[SPIR-V] Add support for HLSL SV_GroupIndex

This PR lowers the llvm.spv.flattened.thread.id.in.group intrinsic as a
`LocalInvocationIndex` builtin variable.

Author: cassiebeckley

llvm/docs/SPIRVUsage.rst

@@ -399,6 +399,10 @@ SPIR-V backend, along with their descriptions and argument details.
      - 32-bit Integer
      - `[32-bit Integer]`
      - Retrieves the thread ID within a workgroup. Essential for identifying execution context in parallel compute operations.
+   * - `int_spv_flattened_thread_id_in_group`
+     - 32-bit Integer
+     - `[32-bit Integer]`
+     - Provides a flattened index for a given thread within a given group (SV_GroupIndex)
    * - `int_spv_create_handle`
      - Pointer
      - `[8-bit Integer]`

llvm/include/llvm/IR/IntrinsicsSPIRV.td

@@ -61,6 +61,7 @@ let TargetPrefix = "spv" in {
   def int_spv_thread_id : Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoMem, IntrWillReturn]>;
   def int_spv_group_id : Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoMem, IntrWillReturn]>;
   def int_spv_thread_id_in_group : Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoMem, IntrWillReturn]>;
+  def int_spv_flattened_thread_id_in_group : Intrinsic<[llvm_i32_ty], [], [IntrNoMem, IntrWillReturn]>;
   def int_spv_all : DefaultAttrsIntrinsic<[llvm_i1_ty], [llvm_any_ty], [IntrNoMem]>;
   def int_spv_any : DefaultAttrsIntrinsic<[llvm_i1_ty], [llvm_any_ty], [IntrNoMem]>;
   def int_spv_cross : DefaultAttrsIntrinsic<[llvm_anyfloat_ty], [LLVMMatchType<0>, LLVMMatchType<0>], [IntrNoMem]>;

llvm/lib/Target/SPIRV/SPIRVInstructionSelector.cpp

@@ -341,6 +341,9 @@ class SPIRVInstructionSelector : public InstructionSelector {
   bool loadVec3BuiltinInputID(SPIRV::BuiltIn::BuiltIn BuiltInValue,
                               Register ResVReg, const SPIRVType *ResType,
                               MachineInstr &I) const;
+  bool loadBuiltinInputID(SPIRV::BuiltIn::BuiltIn BuiltInValue,
+                          Register ResVReg, const SPIRVType *ResType,
+                          MachineInstr &I) const;
   bool loadHandleBeforePosition(Register &HandleReg, const SPIRVType *ResType,
                                 GIntrinsic &HandleDef, MachineInstr &Pos) const;
 };
@@ -3059,6 +3062,15 @@ bool SPIRVInstructionSelector::selectIntrinsic(Register ResVReg,
     // builtin variable
     return loadVec3BuiltinInputID(SPIRV::BuiltIn::WorkgroupId, ResVReg, ResType,
                                   I);
+  case Intrinsic::spv_flattened_thread_id_in_group:
+    // The HLSL SV_GroupIndex semantic is lowered to
+    // llvm.spv.flattened.thread.id.in.group() intrinsic in LLVM IR for SPIR-V
+    // backend.
+    //
+    // In SPIR-V backend, llvm.spv.flattened.thread.id.in.group is translated to
+    // a `LocalInvocationIndex` builtin variable
+    return loadBuiltinInputID(SPIRV::BuiltIn::LocalInvocationIndex, ResVReg,
+                              ResType, I);
   case Intrinsic::spv_fdot:
     return selectFloatDot(ResVReg, ResType, I);
   case Intrinsic::spv_udot:
@@ -4005,6 +4017,38 @@ bool SPIRVInstructionSelector::loadVec3BuiltinInputID(
   return Result && MIB.constrainAllUses(TII, TRI, RBI);
 }
 
+// Generate the instructions to load 32-bit integer builtin input IDs/Indices.
+// Like LocalInvocationIndex
+bool SPIRVInstructionSelector::loadBuiltinInputID(
+    SPIRV::BuiltIn::BuiltIn BuiltInValue, Register ResVReg,
+    const SPIRVType *ResType, MachineInstr &I) const {
+  MachineIRBuilder MIRBuilder(I);
+  const SPIRVType *U32Type = GR.getOrCreateSPIRVIntegerType(32, MIRBuilder);
+  const SPIRVType *PtrType = GR.getOrCreateSPIRVPointerType(
+      U32Type, MIRBuilder, SPIRV::StorageClass::Input);
+
+  // Create new register for the input ID builtin variable.
+  Register NewRegister =
+      MIRBuilder.getMRI()->createVirtualRegister(&SPIRV::iIDRegClass);
+  MIRBuilder.getMRI()->setType(NewRegister, LLT::pointer(0, 64));
+  GR.assignSPIRVTypeToVReg(PtrType, NewRegister, MIRBuilder.getMF());
+
+  // Build global variable with the necessary decorations for the input ID
+  // builtin variable.
+  Register Variable = GR.buildGlobalVariable(
+      NewRegister, PtrType, getLinkStringForBuiltIn(BuiltInValue), nullptr,
+      SPIRV::StorageClass::Input, nullptr, true, true,
+      SPIRV::LinkageType::Import, MIRBuilder, false);
+
+  // Load uint value from the global variable.
+  auto MIB = BuildMI(*I.getParent(), I, I.getDebugLoc(), TII.get(SPIRV::OpLoad))
+                 .addDef(ResVReg)
+                 .addUse(GR.getSPIRVTypeID(U32Type))
+                 .addUse(Variable);
+
+  return MIB.constrainAllUses(TII, TRI, RBI);
+}
+
 SPIRVType *SPIRVInstructionSelector::widenTypeToVec4(const SPIRVType *Type,
                                                      MachineInstr &I) const {
   MachineIRBuilder MIRBuilder(I);

llvm/test/CodeGen/SPIRV/hlsl-intrinsics/SV_GroupIndex.ll

@@ -0,0 +1,32 @@
+; RUN: llc -O0 -verify-machineinstrs -mtriple=spirv-vulkan-unknown %s -o - | FileCheck %s
+; RUN: %if spirv-tools %{ llc -O0 -mtriple=spirv-vulkan-unknown %s -o - -filetype=obj | spirv-val %}
+
+; CHECK-DAG:        %[[#int:]] = OpTypeInt 32 0
+; CHECK-DAG:        %[[#ptr_Input_int:]] = OpTypePointer Input %[[#int]]
+; CHECK-DAG:        %[[#LocalInvocationIndex:]] = OpVariable %[[#ptr_Input_int]] Input
+
+; CHECK-DAG:        OpEntryPoint GLCompute {{.*}} %[[#LocalInvocationIndex]]
+; CHECK-DAG:        OpName %[[#LocalInvocationIndex]] "__spirv_BuiltInLocalInvocationIndex"
+; CHECK-DAG:        OpDecorate %[[#LocalInvocationIndex]] LinkageAttributes "__spirv_BuiltInLocalInvocationIndex" Import
+; CHECK-DAG:        OpDecorate %[[#LocalInvocationIndex]] BuiltIn LocalInvocationIndex
+
+target triple = "spirv-unknown-vulkan-library"
+
+declare void @local_index_user(i32)
+
+; Function Attrs: convergent noinline norecurse
+define void @main() #1 {
+entry:
+
+; CHECK:        %[[#load:]] = OpLoad %[[#int]] %[[#LocalInvocationIndex]]
+  %1 = call i32 @llvm.spv.flattened.thread.id.in.group()
+
+  call spir_func void @local_index_user(i32 %1)
+  ret void
+}
+
+; Function Attrs: nounwind willreturn memory(none)
+declare i32 @llvm.spv.flattened.thread.id.in.group() #3
+
+attributes #1 = { convergent noinline norecurse "hlsl.numthreads"="1,1,1" "hlsl.shader"="compute" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
+attributes #3 = { nounwind willreturn memory(none) }