summaryrefslogtreecommitdiffstats
path: root/llvm/lib/CodeGen
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/lib/CodeGen')
-rw-r--r--llvm/lib/CodeGen/CMakeLists.txt1
-rw-r--r--llvm/lib/CodeGen/CodeGen.cpp1
-rw-r--r--llvm/lib/CodeGen/MachineFunction.cpp38
-rw-r--r--llvm/lib/CodeGen/Passes.cpp30
-rw-r--r--llvm/lib/CodeGen/PrologEpilogInserter.cpp114
-rw-r--r--llvm/lib/CodeGen/ShrinkWrap.cpp383
6 files changed, 530 insertions, 37 deletions
diff --git a/llvm/lib/CodeGen/CMakeLists.txt b/llvm/lib/CodeGen/CMakeLists.txt
index ef5763855a8..6ce5b13ea39 100644
--- a/llvm/lib/CodeGen/CMakeLists.txt
+++ b/llvm/lib/CodeGen/CMakeLists.txt
@@ -93,6 +93,7 @@ add_llvm_library(LLVMCodeGen
ScheduleDAGInstrs.cpp
ScheduleDAGPrinter.cpp
ScoreboardHazardRecognizer.cpp
+ ShrinkWrap.cpp
ShadowStackGC.cpp
ShadowStackGCLowering.cpp
SjLjEHPrepare.cpp
diff --git a/llvm/lib/CodeGen/CodeGen.cpp b/llvm/lib/CodeGen/CodeGen.cpp
index da66639d02f..2c6eaf35a25 100644
--- a/llvm/lib/CodeGen/CodeGen.cpp
+++ b/llvm/lib/CodeGen/CodeGen.cpp
@@ -61,6 +61,7 @@ void llvm::initializeCodeGen(PassRegistry &Registry) {
initializePostRASchedulerPass(Registry);
initializeProcessImplicitDefsPass(Registry);
initializeRegisterCoalescerPass(Registry);
+ initializeShrinkWrapPass(Registry);
initializeSlotIndexesPass(Registry);
initializeStackColoringPass(Registry);
initializeStackMapLivenessPass(Registry);
diff --git a/llvm/lib/CodeGen/MachineFunction.cpp b/llvm/lib/CodeGen/MachineFunction.cpp
index 448531fb716..fb0553b9414 100644
--- a/llvm/lib/CodeGen/MachineFunction.cpp
+++ b/llvm/lib/CodeGen/MachineFunction.cpp
@@ -600,8 +600,8 @@ MachineFrameInfo::getPristineRegs(const MachineBasicBlock *MBB) const {
for (const MCPhysReg *CSR = TRI->getCalleeSavedRegs(MF); CSR && *CSR; ++CSR)
BV.set(*CSR);
- // The entry MBB always has all CSRs pristine.
- if (MBB == &MF->front())
+ // Each MBB before the save point has all CSRs pristine.
+ if (isBeforeSavePoint(*MF, *MBB))
return BV;
// On other MBBs the saved CSRs are not pristine.
@@ -613,6 +613,40 @@ MachineFrameInfo::getPristineRegs(const MachineBasicBlock *MBB) const {
return BV;
}
+// Note: We could use some sort of caching mecanism, but we lack the ability
+// to know when the cache is invalid, i.e., the CFG changed.
+// Assuming we have that, we can simply compute all the set of MBBs
+// that are before the save point.
+bool MachineFrameInfo::isBeforeSavePoint(const MachineFunction &MF,
+ const MachineBasicBlock &MBB) const {
+ // Early exit if shrink-wrapping did not kick.
+ if (!Save)
+ return &MBB == &MF.front();
+
+ // Starting from MBB, check if there is a path leading to Save that do
+ // not cross Restore.
+ SmallPtrSet<const MachineBasicBlock *, 8> Visited;
+ SmallVector<const MachineBasicBlock *, 8> WorkList;
+ WorkList.push_back(&MBB);
+ Visited.insert(&MBB);
+ do {
+ const MachineBasicBlock *CurBB = WorkList.pop_back_val();
+ // By construction, the region that is after the save point is
+ // dominated by the Save and post-dominated by the Restore.
+ // If we do not reach Restore and still reach Save, this
+ // means MBB is before Save.
+ if (CurBB == Save)
+ return true;
+ if (CurBB == Restore)
+ continue;
+ // Enqueue all the successors not already visited.
+ for (MachineBasicBlock *SuccBB : CurBB->successors())
+ if (Visited.insert(SuccBB).second)
+ WorkList.push_back(SuccBB);
+ } while (!WorkList.empty());
+ return false;
+}
+
unsigned MachineFrameInfo::estimateStackSize(const MachineFunction &MF) const {
const TargetFrameLowering *TFI = MF.getSubtarget().getFrameLowering();
const TargetRegisterInfo *RegInfo = MF.getSubtarget().getRegisterInfo();
diff --git a/llvm/lib/CodeGen/Passes.cpp b/llvm/lib/CodeGen/Passes.cpp
index c128414c0b3..690224342f6 100644
--- a/llvm/lib/CodeGen/Passes.cpp
+++ b/llvm/lib/CodeGen/Passes.cpp
@@ -52,7 +52,10 @@ static cl::opt<bool> DisableMachineLICM("disable-machine-licm", cl::Hidden,
static cl::opt<bool> DisableMachineCSE("disable-machine-cse", cl::Hidden,
cl::desc("Disable Machine Common Subexpression Elimination"));
static cl::opt<cl::boolOrDefault>
-OptimizeRegAlloc("optimize-regalloc", cl::Hidden,
+ EnableShrinkWrapOpt("enable-shrink-wrap", cl::Hidden,
+ cl::desc("enable the shrink-wrapping pass"));
+static cl::opt<cl::boolOrDefault> OptimizeRegAlloc(
+ "optimize-regalloc", cl::Hidden,
cl::desc("Enable optimized register allocation compilation path."));
static cl::opt<bool> DisablePostRAMachineLICM("disable-postra-machine-licm",
cl::Hidden,
@@ -206,10 +209,10 @@ TargetPassConfig::~TargetPassConfig() {
// Out of line constructor provides default values for pass options and
// registers all common codegen passes.
TargetPassConfig::TargetPassConfig(TargetMachine *tm, PassManagerBase &pm)
- : ImmutablePass(ID), PM(&pm), StartAfter(nullptr), StopAfter(nullptr),
- Started(true), Stopped(false), AddingMachinePasses(false), TM(tm),
- Impl(nullptr), Initialized(false), DisableVerify(false),
- EnableTailMerge(true) {
+ : ImmutablePass(ID), PM(&pm), StartAfter(nullptr), StopAfter(nullptr),
+ Started(true), Stopped(false), AddingMachinePasses(false), TM(tm),
+ Impl(nullptr), Initialized(false), DisableVerify(false),
+ EnableTailMerge(true), EnableShrinkWrap(false) {
Impl = new PassConfigImpl();
@@ -524,6 +527,8 @@ void TargetPassConfig::addMachinePasses() {
addPostRegAlloc();
// Insert prolog/epilog code. Eliminate abstract frame index references...
+ if (getEnableShrinkWrap())
+ addPass(&ShrinkWrapID);
addPass(&PrologEpilogCodeInserterID);
/// Add passes that optimize machine instructions after register allocation.
@@ -599,6 +604,21 @@ void TargetPassConfig::addMachineSSAOptimization() {
addPass(&DeadMachineInstructionElimID);
}
+bool TargetPassConfig::getEnableShrinkWrap() const {
+ switch (EnableShrinkWrapOpt) {
+ case cl::BOU_UNSET:
+ return EnableShrinkWrap && getOptLevel() != CodeGenOpt::None;
+ // If EnableShrinkWrap is set, it takes precedence on whatever the
+ // target sets. The rational is that we assume we want to test
+ // something related to shrink-wrapping.
+ case cl::BOU_TRUE:
+ return true;
+ case cl::BOU_FALSE:
+ return false;
+ }
+ llvm_unreachable("Invalid shrink-wrapping state");
+}
+
//===---------------------------------------------------------------------===//
/// Register Allocation Pass Configuration
//===---------------------------------------------------------------------===//
diff --git a/llvm/lib/CodeGen/PrologEpilogInserter.cpp b/llvm/lib/CodeGen/PrologEpilogInserter.cpp
index 5334a633ead..e4f359c213c 100644
--- a/llvm/lib/CodeGen/PrologEpilogInserter.cpp
+++ b/llvm/lib/CodeGen/PrologEpilogInserter.cpp
@@ -71,9 +71,9 @@ private:
// stack frame indexes.
unsigned MinCSFrameIndex, MaxCSFrameIndex;
- // Entry and return blocks of the current function.
- MachineBasicBlock *EntryBlock;
- SmallVector<MachineBasicBlock *, 4> ReturnBlocks;
+ // Save and Restore blocks of the current function.
+ MachineBasicBlock *SaveBlock;
+ SmallVector<MachineBasicBlock *, 4> RestoreBlocks;
// Flag to control whether to use the register scavenger to resolve
// frame index materialization registers. Set according to
@@ -133,20 +133,26 @@ bool PEI::isReturnBlock(MachineBasicBlock* MBB) {
/// Compute the set of return blocks
void PEI::calculateSets(MachineFunction &Fn) {
- // Sets used to compute spill, restore placement sets.
- const std::vector<CalleeSavedInfo> &CSI =
- Fn.getFrameInfo()->getCalleeSavedInfo();
+ const MachineFrameInfo *MFI = Fn.getFrameInfo();
- // If no CSRs used, we are done.
- if (CSI.empty())
+ // Even when we do not change any CSR, we still want to insert the
+ // prologue and epilogue of the function.
+ // So set the save points for those.
+
+ // Use the points found by shrink-wrapping, if any.
+ if (MFI->getSavePoint()) {
+ SaveBlock = MFI->getSavePoint();
+ assert(MFI->getRestorePoint() && "Both restore and save must be set");
+ RestoreBlocks.push_back(MFI->getRestorePoint());
return;
+ }
// Save refs to entry and return blocks.
- EntryBlock = Fn.begin();
+ SaveBlock = Fn.begin();
for (MachineFunction::iterator MBB = Fn.begin(), E = Fn.end();
MBB != E; ++MBB)
if (isReturnBlock(MBB))
- ReturnBlocks.push_back(MBB);
+ RestoreBlocks.push_back(MBB);
return;
}
@@ -226,7 +232,7 @@ bool PEI::runOnMachineFunction(MachineFunction &Fn) {
}
delete RS;
- ReturnBlocks.clear();
+ RestoreBlocks.clear();
return true;
}
@@ -372,6 +378,61 @@ void PEI::calculateCalleeSavedRegisters(MachineFunction &F) {
MFI->setCalleeSavedInfo(CSI);
}
+/// Helper function to update the liveness information for the callee-saved
+/// registers.
+static void updateLiveness(MachineFunction &MF) {
+ MachineFrameInfo *MFI = MF.getFrameInfo();
+ // Visited will contain all the basic blocks that are in the region
+ // where the callee saved registers are alive:
+ // - Anything that is not Save or Restore -> LiveThrough.
+ // - Save -> LiveIn.
+ // - Restore -> LiveOut.
+ // The live-out is not attached to the block, so no need to keep
+ // Restore in this set.
+ SmallPtrSet<MachineBasicBlock *, 8> Visited;
+ SmallVector<MachineBasicBlock *, 8> WorkList;
+ MachineBasicBlock *Entry = &MF.front();
+ MachineBasicBlock *Save = MFI->getSavePoint();
+
+ if (!Save)
+ Save = Entry;
+
+ if (Entry != Save) {
+ WorkList.push_back(Entry);
+ Visited.insert(Entry);
+ }
+ Visited.insert(Save);
+
+ MachineBasicBlock *Restore = MFI->getRestorePoint();
+ if (Restore)
+ // By construction Restore cannot be visited, otherwise it
+ // means there exists a path to Restore that does not go
+ // through Save.
+ WorkList.push_back(Restore);
+
+ while (!WorkList.empty()) {
+ const MachineBasicBlock *CurBB = WorkList.pop_back_val();
+ // By construction, the region that is after the save point is
+ // dominated by the Save and post-dominated by the Restore.
+ if (CurBB == Save)
+ continue;
+ // Enqueue all the successors not already visited.
+ // Those are by construction either before Save or after Restore.
+ for (MachineBasicBlock *SuccBB : CurBB->successors())
+ if (Visited.insert(SuccBB).second)
+ WorkList.push_back(SuccBB);
+ }
+
+ const std::vector<CalleeSavedInfo> &CSI = MFI->getCalleeSavedInfo();
+
+ for (unsigned i = 0, e = CSI.size(); i != e; ++i) {
+ for (MachineBasicBlock *MBB : Visited)
+ // Add the callee-saved register as live-in.
+ // It's killed at the spill.
+ MBB->addLiveIn(CSI[i].getReg());
+ }
+}
+
/// insertCSRSpillsAndRestores - Insert spill and restore code for
/// callee saved registers used in the function.
///
@@ -392,26 +453,22 @@ void PEI::insertCSRSpillsAndRestores(MachineFunction &Fn) {
MachineBasicBlock::iterator I;
// Spill using target interface.
- I = EntryBlock->begin();
- if (!TFI->spillCalleeSavedRegisters(*EntryBlock, I, CSI, TRI)) {
+ I = SaveBlock->begin();
+ if (!TFI->spillCalleeSavedRegisters(*SaveBlock, I, CSI, TRI)) {
for (unsigned i = 0, e = CSI.size(); i != e; ++i) {
- // Add the callee-saved register as live-in.
- // It's killed at the spill.
- EntryBlock->addLiveIn(CSI[i].getReg());
-
// Insert the spill to the stack frame.
unsigned Reg = CSI[i].getReg();
const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(Reg);
- TII.storeRegToStackSlot(*EntryBlock, I, Reg, true, CSI[i].getFrameIdx(),
+ TII.storeRegToStackSlot(*SaveBlock, I, Reg, true, CSI[i].getFrameIdx(),
RC, TRI);
}
}
+ // Update the live-in information of all the blocks up to the save point.
+ updateLiveness(Fn);
// Restore using target interface.
- for (unsigned ri = 0, re = ReturnBlocks.size(); ri != re; ++ri) {
- MachineBasicBlock *MBB = ReturnBlocks[ri];
+ for (MachineBasicBlock *MBB : RestoreBlocks) {
I = MBB->end();
- --I;
// Skip over all terminator instructions, which are part of the return
// sequence.
@@ -721,21 +778,18 @@ void PEI::insertPrologEpilogCode(MachineFunction &Fn) {
const TargetFrameLowering &TFI = *Fn.getSubtarget().getFrameLowering();
// Add prologue to the function...
- TFI.emitPrologue(Fn);
+ TFI.emitPrologue(Fn, *SaveBlock);
- // Add epilogue to restore the callee-save registers in each exiting block
- for (MachineFunction::iterator I = Fn.begin(), E = Fn.end(); I != E; ++I) {
- // If last instruction is a return instruction, add an epilogue
- if (!I->empty() && I->back().isReturn())
- TFI.emitEpilogue(Fn, *I);
- }
+ // Add epilogue to restore the callee-save registers in each exiting block.
+ for (MachineBasicBlock *RestoreBlock : RestoreBlocks)
+ TFI.emitEpilogue(Fn, *RestoreBlock);
// Emit additional code that is required to support segmented stacks, if
// we've been asked for it. This, when linked with a runtime with support
// for segmented stacks (libgcc is one), will result in allocating stack
// space in small chunks instead of one large contiguous block.
if (Fn.shouldSplitStack())
- TFI.adjustForSegmentedStacks(Fn);
+ TFI.adjustForSegmentedStacks(Fn, *SaveBlock);
// Emit additional code that is required to explicitly handle the stack in
// HiPE native code (if needed) when loaded in the Erlang/OTP runtime. The
@@ -743,7 +797,7 @@ void PEI::insertPrologEpilogCode(MachineFunction &Fn) {
// different conditional check and another BIF for allocating more stack
// space.
if (Fn.getFunction()->getCallingConv() == CallingConv::HiPE)
- TFI.adjustForHiPEPrologue(Fn);
+ TFI.adjustForHiPEPrologue(Fn, *SaveBlock);
}
/// replaceFrameIndices - Replace all MO_FrameIndex operands with physical
diff --git a/llvm/lib/CodeGen/ShrinkWrap.cpp b/llvm/lib/CodeGen/ShrinkWrap.cpp
new file mode 100644
index 00000000000..56f1200619c
--- /dev/null
+++ b/llvm/lib/CodeGen/ShrinkWrap.cpp
@@ -0,0 +1,383 @@
+//===-- ShrinkWrap.cpp - Compute safe point for prolog/epilog insertion ---===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This pass looks for safe point where the prologue and epilogue can be
+// inserted.
+// The safe point for the prologue (resp. epilogue) is called Save
+// (resp. Restore).
+// A point is safe for prologue (resp. epilogue) if and only if
+// it 1) dominates (resp. post-dominates) all the frame related operations and
+// between 2) two executions of the Save (resp. Restore) point there is an
+// execution of the Restore (resp. Save) point.
+//
+// For instance, the following points are safe:
+// for (int i = 0; i < 10; ++i) {
+// Save
+// ...
+// Restore
+// }
+// Indeed, the execution looks like Save -> Restore -> Save -> Restore ...
+// And the following points are not:
+// for (int i = 0; i < 10; ++i) {
+// Save
+// ...
+// }
+// for (int i = 0; i < 10; ++i) {
+// ...
+// Restore
+// }
+// Indeed, the execution looks like Save -> Save -> ... -> Restore -> Restore.
+//
+// This pass also ensures that the safe points are 3) cheaper than the regular
+// entry and exits blocks.
+//
+// Property #1 is ensured via the use of MachineDominatorTree and
+// MachinePostDominatorTree.
+// Property #2 is ensured via property #1 and MachineLoopInfo, i.e., both
+// points must be in the same loop.
+// Property #3 is ensured via the MachineBlockFrequencyInfo.
+//
+// If this pass found points matching all this properties, then
+// MachineFrameInfo is updated this that information.
+//===----------------------------------------------------------------------===//
+#include "llvm/ADT/Statistic.h"
+// To check for profitability.
+#include "llvm/CodeGen/MachineBlockFrequencyInfo.h"
+// For property #1 for Save.
+#include "llvm/CodeGen/MachineDominators.h"
+#include "llvm/CodeGen/MachineFunctionPass.h"
+// To record the result of the analysis.
+#include "llvm/CodeGen/MachineFrameInfo.h"
+// For property #2.
+#include "llvm/CodeGen/MachineLoopInfo.h"
+// For property #1 for Restore.
+#include "llvm/CodeGen/MachinePostDominators.h"
+#include "llvm/CodeGen/Passes.h"
+// To know about callee-saved.
+#include "llvm/CodeGen/RegisterClassInfo.h"
+#include "llvm/Support/Debug.h"
+// To know about frame setup operation.
+#include "llvm/Target/TargetInstrInfo.h"
+// To access TargetInstrInfo.
+#include "llvm/Target/TargetSubtargetInfo.h"
+
+#define DEBUG_TYPE "shrink-wrap"
+
+using namespace llvm;
+
+STATISTIC(NumFunc, "Number of functions");
+STATISTIC(NumCandidates, "Number of shrink-wrapping candidates");
+STATISTIC(NumCandidatesDropped,
+ "Number of shrink-wrapping candidates dropped because of frequency");
+
+namespace {
+/// \brief Class to determine where the safe point to insert the
+/// prologue and epilogue are.
+/// Unlike the paper from Fred C. Chow, PLDI'88, that introduces the
+/// shrink-wrapping term for prologue/epilogue placement, this pass
+/// does not rely on expensive data-flow analysis. Instead we use the
+/// dominance properties and loop information to decide which point
+/// are safe for such insertion.
+class ShrinkWrap : public MachineFunctionPass {
+ /// Hold callee-saved information.
+ RegisterClassInfo RCI;
+ MachineDominatorTree *MDT;
+ MachinePostDominatorTree *MPDT;
+ /// Current safe point found for the prologue.
+ /// The prologue will be inserted before the first instruction
+ /// in this basic block.
+ MachineBasicBlock *Save;
+ /// Current safe point found for the epilogue.
+ /// The epilogue will be inserted before the first terminator instruction
+ /// in this basic block.
+ MachineBasicBlock *Restore;
+ /// Hold the information of the basic block frequency.
+ /// Use to check the profitability of the new points.
+ MachineBlockFrequencyInfo *MBFI;
+ /// Hold the loop information. Used to determine if Save and Restore
+ /// are in the same loop.
+ MachineLoopInfo *MLI;
+ /// Frequency of the Entry block.
+ uint64_t EntryFreq;
+ /// Current opcode for frame setup.
+ int FrameSetupOpcode;
+ /// Current opcode for frame destroy.
+ int FrameDestroyOpcode;
+ /// Entry block.
+ const MachineBasicBlock *Entry;
+
+ /// \brief Check if \p MI uses or defines a callee-saved register or
+ /// a frame index. If this is the case, this means \p MI must happen
+ /// after Save and before Restore.
+ bool useOrDefCSROrFI(const MachineInstr &MI) const;
+
+ /// \brief Update the Save and Restore points such that \p MBB is in
+ /// the region that is dominated by Save and post-dominated by Restore
+ /// and Save and Restore still match the safe point definition.
+ /// Such point may not exist and Save and/or Restore may be null after
+ /// this call.
+ void updateSaveRestorePoints(MachineBasicBlock &MBB);
+
+ /// \brief Initialize the pass for \p MF.
+ void init(MachineFunction &MF) {
+ RCI.runOnMachineFunction(MF);
+ MDT = &getAnalysis<MachineDominatorTree>();
+ MPDT = &getAnalysis<MachinePostDominatorTree>();
+ Save = nullptr;
+ Restore = nullptr;
+ MBFI = &getAnalysis<MachineBlockFrequencyInfo>();
+ MLI = &getAnalysis<MachineLoopInfo>();
+ EntryFreq = MBFI->getEntryFreq();
+ const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
+ FrameSetupOpcode = TII.getCallFrameSetupOpcode();
+ FrameDestroyOpcode = TII.getCallFrameDestroyOpcode();
+ Entry = &MF.front();
+
+ ++NumFunc;
+ }
+
+ /// Check whether or not Save and Restore points are still interesting for
+ /// shrink-wrapping.
+ bool ArePointsInteresting() const { return Save != Entry && Save && Restore; }
+
+public:
+ static char ID;
+
+ ShrinkWrap() : MachineFunctionPass(ID) {
+ initializeShrinkWrapPass(*PassRegistry::getPassRegistry());
+ }
+
+ void getAnalysisUsage(AnalysisUsage &AU) const override {
+ AU.setPreservesAll();
+ AU.addRequired<MachineBlockFrequencyInfo>();
+ AU.addRequired<MachineDominatorTree>();
+ AU.addRequired<MachinePostDominatorTree>();
+ AU.addRequired<MachineLoopInfo>();
+ MachineFunctionPass::getAnalysisUsage(AU);
+ }
+
+ const char *getPassName() const override {
+ return "Shrink Wrapping analysis";
+ }
+
+ /// \brief Perform the shrink-wrapping analysis and update
+ /// the MachineFrameInfo attached to \p MF with the results.
+ bool runOnMachineFunction(MachineFunction &MF) override;
+};
+} // End anonymous namespace.
+
+char ShrinkWrap::ID = 0;
+char &llvm::ShrinkWrapID = ShrinkWrap::ID;
+
+INITIALIZE_PASS_BEGIN(ShrinkWrap, "shrink-wrap", "Shrink Wrap Pass", false,
+ false)
+INITIALIZE_PASS_DEPENDENCY(MachineBlockFrequencyInfo)
+INITIALIZE_PASS_DEPENDENCY(MachineDominatorTree)
+INITIALIZE_PASS_DEPENDENCY(MachinePostDominatorTree)
+INITIALIZE_PASS_DEPENDENCY(MachineLoopInfo)
+INITIALIZE_PASS_END(ShrinkWrap, "shrink-wrap", "Shrink Wrap Pass", false, false)
+
+bool ShrinkWrap::useOrDefCSROrFI(const MachineInstr &MI) const {
+ if (MI.getOpcode() == FrameSetupOpcode ||
+ MI.getOpcode() == FrameDestroyOpcode) {
+ DEBUG(dbgs() << "Frame instruction: " << MI << '\n');
+ return true;
+ }
+ for (const MachineOperand &MO : MI.operands()) {
+ bool UseCSR = false;
+ if (MO.isReg()) {
+ unsigned PhysReg = MO.getReg();
+ if (!PhysReg)
+ continue;
+ assert(TargetRegisterInfo::isPhysicalRegister(PhysReg) &&
+ "Unallocated register?!");
+ UseCSR = RCI.getLastCalleeSavedAlias(PhysReg);
+ }
+ // TODO: Handle regmask more accurately.
+ // For now, be conservative about them.
+ if (UseCSR || MO.isFI() || MO.isRegMask()) {
+ DEBUG(dbgs() << "Use or define CSR(" << UseCSR << ") or FI(" << MO.isFI()
+ << "): " << MI << '\n');
+ return true;
+ }
+ }
+ return false;
+}
+
+/// \brief Helper function to find the immediate (post) dominator.
+template <typename ListOfBBs, typename DominanceAnalysis>
+MachineBasicBlock *FindIDom(MachineBasicBlock &Block, ListOfBBs BBs,
+ DominanceAnalysis &Dom) {
+ MachineBasicBlock *IDom = &Block;
+ for (MachineBasicBlock *BB : BBs) {
+ IDom = Dom.findNearestCommonDominator(IDom, BB);
+ if (!IDom)
+ break;
+ }
+ return IDom;
+}
+
+void ShrinkWrap::updateSaveRestorePoints(MachineBasicBlock &MBB) {
+ // Get rid of the easy cases first.
+ if (!Save)
+ Save = &MBB;
+ else
+ Save = MDT->findNearestCommonDominator(Save, &MBB);
+
+ if (!Save) {
+ DEBUG(dbgs() << "Found a block that is not reachable from Entry\n");
+ return;
+ }
+
+ if (!Restore)
+ Restore = &MBB;
+ else
+ Restore = MPDT->findNearestCommonDominator(Restore, &MBB);
+
+ // Make sure we would be able to insert the restore code before the
+ // terminator.
+ if (Restore == &MBB) {
+ for (const MachineInstr &Terminator : MBB.terminators()) {
+ if (!useOrDefCSROrFI(Terminator))
+ continue;
+ // One of the terminator needs to happen before the restore point.
+ if (MBB.succ_empty()) {
+ Restore = nullptr;
+ break;
+ }
+ // Look for a restore point that post-dominates all the successors.
+ // The immediate post-dominator is what we are looking for.
+ Restore = FindIDom<>(*Restore, Restore->successors(), *MPDT);
+ break;
+ }
+ }
+
+ if (!Restore) {
+ DEBUG(dbgs() << "Restore point needs to be spanned on several blocks\n");
+ return;
+ }
+
+ // Make sure Save and Restore are suitable for shrink-wrapping:
+ // 1. all path from Save needs to lead to Restore before exiting.
+ // 2. all path to Restore needs to go through Save from Entry.
+ // We achieve that by making sure that:
+ // A. Save dominates Restore.
+ // B. Restore post-dominates Save.
+ // C. Save and Restore are in the same loop.
+ bool SaveDominatesRestore = false;
+ bool RestorePostDominatesSave = false;
+ while (Save && Restore &&
+ (!(SaveDominatesRestore = MDT->dominates(Save, Restore)) ||
+ !(RestorePostDominatesSave = MPDT->dominates(Restore, Save)) ||
+ MLI->getLoopFor(Save) != MLI->getLoopFor(Restore))) {
+ // Fix (A).
+ if (!SaveDominatesRestore) {
+ Save = MDT->findNearestCommonDominator(Save, Restore);
+ continue;
+ }
+ // Fix (B).
+ if (!RestorePostDominatesSave)
+ Restore = MPDT->findNearestCommonDominator(Restore, Save);
+
+ // Fix (C).
+ if (Save && Restore && Save != Restore &&
+ MLI->getLoopFor(Save) != MLI->getLoopFor(Restore)) {
+ if (MLI->getLoopDepth(Save) > MLI->getLoopDepth(Restore))
+ // Push Save outside of this loop.
+ Save = FindIDom<>(*Save, Save->predecessors(), *MDT);
+ else
+ // Push Restore outside of this loop.
+ Restore = FindIDom<>(*Restore, Restore->successors(), *MPDT);
+ }
+ }
+}
+
+bool ShrinkWrap::runOnMachineFunction(MachineFunction &MF) {
+ if (MF.empty())
+ return false;
+ DEBUG(dbgs() << "**** Analysing " << MF.getName() << '\n');
+
+ init(MF);
+
+ for (MachineBasicBlock &MBB : MF) {
+ DEBUG(dbgs() << "Look into: " << MBB.getNumber() << ' ' << MBB.getName()
+ << '\n');
+
+ for (const MachineInstr &MI : MBB) {
+ if (!useOrDefCSROrFI(MI))
+ continue;
+ // Save (resp. restore) point must dominate (resp. post dominate)
+ // MI. Look for the proper basic block for those.
+ updateSaveRestorePoints(MBB);
+ // If we are at a point where we cannot improve the placement of
+ // save/restore instructions, just give up.
+ if (!ArePointsInteresting()) {
+ DEBUG(dbgs() << "No Shrink wrap candidate found\n");
+ return false;
+ }
+ // No need to look for other instructions, this basic block
+ // will already be part of the handled region.
+ break;
+ }
+ }
+ if (!ArePointsInteresting()) {
+ // If the points are not interesting at this point, then they must be null
+ // because it means we did not encounter any frame/CSR related code.
+ // Otherwise, we would have returned from the previous loop.
+ assert(!Save && !Restore && "We miss a shrink-wrap opportunity?!");
+ DEBUG(dbgs() << "Nothing to shrink-wrap\n");
+ return false;
+ }
+
+ DEBUG(dbgs() << "\n ** Results **\nFrequency of the Entry: " << EntryFreq
+ << '\n');
+
+ do {
+ DEBUG(dbgs() << "Shrink wrap candidates (#, Name, Freq):\nSave: "
+ << Save->getNumber() << ' ' << Save->getName() << ' '
+ << MBFI->getBlockFreq(Save).getFrequency() << "\nRestore: "
+ << Restore->getNumber() << ' ' << Restore->getName() << ' '
+ << MBFI->getBlockFreq(Restore).getFrequency() << '\n');
+
+ bool IsSaveCheap;
+ if ((IsSaveCheap = EntryFreq >= MBFI->getBlockFreq(Save).getFrequency()) &&
+ EntryFreq >= MBFI->getBlockFreq(Restore).getFrequency())
+ break;
+ DEBUG(dbgs() << "New points are too expensive\n");
+ MachineBasicBlock *NewBB;
+ if (!IsSaveCheap) {
+ Save = FindIDom<>(*Save, Save->predecessors(), *MDT);
+ if (!Save)
+ break;
+ NewBB = Save;
+ } else {
+ // Restore is expensive.
+ Restore = FindIDom<>(*Restore, Restore->successors(), *MPDT);
+ if (!Restore)
+ break;
+ NewBB = Restore;
+ }
+ updateSaveRestorePoints(*NewBB);
+ } while (Save && Restore);
+
+ if (!ArePointsInteresting()) {
+ ++NumCandidatesDropped;
+ return false;
+ }
+
+ DEBUG(dbgs() << "Final shrink wrap candidates:\nSave: " << Save->getNumber()
+ << ' ' << Save->getName() << "\nRestore: "
+ << Restore->getNumber() << ' ' << Restore->getName() << '\n');
+
+ MachineFrameInfo *MFI = MF.getFrameInfo();
+ MFI->setSavePoint(Save);
+ MFI->setRestorePoint(Restore);
+ ++NumCandidates;
+ return false;
+}
OpenPOWER on IntegriCloud