[Bug middle-end/49035] Avoid setting up stack frame for short, hot code paths

[scovich at gmail dot com]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=49035

--- Comment #1 from Ryan Johnson <scovich at gmail dot com> 2011-05-18 02:56:23 UTC ---
Update: using __attribute__((noinline)) it is actually possible to force the
compiler to do the right thing, though it makes the code significantly less
readable:

=== example.cpp ============
struct link {
    link* prev;
    long go_slow;
    void frob(link* parent, link* grandparent);
};

link* __attribute__((noinline)) foo_slow(link* list, link* prev) {
    do {
        link* pprev = __sync_lock_test_and_set(&prev->prev, 0);
        pprev->frob(prev, list);
        prev = pprev;
    } while(__builtin_expect(prev->go_slow, 0));
    return prev;
}

link* foo_fast(link* list) {
    link* prev = list->prev;
    if (__builtin_expect(prev->go_slow, 0))
        return foo_slow(list, prev);
    return prev;
}
=== example.cpp ============

The above compiles down to something much better, though the calling convention
requires an extra movq and there are more jumps than required (the compiler
probably doesn't ever perform tail recursion using a conditional jump):

_Z8foo_fastP4link:
        movq    (%rdi), %rax
        cmpq    $0, 8(%rax)
        jne     .L7
        rep
        ret
.L7:
        movq    %rax, %rsi
        jmp     _Z8foo_slowP4linkS0_

_Z8foo_slowP4linkS0_:
        movq    %rbp, -16(%rsp)
        movq    %r12, -8(%rsp)
        xorl    %ebp, %ebp
        movq    %rbx, -24(%rsp)
        movq    %rdi, %r12
        subq    $24, %rsp
.L2:
        movq    %rbp, %rbx
        xchgq   (%rsi), %rbx
        movq    %r12, %rdx
        movq    %rbx, %rdi
        call    _ZN4link4frobEPS_S0_
        cmpq    $0, 8(%rbx)
        jne     .L3
        movq    %rbx, %rax
        movq    8(%rsp), %rbp
        movq    (%rsp), %rbx
        movq    16(%rsp), %r12
        addq    $24, %rsp
        ret
.L3:
        movq    %rbx, %rsi
        jmp     .L2