为什么GCC没有优化这个尾调用？

Question

I have the code working with lined lists. I use tail calls . Unfortunately, GCC does not optimise the calls.

Here is C code of the function that recursively calculates length of the linked list:

size_t ll_length(const ll_t* list) {
    return ll_length_rec(list, 0);
}

size_t ll_length_rec(const ll_t* list, size_t size_so_far)
{
    if (list)   {
        return ll_length_rec(list->next, size_so_far + 1);
    } else {
        return size_so_far;
    }
}

and here is the assembler code:

.globl _ll_length_rec
_ll_length_rec:
LFB8:
    .loc 1 47 0
    pushq   %rbp
LCFI6:
    movq    %rsp, %rbp
LCFI7:
    subq    $32, %rsp
LCFI8:
    movq    %rdi, -8(%rbp)
    movq    %rsi, -16(%rbp)
    .loc 1 48 0
    cmpq    $0, -8(%rbp)
    je  L8
    .loc 1 49 0
    movq    -16(%rbp), %rsi
    incq    %rsi
    movq    -8(%rbp), %rax
    movq    8(%rax), %rdi
    call    _ll_length_rec  # < THIS SHOUD BE OPTIMIZED
    movq    %rax, -24(%rbp)
    jmp L10

If GCC would optimize it, there would be no call in the asm. I compile it with:

gcc  -S -fnested-functions -foptimize-sibling-calls \
    -03 -g -Wall -o llist llist.c

and GCC version is:

i686-apple-darwin10-gcc-4.2.1 (GCC) 4.2.1 (Apple Inc. build 5666) (dot 3)

Answer 1

If I add -O3 to your compilation line, it does not seem to generate the offending call, while without it, I get the unoptimised call. I don't know all gcc options in my head, but is -03 a typo for -O3 or intentional?

Ltmp2:
        pushq   %rbp
Ltmp0:
        movq    %rsp, %rbp
Ltmp1:
        jmp     LBB1_1
        .align  4, 0x90
LBB1_3:
        addq    $2, %rsi
Ltmp3:
        movq    (%rax), %rdi
Ltmp4:
LBB1_1:
Ltmp5:
        testq   %rdi, %rdi
        je      LBB1_5
Ltmp6:
        movq    (%rdi), %rax
        testq   %rax, %rax
        jne     LBB1_3
        incq    %rsi
LBB1_5:
        movq    %rsi, %rax
Ltmp7:
Ltmp8:
        popq    %rbp
        ret

Answer 2

Most likely because neither of your functions are declared as static , which means that the symbols must be visible to the linker in case any other compilation units need them at link time. Try to compile with the -fwhole-program flag and see what happens.

Answer 3

Probably depends on the version of GCC and specific build. This is what I get from GCC 3.4.4 on Windows starting from -O2 and up

.globl _ll_length_rec
    .def    _ll_length_rec; .scl    2;  .type   32; .endef
_ll_length_rec:
    pushl   %ebp
    movl    %esp, %ebp
    movl    8(%ebp), %edx
    movl    12(%ebp), %eax
    jmp L3
    .p2align 4,,7
L6:
    movl    (%edx), %edx
    incl    %eax
L3:
    testl   %edx, %edx
    jne L6
    popl    %ebp
    ret