79806998

Date: 2025-11-02 07:52:57
Score: 0.5
Natty:
Report link

@John Bollinger

It is also very meaningful in the case of structures or arrays. In Windows, there is a type of programming called COM, and the well-known graphics API DirectX3D also uses COM. COM objects are generally called in this way.

typedef struct {
    void (*func1)();
    void (*func2)();
    void (*func3)();
    void (*func4)();
    void (*func5)();
} i_ibject_vtable;

typedef struct {
    i_ibject_vtable *vtable;
} i_object;

int object_create(i_object **);

int entry() {
    i_object *p_object;

    object_create(&p_object);
    
    p_object->vtable->func1();
    p_object->vtable->func2();
    p_object->vtable->func3();
    p_object->vtable->func4();
    p_object->vtable->func5();

    return 0;
}

        .file   "example.c"
# GNU C23 (Compiler-Explorer-Build-gcc--binutils-2.44) version 15.2.0 (x86_64-linux-gnu)
#       compiled by GNU C version 11.4.0, GMP version 6.2.1, MPFR version 4.1.0, MPC version 1.2.1, isl version isl-0.24-GMP

# GGC heuristics: --param ggc-min-expand=100 --param ggc-min-heapsize=131072
# options passed: -mtune=generic -march=x86-64 -g -g0 -Ofast -fno-asynchronous-unwind-tables
        .text
        .p2align 4
        .globl  entry
        .type   entry, @function
entry:
        subq    $24, %rsp       #,
# /app/example.c:18:     object_create(&p_object);
        leaq    8(%rsp), %rdi   #, tmp114
        call    object_create   #
# /app/example.c:20:     p_object->vtable->func1();
        movq    8(%rsp), %rax   # p_object, p_object
# /app/example.c:20:     p_object->vtable->func1();
        movq    (%rax), %rax    # p_object.0_1->vtable, p_object.0_1->vtable
# /app/example.c:20:     p_object->vtable->func1();
        call    *(%rax) # _2->func1
# /app/example.c:21:     p_object->vtable->func2();
        movq    8(%rsp), %rax   # p_object, p_object
# /app/example.c:21:     p_object->vtable->func2();
        movq    (%rax), %rax    # p_object.1_4->vtable, p_object.1_4->vtable
# /app/example.c:21:     p_object->vtable->func2();
        call    *8(%rax)        # _5->func2
# /app/example.c:22:     p_object->vtable->func3();
        movq    8(%rsp), %rax   # p_object, p_object
# /app/example.c:22:     p_object->vtable->func3();
        movq    (%rax), %rax    # p_object.2_7->vtable, p_object.2_7->vtable
# /app/example.c:22:     p_object->vtable->func3();
        call    *16(%rax)       # _8->func3
# /app/example.c:23:     p_object->vtable->func4();
        movq    8(%rsp), %rax   # p_object, p_object
# /app/example.c:23:     p_object->vtable->func4();
        movq    (%rax), %rax    # p_object.3_10->vtable, p_object.3_10->vtable
# /app/example.c:23:     p_object->vtable->func4();
        call    *24(%rax)       # _11->func4
# /app/example.c:24:     p_object->vtable->func5();
        movq    8(%rsp), %rax   # p_object, p_object
# /app/example.c:24:     p_object->vtable->func5();
        movq    (%rax), %rax    # p_object.4_13->vtable, p_object.4_13->vtable
# /app/example.c:24:     p_object->vtable->func5();
        call    *32(%rax)       # _14->func5
# /app/example.c:27: }
        xorl    %eax, %eax      #
        addq    $24, %rsp       #,
        ret     
        .size   entry, .-entry
        .ident  "GCC: (Compiler-Explorer-Build-gcc--binutils-2.44) 15.2.0"
        .section        .note.GNU-stack,"",@progbits

Manually saving these function pointers results in negative optimization

typedef struct {
    void (*func1)();
    void (*func2)();
    void (*func3)();
    void (*func4)();
    void (*func5)();
} i_ibject_vtable;

typedef struct {
    i_ibject_vtable *vtable;
} i_object;

int object_create(i_object **);

int entry() {
    i_object *p_object;

    object_create(&p_object);

    i_ibject_vtable vtable;
    __builtin_memcpy(&vtable, p_object->vtable, sizeof(vtable));

    vtable.func1();
    vtable.func2();
    vtable.func3();
    vtable.func4();
    vtable.func5();

    return 0;
}

        .file   "example.c"
# GNU C23 (Compiler-Explorer-Build-gcc--binutils-2.44) version 15.2.0 (x86_64-linux-gnu)
#       compiled by GNU C version 11.4.0, GMP version 6.2.1, MPFR version 4.1.0, MPC version 1.2.1, isl version isl-0.24-GMP

# GGC heuristics: --param ggc-min-expand=100 --param ggc-min-heapsize=131072
# options passed: -mtune=generic -march=x86-64 -g -g0 -Ofast -fno-asynchronous-unwind-tables
        .text
        .p2align 4
        .globl  entry
        .type   entry, @function
entry:
        subq    $72, %rsp       #,
# /app/example.c:18:     object_create(&p_object);
        leaq    8(%rsp), %rdi   #, tmp106
        call    object_create   #
# /app/example.c:21:     __builtin_memcpy(&vtable, p_object->vtable, sizeof(vtable));
        movq    8(%rsp), %rax   # p_object, p_object
# /app/example.c:21:     __builtin_memcpy(&vtable, p_object->vtable, sizeof(vtable));
        movq    (%rax), %rax    # p_object.0_1->vtable, p_object.0_1->vtable
        movdqu  (%rax), %xmm0       # MEM <char[1:40]> [(void *)_2], MEM <char[1:40]> [(void *)_2]
        movq    %xmm0, %rdx     # MEM <char[1:40]> [(void *)_2], tmp119
        movaps  %xmm0, 16(%rsp)     # MEM <char[1:40]> [(void *)_2], MEM <char[1:40]> [(void *)&vtable]
        movdqu  16(%rax), %xmm0     # MEM <char[1:40]> [(void *)_2], MEM <char[1:40]> [(void *)_2]
        movq    32(%rax), %rax  # MEM <char[1:40]> [(void *)_2], MEM <char[1:40]> [(void *)_2]
        movaps  %xmm0, 32(%rsp)     # MEM <char[1:40]> [(void *)_2], MEM <char[1:40]> [(void *)&vtable]
        movq    %rax, 48(%rsp)  # MEM <char[1:40]> [(void *)_2], MEM <char[1:40]> [(void *)&vtable]
# /app/example.c:23:     vtable.func1();
        call    *%rdx   # tmp119
# /app/example.c:24:     vtable.func2();
        call    *24(%rsp)       # vtable.func2
# /app/example.c:25:     vtable.func3();
        call    *32(%rsp)       # vtable.func3
# /app/example.c:26:     vtable.func4();
        call    *40(%rsp)       # vtable.func4
# /app/example.c:27:     vtable.func5();
        call    *48(%rsp)       # vtable.func5
# /app/example.c:30: }
        xorl    %eax, %eax      #
        addq    $72, %rsp       #,
        ret     
        .size   entry, .-entry
        .ident  "GCC: (Compiler-Explorer-Build-gcc--binutils-2.44) 15.2.0"
        .section        .note.GNU-stack,"",@progbits

I also can't do this for every object. Once the compiler knows that i_object_vtable will not be constantly changed, it is able to optimize it.

typedef struct {
    void (*func1)();
    void (*func2)();
    void (*func3)();
    void (*func4)();
    void (*func5)();
} i_ibject_vtable;

typedef struct {
    i_ibject_vtable *vtable;
} i_object;

__attribute__((malloc)) i_object *object_create();

int entry() {
    i_object *p_object;

    p_object = object_create();

    p_object->vtable->func1();
    p_object->vtable->func2();
    p_object->vtable->func3();
    p_object->vtable->func4();
    p_object->vtable->func5();

    // Saved the pointer into the register
    p_object->vtable->func1();
    p_object->vtable->func1();
    p_object->vtable->func1();

    return 0;
}

        .file   "example.c"
# GNU C23 (Compiler-Explorer-Build-gcc--binutils-2.44) version 15.2.0 (x86_64-linux-gnu)
#       compiled by GNU C version 11.4.0, GMP version 6.2.1, MPFR version 4.1.0, MPC version 1.2.1, isl version isl-0.24-GMP

# GGC heuristics: --param ggc-min-expand=100 --param ggc-min-heapsize=131072
# options passed: -mtune=generic -march=x86-64 -g -g0 -Ofast -fno-asynchronous-unwind-tables
        .text
        .p2align 4
        .globl  entry
        .type   entry, @function
entry:
        pushq   %rbx  #
# /app/example.c:18:     p_object = object_create();
        call    object_create   #
# /app/example.c:20:     p_object->vtable->func1();
        movq    (%rax), %rbx    # p_object_12->vtable, _1
# /app/example.c:20:     p_object->vtable->func1();
        call    *(%rbx) # _1->func1
# /app/example.c:21:     p_object->vtable->func2();
        call    *8(%rbx)        # _1->func2
# /app/example.c:22:     p_object->vtable->func3();
        call    *16(%rbx)       # _1->func3
# /app/example.c:23:     p_object->vtable->func4();
        call    *24(%rbx)       # _1->func4
# /app/example.c:24:     p_object->vtable->func5();
        call    *32(%rbx)       # _1->func5
# /app/example.c:27:     p_object->vtable->func1();
        call    *(%rbx) # _1->func1
# /app/example.c:28:     p_object->vtable->func1();
        call    *(%rbx) # _1->func1
# /app/example.c:29:     p_object->vtable->func1();
        call    *(%rbx) # _1->func1
# /app/example.c:32: }
        xorl    %eax, %eax      #
        popq    %rbx    #
        ret     
        .size   entry, .-entry
        .ident  "GCC: (Compiler-Explorer-Build-gcc--binutils-2.44) 15.2.0"
        .section        .note.GNU-stack,"",@progbits

Unfortunately, most APIs return error codes instead of pointers, making it impossible to use __attribute__.

Reasons:
  • Long answer (-1):
  • Has code block (-0.5):
  • User mentioned (1): @John
  • Self-answer (0.5):
  • Low reputation (0.5):
Posted by: Moi5t