[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

llvm-svn: 244578

2 files changed, 63 insertions, 2 deletions

diff --git a/llvm/test/CodeGen/X86/fold-push.ll b/llvm/test/CodeGen/X86/fold-push.ll
index f5f33321c13..cb4e435e35c 100644
--- a/llvm/test/CodeGen/X86/fold-push.ll
+++ b/llvm/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/llvm/test/CodeGen/X86/pop-stack-cleanup.ll b/llvm/test/CodeGen/X86/pop-stack-cleanup.ll
new file mode 100644
index 00000000000..c6fb2d8885b
--- /dev/null
+++ b/llvm/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
+}