[dpdk-dev] some questions about rte_memcpy

[Linhaifeng]

On 2015/1/22 23:21, Bruce Richardson wrote:
> This (size_c) is a run-time constant, not a compile-time constant. To trigger the
> memcpy optimizations inside the compiler, the size value must be constant at
> compile time.


Hi, Bruce

You are right. When use compile-time constant memcpy is faster.Thank you for all.

Here is my test result:

rte_memcpy(constant) size:8 time:876
rte_memcpy(variable) size:8 time:2824
rte_memcpy(constant) size:16 time:868
rte_memcpy(variable) size:16 time:4436
rte_memcpy(constant) size:32 time:856
rte_memcpy(variable) size:32 time:3264
rte_memcpy(constant) size:48 time:872
rte_memcpy(variable) size:48 time:3972
rte_memcpy(constant) size:64 time:856
rte_memcpy(variable) size:64 time:3644
rte_memcpy(constant) size:128 time:868
rte_memcpy(variable) size:128 time:4720
rte_memcpy(constant) size:256 time:868
rte_memcpy(variable) size:256 time:9624

Here is my test program(Who know how to use a loop to test 'constant memcpy'?):

#include <stdio.h>
#include <rte_memcpy.h>
#include <rte_cycles.h>


int main(int narg, char** args)
{
        int i,t;
        char buf[256];
        int tests[7] = {8,16,32,48,64,128,256};
        char buf8[8],buf16[16],buf32[32],buf48[48],buf64[64],buf128[128],buf256[256];
        uint64_t start, end;
        int times = 9999999;
        uint64_t result_c[7];

        if (narg < 2) {
                printf("usage:./rte_memcpy_test times\n");
                return -1;
        }

        times = atoi(args[1]);

        start = rte_rdtsc();
        for(t = 0; t < times; t++) {
                rte_memcpy(buf8, buf8, sizeof buf8);
        }
        end = rte_rdtsc();
        result_c[0] = end - start;

        start = rte_rdtsc();
        for(t = 0; t < times; t++) {
                rte_memcpy(buf16, buf16, sizeof buf16);
        }
        end = rte_rdtsc();
        result_c[1] = end - start;

        start = rte_rdtsc();
        for(t = 0; t < times; t++) {
                rte_memcpy(buf32, buf32, sizeof buf32);
        }
        end = rte_rdtsc();
        result_c[2] = end - start;

        start = rte_rdtsc();
        for(t = 0; t < times; t++) {
                rte_memcpy(buf48, buf48, sizeof buf48);
        }
        end = rte_rdtsc();
        result_c[3] = end - start;

        start = rte_rdtsc();
        for(t = 0; t < times; t++) {
                rte_memcpy(buf64, buf64, sizeof buf64);
        }
        end = rte_rdtsc();
        result_c[4] = end - start;

        start = rte_rdtsc();
        for(t = 0; t < times; t++) {
                rte_memcpy(buf128, buf128, sizeof buf128);
        }
        end = rte_rdtsc();
        result_c[5] = end - start;

        start = rte_rdtsc();
        for(t = 0; t < times; t++) {
                rte_memcpy(buf256, buf256, sizeof buf256);
        }
        end = rte_rdtsc();
        result_c[6] = end - start;

        for (i = 0; i < (sizeof tests / sizeof tests[0]); i++) {
                start = rte_rdtsc();
                for(t = 0; t < times; t++) {
                        rte_memcpy(buf, buf, tests[i]);
                }
                end = rte_rdtsc();
                printf("rte_memcpy(constant) size:%d time:%llu\n", tests[i], result_c[i]);
                printf("rte_memcpy(variable) size:%d time:%llu\n", tests[i], end - start);
        }

        return 0;
}

-- 
Regards,
Haifeng