[AMDGPU][NPM] Port SIInsertHardClauses to NPM (#130062)

Author: optimisan

llvm/lib/Target/AMDGPU/AMDGPU.h

@@ -385,6 +385,12 @@ class SIInsertWaitcntsPass : public PassInfoMixin<SIInsertWaitcntsPass> {
   static bool isRequired() { return true; }
 };
 
+class SIInsertHardClausesPass : public PassInfoMixin<SIInsertHardClausesPass> {
+public:
+  PreservedAnalyses run(MachineFunction &MF,
+                        MachineFunctionAnalysisManager &MFAM);
+};
+
 FunctionPass *createAMDGPUAnnotateUniformValuesLegacy();
 
 ModulePass *createAMDGPUPrintfRuntimeBinding();
@@ -458,7 +464,7 @@ extern char &SIModeRegisterID;
 void initializeAMDGPUInsertDelayAluLegacyPass(PassRegistry &);
 extern char &AMDGPUInsertDelayAluID;
 
-void initializeSIInsertHardClausesPass(PassRegistry &);
+void initializeSIInsertHardClausesLegacyPass(PassRegistry &);
 extern char &SIInsertHardClausesID;
 
 void initializeSIInsertWaitcntsLegacyPass(PassRegistry &);

llvm/lib/Target/AMDGPU/AMDGPUPassRegistry.def

@@ -111,6 +111,7 @@ MACHINE_FUNCTION_PASS("si-fix-vgpr-copies", SIFixVGPRCopiesPass())
 MACHINE_FUNCTION_PASS("si-fold-operands", SIFoldOperandsPass());
 MACHINE_FUNCTION_PASS("si-form-memory-clauses", SIFormMemoryClausesPass())
 MACHINE_FUNCTION_PASS("si-i1-copies", SILowerI1CopiesPass())
+MACHINE_FUNCTION_PASS("si-insert-hard-clauses", SIInsertHardClausesPass())
 MACHINE_FUNCTION_PASS("si-insert-waitcnts", SIInsertWaitcntsPass())
 MACHINE_FUNCTION_PASS("si-load-store-opt", SILoadStoreOptimizerPass())
 MACHINE_FUNCTION_PASS("si-lower-control-flow", SILowerControlFlowPass())
@@ -133,7 +134,6 @@ DUMMY_MACHINE_FUNCTION_PASS("amdgpu-pre-ra-optimizations", GCNPreRAOptimizations
 DUMMY_MACHINE_FUNCTION_PASS("amdgpu-rewrite-partial-reg-uses", GCNRewritePartialRegUsesPass())
 DUMMY_MACHINE_FUNCTION_PASS("amdgpu-set-wave-priority", AMDGPUSetWavePriorityPass())
 
-DUMMY_MACHINE_FUNCTION_PASS("si-insert-hard-clauses", SIInsertHardClausesPass())
 DUMMY_MACHINE_FUNCTION_PASS("si-late-branch-lowering", SILateBranchLoweringPass())
 DUMMY_MACHINE_FUNCTION_PASS("si-pre-emit-peephole", SIPreEmitPeepholePass())
 // TODO: Move amdgpu-preload-kern-arg-prolog to MACHINE_FUNCTION_PASS since it

llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp

@@ -535,7 +535,7 @@ extern "C" LLVM_EXTERNAL_VISIBILITY void LLVMInitializeAMDGPUTarget() {
   initializeAMDGPUUnifyMetadataPass(*PR);
   initializeSIAnnotateControlFlowLegacyPass(*PR);
   initializeAMDGPUInsertDelayAluLegacyPass(*PR);
-  initializeSIInsertHardClausesPass(*PR);
+  initializeSIInsertHardClausesLegacyPass(*PR);
   initializeSIInsertWaitcntsLegacyPass(*PR);
   initializeSIModeRegisterLegacyPass(*PR);
   initializeSIWholeQuadModeLegacyPass(*PR);

llvm/lib/Target/AMDGPU/SIInsertHardClauses.cpp

@@ -36,6 +36,7 @@
 #include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
+#include "llvm/CodeGen/MachinePassManager.h"
 
 using namespace llvm;
 
@@ -89,18 +90,10 @@ enum HardClauseType {
   HARDCLAUSE_ILLEGAL,
 };
 
-class SIInsertHardClauses : public MachineFunctionPass {
+class SIInsertHardClauses {
 public:
-  static char ID;
   const GCNSubtarget *ST = nullptr;
 
-  SIInsertHardClauses() : MachineFunctionPass(ID) {}
-
-  void getAnalysisUsage(AnalysisUsage &AU) const override {
-    AU.setPreservesCFG();
-    MachineFunctionPass::getAnalysisUsage(AU);
-  }
-
   HardClauseType getHardClauseType(const MachineInstr &MI) {
     if (MI.mayLoad() || (MI.mayStore() && ST->shouldClusterStores())) {
       if (ST->getGeneration() == AMDGPUSubtarget::GFX10) {
@@ -189,9 +182,7 @@ class SIInsertHardClauses : public MachineFunctionPass {
     return true;
   }
 
-  bool runOnMachineFunction(MachineFunction &MF) override {
-    if (skipFunction(MF.getFunction()))
-      return false;
+  bool run(MachineFunction &MF) {
 
     ST = &MF.getSubtarget<GCNSubtarget>();
     if (!ST->hasHardClauses())
@@ -265,11 +256,40 @@ class SIInsertHardClauses : public MachineFunctionPass {
   }
 };
 
+class SIInsertHardClausesLegacy : public MachineFunctionPass {
+public:
+  static char ID;
+  SIInsertHardClausesLegacy() : MachineFunctionPass(ID) {}
+
+  bool runOnMachineFunction(MachineFunction &MF) override {
+    if (skipFunction(MF.getFunction()))
+      return false;
+
+    return SIInsertHardClauses().run(MF);
+  }
+
+  void getAnalysisUsage(AnalysisUsage &AU) const override {
+    AU.setPreservesCFG();
+    MachineFunctionPass::getAnalysisUsage(AU);
+  }
+};
+
 } // namespace
 
-char SIInsertHardClauses::ID = 0;
+PreservedAnalyses
+llvm::SIInsertHardClausesPass::run(MachineFunction &MF,
+                                   MachineFunctionAnalysisManager &MFAM) {
+  if (!SIInsertHardClauses().run(MF))
+    return PreservedAnalyses::all();
+
+  auto PA = getMachineFunctionPassPreservedAnalyses();
+  PA.preserveSet<CFGAnalyses>();
+  return PA;
+}
+
+char SIInsertHardClausesLegacy::ID = 0;
 
-char &llvm::SIInsertHardClausesID = SIInsertHardClauses::ID;
+char &llvm::SIInsertHardClausesID = SIInsertHardClausesLegacy::ID;
 
-INITIALIZE_PASS(SIInsertHardClauses, DEBUG_TYPE, "SI Insert Hard Clauses",
+INITIALIZE_PASS(SIInsertHardClausesLegacy, DEBUG_TYPE, "SI Insert Hard Clauses",
                 false, false)

llvm/test/CodeGen/AMDGPU/hard-clauses-img-gfx10.mir

@@ -1,5 +1,6 @@
 # NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
 # RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -verify-machineinstrs -run-pass si-insert-hard-clauses %s -o - | FileCheck %s
+# RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -passes si-insert-hard-clauses %s -o - | FileCheck %s
 
 ---
 name: mimg_nsa

llvm/test/CodeGen/AMDGPU/hard-clauses-img-gfx11.mir

@@ -1,5 +1,6 @@
 # NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
 # RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -verify-machineinstrs -run-pass si-insert-hard-clauses %s -o - | FileCheck %s
+# RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -passes si-insert-hard-clauses %s -o - | FileCheck %s
 
 ---
 name: mimg_nsa