SimplifyCFG has stopped duplicating returns into predecessors to canonicalize IR

to have single return block (at least getting there) for optimizations. This
is general goodness but it would prevent some tailcall optimizations.
One specific case is code like this:
int f1(void);
int f2(void);
int f3(void);
int f4(void);
int f5(void);
int f6(void);
int foo(int x) {
  switch(x) {
  case 1: return f1();
  case 2: return f2();
  case 3: return f3();
  case 4: return f4();
  case 5: return f5();
  case 6: return f6();
  }
}

=>
LBB0_2:                                 ## %sw.bb
  callq   _f1
  popq    %rbp
  ret
LBB0_3:                                 ## %sw.bb1
  callq   _f2
  popq    %rbp
  ret
LBB0_4:                                 ## %sw.bb3
  callq   _f3
  popq    %rbp
  ret

This patch teaches codegenprep to duplicate returns when the return value
is a phi and where the phi operands are produced by tail calls followed by
an unconditional branch:

sw.bb7:                                           ; preds = %entry
  %call8 = tail call i32 @f5() nounwind
  br label %return
sw.bb9:                                           ; preds = %entry
  %call10 = tail call i32 @f6() nounwind
  br label %return
return:
  %retval.0 = phi i32 [ %call10, %sw.bb9 ], [ %call8, %sw.bb7 ], ... [ 0, %entry ]
  ret i32 %retval.0

This allows codegen to generate better code like this:

LBB0_2:                                 ## %sw.bb
        jmp     _f1                     ## TAILCALL
LBB0_3:                                 ## %sw.bb1
        jmp     _f2                     ## TAILCALL
LBB0_4:                                 ## %sw.bb3
        jmp     _f3                     ## TAILCALL

rdar://9147433


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127953 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 15 insertions, 0 deletions

diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 576c879..58acf4f 100644
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -45,6 +45,7 @@
 #include "llvm/ADT/Statistic.h"
 #include "llvm/ADT/StringExtras.h"
 #include "llvm/ADT/VectorExtras.h"
+#include "llvm/Support/CallSite.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/Dwarf.h"
 #include "llvm/Support/ErrorHandling.h"
@@ -1595,6 +1596,18 @@ static bool IsTailCallConvention(CallingConv::ID CC) {
   return (CC == CallingConv::Fast || CC == CallingConv::GHC);
 }
 
+bool X86TargetLowering::mayBeEmittedAsTailCall(CallInst *CI) const {
+  if (!CI->isTailCall())
+    return false;
+
+  CallSite CS(CI);
+  CallingConv::ID CalleeCC = CS.getCallingConv();
+  if (!IsTailCallConvention(CalleeCC) && CalleeCC != CallingConv::C)
+    return false;
+
+  return true;
+}
+
 /// FuncIsMadeTailCallSafe - Return true if the function is being made into
 /// a tailcall target by changing its ABI.
 static bool FuncIsMadeTailCallSafe(CallingConv::ID CC) {
diff --git a/lib/Target/X86/X86ISelLowering.h b/lib/Target/X86/X86ISelLowering.h
index 7c1b13a..6301057 100644
--- a/lib/Target/X86/X86ISelLowering.h
+++ b/lib/Target/X86/X86ISelLowering.h
@@ -843,6 +843,8 @@ namespace llvm {
 
     virtual bool isUsedByReturnOnly(SDNode *N) const;
 
+    virtual bool mayBeEmittedAsTailCall(CallInst *CI) const;
+
     virtual EVT
     getTypeForExtArgOrReturn(LLVMContext &Context, EVT VT,
                              ISD::NodeType ExtendKind) const;