[DirectX] Add GlobalDCE pass after finalize linkage pass in DirectX backend (#151071)

Fixes #139023.

This PR essentially removes unused global variables:
- Restores the `GlobalDCE` Legacy pass and adds it to the DirectX
backend after the finalize linkage pass
- Converts external global variables with no usage to internal linkage
in the finalize linkage pass
  - (so they can be removed by `GlobalDCE`)
- Makes the `dxil-finalize-linkage` pass usable using the new pass
manager flag syntax
- Adds tests to `finalize_linkage.ll` that make sure unused global
variables are removed
- Adds a use for variable `@CBV` in `opaque-value_as_metadata.ll` so it
isn't removed
- Changes the `scalar-data.ll` run command to avoid removing its global
variables

---------

Co-authored-by: Farzon Lotfi <[email protected]>

Author: kmpeng

llvm/include/llvm/InitializePasses.h

@@ -128,6 +128,7 @@ LLVM_ABI void initializeGCEmptyBasicBlocksPass(PassRegistry &);
 LLVM_ABI void initializeGCMachineCodeAnalysisPass(PassRegistry &);
 LLVM_ABI void initializeGCModuleInfoPass(PassRegistry &);
 LLVM_ABI void initializeGVNLegacyPassPass(PassRegistry &);
+LLVM_ABI void initializeGlobalDCELegacyPassPass(PassRegistry &);
 LLVM_ABI void initializeGlobalMergeFuncPassWrapperPass(PassRegistry &);
 LLVM_ABI void initializeGlobalMergePass(PassRegistry &);
 LLVM_ABI void initializeGlobalsAAWrapperPassPass(PassRegistry &);

llvm/include/llvm/LinkAllPasses.h

@@ -38,6 +38,7 @@
 #include "llvm/Support/Valgrind.h"
 #include "llvm/Transforms/IPO.h"
 #include "llvm/Transforms/IPO/AlwaysInliner.h"
+#include "llvm/Transforms/IPO/GlobalDCE.h"
 #include "llvm/Transforms/InstCombine/InstCombine.h"
 #include "llvm/Transforms/ObjCARC.h"
 #include "llvm/Transforms/Scalar.h"
@@ -84,6 +85,7 @@ struct ForcePassLinking {
     (void)llvm::createDomOnlyViewerWrapperPassPass();
     (void)llvm::createDomViewerWrapperPassPass();
     (void)llvm::createAlwaysInlinerLegacyPass();
+    (void)llvm::createGlobalDCEPass();
     (void)llvm::createGlobalMergeFuncPass();
     (void)llvm::createGlobalsAAWrapperPass();
     (void)llvm::createInstSimplifyLegacyPass();

llvm/include/llvm/Transforms/IPO/GlobalDCE.h

@@ -32,6 +32,7 @@ class GlobalVariable;
 class Metadata;
 class Module;
 class Value;
+class ModulePass;
 
 /// Pass to remove unused function declarations.
 class GlobalDCEPass : public PassInfoMixin<GlobalDCEPass> {
@@ -80,6 +81,7 @@ class GlobalDCEPass : public PassInfoMixin<GlobalDCEPass> {
   void ComputeDependencies(Value *V, SmallPtrSetImpl<GlobalValue *> &U);
 };
 
+ModulePass *createGlobalDCEPass();
 }
 
 #endif // LLVM_TRANSFORMS_IPO_GLOBALDCE_H

llvm/lib/Target/DirectX/CMakeLists.txt

@@ -49,6 +49,7 @@ add_llvm_target(DirectXCodeGen
   DirectXInfo
   DirectXPointerTypeAnalysis
   FrontendHLSL
+  IPO
   MC
   ScalarOpts
   SelectionDAG

llvm/lib/Target/DirectX/DXILFinalizeLinkage.cpp

@@ -20,13 +20,13 @@ using namespace llvm;
 static bool finalizeLinkage(Module &M) {
   bool MadeChange = false;
 
-  // Convert private global variables to internal linkage.
-  for (GlobalVariable &GV : M.globals()) {
-    if (GV.hasPrivateLinkage()) {
+  // Convert private globals and external globals with no usage to internal
+  // linkage.
+  for (GlobalVariable &GV : M.globals())
+    if (GV.hasPrivateLinkage() || (GV.hasExternalLinkage() && GV.use_empty())) {
       GV.setLinkage(GlobalValue::InternalLinkage);
       MadeChange = true;
     }
-  }
 
   SmallVector<Function *> Funcs;
 

llvm/lib/Target/DirectX/DirectXPassRegistry.def

@@ -24,6 +24,7 @@ MODULE_ANALYSIS("dxil-root-signature-analysis", dxil::RootSignatureAnalysis())
 #define MODULE_PASS(NAME, CREATE_PASS)
 #endif
 MODULE_PASS("dxil-cbuffer-access", DXILCBufferAccess())
+MODULE_PASS("dxil-finalize-linkage", DXILFinalizeLinkage())
 MODULE_PASS("dxil-data-scalarization", DXILDataScalarization())
 MODULE_PASS("dxil-flatten-arrays", DXILFlattenArrays())
 MODULE_PASS("dxil-intrinsic-expansion", DXILIntrinsicExpansion())

llvm/lib/Target/DirectX/DirectXTargetMachine.cpp

@@ -14,6 +14,7 @@
 #include "DirectXTargetMachine.h"
 #include "DXILCBufferAccess.h"
 #include "DXILDataScalarization.h"
+#include "DXILFinalizeLinkage.h"
 #include "DXILFlattenArrays.h"
 #include "DXILForwardHandleAccesses.h"
 #include "DXILIntrinsicExpansion.h"
@@ -45,6 +46,7 @@
 #include "llvm/Support/Compiler.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Target/TargetLoweringObjectFile.h"
+#include "llvm/Transforms/IPO/GlobalDCE.h"
 #include "llvm/Transforms/Scalar.h"
 #include "llvm/Transforms/Scalar/Scalarizer.h"
 #include <optional>
@@ -63,6 +65,7 @@ extern "C" LLVM_EXTERNAL_VISIBILITY void LLVMInitializeDirectXTarget() {
   initializeEmbedDXILPassPass(*PR);
   initializeWriteDXILPassPass(*PR);
   initializeDXContainerGlobalsPass(*PR);
+  initializeGlobalDCELegacyPassPass(*PR);
   initializeDXILOpLoweringLegacyPass(*PR);
   initializeDXILResourceAccessLegacyPass(*PR);
   initializeDXILResourceImplicitBindingLegacyPass(*PR);
@@ -105,6 +108,7 @@ class DirectXPassConfig : public TargetPassConfig {
   FunctionPass *createTargetRegisterAllocator(bool) override { return nullptr; }
   void addCodeGenPrepare() override {
     addPass(createDXILFinalizeLinkageLegacyPass());
+    addPass(createGlobalDCEPass());
     addPass(createDXILResourceAccessLegacyPass());
     addPass(createDXILIntrinsicExpansionLegacyPass());
     addPass(createDXILCBufferAccessLegacyPass());

llvm/lib/Transforms/IPO/GlobalDCE.cpp

@@ -21,6 +21,8 @@
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/Module.h"
+#include "llvm/InitializePasses.h"
+#include "llvm/Pass.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Transforms/IPO.h"
 #include "llvm/Transforms/Utils/CtorUtils.h"
@@ -30,6 +32,35 @@ using namespace llvm;
 
 #define DEBUG_TYPE "globaldce"
 
+namespace {
+class GlobalDCELegacyPass : public ModulePass {
+public:
+  static char ID; // Pass identification, replacement for typeid
+  GlobalDCELegacyPass() : ModulePass(ID) {
+    initializeGlobalDCELegacyPassPass(*PassRegistry::getPassRegistry());
+  }
+  bool runOnModule(Module &M) override {
+    if (skipModule(M))
+      return false;
+    // Note: GlobalDCEPass does not use any analyses, so we're safe to call the
+    // new-pm style pass with a default-initialized analysis manager here
+    ModuleAnalysisManager MAM;
+    auto PA = Impl.run(M, MAM);
+    return !PA.areAllPreserved();
+  }
+
+private:
+  GlobalDCEPass Impl;
+};
+} // namespace
+
+char GlobalDCELegacyPass::ID = 0;
+INITIALIZE_PASS(GlobalDCELegacyPass, "globaldce", "Dead Global Elimination",
+                false, false)
+
+// Public interface to the GlobalDCEPass.
+ModulePass *llvm::createGlobalDCEPass() { return new GlobalDCELegacyPass(); }
+
 static cl::opt<bool>
     ClEnableVFE("enable-vfe", cl::Hidden, cl::init(true),
                 cl::desc("Enable virtual function elimination"));

llvm/test/CodeGen/DirectX/finalize_linkage.ll

@@ -4,7 +4,8 @@
 target triple = "dxilv1.5-pc-shadermodel6.5-compute"
 
 ; DXILFinalizeLinkage changes linkage of all functions that are hidden to
-; internal, and converts private global variables to internal linkage.
+; internal, converts private globals to internal linkage, and converts external globals 
+; with no usage to internal linkage.
 
 ; CHECK: @switch.table = internal unnamed_addr constant [4 x i32]
 @switch.table = private unnamed_addr constant [4 x i32] [i32 1, i32 257, i32 65793, i32 16843009], align 4
@@ -27,6 +28,27 @@ target triple = "dxilv1.5-pc-shadermodel6.5-compute"
 ; CHECK: @hidden_var = hidden global i32
 @hidden_var = hidden global i32 1, align 4
 
+; Running the whole pipeline should remove unused global variables
+
+; CHECK: @aTile = internal addrspace(3) global
+; CHECK-LLC-NOT: @aTile
+@aTile = hidden addrspace(3) global [4 x [1 x i32]] zeroinitializer, align 4
+
+; CHECK: @bTile = internal addrspace(3) global
+; CHECK-LLC-NOT: @bTile
+@bTile = hidden addrspace(3) global [1 x [1 x i32]] zeroinitializer, align 4
+
+define void @anchor_function() #0 {
+entry:
+  %0 = load i32, ptr @switch.table, align 4
+  %1 = load [3 x float], ptr @private_array, align 4
+  %2 = load i32, ptr @private_var, align 4
+  %3 = load i32, ptr @internal_var, align 4
+  %4 = load i32, ptr @external_var, align 4
+  %5 = load i32, ptr @hidden_var, align 4
+  ret void
+}
+
 ; CHECK-NOT: define internal void @"?f1@@YAXXZ"()
 define void @"?f1@@YAXXZ"() #0 {
 entry:

llvm/test/CodeGen/DirectX/llc-pipeline.ll

@@ -14,6 +14,7 @@
 
 ; CHECK-NEXT: ModulePass Manager
 ; CHECK-NEXT:   DXIL Finalize Linkage
+; CHECK-NEXT:   Dead Global Elimination
 ; CHECK-NEXT:   FunctionPass Manager
 ; CHECK-NEXT:     DXIL Resource Access
 ; CHECK-NEXT:   DXIL Intrinsic Expansion