c - 将两个 64 位整数乘以 128 位然后 >> 乘以 64 位的最快方法？

Question

<分区>

Answer 1

正如该问题的评论者所指出的，这最容易通过依赖于机器的代码而不是通过可移植代码高效地完成。提问者指出主要平台是 x86_64，并且有一个内置指令用于执行 64 ✕ 64 → 128 位乘法。使用一小段内联汇编很容易访问。请注意，内联汇编的细节可能因编译器而有所不同，以下代码是使用英特尔 C/C++ 编译器构建的。

#include <stdint.h>

/* compute mul_wide (a, b) >> s, for s in [0,63] */
int64_t mulshift (int64_t a, int64_t b, int s)
{
    int64_t res;
    __asm__ (
        "movq  %1, %%rax;\n\t"          // rax = a
        "movl  %3, %%ecx;\n\t"          // ecx = s
        "imulq %2;\n\t"                 // rdx:rax = a * b
        "shrdq %%cl, %%rdx, %%rax;\n\t" // rax = int64_t (rdx:rax >> s)
        "movq  %%rax, %0;\n\t"          // res = rax
        : "=rm" (res)
        : "rm"(a), "rm"(b), "rm"(s)
        : "%rax", "%rdx", "%ecx");
    return res;
}

与上述代码等效的可移植 C99 如下所示。我已经针对内联汇编版本对此进行了广泛的测试，没有发现不匹配的情况。

void umul64wide (uint64_t a, uint64_t b, uint64_t *hi, uint64_t *lo)
{
    uint64_t a_lo = (uint64_t)(uint32_t)a;
    uint64_t a_hi = a >> 32;
    uint64_t b_lo = (uint64_t)(uint32_t)b;
    uint64_t b_hi = b >> 32;

    uint64_t p0 = a_lo * b_lo;
    uint64_t p1 = a_lo * b_hi;
    uint64_t p2 = a_hi * b_lo;
    uint64_t p3 = a_hi * b_hi;

    uint32_t cy = (uint32_t)(((p0 >> 32) + (uint32_t)p1 + (uint32_t)p2) >> 32);

    *lo = p0 + (p1 << 32) + (p2 << 32);
    *hi = p3 + (p1 >> 32) + (p2 >> 32) + cy;
}

void mul64wide (int64_t a, int64_t b, int64_t *hi, int64_t *lo)
{
    umul64wide ((uint64_t)a, (uint64_t)b, (uint64_t *)hi, (uint64_t *)lo);
    if (a < 0LL) *hi -= b;
    if (b < 0LL) *hi -= a;
}

/* compute mul_wide (a, b) >> s, for s in [0,63] */
int64_t mulshift (int64_t a, int64_t b, int s)
{
    int64_t res;
    int64_t hi, lo;
    mul64wide (a, b, &hi, &lo);
    if (s) {
        res = ((uint64_t)hi << (64 - s)) | ((uint64_t)lo >> s);
    } else {
        res = lo;
    }
    return res;
}