Added tail call optimization to the x86 back end. It can be

enabled by passing -tailcallopt to llc.  The optimization is
performed if the following conditions are satisfied:
* caller/callee are fastcc
* elf/pic is disabled OR
  elf/pic enabled + callee is in module + callee has
  visibility protected or hidden


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@42870 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 50 insertions, 0 deletions

diff --git a/lib/Target/X86/X86CallingConv.td b/lib/Target/X86/X86CallingConv.td
index 9c2d95a199..f23e580656 100644
--- a/lib/Target/X86/X86CallingConv.td
+++ b/lib/Target/X86/X86CallingConv.td
@@ -127,6 +127,40 @@ def CC_X86_64_C : CallingConv<[
   CCIfType<[v8i8, v4i16, v2i32, v1i64], CCAssignToStack<8, 8>>
 ]>;
 
+// tail call convetion (fast) one register is reserved for target address
+// namely R9
+def CC_X86_64_TailCall : CallingConv<[
+  // Promote i8/i16 arguments to i32.
+  CCIfType<[i8, i16], CCPromoteToType<i32>>,
+  
+  CCIfStruct<CCStructAssign<[RDI, RSI, RDX, RCX, R8]>>,
+
+  // The first 6 integer arguments are passed in integer registers.
+  CCIfType<[i32], CCAssignToReg<[EDI, ESI, EDX, ECX, R8D]>>,
+  CCIfType<[i64], CCAssignToReg<[RDI, RSI, RDX, RCX, R8]>>,
+  
+  // The first 8 FP/Vector arguments are passed in XMM registers.
+  CCIfType<[f32, f64, v16i8, v8i16, v4i32, v2i64, v4f32, v2f64],
+              CCAssignToReg<[XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7]>>,
+
+  // The first 8 MMX vector arguments are passed in GPRs.
+  CCIfType<[v8i8, v4i16, v2i32, v1i64],
+              CCAssignToReg<[RDI, RSI, RDX, RCX, R8]>>,
+
+  // The 'nest' parameter, if any, is passed in R10.
+  CCIfNest<CCAssignToReg<[R10]>>,
+
+  // Integer/FP values get stored in stack slots that are 8 bytes in size and
+  // 8-byte aligned if there are no more registers to hold them.
+  CCIfType<[i32, i64, f32, f64], CCAssignToStack<8, 8>>,
+  
+  // Vectors get 16-byte stack slots that are 16-byte aligned.
+  CCIfType<[v16i8, v8i16, v4i32, v2i64, v4f32, v2f64], CCAssignToStack<16, 16>>,
+
+  // __m64 vectors get 8-byte stack slots that are 8-byte aligned.
+  CCIfType<[v8i8, v4i16, v2i32, v1i64], CCAssignToStack<8, 8>>
+]>;
+
 
 //===----------------------------------------------------------------------===//
 // X86 C Calling Convention
@@ -173,6 +207,22 @@ def CC_X86_32_C : CallingConv<[
   CCDelegateTo<CC_X86_32_Common>
 ]>;
 
+/// Same as C calling convention up to nonfree ECX which is used for storing 
+/// potential pointer to tail called function
+def CC_X86_32_TailCall : CallingConv<[
+  // Promote i8/i16 arguments to i32.
+  CCIfType<[i8, i16], CCPromoteToType<i32>>,
+
+  // The 'nest' parameter, if any, is passed in ECX.
+  CCIfNest<CCAssignToReg<[ECX]>>,
+
+  // The first 3 integer arguments, if marked 'inreg' and if the call is not
+  // a vararg call, are passed in integer registers.
+  CCIfNotVarArg<CCIfInReg<CCIfType<[i32], CCAssignToReg<[EAX, EDX]>>>>,
+
+  // Otherwise, same as everything else.
+  CCDelegateTo<CC_X86_32_Common>
+]>;
 
 def CC_X86_32_FastCall : CallingConv<[
   // Promote i8/i16 arguments to i32.