.vimrc

set tabstop=4
set shiftwidth=4
set expandtab

command.sh

sudo apt install gcc-8 clang-8
gcc-8 -mavx512f -march=icelake-server  main.c -o main

main.c

#include <immintrin.h>
#include <stdio.h>

int main()
{
    int8_t __attribute__((aligned(64)))   op1_int8[64];
    int8_t __attribute__((aligned(64)))    op2_int8[64];
    int    __attribute__((aligned(64)))   op3_int[16];
    int    __attribute__((aligned(64)))   presult[16];

    int16_t __attribute__((aligned(64)))   op4_int16[32];
    int16_t __attribute__((aligned(64)))   op5_int16[32];

    __m512i  v1_int8;
    __m512i  v2_int8;
    __m512i  v3_int;
    __m512i  v4_int16;
    __m512i  v5_int16;

    printf("size of int8_t is %zu\n", sizeof(int8_t));
    printf("size of int is %zu\n", sizeof(int));
    printf("size of int16_t is %zu\n", sizeof(int16_t));

    for (int i = 0;i < 64;i++) {
        op1_int8[i] = i;
        op2_int8[i] = i;
    }
    for (int i = 0;i < 16;i++) {
        op3_int[i] = 0;
    }
    for (int i = 0;i < 32;i++) {
        op4_int16[i] = i;
        op5_int16[i] = i;
    }

    v1_int8 = _mm512_load_si512(&op1_int8);
    v2_int8 =_mm512_load_si512(&op2_int8);
    v3_int = _mm512_load_si512(&op3_int);
    v4_int16 = _mm512_load_si512(&op4_int16);
    v5_int16 = _mm512_load_si512(&op5_int16);

    __m512i result = _mm512_dpbusds_epi32(v3_int, v1_int8, v2_int8);
    _mm512_store_si512(presult, result);


    printf("vpdpbusds\n");
    for (int i = 0; i < 16; i++) {
	    int val = presult[i];
        printf("%d = %d\n", i, val);
    }

    printf("vpmaddwd + vpaddd\n");
    result = _mm512_madd_epi16(v4_int16, v5_int16);
    result = _mm512_add_epi32(result, v3_int);
    _mm512_store_si512(presult, result);
    for (int i = 0; i < 16; i++) {
	    int val = presult[i];
        printf("%d = %d\n", i, val);
    }


    return 0;
}