenFunction &CGF, AggValueSlot &ValueSlot,
+ const ConstantArrayType *ArrayTy, CXXConstructorDecl *CD,
+ llvm::Value *Range, llvm::Value *StartIndex, StringRef ResourceName,
+ HLSLResourceBindingAttr *RBA, HLSLVkBindingAttr *VkBinding,
+ ArrayRef<llvm::Value *> PrevGEPIndices, SourceLocation ArraySubsExprLoc) {
+
+ llvm::IntegerType *IntTy = CGF.CGM.IntTy;
+ llvm::Value *Index = StartIndex;
+ llvm::Value *One = llvm::ConstantInt::get(IntTy, 1);
+ uint64_t ArraySize = ArrayTy->getSExtSize();
+ QualType ElemType = ArrayTy->getElementType();
+ Address TmpArrayAddr = ValueSlot.getAddress();
+
+ // Add additional index to the getelementptr call indices.
+ // This index will be updated for each array element in the loops below.
+ SmallVector<llvm::Value *> GEPIndices(PrevGEPIndices);
+ GEPIndices.push_back(llvm::ConstantInt::get(IntTy, 0));
+
+ // array of arrays - recursively initialize the sub-arrays
+ if (ElemType->isArrayType()) {
+ const ConstantArrayType *SubArrayTy = cast<ConstantArrayType>(ElemType);
+ for (uint64_t I = 0; I < ArraySize; I++) {
+ if (I > 0) {
+ Index = CGF.Builder.CreateAdd(Index, One);
+ GEPIndices.back() = llvm::ConstantInt::get(IntTy, I);
+ }
+ // recursively initialize the sub-array
+ Index = initializeLocalResourceArray(
+ CGF, ValueSlot, SubArrayTy, CD, Range, Index, ResourceName, RBA,
+ VkBinding, GEPIndices, ArraySubsExprLoc);
+ }
+ return Index;
+ }
+
+ // array of resources - initialize each resource in the array
+ llvm::Type *Ty = CGF.ConvertTypeForMem(ElemType);
+ CharUnits ElemSize = CD->getASTContext().getTypeSizeInChars(ElemType);
+ CharUnits Align =
+ TmpArrayAddr.getAlignment().alignmentOfArrayElement(ElemSize);
+
+ for (uint64_t I = 0; I < ArraySize; I++) {
+ if (I > 0) {
+ Index = CGF.Builder.CreateAdd(Index, One);
+ GEPIndices.back() = llvm::ConstantInt::get(IntTy, I);
+ }
+ Address ThisAddress =
+ CGF.Builder.CreateGEP(TmpArrayAddr, GEPIndices, Ty, Align);
+ llvm::Value *ThisPtr = CGF.getAsNaturalPointerTo(ThisAddress, ElemType);
+
+ CallArgList Args;
+ createResourceCtorArgs(CGF.CGM, CD, ThisPtr, Range, Index, ResourceName,
+ RBA, VkBinding, Args);
+ CGF.EmitCXXConstructorCall(CD, Ctor_Complete, false, false, ThisAddress,
+ Args, ValueSlot.mayOverlap(), ArraySubsExprLoc,
+ ValueSlot.isSanitizerChecked());
+ }
+ return Index;
+}
+
} // namespace
llvm::Type *
@@ -802,16 +869,14 @@ std::optional<LValue> CGHLSLRuntime::emitResourceArraySubscriptExpr(
ArraySubsExpr->getType()->isHLSLResourceRecordArray() &&
"expected resource array subscript expression");
- // let clang codegen handle local resource array subscripts
- const VarDecl *ArrayDecl = dyn_cast<VarDecl>(getArrayDecl(ArraySubsExpr));
+ // Let clang codegen handle local resource array subscripts,
+ // or when the subscript references on opaque expression (as part of
+ // ArrayInitLoopExpr AST node).
+ const VarDecl *ArrayDecl =
+ dyn_cast_or_null<VarDecl>(getArrayDecl(ArraySubsExpr));
if (!ArrayDecl || !ArrayDecl->hasGlobalStorage())
return std::nullopt;
- if (ArraySubsExpr->getType()->isArrayType())
- // FIXME: this is not yet implemented (llvm/llvm-project#145426)
- llvm_unreachable(
- "indexing of sub-arrays of multidimensional arrays not supported yet");
-
// get the resource array type
ASTContext &AST = ArrayDecl->getASTContext();
const Type *ResArrayTy = ArrayDecl->getType().getTypePtr();
@@ -832,26 +897,30 @@ std::optional<LValue> CGHLSLRuntime::emitResourceArraySubscriptExpr(
CGM.IntTy, AST.getConstantArrayElementCount(ArrayTy));
SubIndex = CGF.Builder.CreateMul(SubIndex, Multiplier);
}
-
Index = Index ? CGF.Builder.CreateAdd(Index, SubIndex) : SubIndex;
ASE = dyn_cast<ArraySubscriptExpr>(ASE->getBase()->IgnoreParenImpCasts());
}
// find binding info for the resource array (for implicit binding
// an HLSLResourceBindingAttr should have been added by SemaHLSL)
- QualType ResourceTy = ArraySubsExpr->getType();
HLSLVkBindingAttr *VkBinding = ArrayDecl->getAttr<HLSLVkBindingAttr>();
HLSLResourceBindingAttr *RBA = ArrayDecl->getAttr<HLSLResourceBindingAttr>();
assert((VkBinding || RBA) && "resource array must have a binding attribute");
+ // Find the individual resource type
+ QualType ResultTy = ArraySubsExpr->getType();
+ QualType ResourceTy =
+ ResultTy->isArrayType() ? AST.getBaseElementType(ResultTy) : ResultTy;
+
// lookup the resource class constructor based on the resource type and
// binding
CXXConstructorDecl *CD = findResourceConstructorDecl(
AST, ResourceTy, VkBinding || RBA->hasRegisterSlot());
- // create a temporary variable for the resource class instance (we need to
+ // create a temporary variable for the result, which is either going
+ // to be a single resource instance or a local array of resources (we need to
// return an LValue)
- RawAddress TmpVar = CGF.CreateMemTemp(ResourceTy);
+ RawAddress TmpVar = CGF.CreateMemTemp(ResultTy);
if (CGF.EmitLifetimeStart(TmpVar.getPointer()))
CGF.pushFullExprCleanup<CodeGenFunction::CallLifetimeEnd>(
NormalEHLifetimeMarker, TmpVar);
@@ -860,26 +929,35 @@ std::optional<LValue> CGHLSLRuntime::emitResourceArraySubscriptExpr(
TmpVar, Qualifiers(), AggValueSlot::IsDestructed_t(true),
AggValueSlot::DoesNotNeedGCBarriers, AggValueSlot::IsAliased_t(false),
AggValueSlot::DoesNotOverlap);
-
- Address ThisAddress = ValueSlot.getAddress();
- llvm::Value *ThisPtr = CGF.getAsNaturalPointerTo(
- ThisAddress, CD->getThisType()->getPointeeType());
+ Address TmpVarAddress = ValueSlot.getAddress();
// get total array size (= range size)
llvm::Value *Range =
llvm::ConstantInt::get(CGM.IntTy, getTotalArraySize(AST, ResArrayTy));
- // assemble the constructor parameters
- CallArgList Args;
- createResourceCtorArgs(CGM, CD, ThisPtr, Range, Index, ArrayDecl->getName(),
- RBA, VkBinding, Args);
-
- // call the constructor
- CGF.EmitCXXConstructorCall(CD, Ctor_Complete, false, false, ThisAddress, Args,
- ValueSlot.mayOverlap(),
- ArraySubsExpr->getExprLoc(),
- ValueSlot.isSanitizerChecked());
-
- return CGF.MakeAddrLValue(TmpVar, ArraySubsExpr->getType(),
- AlignmentSource::Decl);
+ // if the result of the subscript operation is a single resource - call the
+ // constructor
+ if (ResultTy == ResourceTy) {
+ QualType ThisType = CD->getThisType()->getPointeeType();
+ llvm::Value *ThisPtr = CGF.getAsNaturalPointerTo(TmpVarAddress, ThisType);
+
+ // assemble the constructor parameters
+ CallArgList Args;
+ createResourceCtorArgs(CGM, CD, ThisPtr, Range, Index, ArrayDecl->getName(),
+ RBA, VkBinding, Args);
+ // call the constructor
+ CGF.EmitCXXConstructorCall(CD, Ctor_Complete, false, false, TmpVarAddress,
+ Args, ValueSlot.mayOverlap(),
+ ArraySubsExpr->getExprLoc(),
+ ValueSlot.isSanitizerChecked());
+ } else {
+ // result of the subscript operation is a local resource array
+ const ConstantArrayType *ArrayTy =
+ cast<ConstantArrayType>(ResultTy.getTypePtr());
+ initializeLocalResourceArray(CGF, ValueSlot, ArrayTy, CD, Range, Index,
+ ArrayDecl->getName(), RBA, VkBinding,
+ {llvm::ConstantInt::get(CGM.IntTy, 0)},
+ ArraySubsExpr->getExprLoc());
+ }
+ return CGF.MakeAddrLValue(TmpVar, ResultTy, AlignmentSource::Decl);
}
diff --git a/clang/test/CodeGenHLSL/resources/res-array-global-subarray-many.hlsl b/clang/test/CodeGenHLSL/resources/res-array-global-subarray-many.hlsl
new file mode 100644
index 0000000000000..dbd03b4c034af
--- /dev/null
+++ b/clang/test/CodeGenHLSL/resources/res-array-global-subarray-many.hlsl
@@ -0,0 +1,102 @@
+// RUN: %clang_cc1 -triple dxil-pc-shadermodel6.6-compute -finclude-default-header \
+// RUN: -emit-llvm -disable-llvm-passes -o - %s | FileCheck %s
+
+// CHECK: @[[BufA:.*]] = private unnamed_addr constant [2 x i8] c"A\00", align 1
+
+RWBuffer<float> A[5][4][3][2] : register(u10, space2);
+RWStructuredBuffer<float> Out;
+
+float foo(RWBuffer<float> Arr[3][2]) {
+ return Arr[1][0][0];
+}
+
+// NOTE:
+// - _ZN4hlsl8RWBufferIfEC1EjjijPKc is the constructor call for explicit binding
+// (has "jjij" in the mangled name) and the arguments are (register, space, range_size, index, name).
+// - _ZN4hlsl8RWBufferIfEixEj is the subscript operator for RWBuffer<float>
+
+// CHECK: define internal void @_Z4mainj(i32 noundef %GI)
+// CHECK-NEXT: entry:
+// CHECK-NEXT: %[[GI_alloca:.*]] = alloca i32, align 4
+// CHECK-NEXT: %Sub = alloca [3 x [2 x %"class.hlsl::RWBuffer"]], align 4
+// CHECK-NEXT: %[[Tmp0:.*]] = alloca [3 x [2 x %"class.hlsl::RWBuffer"]], align 4
+// CHECK-NEXT: %a = alloca float, align 4
+// CHECK-NEXT: %b = alloca float, align 4
+// CHECK-NEXT: %[[Tmp1:.*]] = alloca [3 x [2 x %"class.hlsl::RWBuffer"]], align 4
+// CHECK-NEXT: %[[Tmp2:.*]] = alloca [3 x [2 x %"class.hlsl::RWBuffer"]], align 4
+// CHECK-NEXT: store i32 %GI, ptr %[[GI_alloca]], align 4
+[numthreads(4,1,1)]
+void main(uint GI : SV_GroupThreadID) {
+// Codegen for "A[4][1]" - create local array [[Tmp0]] of size 3 x 2 and initialize
+// each element by a call to the resource constructor
+// The resource index for A[4][1][0][0] is 102 = 4 * (4 * 3 * 2) + 1 * (3 * 2)
+// (index in the resource array as if it was flattened)
+// CHECK-NEXT: %[[Ptr_Tmp0_0_0:.*]] = getelementptr [3 x [2 x %"class.hlsl::RWBuffer"]], ptr %tmp, i32 0, i32 0, i32 0
+// CHECK-NEXT: call void @_ZN4hlsl8RWBufferIfEC1EjjijPKc(ptr {{.*}} %[[Ptr_Tmp0_0_0]], i32 noundef 10, i32 noundef 2, i32 noundef 120, i32 noundef 102, ptr noundef @A.str) #6
+// CHECK-NEXT: %[[Ptr_Tmp0_0_1:.*]] = getelementptr [3 x [2 x %"class.hlsl::RWBuffer"]], ptr %tmp, i32 0, i32 0, i32 1
+// CHECK-NEXT: call void @_ZN4hlsl8RWBufferIfEC1EjjijPKc(ptr {{.*}} %[[Ptr_Tmp0_0_1]], i32 noundef 10, i32 noundef 2, i32 noundef 120, i32 noundef 103, ptr noundef @A.str) #6
+// CHECK-NEXT: %[[Ptr_Tmp0_1_0:.*]] = getelementptr [3 x [2 x %"class.hlsl::RWBuffer"]], ptr %tmp, i32 0, i32 1, i32 0
+// CHECK-NEXT: call void @_ZN4hlsl8RWBufferIfEC1EjjijPKc(ptr {{.*}} %[[Ptr_Tmp0_1_0]], i32 noundef 10, i32 noundef 2, i32 noundef 120, i32 noundef 104, ptr noundef @A.str) #6
+// CHECK-NEXT: %[[Ptr_Tmp0_1_1:.*]] = getelementptr [3 x [2 x %"class.hlsl::RWBuffer"]], ptr %tmp, i32 0, i32 1, i32 1
+// CHECK-NEXT: call void @_ZN4hlsl8RWBufferIfEC1EjjijPKc(ptr {{.*}} %[[Ptr_Tmp0_1_1]], i32 noundef 10, i32 noundef 2, i32 noundef 120, i32 noundef 105, ptr noundef @A.str) #6
+// CHECK-NEXT: %[[Ptr_Tmp0_2_0:.*]] = getelementptr [3 x [2 x %"class.hlsl::RWBuffer"]], ptr %tmp, i32 0, i32 2, i32 0
+// CHECK-NEXT: call void @_ZN4hlsl8RWBufferIfEC1EjjijPKc(ptr {{.*}} %[[Ptr_Tmp0_2_0]], i32 noundef 10, i32 noundef 2, i32 noundef 120, i32 noundef 106, ptr noundef @A.str) #6
+// CHECK-NEXT: %[[Ptr_Tmp0_2_1:.*]] = getelementptr [3 x [2 x %"class.hlsl::RWBuffer"]], ptr %tmp, i32 0, i32 2, i32 1
+// CHECK-NEXT: call void @_ZN4hlsl8RWBufferIfEC1EjjijPKc(ptr {{.*}} %[[Ptr_Tmp0_2_1]], i32 noundef 10, i32 noundef 2, i32 noundef 120, i32 noundef 107, ptr noundef @A.str) #6
+// After this Tmp0 values are copied to %Sub using the standard array loop initializaion
+// (generated from ArrayInitLoopExpr AST node)
+ RWBuffer<float> Sub[3][2] = A[4][1];
+
+// CHECK: %[[Ptr_Sub_2:.*]] = getelementptr inbounds [3 x [2 x %"class.hlsl::RWBuffer"]], ptr %Sub, i32 0, i32 2
+// CHECK: %[[Ptr_Sub_2_1:.*]] = getelementptr inbounds [2 x %"class.hlsl::RWBuffer"], ptr %[[Ptr_Sub_2]], i32 0, i32 1
+// CHECK-NEXT: %[[BufPtr:.*]] = call {{.*}} ptr @_ZN4hlsl8RWBufferIfEixEj(ptr {{.*}} %[[Ptr_Sub_2_1]], i32 noundef 0)
+// CHECK-NEXT: %[[Sub_2_1_0_Value:.*]] = load float, ptr %[[BufPtr]], align 4
+// CHECK-NEXT: store float %[[Sub_2_1_0_Value]], ptr %a, align 4
+float a = Sub[2][1][0];
+
+// Codegen for "foo(A[2][GI])" - create local array [[Tmp2]] of size 3 x 2 and initialize
+// each element by a call to the resource constructor with dynamic index, and then
+// copy-in the array as an argument of "foo"
+
+// Calculate the resource index for A[2][GI][0][0] (index in the resource array as if it was flattened)
+// The index is 2 * (4 * 3 * 2) + GI * (3 * 2) = 48 + GI * 6
+// CHECK: %[[GI:.*]] = load i32, ptr %[[GI_alloca]], align 4
+// CHECK-NEXT: %[[Index_A_2_GI_Tmp:.*]] = mul i32 %[[GI]], 6
+// CHECK-NEXT: %[[Index_A_2_GI_0_0:.*]] = add i32 %[[Index_A_2_GI_Tmp]], 48
+
+// A[2][GI][0][0]
+// CHECK-NEXT: %[[Ptr_Tmp2_0_0:.*]] = getelementptr [3 x [2 x %"class.hlsl::RWBuffer"]], ptr %[[Tmp2]], i32 0, i32 0, i32 0
+// CHECK-NEXT: call void @_ZN4hlsl8RWBufferIfEC1EjjijPKc(ptr {{.*}} %[[Ptr_Tmp2_0_0]], i32 noundef 10, i32 noundef 2, i32 noundef 120, i32 noundef %[[Index_A_2_GI_0_0]], ptr noundef @A.str)
+
+// A[2][GI][0][1]
+// CHECK-NEXT: %[[Index_A_2_GI_0_1:.*]] = add i32 %[[Index_A_2_GI_0_0]], 1
+// CHECK-NEXT: %[[Ptr_Tmp2_0_1:.*]] = getelementptr [3 x [2 x %"class.hlsl::RWBuffer"]], ptr %[[Tmp2]], i32 0, i32 0, i32 1
+// CHECK-NEXT: call void @_ZN4hlsl8RWBufferIfEC1EjjijPKc(ptr {{.*}} %[[Ptr_Tmp2_0_1]], i32 noundef 10, i32 noundef 2, i32 noundef 120, i32 noundef %[[Index_A_2_GI_0_1]], ptr noundef @A.str)
+
+// A[2][GI][1][0]
+// CHECK-NEXT: %[[Index_A_2_GI_1_0:.*]] = add i32 %[[Index_A_2_GI_0_1]], 1
+// CHECK-NEXT: %[[Ptr_Tmp2_1_0:.*]] = getelementptr [3 x [2 x %"class.hlsl::RWBuffer"]], ptr %[[Tmp2]], i32 0, i32 1, i32 0
+// CHECK-NEXT: call void @_ZN4hlsl8RWBufferIfEC1EjjijPKc(ptr {{.*}} %[[Ptr_Tmp2_1_0]], i32 noundef 10, i32 noundef 2, i32 noundef 120, i32 noundef %[[Index_A_2_GI_1_0]], ptr noundef @A.str)
+
+// A[2][GI][1][1]
+// CHECK-NEXT: %[[Index_A_2_GI_1_1:.*]] = add i32 %[[Index_A_2_GI_1_0]], 1
+// CHECK-NEXT: %[[Ptr_Tmp2_1_1:.*]] = getelementptr [3 x [2 x %"class.hlsl::RWBuffer"]], ptr %[[Tmp2]], i32 0, i32 1, i32 1
+// CHECK-NEXT: call void @_ZN4hlsl8RWBufferIfEC1EjjijPKc(ptr {{.*}} %[[Ptr_Tmp2_1_1]], i32 noundef 10, i32 noundef 2, i32 noundef 120, i32 noundef %[[Index_A_2_GI_1_1]], ptr noundef @A.str)
+
+// A[2][GI][2][0]
+// CHECK-NEXT: %[[Index_A_2_GI_2_0:.*]] = add i32 %[[Index_A_2_GI_1_1]], 1
+// CHECK-NEXT: %[[Ptr_Tmp2_2_0:.*]] = getelementptr [3 x [2 x %"class.hlsl::RWBuffer"]], ptr %[[Tmp2]], i32 0, i32 2, i32 0
+// CHECK-NEXT: call void @_ZN4hlsl8RWBufferIfEC1EjjijPKc(ptr {{.*}} %[[Ptr_Tmp2_2_0]], i32 noundef 10, i32 noundef 2, i32 noundef 120, i32 noundef %[[Index_A_2_GI_2_0]], ptr noundef @A.str)
+
+// A[2][GI][2][1]
+// CHECK-NEXT: %[[Index_A_2_GI_2_1:.*]] = add i32 %[[Index_A_2_GI_2_0]], 1
+// CHECK-NEXT: %[[Ptr_Tmp2_2_1:.*]] = getelementptr [3 x [2 x %"class.hlsl::RWBuffer"]], ptr %[[Tmp2]], i32 0, i32 2, i32 1
+// CHECK-NEXT: call void @_ZN4hlsl8RWBufferIfEC1EjjijPKc(ptr {{.*}} %[[Ptr_Tmp2_2_1]], i32 noundef 10, i32 noundef 2, i32 noundef 120, i32 noundef %[[Index_A_2_GI_2_1]], ptr noundef @A.str)
+
+// CHECK-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 4 %[[Tmp1]], ptr align 4 %[[Tmp2]], i32 24, i1 false)
+// CHECK-NEXT: %[[FooReturned:.*]] = call {{.*}} float @_Z3fooA3_A2_N4hlsl8RWBufferIfEE(ptr noundef byval([3 x [2 x %"class.hlsl::RWBuffer"]]) align 4 %[[Tmp1]])
+// CHECK-NEXT: store float %[[FooReturned]], ptr %b, align 4
+ float b = foo(A[2][GI]);
+
+ Out[0] = a + b;
+}
diff --git a/clang/test/CodeGenHLSL/resources/res-array-global-subarray-one.hlsl b/clang/test/CodeGenHLSL/resources/res-array-global-subarray-one.hlsl
new file mode 100644
index 0000000000000..c73873206d54c
--- /dev/null
+++ b/clang/test/CodeGenHLSL/resources/res-array-global-subarray-one.hlsl
@@ -0,0 +1,62 @@
+// RUN: %clang_cc1 -triple dxil-pc-shadermodel6.6-compute -finclude-default-header \
+// RUN: -emit-llvm -disable-llvm-passes -o - %s | FileCheck %s
+
+// CHECK: @[[BufA:.*]] = private unnamed_addr constant [2 x i8] c"A\00", align 1
+
+RWBuffer<float> A[4][2] : register(u10, space2);
+RWStructuredBuffer<float> Out;
+
+float foo(RWBuffer<float> Arr[2]) {
+ return Arr[1][0];
+}
+
+// NOTE:
+// - _ZN4hlsl8RWBufferIfEC1EjjijPKc is the constructor call for explicit binding
+// (has "jjij" in the mangled name) and the arguments are (register, space, range_size, index, name).
+// - _ZN4hlsl8RWBufferIfEixEj is the subscript operator for RWBuffer<float>
+
+// CHECK: define internal void @_Z4mainj(i32 noundef %GI)
+// CHECK-NEXT: entry:
+// CHECK-NEXT: %[[GI_alloca:.*]] = alloca i32, align 4
+// CHECK-NEXT: %Sub = alloca [2 x %"class.hlsl::RWBuffer"], align 4
+// CHECK-NEXT: %[[Tmp0:.*]] = alloca [2 x %"class.hlsl::RWBuffer"], align 4
+// CHECK-NEXT: %a = alloca float, align 4
+// CHECK-NEXT: %b = alloca float, align 4
+// CHECK-NEXT: %[[Tmp1:.*]] = alloca [2 x %"class.hlsl::RWBuffer"], align 4
+// CHECK-NEXT: %[[Tmp2:.*]] = alloca [2 x %"class.hlsl::RWBuffer"], align 4
+// CHECK-NEXT: store i32 %GI, ptr %[[GI_alloca]], align 4
+[numthreads(4,1,1)]
+void main(uint GI : SV_GroupThreadID) {
+// Codegen for "A[2]" - create local array [[Tmp0]] of size 2 and initialize
+// each element by a call to the resource constructor
+// CHECK-NEXT: %[[Ptr_Tmp0_0:.*]] = getelementptr [2 x %"class.hlsl::RWBuffer"], ptr %[[Tmp0]], i32 0, i32 0
+// CHECK-NEXT: call void @_ZN4hlsl8RWBufferIfEC1EjjijPKc(ptr {{.*}} %[[Ptr_Tmp0_0]], i32 noundef 10, i32 noundef 2, i32 noundef 8, i32 noundef 6, ptr noundef @A.str)
+// CHECK-NEXT: %[[Ptr_Tmp0_1:.*]] = getelementptr [2 x %"class.hlsl::RWBuffer"], ptr %[[Tmp0]], i32 0, i32 1
+// CHECK-NEXT: call void @_ZN4hlsl8RWBufferIfEC1EjjijPKc(ptr {{.*}} %[[Ptr_Tmp0_1]], i32 noundef 10, i32 noundef 2, i32 noundef 8, i32 noundef 7, ptr noundef @A.str)
+// After this Tmp0 values are copied to %Sub using the standard array loop initializaion
+// (generated from ArrayInitLoopExpr AST node)
+ RWBuffer<float> Sub[2] = A[3];
+
+// CHECK: %[[Ptr_Sub_1:.*]] = getelementptr inbounds [2 x %"class.hlsl::RWBuffer"], ptr %Sub, i32 0, i32 1
+// CHECK-NEXT: %[[BufPtr:.*]] = call {{.*}} ptr @_ZN4hlsl8RWBufferIfEixEj(ptr {{.*}} %[[Ptr_Sub_1]], i32 noundef 0)
+// CHECK-NEXT: %[[Sub_1_0_Value:.*]] = load float, ptr %[[BufPtr]], align 4
+// CHECK-NEXT: store float %[[Sub_1_0_Value]], ptr %a, align 4
+float a = Sub[1][0];
+
+// Codegen for "foo(A[GI])" - create local array [[Tmp2]] of size 2 and initialize
+// each element by a call to the resource constructor with dynamic index, and then
+// copy-in the array as an argument of "foo"
+// CHECK: %[[GI:.*]] = load i32, ptr %[[GI_alloca]], align 4
+// CHECK-NEXT: %[[Index_A_GI_0:.*]] = mul i32 %[[GI]], 2
+// CHECK-NEXT: %[[Ptr_Tmp2_GI_0:.*]] = getelementptr [2 x %"class.hlsl::RWBuffer"], ptr %[[Tmp2]], i32 0, i32 0
+// CHECK-NEXT: call void @_ZN4hlsl8RWBufferIfEC1EjjijPKc(ptr {{.*}} %[[Ptr_Tmp2_GI_0]], i32 noundef 10, i32 noundef 2, i32 noundef 8, i32 noundef %[[Index_A_GI_0]], ptr noundef @A.str)
+// CHECK-NEXT: %[[Index_A_GI_1:.*]] = add i32 %[[Index_A_GI_0]], 1
+// CHECK-NEXT: %[[Ptr_Tmp2_GI_1:.*]] = getelementptr [2 x %"class.hlsl::RWBuffer"], ptr %[[Tmp2]], i32 0, i32 1
+// CHECK-NEXT: call void @_ZN4hlsl8RWBufferIfEC1EjjijPKc(ptr {{.*}} %[[Ptr_Tmp2_GI_1]], i32 noundef 10, i32 noundef 2, i32 noundef 8, i32 noundef %[[Index_A_GI_1]], ptr noundef @A.str)
+// CHECK-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 4 %[[Tmp1]], ptr align 4 %[[Tmp2]], i32 8, i1 false)
+// CHECK-NEXT: %[[FooReturned:.*]] = call {{.*}} float @_Z3fooA2_N4hlsl8RWBufferIfEE(ptr noundef byval([2 x %"class.hlsl::RWBuffer"]) align 4 %[[Tmp1]])
+// CHECK-NEXT: store float %[[FooReturned]], ptr %b, align 4
+ float b = foo(A[GI]);
+
+ Out[0] = a + b;
+}
>From 7afa5cc2fcd1c7690e263e83632232a84cf85ad2 Mon Sep 17 00:00:00 2001
From: Helena Kotas <hekotas at microsoft.com>
Date: Fri, 22 Aug 2025 17:30:13 -0700
Subject: [PATCH 2/3] [HLSL] Enable unbounded resource arrays at global scope
Closes #145427
---
.../clang/Basic/DiagnosticSemaKinds.td | 3 +
clang/lib/AST/Type.cpp | 4 +-
clang/lib/Sema/SemaDecl.cpp | 17 ++++-
clang/lib/Sema/SemaHLSL.cpp | 18 +++---
.../resources/res-array-global-unbounded.hlsl | 64 +++++++++++++++++++
.../SemaHLSL/unbounded_resource_arrays.hlsl | 21 ++++++
6 files changed, 114 insertions(+), 13 deletions(-)
create mode 100644 clang/test/CodeGenHLSL/resources/res-array-global-unbounded.hlsl
create mode 100644 clang/test/SemaHLSL/unbounded_resource_arrays.hlsl
diff --git a/clang/include/clang/Basic/DiagnosticSemaKinds.td b/clang/include/clang/Basic/DiagnosticSemaKinds.td
index c733e8823cea6..ed9c772035511 100644
--- a/clang/include/clang/Basic/DiagnosticSemaKinds.td
+++ b/clang/include/clang/Basic/DiagnosticSemaKinds.td
@@ -13159,6 +13159,9 @@ def err_hlsl_resource_range_overlap: Error<
"%select{All|Vertex|Hull|Domain|Geometry|Pixel|Amplification|Mesh}9">;
def note_hlsl_resource_range_here: Note<"overlapping resource range here">;
+def err_hlsl_incomplete_resource_array_in_function_param: Error<
+ "incomplete resource array in a function parameter">;
+
// Layout randomization diagnostics.
def err_non_designated_init_used : Error<
"a randomized struct can only be initialized with a designated initializer">;
diff --git a/clang/lib/AST/Type.cpp b/clang/lib/AST/Type.cpp
index 5fbf1999ed725..1815eba4eedba 100644
--- a/clang/lib/AST/Type.cpp
+++ b/clang/lib/AST/Type.cpp
@@ -5419,7 +5419,7 @@ bool Type::isHLSLResourceRecordArray() const {
const Type *Ty = getUnqualifiedDesugaredType();
if (!Ty->isArrayType())
return false;
- while (isa<ConstantArrayType>(Ty))
+ while (isa<ArrayType>(Ty))
Ty = Ty->getArrayElementTypeNoTypeQual();
return Ty->isHLSLResourceRecord();
}
@@ -5432,7 +5432,7 @@ bool Type::isHLSLIntangibleType() const {
return Ty->isHLSLBuiltinIntangibleType();
// unwrap arrays
- while (isa<ConstantArrayType>(Ty))
+ while (isa<ArrayType>(Ty))
Ty = Ty->getArrayElementTypeNoTypeQual();
const RecordType *RT =
diff --git a/clang/lib/Sema/SemaDecl.cpp b/clang/lib/Sema/SemaDecl.cpp
index 98485cf9e72be..09ba88eef741d 100644
--- a/clang/lib/Sema/SemaDecl.cpp
+++ b/clang/lib/Sema/SemaDecl.cpp
@@ -14380,9 +14380,12 @@ void Sema::ActOnUninitializedDecl(Decl *RealDecl) {
return;
}
- // Provide a specific diagnostic for uninitialized variable
- // definitions with incomplete array type.
- if (Type->isIncompleteArrayType()) {
+ // Provide a specific diagnostic for uninitialized variable definitions
+ // with incomplete array type, unless it is a global unbounded HLSL resource
+ // array.
+ if (Type->isIncompleteArrayType() &&
+ !(getLangOpts().HLSL && Var->hasGlobalStorage() &&
+ Type->isHLSLResourceRecordArray())) {
if (Var->isConstexpr())
Diag(Var->getLocation(), diag::err_constexpr_var_requires_const_init)
<< Var;
@@ -15471,6 +15474,14 @@ Decl *Sema::ActOnParamDeclarator(Scope *S, Declarator &D,
}
}
+ // Incomplete resource arrays are not allowed as function parameters in HLSL
+ if (getLangOpts().HLSL && parmDeclType->isIncompleteArrayType() &&
+ parmDeclType->isHLSLResourceRecordArray()) {
+ Diag(D.getIdentifierLoc(),
+ diag::err_hlsl_incomplete_resource_array_in_function_param);
+ D.setInvalidType(true);
+ }
+
// Temporarily put parameter variables in the translation unit, not
// the enclosing context. This prevents them from accidentally
// looking like class members in C++.
diff --git a/clang/lib/Sema/SemaHLSL.cpp b/clang/lib/Sema/SemaHLSL.cpp
index f87715950c74c..0028be459d13d 100644
--- a/clang/lib/Sema/SemaHLSL.cpp
+++ b/clang/lib/Sema/SemaHLSL.cpp
@@ -351,8 +351,8 @@ getResourceArrayHandleType(VarDecl *VD) {
assert(VD->getType()->isHLSLResourceRecordArray() &&
"expected array of resource records");
const Type *Ty = VD->getType()->getUnqualifiedDesugaredType();
- while (const ConstantArrayType *CAT = dyn_cast<ConstantArrayType>(Ty))
- Ty = CAT->getArrayElementTypeNoTypeQual()->getUnqualifiedDesugaredType();
+ while (const ArrayType *AT = dyn_cast<ArrayType>(Ty))
+ Ty = AT->getArrayElementTypeNoTypeQual()->getUnqualifiedDesugaredType();
return HLSLAttributedResourceType::findHandleTypeOnResource(Ty);
}
@@ -2008,9 +2008,11 @@ static bool DiagnoseHLSLRegisterAttribute(Sema &S, SourceLocation &ArgLoc,
}
void SemaHLSL::handleResourceBindingAttr(Decl *TheDecl, const ParsedAttr &AL) {
- if (isa<VarDecl>(TheDecl)) {
- if (SemaRef.RequireCompleteType(TheDecl->getBeginLoc(),
- cast<ValueDecl>(TheDecl)->getType(),
+ if (VarDecl *VD = dyn_cast<VarDecl>(TheDecl)) {
+ QualType Ty = VD->getType();
+ if (Ty->isIncompleteArrayType())
+ Ty = cast<IncompleteArrayType>(Ty)->getElementType();
+ if (SemaRef.RequireCompleteType(TheDecl->getBeginLoc(), Ty,
diag::err_incomplete_type))
return;
}
@@ -3820,9 +3822,9 @@ void SemaHLSL::collectResourceBindingsOnVarDecl(VarDecl *VD) {
// Unwrap arrays
// FIXME: Calculate array size while unwrapping
const Type *Ty = VD->getType()->getUnqualifiedDesugaredType();
- while (Ty->isConstantArrayType()) {
- const ConstantArrayType *CAT = cast<ConstantArrayType>(Ty);
- Ty = CAT->getElementType()->getUnqualifiedDesugaredType();
+ while (Ty->isArrayType()) {
+ const ArrayType *AT = cast<ArrayType>(Ty);
+ Ty = AT->getElementType()->getUnqualifiedDesugaredType();
}
// Resource (or array of resources)
diff --git a/clang/test/CodeGenHLSL/resources/res-array-global-unbounded.hlsl b/clang/test/CodeGenHLSL/resources/res-array-global-unbounded.hlsl
new file mode 100644
index 0000000000000..631e4fcc0e4e5
--- /dev/null
+++ b/clang/test/CodeGenHLSL/resources/res-array-global-unbounded.hlsl
@@ -0,0 +1,64 @@
+// RUN: %clang_cc1 -triple dxil-pc-shadermodel6.6-compute -finclude-default-header \
+// RUN: -emit-llvm -disable-llvm-passes -o - %s | FileCheck %s -check-prefixes=CHECK,DXIL
+// RUN: %clang_cc1 -finclude-default-header -triple spirv-unknown-vulkan-compute \
+// RUN: -emit-llvm -disable-llvm-passes -o - %s | FileCheck %s -check-prefixes=CHECK,SPV
+
+// CHECK: @[[BufA:.*]] = private unnamed_addr constant [2 x i8] c"A\00", align 1
+// CHECK: @[[BufB:.*]] = private unnamed_addr constant [2 x i8] c"B\00", align 1
+
+RWBuffer<float> A[] : register(u10, space1);
+RWBuffer<int> B[][5][4];
+
+RWStructuredBuffer<float> Out;
+
+float foo(RWBuffer<int> Arr[4], uint Index) {
+ return (float)Arr[Index][0];
+}
+
+// NOTE:
+// - _ZN4hlsl8RWBufferIfEC1EjjijPKc is the constructor call for explicit binding for RWBuffer<float>
+// (has "jjij" in the mangled name) and the arguments are (register, space, range_size, index, name).
+// - _ZN4hlsl8RWBufferIiEC1EjijjPKc is the constructor call for implicit binding for RWBuffer<int>
+// (has "jijj" in the mangled name) and the arguments are (space, range_size, index, order_id, name).
+// - _ZN4hlsl8RWBufferIfEixEj is the subscript operator on RWBuffer<float>
+
+[numthreads(4,1,1)]
+void main(uint GI : SV_GroupIndex) {
+ // CHECK: define internal {{.*}}void @_Z4mainj(i32 noundef %GI)
+ // CHECK: %[[GI_alloca:.*]] = alloca i32, align 4
+ // CHECK-NEXT: %a = alloca float, align 4
+ // CHECK-NEXT: %[[Tmp0:.*]] = alloca %"class.hlsl::RWBuffer
+ // CHECK-NEXT: %b = alloca float, align 4
+ // CHECK-NEXT: %[[Tmp1:.*]] = alloca [4 x %"class.hlsl::RWBuffer"]
+ // CHECK-NEXT: %[[Tmp2:.*]] = alloca [4 x %"class.hlsl::RWBuffer"]
+ // CHECK-NEXT: store i32 %GI, ptr %[[GI_alloca]], align 4
+
+ // Make sure A[100] is translated to a RWBuffer<float> constructor call with range -1 and index 100
+ // and explicit binding (u10, space1)
+ // CHECK: call void @_ZN4hlsl8RWBufferIfEC1EjjijPKc(ptr {{.*}} %[[Tmp0]], i32 noundef 10, i32 noundef 1, i32 noundef -1, i32 noundef 100, ptr noundef @A.str)
+ // CHECK-NEXT: %[[BufPtr:.*]] = call {{.*}} ptr{{.*}} @_ZN4hlsl8RWBufferIfEixEj(ptr {{.*}} %[[Tmp0]], i32 noundef 0)
+ // CHECK-NEXT: %[[Value1:.*]] = load float, ptr{{.*}} %[[BufPtr]], align 4
+ // CHECK-NEXT: store float %[[Value1]], ptr %a, align 4
+ float a = A[100][0];
+
+ // Make sure B[2][3] is translated to a local RWBuffer<int>[4] array where each array element
+ // is initialized by a constructor call with range -1 and index 52-54
+ // and implicit binding (space 0, order_id 0)
+ // CHECK-NEXT: %[[Ptr_Tmp2_0:.*]] = getelementptr [4 x %"class.hlsl::RWBuffer"], ptr %[[Tmp2]], i32 0, i32 0
+ // CHECK-NEXT: call void @_ZN4hlsl8RWBufferIiEC1EjijjPKc(ptr {{.*}} %[[Ptr_Tmp2_0]], i32 noundef 0, i32 noundef -1, i32 noundef 52, i32 noundef 0, ptr noundef @B.str)
+ // CHECK-NEXT: %[[Ptr_Tmp2_1:.*]] = getelementptr [4 x %"class.hlsl::RWBuffer"], ptr %[[Tmp2]], i32 0, i32 1
+ // CHECK-NEXT: call void @_ZN4hlsl8RWBufferIiEC1EjijjPKc(ptr {{.*}} %[[Ptr_Tmp2_1]], i32 noundef 0, i32 noundef -1, i32 noundef 53, i32 noundef 0, ptr noundef @B.str)
+ // CHECK-NEXT: %[[Ptr_Tmp2_2:.*]] = getelementptr [4 x %"class.hlsl::RWBuffer"], ptr %[[Tmp2]], i32 0, i32 2
+ // CHECK-NEXT: call void @_ZN4hlsl8RWBufferIiEC1EjijjPKc(ptr {{.*}} %[[Ptr_Tmp2_2]], i32 noundef 0, i32 noundef -1, i32 noundef 54, i32 noundef 0, ptr noundef @B.str)
+ // CHECK-NEXT: %[[Ptr_Tmp2_3:.*]] = getelementptr [4 x %"class.hlsl::RWBuffer"], ptr %[[Tmp2]], i32 0, i32 3
+ // CHECK-NEXT: call void @_ZN4hlsl8RWBufferIiEC1EjijjPKc(ptr {{.*}} %[[Ptr_Tmp2_3]], i32 noundef 0, i32 noundef -1, i32 noundef 55, i32 noundef 0, ptr noundef @B.str)
+ // DXIL-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 4 %[[Tmp1]], ptr align 4 %[[Tmp2]], i32 16, i1 false)
+ // SPV-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 8 %[[Tmp1]], ptr align 8 %[[Tmp2]], i64 32, i1 false)
+ // CHECK-NEXT: %[[GI:.*]] = load i32, ptr %[[GI_alloca]], align 4
+ // DXIL-NEXT: %[[Value2:.*]] = call {{.*}} float @_Z3fooA4_N4hlsl8RWBufferIiEEj(ptr noundef byval([4 x %"class.hlsl::RWBuffer"]) align 4 %[[Tmp1]], i32 noundef %[[GI]])
+ // SPV-NEXT: %[[Value2:.*]] = call {{.*}} float @_Z3fooA4_N4hlsl8RWBufferIiEEj(ptr noundef byval([4 x %"class.hlsl::RWBuffer"]) align 8 %[[Tmp1]], i32 noundef %[[GI]])
+ // CHECK-NEXT: store float %[[Value2]], ptr %b, align 4
+ float b = foo(B[2][3], GI);
+
+ Out[0] = a + b;
+}
diff --git a/clang/test/SemaHLSL/unbounded_resource_arrays.hlsl b/clang/test/SemaHLSL/unbounded_resource_arrays.hlsl
new file mode 100644
index 0000000000000..b65deeda9a4ff
--- /dev/null
+++ b/clang/test/SemaHLSL/unbounded_resource_arrays.hlsl
@@ -0,0 +1,21 @@
+// RUN: not %clang_cc1 -triple dxil-pc-shadermodel6.3-compute -finclude-default-header --o - %s -verify
+
+// unbounded resource array at a global scope
+RWBuffer<float> unbounded_array[]; // no_error
+
+// expected-error at +1 {{incomplete resource array in a function parameter}}
+void foo(RWBuffer<float> array_arg[]) {}
+
+RWBuffer<float> A, B;
+
+[numthreads(4,1,1)]
+void main() {
+ // expected-error at +1{{definition of variable with array type needs an explicit size or an initializer}}
+ RWBuffer<float> res_local_array1[];
+
+ // expected-error at +1{{array initializer must be an initialzer list}}
+ RWBuffer<float> res_local_array2[] = unbounded_array;
+
+ // local incomplete resource array with initializer
+ RWBuffer<float> res_local_array3[] = { A, B }; // no error
+}
>From ad85d72bc6000f5a864dfc6b5930ccfac17748bb Mon Sep 17 00:00:00 2001
From: Helena Kotas <hekotas at microsoft.com>
Date: Thu, 4 Sep 2025 21:04:59 -0700
Subject: [PATCH 3/3] code review feedback - use dyncast
---
clang/lib/Sema/SemaHLSL.cpp | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/clang/lib/Sema/SemaHLSL.cpp b/clang/lib/Sema/SemaHLSL.cpp
index 0028be459d13d..f739b31c04bf0 100644
--- a/clang/lib/Sema/SemaHLSL.cpp
+++ b/clang/lib/Sema/SemaHLSL.cpp
@@ -2010,8 +2010,8 @@ static bool DiagnoseHLSLRegisterAttribute(Sema &S, SourceLocation &ArgLoc,
void SemaHLSL::handleResourceBindingAttr(Decl *TheDecl, const ParsedAttr &AL) {
if (VarDecl *VD = dyn_cast<VarDecl>(TheDecl)) {
QualType Ty = VD->getType();
- if (Ty->isIncompleteArrayType())
- Ty = cast<IncompleteArrayType>(Ty)->getElementType();
+ if (const auto *IAT = dyn_cast<IncompleteArrayType>(Ty))
+ Ty = IAT->getElementType();
if (SemaRef.RequireCompleteType(TheDecl->getBeginLoc(), Ty,
diag::err_incomplete_type))
return;
More information about the cfe-commits
mailing list