Recommit "[llvm-reduce] Add MIR support"

(Second try. Need to link against CodeGen and MC libs.)

The llvm-reduce tool has been extended to operate on MIR (import, clone and
export). Current limitation is that only a single machine function is
supported. A single reducer pass that operates on machine instructions (while
on SSA-form) has been added. Additional MIR specific reducer passes can be
added later as needed.

Differential Revision: https://reviews.llvm.org/D110527

Author: markuslavin

llvm/test/tools/llvm-reduce/mir/instr-reduce.mir

@@ -0,0 +1,30 @@
+# RUN: llvm-reduce -mtriple=riscv32 --test %python --test-arg %p/instr-reduce.py %s -o %t
+# RUN: cat %t | FileCheck --match-full-lines %s
+
+# REQUIRES: riscv-registered-target
+
+# Verify that after reduction the following instruction sequence remains. The
+# interestingness-test 'instr-reduce.py' matches a '%[0-9]+:gpr = ADDI %[0-9]+, 5'
+# pattern in the output and that combined with that the MIR has to be valid
+# (pass verify) results in the given sequence.
+
+# CHECK:      %0:gpr = COPY $x10
+# CHECK-NEXT: %2:gpr = ADDI %0, 5
+# CHECK-NEXT: PseudoRET implicit $x10
+
+...
+---
+name:            f
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $x10
+
+    %10:gpr = COPY $x10
+    %20:gpr = ADDI %10, 1
+    %30:gpr = ADDI %20, 5
+    %40:gpr = ADDI %30, 9
+    $x10 = COPY %40
+    PseudoRET implicit $x10
+...
+---

llvm/test/tools/llvm-reduce/mir/instr-reduce.py

@@ -0,0 +1,16 @@
+from subprocess import run, PIPE
+import re
+import sys
+
+llc = run( [ 'llc', '-disable-symbolication','-verify-machineinstrs', '-mtriple=riscv32', '-run-pass=none', '-o', '-', sys.argv[1]], stdout=PIPE, stderr=PIPE )
+
+stdout = llc.stdout.decode()
+
+p = re.compile(r'^\s*%[0-9]+:gpr = ADDI %[0-9]+, 5$', flags=re.MULTILINE)
+
+if (llc.returncode == 0 and p.search(stdout)):
+  print('This is interesting!')
+  sys.exit(0)
+else:
+  print('This is NOT interesting!')
+  sys.exit(1)

llvm/tools/llvm-reduce/CMakeLists.txt

@@ -3,15 +3,19 @@ set(LLVM_LINK_COMPONENTS
   AllTargetsCodeGens
   AllTargetsDescs
   AllTargetsInfos
+  CodeGen
   Core
   IRReader
+  MC
+  MIRParser
   Support
   Target
   TransformUtils
   )
 
 add_llvm_tool(llvm-reduce
   DeltaManager.cpp
+  ReducerWorkItem.cpp
   TestRunner.cpp
   deltas/Delta.cpp
   deltas/ReduceAliases.cpp
@@ -30,6 +34,7 @@ add_llvm_tool(llvm-reduce
   deltas/ReduceSpecialGlobals.cpp
   deltas/ReduceOperands.cpp
   deltas/ReduceOperandsToArgs.cpp
+  deltas/ReduceInstructionsMIR.cpp
   llvm-reduce.cpp
 
   DEPENDS

llvm/tools/llvm-reduce/DeltaManager.cpp

@@ -24,6 +24,7 @@
 #include "deltas/ReduceGlobalVarInitializers.h"
 #include "deltas/ReduceGlobalVars.h"
 #include "deltas/ReduceInstructions.h"
+#include "deltas/ReduceInstructionsMIR.h"
 #include "deltas/ReduceMetadata.h"
 #include "deltas/ReduceModuleData.h"
 #include "deltas/ReduceOperandBundles.h"
@@ -59,9 +60,16 @@ static cl::opt<std::string>
   DELTA_PASS("attributes", reduceAttributesDeltaPass)                          \
   DELTA_PASS("module-data", reduceModuleDataDeltaPass)
 
+#define DELTA_PASSES_MIR                                                       \
+  DELTA_PASS("instructions", reduceInstructionsMIRDeltaPass)
+
 static void runAllDeltaPasses(TestRunner &Tester) {
 #define DELTA_PASS(NAME, FUNC) FUNC(Tester);
-  DELTA_PASSES
+  if (Tester.getProgram().isMIR()) {
+    DELTA_PASSES_MIR
+  } else {
+    DELTA_PASSES
+  }
 #undef DELTA_PASS
 }
 
@@ -71,7 +79,11 @@ static void runDeltaPassName(TestRunner &Tester, StringRef PassName) {
     FUNC(Tester);                                                              \
     return;                                                                    \
   }
-  DELTA_PASSES
+  if (Tester.getProgram().isMIR()) {
+    DELTA_PASSES_MIR
+  } else {
+    DELTA_PASSES
+  }
 #undef DELTA_PASS
   errs() << "unknown pass \"" << PassName << "\"";
   exit(1);
@@ -80,7 +92,10 @@ static void runDeltaPassName(TestRunner &Tester, StringRef PassName) {
 void llvm::printDeltaPasses(raw_ostream &OS) {
   OS << "Delta passes (pass to `--delta-passes=` as a comma separated list):\n";
 #define DELTA_PASS(NAME, FUNC) OS << "  " << NAME << "\n";
+  OS << " IR:\n";
   DELTA_PASSES
+  OS << " MIR:\n";
+  DELTA_PASSES_MIR
 #undef DELTA_PASS
 }
 

llvm/tools/llvm-reduce/ReducerWorkItem.cpp

@@ -0,0 +1,174 @@
+//===- ReducerWorkItem.cpp - Wrapper for Module and MachineFunction -------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "ReducerWorkItem.h"
+#include "llvm/CodeGen/MIRParser/MIRParser.h"
+#include "llvm/CodeGen/MIRPrinter.h"
+#include "llvm/CodeGen/MachineDominators.h"
+#include "llvm/CodeGen/MachineFunction.h"
+#include "llvm/CodeGen/MachineFunctionPass.h"
+#include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/TargetInstrInfo.h"
+#include "llvm/IR/Verifier.h"
+#include "llvm/IRReader/IRReader.h"
+#include "llvm/Target/TargetMachine.h"
+#include "llvm/Transforms/Utils/Cloning.h"
+
+static std::unique_ptr<MachineFunction> cloneMF(MachineFunction *SrcMF) {
+  auto DstMF = std::make_unique<MachineFunction>(
+      SrcMF->getFunction(), SrcMF->getTarget(), SrcMF->getSubtarget(),
+      SrcMF->getFunctionNumber(), SrcMF->getMMI());
+  DenseMap<MachineBasicBlock *, MachineBasicBlock *> Src2DstMBB;
+  DenseMap<Register, Register> Src2DstReg;
+
+  auto *SrcMRI = &SrcMF->getRegInfo();
+  auto *DstMRI = &DstMF->getRegInfo();
+
+  // Create vregs.
+  for (auto &SrcMBB : *SrcMF) {
+    for (auto &SrcMI : SrcMBB) {
+      for (unsigned I = 0, E = SrcMI.getNumOperands(); I < E; ++I) {
+        auto &DMO = SrcMI.getOperand(I);
+        if (!DMO.isReg() || !DMO.isDef())
+          continue;
+        Register SrcReg = DMO.getReg();
+        if (Register::isPhysicalRegister(SrcReg))
+          continue;
+        auto SrcRC = SrcMRI->getRegClass(SrcReg);
+        auto DstReg = DstMRI->createVirtualRegister(SrcRC);
+        Src2DstReg[SrcReg] = DstReg;
+      }
+    }
+  }
+
+  // Clone blocks.
+  for (auto &SrcMBB : *SrcMF)
+    Src2DstMBB[&SrcMBB] = DstMF->CreateMachineBasicBlock();
+  // Link blocks.
+  for (auto &SrcMBB : *SrcMF) {
+    auto *DstMBB = Src2DstMBB[&SrcMBB];
+    DstMF->push_back(DstMBB);
+    for (auto It = SrcMBB.succ_begin(), IterEnd = SrcMBB.succ_end();
+         It != IterEnd; ++It) {
+      auto *SrcSuccMBB = *It;
+      auto *DstSuccMBB = Src2DstMBB[SrcSuccMBB];
+      DstMBB->addSuccessor(DstSuccMBB);
+    }
+    for (auto &LI : SrcMBB.liveins())
+      DstMBB->addLiveIn(LI);
+  }
+  // Clone instructions.
+  for (auto &SrcMBB : *SrcMF) {
+    auto *DstMBB = Src2DstMBB[&SrcMBB];
+    for (auto &SrcMI : SrcMBB) {
+      const auto &MCID =
+          DstMF->getSubtarget().getInstrInfo()->get(SrcMI.getOpcode());
+      auto *DstMI = DstMF->CreateMachineInstr(MCID, SrcMI.getDebugLoc(),
+                                              /*NoImplicit=*/true);
+      DstMBB->push_back(DstMI);
+      for (auto &SrcMO : SrcMI.operands()) {
+        MachineOperand DstMO(SrcMO);
+        DstMO.clearParent();
+        // Update vreg.
+        if (DstMO.isReg() && Src2DstReg.count(DstMO.getReg())) {
+          DstMO.setReg(Src2DstReg[DstMO.getReg()]);
+        }
+        // Update MBB.
+        if (DstMO.isMBB()) {
+          DstMO.setMBB(Src2DstMBB[DstMO.getMBB()]);
+        }
+        DstMI->addOperand(DstMO);
+      }
+      DstMI->setMemRefs(*DstMF, SrcMI.memoperands());
+    }
+  }
+
+  DstMF->verify(nullptr, "", /*AbortOnErrors=*/true);
+  return DstMF;
+}
+
+std::unique_ptr<ReducerWorkItem> parseReducerWorkItem(StringRef Filename,
+                                                      LLVMContext &Ctxt,
+                                                      MachineModuleInfo *MMI) {
+  auto MMM = std::make_unique<ReducerWorkItem>();
+  if (MMI) {
+    auto FileOrErr = MemoryBuffer::getFileOrSTDIN(Filename, /*IsText=*/true);
+    std::unique_ptr<MIRParser> MParser =
+        createMIRParser(std::move(FileOrErr.get()), Ctxt);
+
+    auto SetDataLayout =
+        [&](StringRef DataLayoutTargetTriple) -> Optional<std::string> {
+      return MMI->getTarget().createDataLayout().getStringRepresentation();
+    };
+
+    std::unique_ptr<Module> M = MParser->parseIRModule(SetDataLayout);
+    MParser->parseMachineFunctions(*M, *MMI);
+    MachineFunction *MF = nullptr;
+    for (auto &F : *M) {
+      if (auto *MF4F = MMI->getMachineFunction(F)) {
+        // XXX: Maybe it would not be a lot of effort to handle multiple MFs by
+        // simply storing them in a ReducerWorkItem::SmallVector or similar. The
+        // single MF use-case seems a lot more common though so that will do for
+        // now.
+        assert(!MF && "Only single MF supported!");
+        MF = MF4F;
+      }
+    }
+    assert(MF && "No MF found!");
+
+    MMM->M = std::move(M);
+    MMM->MF = cloneMF(MF);
+  } else {
+    SMDiagnostic Err;
+    std::unique_ptr<Module> Result = parseIRFile(Filename, Err, Ctxt);
+    if (!Result) {
+      Err.print("llvm-reduce", errs());
+      return std::unique_ptr<ReducerWorkItem>();
+    }
+    MMM->M = std::move(Result);
+  }
+  if (verifyReducerWorkItem(*MMM, &errs())) {
+    errs() << "Error: " << Filename << " - input module is broken!\n";
+    return std::unique_ptr<ReducerWorkItem>();
+  }
+  return MMM;
+}
+
+std::unique_ptr<ReducerWorkItem>
+cloneReducerWorkItem(const ReducerWorkItem &MMM) {
+  auto CloneMMM = std::make_unique<ReducerWorkItem>();
+  if (MMM.MF) {
+    // Note that we cannot clone the Module as then we would need a way to
+    // updated the cloned MachineFunction's IR references.
+    // XXX: Actually have a look at
+    // std::unique_ptr<Module> CloneModule(const Module &M, ValueToValueMapTy
+    // &VMap);
+    CloneMMM->M = MMM.M;
+    CloneMMM->MF = cloneMF(MMM.MF.get());
+  } else {
+    CloneMMM->M = CloneModule(*MMM.M);
+  }
+  return CloneMMM;
+}
+
+bool verifyReducerWorkItem(const ReducerWorkItem &MMM, raw_fd_ostream *OS) {
+  if (verifyModule(*MMM.M, OS))
+    return true;
+  if (MMM.MF && !MMM.MF->verify(nullptr, "", /*AbortOnErrors=*/false))
+    return true;
+  return false;
+}
+
+void ReducerWorkItem::print(raw_ostream &ROS, void *p) const {
+  if (MF) {
+    printMIR(ROS, *M);
+    printMIR(ROS, *MF);
+  } else {
+    M->print(ROS, nullptr);
+  }
+}

llvm/tools/llvm-reduce/ReducerWorkItem.h

@@ -0,0 +1,37 @@
+//===- ReducerWorkItem.h - Wrapper for Module and MachineFunction ---------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_TOOLS_LLVM_REDUCE_REDUCERWORKITEM_H
+#define LLVM_TOOLS_LLVM_REDUCE_REDUCERWORKITEM_H
+
+#include "llvm/CodeGen/MachineFunction.h"
+#include "llvm/CodeGen/MachineModuleInfo.h"
+#include "llvm/IR/Module.h"
+
+using namespace llvm;
+
+class ReducerWorkItem {
+public:
+  std::shared_ptr<Module> M;
+  std::unique_ptr<MachineFunction> MF;
+  void print(raw_ostream &ROS, void *p = nullptr) const;
+  bool isMIR() { return MF != nullptr; }
+  operator Module &() const { return *M; }
+  operator MachineFunction &() const { return *MF; }
+};
+
+std::unique_ptr<ReducerWorkItem> parseReducerWorkItem(StringRef Filename,
+                                                      LLVMContext &Ctxt,
+                                                      MachineModuleInfo *MMI);
+
+std::unique_ptr<ReducerWorkItem>
+cloneReducerWorkItem(const ReducerWorkItem &MMM);
+
+bool verifyReducerWorkItem(const ReducerWorkItem &MMM, raw_fd_ostream *OS);
+
+#endif

llvm/tools/llvm-reduce/TestRunner.cpp

@@ -12,7 +12,7 @@ using namespace llvm;
 
 TestRunner::TestRunner(StringRef TestName,
                        const std::vector<std::string> &TestArgs,
-                       std::unique_ptr<Module> Program)
+                       std::unique_ptr<ReducerWorkItem> Program)
     : TestName(TestName), TestArgs(TestArgs), Program(std::move(Program)) {
   assert(this->Program && "Initialized with null program?");
 }

llvm/tools/llvm-reduce/TestRunner.h

@@ -9,6 +9,7 @@
 #ifndef LLVM_TOOLS_LLVM_REDUCE_TESTRUNNER_H
 #define LLVM_TOOLS_LLVM_REDUCE_TESTRUNNER_H
 
+#include "ReducerWorkItem.h"
 #include "llvm/ADT/SmallString.h"
 #include "llvm/IR/Module.h"
 #include "llvm/Support/Error.h"
@@ -25,24 +26,24 @@ namespace llvm {
 class TestRunner {
 public:
   TestRunner(StringRef TestName, const std::vector<std::string> &TestArgs,
-             std::unique_ptr<Module> Program);
+             std::unique_ptr<ReducerWorkItem> Program);
 
   /// Runs the interesting-ness test for the specified file
   /// @returns 0 if test was successful, 1 if otherwise
   int run(StringRef Filename);
 
   /// Returns the most reduced version of the original testcase
-  Module &getProgram() const { return *Program; }
+  ReducerWorkItem &getProgram() const { return *Program; }
 
-  void setProgram(std::unique_ptr<Module> P) {
+  void setProgram(std::unique_ptr<ReducerWorkItem> P) {
     assert(P && "Setting null program?");
     Program = std::move(P);
   }
 
 private:
   StringRef TestName;
   const std::vector<std::string> &TestArgs;
-  std::unique_ptr<Module> Program;
+  std::unique_ptr<ReducerWorkItem> Program;
 };
 
 } // namespace llvm