X86: Fold tail calls into conditional branches where possible (PR26302)

When branching to a block that immediately tail calls, it is possible to fold
the call directly into the branch if the call is direct and there is no stack
adjustment, saving one byte.

Example:

  define void @f(i32 %x, i32 %y) {
  entry:
    %p = icmp eq i32 %x, %y
    br i1 %p, label %bb1, label %bb2
  bb1:
    tail call void @foo()
    ret void
  bb2:
    tail call void @bar()
    ret void
  }

before:

  f:
          movl    4(%esp), %eax
          cmpl    8(%esp), %eax
          jne     .LBB0_2
          jmp     foo
  .LBB0_2:
          jmp     bar

after:

  f:
          movl    4(%esp), %eax
          cmpl    8(%esp), %eax
          jne     bar
  .LBB0_1:
          jmp     foo

I don't expect any significant size savings from this (on a Clang bootstrap I
saw 288 bytes), but it does make the code a little tighter.

This patch only does 32-bit, but 64-bit would work similarly.

Differential Revision: https://reviews.llvm.org/D24108

llvm-svn: 280832

1 files changed, 26 insertions, 7 deletions

diff --git a/llvm/lib/Target/X86/X86ExpandPseudo.cpp b/llvm/lib/Target/X86/X86ExpandPseudo.cpp
index ca94bf094d5..4bd01b8f00f 100644
--- a/llvm/lib/Target/X86/X86ExpandPseudo.cpp
+++ b/llvm/lib/Target/X86/X86ExpandPseudo.cpp
@@ -77,6 +77,7 @@ bool X86ExpandPseudo::ExpandMI(MachineBasicBlock &MBB,
   default:
     return false;
   case X86::TCRETURNdi:
+  case X86::TCRETURNdicc:
   case X86::TCRETURNri:
   case X86::TCRETURNmi:
   case X86::TCRETURNdi64:
@@ -94,9 +95,13 @@ bool X86ExpandPseudo::ExpandMI(MachineBasicBlock &MBB,
     assert(MaxTCDelta <= 0 && "MaxTCDelta should never be positive");
 
     // Incoporate the retaddr area.
-    Offset = StackAdj-MaxTCDelta;
+    Offset = StackAdj - MaxTCDelta;
     assert(Offset >= 0 && "Offset should never be negative");
 
+    if (Opcode == X86::TCRETURNdicc) {
+      assert(Offset == 0 && "Conditional tail call cannot adjust the stack.");
+    }
+
     if (Offset) {
       // Check for possible merge with preceding ADD instruction.
       Offset += X86FL->mergeSPUpdates(MBB, MBBI, true);
@@ -105,19 +110,33 @@ bool X86ExpandPseudo::ExpandMI(MachineBasicBlock &MBB,
 
     // Jump to label or value in register.
     bool IsWin64 = STI->isTargetWin64();
-    if (Opcode == X86::TCRETURNdi || Opcode == X86::TCRETURNdi64) {
-      unsigned Op = (Opcode == X86::TCRETURNdi)
-                        ? X86::TAILJMPd
-                        : (IsWin64 ? X86::TAILJMPd64_REX : X86::TAILJMPd64);
+    if (Opcode == X86::TCRETURNdi || Opcode == X86::TCRETURNdicc ||
+        Opcode == X86::TCRETURNdi64) {
+      unsigned Op;
+      switch (Opcode) {
+      case X86::TCRETURNdi:
+        Op = X86::TAILJMPd;
+        break;
+      case X86::TCRETURNdicc:
+        Op = X86::TAILJMPd_CC;
+        break;
+      default:
+        Op = IsWin64 ? X86::TAILJMPd64_REX : X86::TAILJMPd64;
+        break;
+      }
       MachineInstrBuilder MIB = BuildMI(MBB, MBBI, DL, TII->get(Op));
-      if (JumpTarget.isGlobal())
+      if (JumpTarget.isGlobal()) {
         MIB.addGlobalAddress(JumpTarget.getGlobal(), JumpTarget.getOffset(),
                              JumpTarget.getTargetFlags());
-      else {
+      } else {
         assert(JumpTarget.isSymbol());
         MIB.addExternalSymbol(JumpTarget.getSymbolName(),
                               JumpTarget.getTargetFlags());
       }
+      if (Op == X86::TAILJMPd_CC) {
+        MIB.addImm(MBBI->getOperand(2).getImm());
+      }
+
     } else if (Opcode == X86::TCRETURNmi || Opcode == X86::TCRETURNmi64) {
       unsigned Op = (Opcode == X86::TCRETURNmi)
                         ? X86::TAILJMPm