CXX_FAST_TLS calling convention: target independent portion.

The access function has a short entry and a short exit, the initialization
block is only run the first time. To improve the performance, we want to
have a short frame at the entry and exit.

We explicitly handle most of the CSRs via copies. Only the CSRs that are not
handled via copies will be in CSR_SaveList.

Frame lowering and prologue/epilogue insertion will generate a short frame
in the entry and exit according to CSR_SaveList. The majority of the CSRs will
be handled by register allcoator. Register allocator will try to spill and
reload them in the initialization block.

We add CSRsViaCopy, it will be explicitly handled during lowering.

1> we first set FunctionLoweringInfo->SplitCSR if conditions are met (the target
   supports it for the given calling convention and the function has only return
   exits). We also call TLI->initializeSplitCSR to perform initialization.
2> we call TLI->insertCopiesSplitCSR to insert copies from CSRsViaCopy to
   virtual registers at beginning of the entry block and copies from virtual
   registers to CSRsViaCopy at beginning of the exit blocks.
3> we also need to make sure the explicit copies will not be eliminated.

rdar://problem/23557469

Differential Revision: http://reviews.llvm.org/D15340

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@255353 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm/CodeGen/FunctionLoweringInfo.h b/include/llvm/CodeGen/FunctionLoweringInfo.h
index bd8da736c16b9e370673555b93d8a0a5fb048f30..09a9991912daaa014e38c3ed15588baaf23d08cb 100644 (file)
--- a/include/llvm/CodeGen/FunctionLoweringInfo.h
+++ b/include/llvm/CodeGen/FunctionLoweringInfo.h
@@ -62,6 +62,9 @@ public:
   /// registers.
   bool CanLowerReturn;
 
+  /// True if part of the CSRs will be handled via explicit copies.
+  bool SplitCSR;
+
   /// DemoteRegister - if CanLowerReturn is false, DemoteRegister is a vreg
   /// allocated to hold a pointer to the hidden sret parameter.
   unsigned DemoteRegister;

diff --git a/include/llvm/Target/TargetLowering.h b/include/llvm/Target/TargetLowering.h
index f7152565f9146f63fb7bbc466125cc1a779c0665..a105917958daf3a025ed317ef401fec3f92b2a53 100644 (file)
--- a/include/llvm/Target/TargetLowering.h
+++ b/include/llvm/Target/TargetLowering.h
@@ -2263,6 +2263,29 @@ public:
     return false;
   }
 
+  /// Return true if the target supports that a subset of CSRs for the given
+  /// calling convention is handled explicitly via copies.
+  virtual bool supportSplitCSR(CallingConv::ID CC) const {
+    return false;
+  }
+
+  /// Perform necessary initialization to handle a subset of CSRs explicitly
+  /// via copies. This function is called at the beginning of instruction
+  /// selection.
+  virtual void initializeSplitCSR(MachineBasicBlock *Entry) const {
+    llvm_unreachable("Not Implemented");
+  }
+
+  /// Insert explicit copies in entry and exit blocks. We copy a subset of
+  /// CSRs to virtual registers in the entry block, and copy them back to
+  /// physical registers in the exit blocks. This function is called at the end
+  /// of instruction selection.
+  virtual void insertCopiesSplitCSR(
+      MachineBasicBlock *Entry,
+      const SmallVectorImpl<MachineBasicBlock *> &Exits) const {
+    llvm_unreachable("Not Implemented");
+  }
+
   //===--------------------------------------------------------------------===//
   // Lowering methods - These methods must be implemented by targets so that
   // the SelectionDAGBuilder code knows how to lower these.

diff --git a/include/llvm/Target/TargetRegisterInfo.h b/include/llvm/Target/TargetRegisterInfo.h
index 414255edb23e128d5141726f74ebd06bee34329b..ffd510440b01ab29d0463edc2fc3587071441f4e 100644 (file)
--- a/include/llvm/Target/TargetRegisterInfo.h
+++ b/include/llvm/Target/TargetRegisterInfo.h
@@ -426,6 +426,11 @@ public:
   virtual const MCPhysReg*
   getCalleeSavedRegs(const MachineFunction *MF) const = 0;
 
+  virtual const MCPhysReg*
+  getCalleeSavedRegsViaCopy(const MachineFunction *MF) const {
+    return nullptr;
+  }
+
   /// Return a mask of call-preserved registers for the given calling convention
   /// on the current function. The mask should include all call-preserved
   /// aliases. This is used by the register allocator to determine which

diff --git a/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp b/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp
index f6c5d90f47ae1386c1c1f91370298d903b773220..5f3e4a02341e8bbd7e35b6f0103f7f0d82272bfb 100644 (file)
--- a/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp
+++ b/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp
@@ -467,15 +467,50 @@ bool SelectionDAGISel::runOnMachineFunction(MachineFunction &mf) {
 
   MF->setHasInlineAsm(false);
 
+  FuncInfo->SplitCSR = false;
+  SmallVector<MachineBasicBlock*, 4> Returns;
+
+  // We split CSR if the target supports it for the given calling convention
+  // and the function has only return exits.
+  if (TLI->supportSplitCSR(Fn.getCallingConv())) {
+    FuncInfo->SplitCSR = true;
+
+    // Collect all the return blocks.
+    for (const BasicBlock &BB : Fn) {
+      if (!succ_empty(&BB))
+        continue;
+
+      const TerminatorInst *Term = BB.getTerminator();
+      if (isa<UnreachableInst>(Term))
+        continue;
+      if (isa<ReturnInst>(Term)) {
+        Returns.push_back(FuncInfo->MBBMap[&BB]);
+        continue;
+      }
+
+      // Bail out if the exit block is not Return nor Unreachable.
+      FuncInfo->SplitCSR = false;
+      break;
+    }
+  }
+
+  MachineBasicBlock *EntryMBB = &MF->front();
+  if (FuncInfo->SplitCSR)
+    // This performs initialization so lowering for SplitCSR will be correct.
+    TLI->initializeSplitCSR(EntryMBB);
+
   SelectAllBasicBlocks(Fn);
 
   // If the first basic block in the function has live ins that need to be
   // copied into vregs, emit the copies into the top of the block before
   // emitting the code for the block.
-  MachineBasicBlock *EntryMBB = &MF->front();
   const TargetRegisterInfo &TRI = *MF->getSubtarget().getRegisterInfo();
   RegInfo->EmitLiveInCopies(EntryMBB, TRI, *TII);
 
+  // Insert copies in the entry block and the return blocks.
+  if (FuncInfo->SplitCSR)
+    TLI->insertCopiesSplitCSR(EntryMBB, Returns);
+
   DenseMap<unsigned, unsigned> LiveInMap;
   if (!FuncInfo->ArgDbgValues.empty())
     for (MachineRegisterInfo::livein_iterator LI = RegInfo->livein_begin(),