python3kgae updated this revision to Diff 450978.
python3kgae added a comment.
Add more test and comment.
Also use getTargetAddressSpace.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D130131/new/
https://reviews.llvm.org/D130131
Files:
clang/include/clang/Basic/AddressSpaces.h
clang/lib/AST/ASTContext.cpp
clang/lib/Basic/Targets/AMDGPU.cpp
clang/lib/Basic/Targets/DirectX.h
clang/lib/Basic/Targets/NVPTX.h
clang/lib/Basic/Targets/SPIR.h
clang/lib/Basic/Targets/TCE.h
clang/lib/Basic/Targets/X86.h
clang/lib/CodeGen/CGDecl.cpp
clang/lib/CodeGen/CGHLSLRuntime.cpp
clang/lib/CodeGen/CGHLSLRuntime.h
clang/lib/CodeGen/CodeGenModule.cpp
clang/test/CodeGenHLSL/cbuf.hlsl
clang/test/CodeGenHLSL/cbuf_in_namespace.hlsl
clang/test/CodeGenHLSL/nest_cbuf.hlsl
clang/test/CodeGenHLSL/static_global_and_function_in_cb.hlsl
Index: clang/test/CodeGenHLSL/static_global_and_function_in_cb.hlsl
===================================================================
--- /dev/null
+++ clang/test/CodeGenHLSL/static_global_and_function_in_cb.hlsl
@@ -0,0 +1,18 @@
+// RUN: %clang_dxc -Tlib_6_7 -fcgl -Fo - %s | FileCheck %s
+
+// CHECK-DAG: @[[CB:.+]] = external addrspace(4) constant { float }
+
+cbuffer A {
+ namespace n0 {
+ float a;
+ }
+ // CHECK-DAG:@b = internal global float 3.000000e+00, align 4
+ static float b = 3;
+ // CHECK:load float, ptr addrspacecast (ptr addrspace(4) @[[CB]] to ptr), align 4
+ // CHECK:load float, ptr @b, align 4
+ float foo() { return n0::a + b; }
+}
+
+float bar() {
+ return foo();
+}
Index: clang/test/CodeGenHLSL/nest_cbuf.hlsl
===================================================================
--- /dev/null
+++ clang/test/CodeGenHLSL/nest_cbuf.hlsl
@@ -0,0 +1,20 @@
+// RUN: %clang_dxc -Tlib_6_7 -fcgl -Fo - %s | FileCheck %s
+
+// CHECK: @[[CB:.+]] = external addrspace(4) constant { float, i32, double }
+cbuffer A {
+ float a;
+ double b;
+ // CHECK: @[[TB:.+]] = external addrspace(5) constant { float, i32, double }
+ tbuffer A : register(t2, space1) {
+ float c;
+ double d;
+ }
+}
+
+float foo() {
+// CHECK: load float, ptr addrspacecast (ptr addrspace(4) @[[CB]] to ptr), align 4
+// CHECK: load double, ptr addrspacecast (ptr addrspace(4) getelementptr inbounds ({ float, i32, double }, ptr addrspace(4) @[[CB]], i32 0, i32 2) to ptr), align 8
+// CHECK: load float, ptr addrspacecast (ptr addrspace(5) @[[TB]] to ptr), align 4
+// CHECK: load double, ptr addrspacecast (ptr addrspace(5) getelementptr inbounds ({ float, i32, double }, ptr addrspace(5) @[[TB]], i32 0, i32 2) to ptr), align 8
+ return a + b + c*d;
+}
Index: clang/test/CodeGenHLSL/cbuf_in_namespace.hlsl
===================================================================
--- /dev/null
+++ clang/test/CodeGenHLSL/cbuf_in_namespace.hlsl
@@ -0,0 +1,18 @@
+// RUN: %clang_dxc -Tlib_6_7 -fcgl -Fo - %s | FileCheck %s
+
+// Make sure namespace inside cbuffer works.
+// CHECK: @[[CB:.+]] = external addrspace(4) constant { float, float }
+cbuffer A {
+ namespace n0 {
+ float a;
+ }
+ namespace n1 {
+ float b;
+ }
+}
+
+float foo() {
+// CHECK: load float, ptr addrspacecast (ptr addrspace(4) @[[CB]] to ptr), align 4
+// CHECK: load float, ptr addrspacecast (ptr addrspace(4) getelementptr inbounds ({ float, float }, ptr addrspace(4) @[[CB]], i32 0, i32 1) to ptr), align 4
+ return n0::a + n1::b;
+}
Index: clang/test/CodeGenHLSL/cbuf.hlsl
===================================================================
--- /dev/null
+++ clang/test/CodeGenHLSL/cbuf.hlsl
@@ -0,0 +1,21 @@
+// RUN: %clang_dxc -Tlib_6_7 -fcgl -Fo - %s | FileCheck %s
+
+// CHECK: @[[CB:.+]] = external addrspace(4) constant { float, i32, double }
+cbuffer A : register(b0, space1) {
+ float a;
+ double b;
+}
+
+// CHECK: @[[TB:.+]] = external addrspace(5) constant { float, i32, double }
+tbuffer A : register(t2, space1) {
+ float c;
+ double d;
+}
+
+float foo() {
+// CHECK: load float, ptr addrspacecast (ptr addrspace(4) @[[CB]] to ptr), align 4
+// CHECK: load double, ptr addrspacecast (ptr addrspace(4) getelementptr inbounds ({ float, i32, double }, ptr addrspace(4) @[[CB]], i32 0, i32 2) to ptr), align 8
+// CHECK: load float, ptr addrspacecast (ptr addrspace(5) @[[TB]] to ptr), align 4
+// CHECK: load double, ptr addrspacecast (ptr addrspace(5) getelementptr inbounds ({ float, i32, double }, ptr addrspace(5) @[[TB]], i32 0, i32 2) to ptr), align 8
+ return a + b + c*d;
+}
Index: clang/lib/CodeGen/CodeGenModule.cpp
===================================================================
--- clang/lib/CodeGen/CodeGenModule.cpp
+++ clang/lib/CodeGen/CodeGenModule.cpp
@@ -6370,6 +6370,10 @@
DI->EmitAndRetainType(getContext().getEnumType(cast<EnumDecl>(D)));
break;
+ case Decl::HLSLBuffer:
+ getHLSLRuntime().addBuffer(cast<HLSLBufferDecl>(D));
+ break;
+
default:
// Make sure we handled everything we should, every other kind is a
// non-top-level decl. FIXME: Would be nice to have an isTopLevelDeclKind
Index: clang/lib/CodeGen/CGHLSLRuntime.h
===================================================================
--- clang/lib/CodeGen/CGHLSLRuntime.h
+++ clang/lib/CodeGen/CGHLSLRuntime.h
@@ -17,15 +17,25 @@
#include "clang/Basic/HLSLRuntime.h"
+#include "llvm/ADT/Optional.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/StringRef.h"
+
+#include <vector>
+
namespace llvm {
class Value;
class GlobalVariable;
class Function;
+class StructType;
} // namespace llvm
+
namespace clang {
+class HLSLBufferDecl;
class CallExpr;
class Type;
class VarDecl;
+class DeclContext;
class FunctionDecl;
@@ -34,6 +44,19 @@
class CodeGenModule;
class CGHLSLRuntime {
+public:
+ struct Buffer {
+ Buffer(HLSLBufferDecl *D);
+ llvm::StringRef Name;
+ // IsCBuffer - Whether the buffer is a cbuffer (and not a tbuffer).
+ bool IsCBuffer;
+ llvm::Optional<unsigned> Reg;
+ unsigned Space;
+ // Global variable and offset for each constant.
+ std::vector<std::pair<llvm::GlobalVariable *, unsigned>> Constants;
+ llvm::StructType *LayoutStruct = nullptr;
+ };
+
protected:
CodeGenModule &CGM;
uint32_t ResourceCounters[static_cast<uint32_t>(
@@ -45,9 +68,15 @@
void annotateHLSLResource(const VarDecl *D, llvm::GlobalVariable *GV);
+ void addBuffer(HLSLBufferDecl *D);
void finishCodeGen();
void setHLSLFunctionAttributes(llvm::Function *, const FunctionDecl *);
+
+private:
+ void addConstant(VarDecl *D, Buffer &CB);
+ void addBufferDecls(DeclContext *DC, Buffer &CB);
+ llvm::SmallVector<Buffer> Buffers;
};
} // namespace CodeGen
Index: clang/lib/CodeGen/CGHLSLRuntime.cpp
===================================================================
--- clang/lib/CodeGen/CGHLSLRuntime.cpp
+++ clang/lib/CodeGen/CGHLSLRuntime.cpp
@@ -13,7 +13,9 @@
//===----------------------------------------------------------------------===//
#include "CGHLSLRuntime.h"
+#include "CGDebugInfo.h"
#include "CodeGenModule.h"
+
#include "clang/Basic/TargetOptions.h"
#include "llvm/IR/Metadata.h"
#include "llvm/IR/Module.h"
@@ -24,6 +26,7 @@
using namespace llvm;
namespace {
+
void addDxilValVersion(StringRef ValVersionStr, llvm::Module &M) {
// The validation of ValVersionStr is done at HLSLToolChain::TranslateArgs.
// Assume ValVersionStr is legal here.
@@ -43,13 +46,184 @@
StringRef DxilValKey = "dx.valver";
M.addModuleFlag(llvm::Module::ModFlagBehavior::AppendUnique, DxilValKey, Val);
}
+
+// cbuffer will be translated into global variable in special address space.
+// If translate into C,
+// cbuffer A {
+// float a;
+// float b;
+// }
+// float foo() { return a + b; }
+//
+// will be translated into
+//
+// struct A {
+// float a;
+// float b;
+// } cbuffer_A __attribute__((address_space(4)));
+// float foo() { return cbuffer_A.a + cbuffer_A.b; }
+//
+// layoutBuffer will create the struct A type.
+// replaceBuffer will replace use of global variable a and b with cbuffer_A.a
+// and cbuffer_A.b.
+//
+void layoutBuffer(CGHLSLRuntime::Buffer &Buf, const DataLayout &DL) {
+ if (Buf.Constants.empty())
+ return;
+
+ // FIXME: support legacy cbuffer layout.
+ auto &Ctx = Buf.Constants[0].first->getContext();
+ std::vector<llvm::Type *> EltTys;
+ uint64_t Offset = 0;
+ for (auto &Const : Buf.Constants) {
+ auto *GV = Const.first;
+ Const.second = EltTys.size();
+ auto *Ty = GV->getValueType();
+ auto Align = DL.getPrefTypeAlign(Ty);
+ if (uint64_t PaddingSize = (Offset % Align.value())) {
+ // Not aligned.
+ // Adding padding.
+ auto *PaddingTy = IntegerType::get(Ctx, 8 * PaddingSize);
+ EltTys.emplace_back(PaddingTy);
+ Offset += PaddingSize;
+ }
+ // Save Index for Ty into Const.second.
+ Const.second = EltTys.size();
+ EltTys.emplace_back(Ty);
+
+ Offset += DL.getTypeAllocSize(Ty);
+ }
+ Buf.LayoutStruct = llvm::StructType::get(EltTys[0]->getContext(), EltTys);
+}
+
+GlobalVariable *replaceBuffer(CGHLSLRuntime::Buffer &Buf,
+ const unsigned AddressSpace) {
+ // Create global variable for CB.
+ GlobalVariable *CBGV =
+ new GlobalVariable(Buf.LayoutStruct, /*isConstant*/ true,
+ GlobalValue::LinkageTypes::ExternalLinkage, nullptr,
+ Buf.Name + (Buf.IsCBuffer ? ".cb." : ".tb."),
+ GlobalValue::NotThreadLocal, AddressSpace);
+
+ IRBuilder<> B(CBGV->getContext());
+ Value *ZeroIdx = B.getInt32(0);
+ // Replace Const use with CB use.
+ for (auto &Const : Buf.Constants) {
+ auto *EltTy = Buf.LayoutStruct->getElementType(Const.second);
+ auto *GV = Const.first;
+ unsigned Offset = Const.second;
+
+ Value *GEP =
+ B.CreateGEP(Buf.LayoutStruct, CBGV, {ZeroIdx, B.getInt32(Offset)});
+
+ auto *GVTy = GV->getValueType();
+ assert(EltTy == GVTy && "constant type mismatch");
+
+ // Cast address space.
+ GEP = B.CreateAddrSpaceCast(GEP, GVTy->getPointerTo());
+ // Replace.
+ GV->replaceAllUsesWith(GEP);
+ // Erase GV.
+ GV->removeDeadConstantUsers();
+ GV->eraseFromParent();
+ }
+ return CBGV;
+}
+
+void addResourceBinding(GlobalVariable *GV, CGHLSLRuntime::Buffer &CB) {
+ // FIXME: add resource binding to GV.
+}
+
} // namespace
+void CGHLSLRuntime::addConstant(VarDecl *D, Buffer &CB) {
+ if (D->getStorageClass() == SC_Static) {
+ // For static inside cbuffer, take as global static.
+ // Don't add to cbuffer.
+ CGM.EmitGlobal(D);
+ return;
+ }
+
+ auto *GV = cast<GlobalVariable>(CGM.GetAddrOfGlobalVar(D));
+ // Add debug info for constVal.
+ if (CGDebugInfo *DI = CGM.getModuleDebugInfo())
+ if (CGM.getCodeGenOpts().getDebugInfo() >=
+ codegenoptions::DebugInfoKind::LimitedDebugInfo)
+ DI->EmitGlobalVariable(cast<GlobalVariable>(GV), D);
+
+ // FIXME: support packoffset.
+ uint32_t Offset = 0;
+ bool HasUserOffset = false;
+
+ unsigned LowerBound = HasUserOffset ? Offset : UINT_MAX;
+ CB.Constants.emplace_back(std::make_pair(GV, LowerBound));
+}
+
+void CGHLSLRuntime::addBufferDecls(DeclContext *DC, Buffer &CB) {
+ for (Decl *it : DC->decls()) {
+ if (VarDecl *ConstDecl = dyn_cast<VarDecl>(it)) {
+ addConstant(ConstDecl, CB);
+ } else if (isa<EmptyDecl>(*it)) {
+ // Nothing to do for this declaration.
+ } else if (isa<CXXRecordDecl>(it)) {
+ // Nothing to do for this declaration.
+ } else if (isa<FunctionDecl>(it)) {
+ // A function within an cbuffer is effectively a top-level function,
+ // as it only refers to globally scoped declarations.
+ CGM.EmitTopLevelDecl(it);
+ } else if (NamespaceDecl *ND = dyn_cast<NamespaceDecl>(it)) {
+ addBufferDecls(ND, CB);
+ } else {
+ HLSLBufferDecl *Inner = dyn_cast<HLSLBufferDecl>(it);
+ if (!Inner) {
+ // FIXME: add test after more Resource Type like Texture2D is supported.
+ DiagnosticsEngine &Diags = CGM.getDiags();
+ unsigned DiagID = Diags.getCustomDiagID(DiagnosticsEngine::Error,
+ "invalid decl inside cbuffer");
+ Diags.Report(it->getLocation(), DiagID);
+ return;
+ }
+ addBuffer(Inner);
+ }
+ }
+}
+
+void CGHLSLRuntime::addBuffer(HLSLBufferDecl *D) {
+ Buffers.emplace_back(Buffer(D));
+ addBufferDecls(D, Buffers.back());
+}
+
void CGHLSLRuntime::finishCodeGen() {
auto &TargetOpts = CGM.getTarget().getTargetOpts();
llvm::Module &M = CGM.getModule();
addDxilValVersion(TargetOpts.DxilValidatorVersion, M);
+ auto &DL = M.getDataLayout();
+ auto &ASMap = CGM.getTarget().getAddressSpaceMap();
+ const unsigned CBufferAddressSpace =
+ CGM.getContext().getTargetAddressSpace(LangAS::hlsl_cbuffer);
+ const unsigned TBufferAddressSpace =
+ CGM.getContext().getTargetAddressSpace(LangAS::hlsl_tbuffer);
+
+ for (auto &Buf : Buffers) {
+ layoutBuffer(Buf, DL);
+ const unsigned AddressSapce =
+ Buf.IsCBuffer ? CBufferAddressSpace : TBufferAddressSpace;
+ GlobalVariable *GV = replaceBuffer(Buf, AddressSapce);
+ M.getGlobalList().push_back(GV);
+ addResourceBinding(GV, Buf);
+ }
+}
+
+CGHLSLRuntime::Buffer::Buffer(HLSLBufferDecl *D) {
+ Name = D->getName();
+ IsCBuffer = D->isCBuffer();
+ if (auto *Binding = D->getAttr<HLSLResourceBindingAttr>()) {
+ Reg = Binding->getID();
+ Space = Binding->getSpace();
+ } else {
+ Space = 0;
+ }
}
void CGHLSLRuntime::annotateHLSLResource(const VarDecl *D, GlobalVariable *GV) {
Index: clang/lib/CodeGen/CGDecl.cpp
===================================================================
--- clang/lib/CodeGen/CGDecl.cpp
+++ clang/lib/CodeGen/CGDecl.cpp
@@ -128,6 +128,7 @@
case Decl::Concept:
case Decl::LifetimeExtendedTemporary:
case Decl::RequiresExprBody:
+ case Decl::HLSLBuffer:
// None of these decls require codegen support.
return;
Index: clang/lib/Basic/Targets/X86.h
===================================================================
--- clang/lib/Basic/Targets/X86.h
+++ clang/lib/Basic/Targets/X86.h
@@ -43,7 +43,9 @@
0, // sycl_private
270, // ptr32_sptr
271, // ptr32_uptr
- 272 // ptr64
+ 272, // ptr64
+ 0, // hlsl_cbuffer
+ 0, // hlsl_tbuffer
};
// X86 target abstract base class; x86-32 and x86-64 are very close, so
Index: clang/lib/Basic/Targets/TCE.h
===================================================================
--- clang/lib/Basic/Targets/TCE.h
+++ clang/lib/Basic/Targets/TCE.h
@@ -50,6 +50,8 @@
0, // ptr32_sptr
0, // ptr32_uptr
0, // ptr64
+ 0, // hlsl_cbuffer
+ 0, // hlsl_tbuffer
};
class LLVM_LIBRARY_VISIBILITY TCETargetInfo : public TargetInfo {
Index: clang/lib/Basic/Targets/SPIR.h
===================================================================
--- clang/lib/Basic/Targets/SPIR.h
+++ clang/lib/Basic/Targets/SPIR.h
@@ -42,7 +42,9 @@
0, // sycl_private
0, // ptr32_sptr
0, // ptr32_uptr
- 0 // ptr64
+ 0, // ptr64
+ 0, // hlsl_cbuffer
+ 0, // hlsl_tbuffer
};
// Used by both the SPIR and SPIR-V targets.
@@ -71,7 +73,9 @@
0, // sycl_private
0, // ptr32_sptr
0, // ptr32_uptr
- 0 // ptr64
+ 0, // ptr64
+ 0, // hlsl_cbuffer
+ 0, // hlsl_tbuffer
};
// Base class for SPIR and SPIR-V target info.
Index: clang/lib/Basic/Targets/NVPTX.h
===================================================================
--- clang/lib/Basic/Targets/NVPTX.h
+++ clang/lib/Basic/Targets/NVPTX.h
@@ -42,7 +42,9 @@
0, // sycl_private
0, // ptr32_sptr
0, // ptr32_uptr
- 0 // ptr64
+ 0, // ptr64
+ 0, // hlsl_cbuffer
+ 0, // hlsl_tbuffer
};
/// The DWARF address class. Taken from
Index: clang/lib/Basic/Targets/DirectX.h
===================================================================
--- clang/lib/Basic/Targets/DirectX.h
+++ clang/lib/Basic/Targets/DirectX.h
@@ -40,7 +40,9 @@
0, // sycl_private
0, // ptr32_sptr
0, // ptr32_uptr
- 0 // ptr64
+ 0, // ptr64
+ 4, // hlsl_cbuffer
+ 5, // hlsl_tbuffer
};
class LLVM_LIBRARY_VISIBILITY DirectXTargetInfo : public TargetInfo {
Index: clang/lib/Basic/Targets/AMDGPU.cpp
===================================================================
--- clang/lib/Basic/Targets/AMDGPU.cpp
+++ clang/lib/Basic/Targets/AMDGPU.cpp
@@ -56,7 +56,9 @@
Private, // sycl_private
Generic, // ptr32_sptr
Generic, // ptr32_uptr
- Generic // ptr64
+ Generic, // ptr64
+ 0, // hlsl_cbuffer
+ 0, // hlsl_tbuffer
};
const LangASMap AMDGPUTargetInfo::AMDGPUDefIsPrivMap = {
@@ -79,7 +81,9 @@
Generic, // sycl_private
Generic, // ptr32_sptr
Generic, // ptr32_uptr
- Generic // ptr64
+ Generic, // ptr64
+ 0, // hlsl_cbuffer
+ 0, // hlsl_tbuffer
};
} // namespace targets
Index: clang/lib/AST/ASTContext.cpp
===================================================================
--- clang/lib/AST/ASTContext.cpp
+++ clang/lib/AST/ASTContext.cpp
@@ -948,7 +948,9 @@
0, // sycl_private
10, // ptr32_sptr
11, // ptr32_uptr
- 12 // ptr64
+ 12, // ptr64
+ 13, // hlsl_cbuffer
+ 14, // hlsl_tbuffer
};
return &FakeAddrSpaceMap;
} else {
Index: clang/include/clang/Basic/AddressSpaces.h
===================================================================
--- clang/include/clang/Basic/AddressSpaces.h
+++ clang/include/clang/Basic/AddressSpaces.h
@@ -56,6 +56,10 @@
ptr32_uptr,
ptr64,
+ // HLSL specific address spaces.
+ hlsl_cbuffer,
+ hlsl_tbuffer,
+
// This denotes the count of language-specific address spaces and also
// the offset added to the target-specific address spaces, which are usually
// specified by address space attributes __attribute__(address_space(n))).
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
