使用单个 divl 指令进行除法和模数(i386、amd64)

发布于 2024-10-31 03:20:53 字数 87 浏览 4 评论 0原文

我试图为 gcc 提供内联汇编,以使用单个 divl 指令获得除法和模数。不幸的是,我不太擅长组装。有人可以帮我解决这个问题吗?谢谢。

I was trying to come up with inline assembly for gcc to get both division and modulus using single divl instruction. Unfortunately, I am not that good at assembly. Could someone please help me on this? Thank you.

如果你对这篇内容有疑问,欢迎到本站社区发帖提问 参与讨论,获取更多帮助,或者扫码二维码加入 Web 技术交流群。

扫码二维码加入Web技术交流群

发布评论

需要 登录 才能够评论, 你可以免费 注册 一个本站的账号。

评论(5

做个少女永远怀春 2024-11-07 03:20:53

你正在寻找这样的东西:

__asm__("divl %2\n"
       : "=d" (remainder), "=a" (quotient)
       : "g" (modulus), "d" (high), "a" (low));

虽然我同意其他评论者的观点,通常 GCC 会为你做这件事,并且你应该尽可能避免内联汇编,但有时你需要这种构造。

例如,如果高位字小于模数,则可以安全地执行这样的除法。然而,GCC 还不够聪明,无法意识到这一点,因为在一般情况下,将 64 位数字除以 32 位数字可能会导致溢出,因此它会调用库例程来完成额外的工作。 (对于 64 位 ISA,替换为 128 位/64 位。)

You're looking for something like this:

__asm__("divl %2\n"
       : "=d" (remainder), "=a" (quotient)
       : "g" (modulus), "d" (high), "a" (low));

Although I agree with the other commenters that usually GCC will do this for you and you should avoid inline assembly when possible, sometimes you need this construct.

For instance, if the high word is less than the modulus, then it is safe to perform the division like this. However, GCC isn't smart enough to realize this, because in the general case dividing a 64 bit number by a 32 bit number can lead to overflow, and so it calls to a library routine to do extra work. (Replace with 128 bit/64 bit for 64 bit ISAs.)

许仙没带伞 2024-11-07 03:20:53

您不应该尝试自己优化它。 GCC 已经这样做了。

volatile int some_a = 18, some_b = 7;

int main(int argc, char *argv[]) {
    int a = some_a, b = some_b;
    printf("%d %d\n", a / b, a % b);
    return 0;
}

运行

gcc -S test.c -O

产生结果

main:
.LFB11:
    .cfi_startproc
    subq    $8, %rsp
    .cfi_def_cfa_offset 16
    movl    some_a(%rip), %esi
    movl    some_b(%rip), %ecx
    movl    %esi, %eax
    movl    %esi, %edx
    sarl    $31, %edx
    idivl   %ecx
    movl    %eax, %esi
    movl    $.LC0, %edi
    movl    $0, %eax
    call    printf
    movl    $0, %eax
    addq    $8, %rsp
    .cfi_def_cfa_offset 8
    ret

请注意,余数 %edx 没有移动,因为它也是传递给 printf 的第三个参数。

编辑:32 位版本不太混乱。传递 -m32 产量

main:
    pushl   %ebp
    movl    %esp, %ebp
    andl    $-16, %esp
    subl    $16, %esp
    movl    some_a, %eax
    movl    some_b, %ecx
    movl    %eax, %edx
    sarl    $31, %edx
    idivl   %ecx
    movl    %edx, 8(%esp)
    movl    %eax, 4(%esp)
    movl    $.LC0, (%esp)
    call    printf
    movl    $0, %eax
    leave
    ret

You shouldn't try to optimize this yourself. GCC already does this.

volatile int some_a = 18, some_b = 7;

int main(int argc, char *argv[]) {
    int a = some_a, b = some_b;
    printf("%d %d\n", a / b, a % b);
    return 0;
}

Running

gcc -S test.c -O

yields

main:
.LFB11:
    .cfi_startproc
    subq    $8, %rsp
    .cfi_def_cfa_offset 16
    movl    some_a(%rip), %esi
    movl    some_b(%rip), %ecx
    movl    %esi, %eax
    movl    %esi, %edx
    sarl    $31, %edx
    idivl   %ecx
    movl    %eax, %esi
    movl    $.LC0, %edi
    movl    $0, %eax
    call    printf
    movl    $0, %eax
    addq    $8, %rsp
    .cfi_def_cfa_offset 8
    ret

Notice that the remainder, %edx, is not moved because it is also the third argument passed to printf.

EDIT: The 32-bit version is less confusing. Passing -m32 yields

main:
    pushl   %ebp
    movl    %esp, %ebp
    andl    $-16, %esp
    subl    $16, %esp
    movl    some_a, %eax
    movl    some_b, %ecx
    movl    %eax, %edx
    sarl    $31, %edx
    idivl   %ecx
    movl    %edx, 8(%esp)
    movl    %eax, 4(%esp)
    movl    $.LC0, (%esp)
    call    printf
    movl    $0, %eax
    leave
    ret
我的鱼塘能养鲲 2024-11-07 03:20:53

幸运的是,您不必借助内联汇编来实现此目的。 gcc 会在可能的情况下自动执行此操作。

$ cat divmod.c

struct sdiv { unsigned long quot; unsigned long rem; };

struct sdiv divide( unsigned long num, unsigned long divisor )
{
        struct sdiv x = { num / divisor, num % divisor };
        return x;
}

$ gcc -O3 -std=c99 -Wall -Wextra -pedantic -S divmod.c -o -

        .file   "divmod.c"
        .text
        .p2align 4,,15
.globl divide
        .type   divide, @function
divide:
.LFB0:
        .cfi_startproc
        movq    %rdi, %rax
        xorl    %edx, %edx
        divq    %rsi
        ret
        .cfi_endproc
.LFE0:
        .size   divide, .-divide
        .ident  "GCC: (GNU) 4.4.4 20100630 (Red Hat 4.4.4-10)"
        .section        .note.GNU-stack,"",@progbits

Fortunately, you don't have to resort to inline assembly to achieve this. gcc will do this automatically when it can.

$ cat divmod.c

struct sdiv { unsigned long quot; unsigned long rem; };

struct sdiv divide( unsigned long num, unsigned long divisor )
{
        struct sdiv x = { num / divisor, num % divisor };
        return x;
}

$ gcc -O3 -std=c99 -Wall -Wextra -pedantic -S divmod.c -o -

        .file   "divmod.c"
        .text
        .p2align 4,,15
.globl divide
        .type   divide, @function
divide:
.LFB0:
        .cfi_startproc
        movq    %rdi, %rax
        xorl    %edx, %edx
        divq    %rsi
        ret
        .cfi_endproc
.LFE0:
        .size   divide, .-divide
        .ident  "GCC: (GNU) 4.4.4 20100630 (Red Hat 4.4.4-10)"
        .section        .note.GNU-stack,"",@progbits
咋地 2024-11-07 03:20:53

是的——divl 将在 eax 中产生商,在 edx 中产生余数。使用 Intel 语法,例如:

mov eax, 17
mov ebx, 3
xor edx, edx
div ebx
; eax = 5
; edx = 2

Yes -- a divl will produce the quotient in eax and the remainder in edx. Using Intel syntax, for example:

mov eax, 17
mov ebx, 3
xor edx, edx
div ebx
; eax = 5
; edx = 2
蓝颜夕 2024-11-07 03:20:53

这是Linux内核代码中关于divl的示例

    /*
 * do_div() is NOT a C function. It wants to return
 * two values (the quotient and the remainder), but
 * since that doesn't work very well in C, what it
 * does is:
 *
 * - modifies the 64-bit dividend _in_place_
 * - returns the 32-bit remainder
 *
 * This ends up being the most efficient "calling
 * convention" on x86.
 */
#define do_div(n, base)                     \
({                              \
    unsigned long __upper, __low, __high, __mod, __base;    \
    __base = (base);                    \
    if (__builtin_constant_p(__base) && is_power_of_2(__base)) { \
        __mod = n & (__base - 1);           \
        n >>= ilog2(__base);                \
    } else {                        \
        asm("" : "=a" (__low), "=d" (__high) : "A" (n));\
        __upper = __high;               \
        if (__high) {                   \
            __upper = __high % (__base);        \
            __high = __high / (__base);     \
        }                       \
        asm("divl %2" : "=a" (__low), "=d" (__mod)  \
            : "rm" (__base), "0" (__low), "1" (__upper));   \
        asm("" : "=A" (n) : "a" (__low), "d" (__high)); \
    }                           \
    __mod;                          \
})

Here is an example in linux kernel code about divl

    /*
 * do_div() is NOT a C function. It wants to return
 * two values (the quotient and the remainder), but
 * since that doesn't work very well in C, what it
 * does is:
 *
 * - modifies the 64-bit dividend _in_place_
 * - returns the 32-bit remainder
 *
 * This ends up being the most efficient "calling
 * convention" on x86.
 */
#define do_div(n, base)                     \
({                              \
    unsigned long __upper, __low, __high, __mod, __base;    \
    __base = (base);                    \
    if (__builtin_constant_p(__base) && is_power_of_2(__base)) { \
        __mod = n & (__base - 1);           \
        n >>= ilog2(__base);                \
    } else {                        \
        asm("" : "=a" (__low), "=d" (__high) : "A" (n));\
        __upper = __high;               \
        if (__high) {                   \
            __upper = __high % (__base);        \
            __high = __high / (__base);     \
        }                       \
        asm("divl %2" : "=a" (__low), "=d" (__mod)  \
            : "rm" (__base), "0" (__low), "1" (__upper));   \
        asm("" : "=A" (n) : "a" (__low), "d" (__high)); \
    }                           \
    __mod;                          \
})
~没有更多了~
我们使用 Cookies 和其他技术来定制您的体验包括您的登录状态等。通过阅读我们的 隐私政策 了解更多相关信息。 单击 接受 或继续使用网站,即表示您同意使用 Cookies 和您的相关数据。
原文