[SPIR-V] Add hlsl_private address space for SPIR-V

In SPIR-V, private global variables have the `Private` storage class.
This PR adds a new address space which allows frontend to emit variable
with this storage class.

Before this change, global variable were emitted with the 'Function'
storage class, which was wrong.

Signed-off-by: Nathan Gauër <[email protected]>

Author: Keenuts

clang/include/clang/Basic/AddressSpaces.h

@@ -58,6 +58,7 @@ enum class LangAS : unsigned {
 
   // HLSL specific address spaces.
   hlsl_groupshared,
+  hlsl_private,
 
   // Wasm specific address spaces.
   wasm_funcref,

clang/lib/AST/TypePrinter.cpp

@@ -2553,6 +2553,8 @@ std::string Qualifiers::getAddrSpaceAsString(LangAS AS) {
     return "__funcref";
   case LangAS::hlsl_groupshared:
     return "groupshared";
+  case LangAS::hlsl_private:
+    return "hlsl_private";
   default:
     return std::to_string(toTargetAddressSpace(AS));
   }

clang/lib/Basic/TargetInfo.cpp

@@ -47,6 +47,7 @@ static const LangASMap FakeAddrSpaceMap = {
     11, // ptr32_uptr
     12, // ptr64
     13, // hlsl_groupshared
+    14, // hlsl_private
     20, // wasm_funcref
 };
 

clang/lib/Basic/Targets/AArch64.h

@@ -44,6 +44,7 @@ static const unsigned ARM64AddrSpaceMap[] = {
     static_cast<unsigned>(AArch64AddrSpace::ptr32_uptr),
     static_cast<unsigned>(AArch64AddrSpace::ptr64),
     0, // hlsl_groupshared
+    0, // hlsl_private
     // Wasm address space values for this target are dummy values,
     // as it is only enabled for Wasm targets.
     20, // wasm_funcref

clang/lib/Basic/Targets/AMDGPU.cpp

@@ -59,6 +59,7 @@ const LangASMap AMDGPUTargetInfo::AMDGPUDefIsGenMap = {
     llvm::AMDGPUAS::FLAT_ADDRESS,     // ptr32_uptr
     llvm::AMDGPUAS::FLAT_ADDRESS,     // ptr64
     llvm::AMDGPUAS::FLAT_ADDRESS,     // hlsl_groupshared
+    llvm::AMDGPUAS::FLAT_ADDRESS,     // hlsl_private
 };
 
 const LangASMap AMDGPUTargetInfo::AMDGPUDefIsPrivMap = {
@@ -83,6 +84,7 @@ const LangASMap AMDGPUTargetInfo::AMDGPUDefIsPrivMap = {
     llvm::AMDGPUAS::FLAT_ADDRESS, // ptr32_uptr
     llvm::AMDGPUAS::FLAT_ADDRESS, // ptr64
     llvm::AMDGPUAS::FLAT_ADDRESS, // hlsl_groupshared
+    llvm::AMDGPUAS::FLAT_ADDRESS, // hlsl_private
 
 };
 } // namespace targets

clang/lib/Basic/Targets/DirectX.h

@@ -33,15 +33,16 @@ static const unsigned DirectXAddrSpaceMap[] = {
     0, // cuda_constant
     0, // cuda_shared
     // SYCL address space values for this map are dummy
-    0, // sycl_global
-    0, // sycl_global_device
-    0, // sycl_global_host
-    0, // sycl_local
-    0, // sycl_private
-    0, // ptr32_sptr
-    0, // ptr32_uptr
-    0, // ptr64
-    3, // hlsl_groupshared
+    0,  // sycl_global
+    0,  // sycl_global_device
+    0,  // sycl_global_host
+    0,  // sycl_local
+    0,  // sycl_private
+    0,  // ptr32_sptr
+    0,  // ptr32_uptr
+    0,  // ptr64
+    3,  // hlsl_groupshared
+    10, // hlsl_private
     // Wasm address space values for this target are dummy values,
     // as it is only enabled for Wasm targets.
     20, // wasm_funcref

clang/lib/Basic/Targets/NVPTX.h

@@ -46,6 +46,7 @@ static const unsigned NVPTXAddrSpaceMap[] = {
     0, // ptr32_uptr
     0, // ptr64
     0, // hlsl_groupshared
+    0, // hlsl_private
     // Wasm address space values for this target are dummy values,
     // as it is only enabled for Wasm targets.
     20, // wasm_funcref

clang/lib/Basic/Targets/SPIR.h

@@ -38,15 +38,16 @@ static const unsigned SPIRDefIsPrivMap[] = {
     0, // cuda_constant
     0, // cuda_shared
     // SYCL address space values for this map are dummy
-    0, // sycl_global
-    0, // sycl_global_device
-    0, // sycl_global_host
-    0, // sycl_local
-    0, // sycl_private
-    0, // ptr32_sptr
-    0, // ptr32_uptr
-    0, // ptr64
-    0, // hlsl_groupshared
+    0,  // sycl_global
+    0,  // sycl_global_device
+    0,  // sycl_global_host
+    0,  // sycl_local
+    0,  // sycl_private
+    0,  // ptr32_sptr
+    0,  // ptr32_uptr
+    0,  // ptr64
+    0,  // hlsl_groupshared
+    10, // hlsl_private
     // Wasm address space values for this target are dummy values,
     // as it is only enabled for Wasm targets.
     20, // wasm_funcref
@@ -69,17 +70,18 @@ static const unsigned SPIRDefIsGenMap[] = {
     // cuda_constant pointer can be casted to default/"flat" pointer, but in
     // SPIR-V casts between constant and generic pointers are not allowed. For
     // this reason cuda_constant is mapped to SPIR-V CrossWorkgroup.
-    1, // cuda_constant
-    3, // cuda_shared
-    1, // sycl_global
-    5, // sycl_global_device
-    6, // sycl_global_host
-    3, // sycl_local
-    0, // sycl_private
-    0, // ptr32_sptr
-    0, // ptr32_uptr
-    0, // ptr64
-    0, // hlsl_groupshared
+    1,  // cuda_constant
+    3,  // cuda_shared
+    1,  // sycl_global
+    5,  // sycl_global_device
+    6,  // sycl_global_host
+    3,  // sycl_local
+    0,  // sycl_private
+    0,  // ptr32_sptr
+    0,  // ptr32_uptr
+    0,  // ptr64
+    0,  // hlsl_groupshared
+    10, // hlsl_private
     // Wasm address space values for this target are dummy values,
     // as it is only enabled for Wasm targets.
     20, // wasm_funcref

clang/lib/Basic/Targets/SystemZ.h

@@ -42,6 +42,7 @@ static const unsigned ZOSAddressMap[] = {
     1, // ptr32_uptr
     0, // ptr64
     0, // hlsl_groupshared
+    0, // hlsl_private
     0  // wasm_funcref
 };
 

clang/lib/Basic/Targets/TCE.h

@@ -51,6 +51,7 @@ static const unsigned TCEOpenCLAddrSpaceMap[] = {
     0, // ptr32_uptr
     0, // ptr64
     0, // hlsl_groupshared
+    0, // hlsl_private
     // Wasm address space values for this target are dummy values,
     // as it is only enabled for Wasm targets.
     20, // wasm_funcref

clang/lib/Basic/Targets/WebAssembly.h

@@ -42,6 +42,7 @@ static const unsigned WebAssemblyAddrSpaceMap[] = {
     0,  // ptr32_uptr
     0,  // ptr64
     0,  // hlsl_groupshared
+    0,  // hlsl_private
     20, // wasm_funcref
 };
 

clang/lib/Basic/Targets/X86.h

@@ -46,6 +46,7 @@ static const unsigned X86AddrSpaceMap[] = {
     271, // ptr32_uptr
     272, // ptr64
     0,   // hlsl_groupshared
+    0,   // hlsl_private
     // Wasm address space values for this target are dummy values,
     // as it is only enabled for Wasm targets.
     20, // wasm_funcref

clang/lib/CodeGen/CodeGenModule.cpp

@@ -5362,6 +5362,23 @@ LangAS CodeGenModule::GetGlobalVarAddressSpace(const VarDecl *D) {
     if (OpenMPRuntime->hasAllocateAttributeForGlobalVar(D, AS))
       return AS;
   }
+
+  if (LangOpts.HLSL) {
+    if (D == nullptr)
+      return LangAS::hlsl_private;
+
+    // Except resources (Uniform, UniformConstant) & instanglble (handles)
+    if (D->getType()->isHLSLResourceType() ||
+        D->getType()->isHLSLIntangibleType())
+      return D->getType().getAddressSpace();
+
+    if (D->getStorageClass() != SC_Static)
+      return D->getType().getAddressSpace();
+
+    LangAS AS = D->getType().getAddressSpace();
+    return AS == LangAS::Default ? LangAS::hlsl_private : AS;
+  }
+
   return getTargetCodeGenInfo().getGlobalVarAddressSpace(*this, D);
 }
 

clang/test/CodeGenHLSL/GlobalDestructors.hlsl

@@ -71,7 +71,7 @@ void main(unsigned GI : SV_GroupIndex) {
 
 // NOINLINE: define internal void @_GLOBAL__D_a() [[IntAttr:\#[0-9]+]]
 // NOINLINE-NEXT: entry:
-// NOINLINE-NEXT:   call void @_ZN4TailD1Ev(ptr @_ZZ3WagvE1T)
+// NOINLINE-NEXT:   call void @_ZN4TailD1Ev(ptr addrspacecast (ptr addrspace(10) @_ZZ3WagvE1T to ptr))
 // NOINLINE-NEXT:   call void @_ZN6PupperD1Ev(ptr @GlobalPup)
 // NOINLINE-NEXT:   ret void
 

clang/test/CodeGenHLSL/out-of-line-static.hlsl

@@ -0,0 +1,27 @@
+// RUN: %clang_cc1 -triple dxil-pc-shadermodel6.0-compute -std=hlsl202x -emit-llvm -o - -disable-llvm-passes %s | FileCheck %s --check-prefixes=CHECK
+// RUN: %clang_cc1 -triple spirv-pc-vulkan1.3-compute -std=hlsl202x -emit-llvm -o - -disable-llvm-passes %s | FileCheck %s --check-prefixes=CHECK
+
+struct S {
+  static int Value;
+};
+
+int S::Value = 1;
+// CHECK: @_ZN1S5ValueE = global i32 1, align 4
+
+[shader("compute")]
+[numthreads(1,1,1)]
+void main() {
+  S s;
+  int value1, value2;
+// CHECK:      %s = alloca %struct.S, align 1
+// CHECK: %value1 = alloca i32, align 4
+// CHECK: %value2 = alloca i32, align 4
+
+// CHECK: [[tmp:%.*]] = load i32, ptr @_ZN1S5ValueE, align 4
+// CHECK: store i32 [[tmp]], ptr %value1, align 4
+  value1 = S::Value;
+
+// CHECK: [[tmp:%.*]] = load i32, ptr @_ZN1S5ValueE, align 4
+// CHECK: store i32 [[tmp]], ptr %value2, align 4
+  value2 = s.Value;
+}

clang/test/CodeGenHLSL/static_global_and_function_in_cb.hlsl

@@ -3,12 +3,13 @@
 
 // CHECK-DAG: @[[CB:.+]] = external constant { float }
 
+// CHECK-DAG:@_ZL1b = internal addrspace(10) global float 3.000000e+00, align 4
+static float b = 3;
+
 cbuffer A {
-    float a;
-  // CHECK-DAG:@_ZL1b = internal global float 3.000000e+00, align 4
-  static float b = 3;
+  float a;
   // CHECK:load float, ptr @[[CB]], align 4
-  // CHECK:load float, ptr @_ZL1b, align 4
+  // CHECK:load float, ptr addrspacecast (ptr addrspace(10) @_ZL1b to ptr), align 4
   float foo() { return a + b; }
 }
 

clang/test/SemaTemplate/address_space-dependent.cpp

@@ -43,7 +43,7 @@ void neg() {
 
 template <long int I>
 void tooBig() {
-  __attribute__((address_space(I))) int *bounds; // expected-error {{address space is larger than the maximum supported (8388586)}}
+  __attribute__((address_space(I))) int *bounds; // expected-error {{address space is larger than the maximum supported (8388585)}}
 }
 
 template <long int I>