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

llvm-svn: 255353

1 files changed, 36 insertions, 1 deletions

diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp
index f6c5d90f47a..5f3e4a02341 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp
+++ b/llvm/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(),