[X86] When optimizing for minsize, use POP for small post-call stack clean-up

When optimizing for size, replace "addl $4, %esp" and "addl $8, %esp"
following a call by one or two pops, respectively. We don't try to do it in
general, but only when the stack adjustment immediately follows a call - which
is the most common case.

That allows taking a short-cut when trying to find a free register to pop into,
instead of a full-blown liveness check. If the adjustment immediately follows a
call, then every register the call clobbers but doesn't define should be dead at
that point, and can be used.

Differential Revision: http://reviews.llvm.org/D11749

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@244578 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86FrameLowering.cpp b/lib/Target/X86/X86FrameLowering.cpp
index b8858362e745a245d1b7b22663894e52d41a3611..6cb2680be215a0ee273094f67c75e445db464e40 100644 (file)
--- a/lib/Target/X86/X86FrameLowering.cpp
+++ b/lib/Target/X86/X86FrameLowering.cpp
@@ -1851,6 +1851,69 @@ void X86FrameLowering::adjustForHiPEPrologue(
 #endif
 }
 
+bool X86FrameLowering::adjustStackWithPops(MachineBasicBlock &MBB,
+    MachineBasicBlock::iterator MBBI, DebugLoc DL, int Offset) const {
+
+  if (Offset % SlotSize)
+    return false;
+
+  int NumPops = Offset / SlotSize;
+  // This is only worth it if we have at most 2 pops.
+  if (NumPops != 1 && NumPops != 2)
+    return false;
+
+  // Handle only the trivial case where the adjustment directly follows
+  // a call. This is the most common one, anyway.
+  if (MBBI == MBB.begin())
+    return false;
+  MachineBasicBlock::iterator Prev = std::prev(MBBI);
+  if (!Prev->isCall() || !Prev->getOperand(1).isRegMask())
+    return false;
+
+  unsigned Regs[2];
+  unsigned FoundRegs = 0;
+
+  auto RegMask = Prev->getOperand(1);
+  
+  // Try to find up to NumPops free registers. 
+  for (auto Candidate : X86::GR32_NOREX_NOSPRegClass) {
+
+    // Poor man's liveness:
+    // Since we're immediately after a call, any register that is clobbered
+    // by the call and not defined by it can be considered dead.
+    if (!RegMask.clobbersPhysReg(Candidate))
+      continue;
+
+    bool IsDef = false;
+    for (const MachineOperand &MO : Prev->implicit_operands()) {
+      if (MO.isReg() && MO.isDef() && MO.getReg() == Candidate) {
+        IsDef = true;
+        break;
+      }
+    }
+
+    if (IsDef)
+      continue;
+
+    Regs[FoundRegs++] = Candidate;
+    if (FoundRegs == (unsigned)NumPops)
+      break;
+  }
+
+  if (FoundRegs == 0)
+    return false;
+
+  // If we found only one free register, but need two, reuse the same one twice.
+  while (FoundRegs < (unsigned)NumPops)
+    Regs[FoundRegs++] = Regs[0];
+
+  for (int i = 0; i < NumPops; ++i)
+    BuildMI(MBB, MBBI, DL, 
+            TII.get(STI.is64Bit() ? X86::POP64r : X86::POP32r), Regs[i]);
+
+  return true;
+}
+
 void X86FrameLowering::
 eliminateCallFramePseudoInstr(MachineFunction &MF, MachineBasicBlock &MBB,
                               MachineBasicBlock::iterator I) const {
@@ -1882,8 +1945,12 @@ eliminateCallFramePseudoInstr(MachineFunction &MF, MachineBasicBlock &MBB,
     if (Amount) {
       // Add Amount to SP to destroy a frame, and subtract to setup.
       int Offset = isDestroy ? Amount : -Amount;
-      BuildStackAdjustment(MBB, I, DL, Offset, /*InEpilogue=*/false);
+
+      if (!(MF.getFunction()->optForMinSize() && 
+            adjustStackWithPops(MBB, I, DL, Offset)))
+        BuildStackAdjustment(MBB, I, DL, Offset, /*InEpilogue=*/false);
     }
+
     return;
   }
 

diff --git a/lib/Target/X86/X86FrameLowering.h b/lib/Target/X86/X86FrameLowering.h
index 495cfcd1c3f78abdeb688364e466d33acfcfae42..b74fcf46169a7828c1819a37034aff750bbff740 100644 (file)
--- a/lib/Target/X86/X86FrameLowering.h
+++ b/lib/Target/X86/X86FrameLowering.h
@@ -146,6 +146,11 @@ private:
                           MachineBasicBlock::iterator MBBI, DebugLoc DL,
                           uint64_t MaxAlign) const;
 
+  /// Make small positive stack adjustments using POPs.
+  bool adjustStackWithPops(MachineBasicBlock &MBB,
+                           MachineBasicBlock::iterator MBBI, DebugLoc DL,
+                           int Offset) const;
+
   /// Adjusts the stack pointer using LEA, SUB, or ADD.
   MachineInstrBuilder BuildStackAdjustment(MachineBasicBlock &MBB,
                                            MachineBasicBlock::iterator MBBI,

diff --git a/test/CodeGen/X86/fold-push.ll b/test/CodeGen/X86/fold-push.ll
index f5f33321c139da6d1f88e371e92c5adf1d5ccd7c..cb4e435e35c1b9778fa82dc31deb7bf8768ab928 100644 (file)
--- a/test/CodeGen/X86/fold-push.ll
+++ b/test/CodeGen/X86/fold-push.ll
@@ -27,11 +27,11 @@ define void @test_min(i32 %a, i32 %b) minsize {
 ; CHECK: movl [[EAX:%e..]], (%esp)
 ; CHECK-NEXT: pushl [[EAX]]
 ; CHECK-NEXT: calll
-; CHECK-NEXT: addl $4, %esp
+; CHECK-NEXT: popl
 ; CHECK: nop
 ; CHECK: pushl (%esp)
 ; CHECK: calll
-; CHECK-NEXT: addl $4, %esp
+; CHECK-NEXT: popl
   %c = add i32 %a, %b
   call void @foo(i32 %c)
   call void asm sideeffect "nop", "~{ax},~{bx},~{cx},~{dx},~{bp},~{si},~{di}"()

diff --git a/test/CodeGen/X86/pop-stack-cleanup.ll b/test/CodeGen/X86/pop-stack-cleanup.ll
new file mode 100644 (file)
index 0000000..c6fb2d8
--- /dev/null
+++ b/test/CodeGen/X86/pop-stack-cleanup.ll
@@ -0,0 +1,61 @@
+; RUN: llc < %s -mtriple=i686-windows | FileCheck %s -check-prefix=CHECK -check-prefix=NORMAL
+
+declare void @param1(i32 %a)
+declare i32 @param2_ret(i32 %a, i32 %b)
+declare i64 @param2_ret64(i32 %a, i32 %b)
+declare void @param2(i32 %a, i32 %b)
+declare void @param3(i32 %a, i32 %b, i32 %c)
+
+define void @test() minsize {
+; CHECK-LABEL: test:
+; CHECK: calll _param1
+; CHECK-NEXT: popl %eax
+; CHECK: calll _param2
+; CHECK-NEXT: popl %eax
+; CHECK-NEXT: popl %ecx
+; CHECK: calll _param2_ret
+; CHECK-NEXT: popl %ecx
+; CHECK-NEXT: popl %edx
+; CHECK-NEXT: pushl %eax
+; CHECK: calll _param3
+; CHECK-NEXT: addl $12, %esp
+; CHECK: calll _param2_ret64
+; CHECK-NEXT: popl %ecx
+; CHECK-NEXT: popl %ecx
+  call void @param1(i32 1)
+  call void @param2(i32 1, i32 2)
+  %ret = call i32 @param2_ret(i32 1, i32 2)
+  call void @param3(i32 1, i32 2, i32 %ret)
+  %ret64 = call i64 @param2_ret64(i32 1, i32 2)  
+  ret void
+}
+
+define void @negative(i32 %k) {
+; CHECK-LABEL: negative:
+; CHECK: calll _param1
+; CHECK-NEXT: addl $4, %esp
+; CHECK: calll _param2
+; CHECK-NEXT: addl $8, %esp
+; CHECK: calll _param3
+; CHECK-NEXT: movl %ebp, %esp
+  %v = alloca i32, i32 %k
+  call void @param1(i32 1)
+  call void @param2(i32 1, i32 2)
+  call void @param3(i32 1, i32 2, i32 3)
+  ret void
+}
+
+define void @spill(i32 inreg %a, i32 inreg %b, i32 inreg %c) minsize {
+; CHECK-LABEL: spill:
+; CHECK-DAG: movl %ecx,
+; CHECK-DAG: movl %edx,
+; CHECK: calll _param2_ret
+; CHECK-NEXT: popl %ecx
+; CHECK-NEXT: popl %edx
+; CHECK-DAG: movl {{.*}}, %ecx
+; CHECK-DAG: movl {{.*}}, %edx
+; CHECK: calll _spill
+  %i = call i32 @param2_ret(i32 1, i32 2)
+  call void @spill(i32 %a, i32 %b, i32 %c)
+  ret void
+}