我问是否mov指令，需要计算该地址，即（在at&t语法
mov i(r, r, i), reg或mov reg, i(r, reg, i)
必须在端口1上执行，因为它们实际上是具有3个操作数+ MOV的莱亚，或者它们可以在端口0156上自由执行。
如果它们确实在端口1上执行莱亚部分，那么一旦地址计算完成，端口1将被解除阻塞，还是整个存储器加载需要首先完成。
在ICL上似乎p7可以做索引地址模式？

#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>

#define BENCH_ATTR __attribute__((noinline, noclone, aligned(4096)))

#define TERMS 3

void BENCH_ATTR
test_store_port() {
    const uint32_t N = (1 << 29);

    uint64_t dst, loop_cnt;
    uint64_t src[16] __attribute__((aligned(64)));

    asm volatile(
        "movl %[N], %k[loop_cnt]\n\t"
        ".p2align 5\n\t"
        "1:\n\t"

        "movl %k[loop_cnt], %k[dst]\n\t"
        "andl $15, %k[dst]\n\t"
#if TERMS == 3
        "movl %k[dst], (%[src], %[dst], 4)\n\t"
#else
        "movl %k[dst], (%[src])\n\t"
#endif

        "decl %k[loop_cnt]\n\t"
        "jnz 1b\n\t"
        : [ dst ] "+r"(dst), [ loop_cnt ] "+r"(loop_cnt)
        : [ N ] "i"(N), [ src ] "r"(src), "m"(*((const uint32_t(*)[16])src))
        : "cc");
}

int
main(int argc, char ** argv) {
    test_store_port();
}

字符串
使用#define TERMS 3的结果：

perf stat -e uops_dispatched.port_2_3 -e uops_dispatched.port_7_8 -e uops_issued.any -e cpu-cycles ./bsf_dep

 Performance counter stats for './bsf_dep':

           297,191      uops_dispatched.port_2_3                                    
       537,039,830      uops_dispatched.port_7_8                                    
     2,149,098,661      uops_issued.any                                             
       761,661,276      cpu-cycles                                                  

       0.210463841 seconds time elapsed

       0.210366000 seconds user
       0.000000000 seconds sys

型
关于#define TERMS 1：

perf stat -e uops_dispatched.port_2_3 -e uops_dispatched.port_7_8 -e uops_issued.any -e cpu-cycles ./bsf_dep

 Performance counter stats for './bsf_dep':

           291,370      uops_dispatched.port_2_3                                    
       537,040,822      uops_dispatched.port_7_8                                    
     2,148,947,408      uops_issued.any                                             
       761,476,510      cpu-cycles                                                  

       0.202235307 seconds time elapsed

       0.202209000 seconds user
       0.000000000 seconds sys

型