我试图看看我是否可以在我的64位机器上优化memset.根据我的理解,memset逐字节地设置并设置值.我假设如果我以64位为单位,它会更快.但不知何故需要更多时间.有人可以看看我的代码并提出原因吗？

/* Code */
#include <stdio.h>
#include <time.h>
#include <stdint.h>
#include <string.h>

void memset8(unsigned char *dest,unsigned char val,uint32_t count)
{
    while (count--)
        *dest++ = val;
}
void memset32(uint32_t *dest,uint32_t val,uint32_t count)
{
    while (count--)
        *dest++ = val;
}
void
memset64(uint64_t *dest,uint64_t val,uint32_t count)
{
    while (count--)
        *dest++ = val;
}
#define CYCLES 1000000000
int main()
{
    clock_t start,end;
    double total;
    uint64_t loop;
    uint64_t val;

    /* memset 32 */
    start = clock();
    for (loop = 0; loop < CYCLES; loop++) {
        val = 0xDEADBEEFDEADBEEF;
        memset32((uint32_t*)&val,2);
    }
    end = clock();
    total = (double)(end-start)/CLOCKS_PER_SEC;
    printf("TiMetaken memset32 %g\n",total);

    /* memset 64 */
    start = clock();
    for (loop = 0; loop < CYCLES; loop++) {
        val = 0xDEADBEEFDEADBEEF;
        memset64(&val,1);
    }
    end = clock();
    total = (double)(end-start)/CLOCKS_PER_SEC;
    printf("TiMetaken memset64 %g\n",total);

    /* memset 8 */
    start = clock();
    for (loop = 0; loop < CYCLES; loop++) {
        val = 0xDEADBEEFDEADBEEF;
        memset8((unsigned char*)&val,8);
    }
    end = clock();
    total = (double)(end-start)/CLOCKS_PER_SEC;
    printf("TiMetaken memset8 %g\n",total);

    /* memset */
    start = clock();
    for (loop = 0; loop < CYCLES; loop++) {
        val = 0xDEADBEEFDEADBEEF;
        memset(&val,8);
    }
    end = clock();
    total = (double)(end-start)/CLOCKS_PER_SEC;
    printf("TiMetaken memset %g\n",total);

    printf("-----------------------------------------\n");
}

/*Result*/
TiMetaken memset32 12.46
TiMetaken memset64 7.57
TiMetaken memset8 37.12
TiMetaken memset 6.03
-----------------------------------------

看起来标准的memset比我的实现更优化.
我试着查看代码,到处都看到memset的实现与我为memset8所做的相同.当我使用memset8时,结果更像我期望的并且与memset非常不同.
有人可以建议我做错了什么吗？