// memcpy.c - Measure how fast we can copy memory

#include <stdio.h>
#include <stdlib.h>
#include <time.h>
#include <string.h>

/* timing function */
#define rdtscll(val) do { \
    unsigned int a,d; \
    asm volatile("rdtsc" : "=a" (a), "=d" (d)); \
    (val) = ((unsigned long)a) | (((unsigned long)d)<<32); \
} while(0)

int main(int argc, char *argv[]) {
 int cpu_rate, num_loops, block_size, block_size_lwords, i, j;
 unsigned char *send_block_p, *rcv_block_p;
 unsigned long start_time, end_time;
 float rate;
 unsigned long *s_p, *r_p;

 if (argc != 4) {
   fprintf(stderr,
     "Usage: %s <cpu clk rate (MHz)> <num. iterations> <copy block size>\n",
          argv[0] );
   return 1;
 }

 cpu_rate = atoi(argv[1]);
 num_loops = atoi(argv[2]);
 block_size = atoi(argv[3]);

 block_size_lwords = block_size / sizeof(unsigned long);
 block_size = sizeof(unsigned long) * block_size_lwords;

 send_block_p = malloc(block_size);
 rcv_block_p = malloc(block_size);

 if ((send_block_p == NULL) || (rcv_block_p == NULL)) {
   fprintf(stderr, "Malloc failed to allocate block(s) of size %d.\n",
           block_size);
 }

// start_time = clock();
   rdtscll(start_time);

 for (i = 0; i < num_loops; i++) {
   memcpy(rcv_block_p, send_block_p, block_size);

// s_p = (unsigned long *) send_block_p;
// r_p = (unsigned long *) rcv_block_p;
//
// for (j = 0 ; j < block_size_lwords; j++) {
// *(r_p++) = *(s_p++);
// }
 }

// end_time = clock();
   rdtscll(end_time);

 rate = (float) (block_size) * (float) (num_loops) /
        ((float) (end_time - start_time)) *
        ((float) cpu_rate) * 1.0E6 / 1.0E6;

 fprintf(stdout,
   "Memory to memory copy rate = %f MBytes / sec. Block size = %d.\n",
   rate, block_size);

} /* end main() */