Performance comparison of C & Python

multiply_matrix.c

#include <stdio.h>

#define N 1024

int main(void) {
    int a[N][N];
    int b[N][N];
    int c[N][N];

    for (int i = 0; i < N; i++) {
        for (int j = 0; j < N; j++) {
            a[i][j] = i * j;
            b[i][j] = i + j;
        }
    }

    for (int i = 0; i < N; i++) {
        for (int j = 0; j < N; j++) {
            c[i][j] = 0;
            for (int k = 0; k < N; k++) {
                c[i][j] += a[i][k] + b[k][j];
            }
        }
    }

    return 0;
}

multiply_matrix.py

N = 1024

a = [[i * j for i in range(N)] for j in range(N)]
b = [[i + j for i in range(N)] for j in range(N)]
c = [[0 for _ in range(N)] for _ in range(N)]

for i in range(N):
    for j in range(N):
        for k in range(N):
            c[i][j] += a[i][k] + b[k][j]