aes-without-ni.h

#include<iostream>
using namespace std;

int s_box[256] = {
    0x63 ,0x7c ,0x77 ,0x7b ,0xf2 ,0x6b ,0x6f ,0xc5 ,0x30 ,0x01 ,0x67 ,0x2b ,0xfe ,0xd7 ,0xab ,0x76,
    0xca ,0x82 ,0xc9 ,0x7d ,0xfa ,0x59 ,0x47 ,0xf0 ,0xad ,0xd4 ,0xa2 ,0xaf ,0x9c ,0xa4 ,0x72 ,0xc0,
    0xb7 ,0xfd ,0x93 ,0x26 ,0x36 ,0x3f ,0xf7 ,0xcc ,0x34 ,0xa5 ,0xe5 ,0xf1 ,0x71 ,0xd8 ,0x31 ,0x15,
    0x04 ,0xc7 ,0x23 ,0xc3 ,0x18 ,0x96 ,0x05 ,0x9a ,0x07 ,0x12 ,0x80 ,0xe2 ,0xeb ,0x27 ,0xb2 ,0x75,
    0x09 ,0x83 ,0x2c ,0x1a ,0x1b ,0x6e ,0x5a ,0xa0 ,0x52 ,0x3b ,0xd6 ,0xb3 ,0x29 ,0xe3 ,0x2f ,0x84,
    0x53 ,0xd1 ,0x00 ,0xed ,0x20 ,0xfc ,0xb1 ,0x5b ,0x6a ,0xcb ,0xbe ,0x39 ,0x4a ,0x4c ,0x58 ,0xcf,
    0xd0 ,0xef ,0xaa ,0xfb ,0x43 ,0x4d ,0x33 ,0x85 ,0x45 ,0xf9 ,0x02 ,0x7f ,0x50 ,0x3c ,0x9f ,0xa8,
    0x51 ,0xa3 ,0x40 ,0x8f ,0x92 ,0x9d ,0x38 ,0xf5 ,0xbc ,0xb6 ,0xda ,0x21 ,0x10 ,0xff ,0xf3 ,0xd2,
    0xcd ,0x0c ,0x13 ,0xec ,0x5f ,0x97 ,0x44 ,0x17 ,0xc4 ,0xa7 ,0x7e ,0x3d ,0x64 ,0x5d ,0x19 ,0x73,
    0x60 ,0x81 ,0x4f ,0xdc ,0x22 ,0x2a ,0x90 ,0x88 ,0x46 ,0xee ,0xb8 ,0x14 ,0xde ,0x5e ,0x0b ,0xdb,
    0xe0 ,0x32 ,0x3a ,0x0a ,0x49 ,0x06 ,0x24 ,0x5c ,0xc2 ,0xd3 ,0xac ,0x62 ,0x91 ,0x95 ,0xe4 ,0x79,
    0xe7 ,0xc8 ,0x37 ,0x6d ,0x8d ,0xd5 ,0x4e ,0xa9 ,0x6c ,0x56 ,0xf4 ,0xea ,0x65 ,0x7a ,0xae ,0x08,
    0xba ,0x78 ,0x25 ,0x2e ,0x1c ,0xa6 ,0xb4 ,0xc6 ,0xe8 ,0xdd ,0x74 ,0x1f ,0x4b ,0xbd ,0x8b ,0x8a,
    0x70 ,0x3e ,0xb5 ,0x66 ,0x48 ,0x03 ,0xf6 ,0x0e ,0x61 ,0x35 ,0x57 ,0xb9 ,0x86 ,0xc1 ,0x1d ,0x9e,
    0xe1 ,0xf8 ,0x98 ,0x11 ,0x69 ,0xd9 ,0x8e ,0x94 ,0x9b ,0x1e ,0x87 ,0xe9 ,0xce ,0x55 ,0x28 ,0xdf,
    0x8c ,0xa1 ,0x89 ,0x0d ,0xbf ,0xe6 ,0x42 ,0x68 ,0x41 ,0x99 ,0x2d ,0x0f ,0xb0 ,0x54 ,0xbb ,0x16
};

unsigned char mul2[] = {
    0x00,0x02,0x04,0x06,0x08,0x0a,0x0c,0x0e,0x10,0x12,0x14,0x16,0x18,0x1a,0x1c,0x1e,
    0x20,0x22,0x24,0x26,0x28,0x2a,0x2c,0x2e,0x30,0x32,0x34,0x36,0x38,0x3a,0x3c,0x3e,
    0x40,0x42,0x44,0x46,0x48,0x4a,0x4c,0x4e,0x50,0x52,0x54,0x56,0x58,0x5a,0x5c,0x5e,
    0x60,0x62,0x64,0x66,0x68,0x6a,0x6c,0x6e,0x70,0x72,0x74,0x76,0x78,0x7a,0x7c,0x7e,
    0x80,0x82,0x84,0x86,0x88,0x8a,0x8c,0x8e,0x90,0x92,0x94,0x96,0x98,0x9a,0x9c,0x9e,
    0xa0,0xa2,0xa4,0xa6,0xa8,0xaa,0xac,0xae,0xb0,0xb2,0xb4,0xb6,0xb8,0xba,0xbc,0xbe,
    0xc0,0xc2,0xc4,0xc6,0xc8,0xca,0xcc,0xce,0xd0,0xd2,0xd4,0xd6,0xd8,0xda,0xdc,0xde,
    0xe0,0xe2,0xe4,0xe6,0xe8,0xea,0xec,0xee,0xf0,0xf2,0xf4,0xf6,0xf8,0xfa,0xfc,0xfe,
    0x1b,0x19,0x1f,0x1d,0x13,0x11,0x17,0x15,0x0b,0x09,0x0f,0x0d,0x03,0x01,0x07,0x05,
    0x3b,0x39,0x3f,0x3d,0x33,0x31,0x37,0x35,0x2b,0x29,0x2f,0x2d,0x23,0x21,0x27,0x25,
    0x5b,0x59,0x5f,0x5d,0x53,0x51,0x57,0x55,0x4b,0x49,0x4f,0x4d,0x43,0x41,0x47,0x45,
    0x7b,0x79,0x7f,0x7d,0x73,0x71,0x77,0x75,0x6b,0x69,0x6f,0x6d,0x63,0x61,0x67,0x65,
    0x9b,0x99,0x9f,0x9d,0x93,0x91,0x97,0x95,0x8b,0x89,0x8f,0x8d,0x83,0x81,0x87,0x85,
    0xbb,0xb9,0xbf,0xbd,0xb3,0xb1,0xb7,0xb5,0xab,0xa9,0xaf,0xad,0xa3,0xa1,0xa7,0xa5,
    0xdb,0xd9,0xdf,0xdd,0xd3,0xd1,0xd7,0xd5,0xcb,0xc9,0xcf,0xcd,0xc3,0xc1,0xc7,0xc5,
    0xfb,0xf9,0xff,0xfd,0xf3,0xf1,0xf7,0xf5,0xeb,0xe9,0xef,0xed,0xe3,0xe1,0xe7,0xe5
};

unsigned char mul3[] = {
    0x00,0x03,0x06,0x05,0x0c,0x0f,0x0a,0x09,0x18,0x1b,0x1e,0x1d,0x14,0x17,0x12,0x11,
    0x30,0x33,0x36,0x35,0x3c,0x3f,0x3a,0x39,0x28,0x2b,0x2e,0x2d,0x24,0x27,0x22,0x21,
    0x60,0x63,0x66,0x65,0x6c,0x6f,0x6a,0x69,0x78,0x7b,0x7e,0x7d,0x74,0x77,0x72,0x71,
    0x50,0x53,0x56,0x55,0x5c,0x5f,0x5a,0x59,0x48,0x4b,0x4e,0x4d,0x44,0x47,0x42,0x41,
    0xc0,0xc3,0xc6,0xc5,0xcc,0xcf,0xca,0xc9,0xd8,0xdb,0xde,0xdd,0xd4,0xd7,0xd2,0xd1,
    0xf0,0xf3,0xf6,0xf5,0xfc,0xff,0xfa,0xf9,0xe8,0xeb,0xee,0xed,0xe4,0xe7,0xe2,0xe1,
    0xa0,0xa3,0xa6,0xa5,0xac,0xaf,0xaa,0xa9,0xb8,0xbb,0xbe,0xbd,0xb4,0xb7,0xb2,0xb1,
    0x90,0x93,0x96,0x95,0x9c,0x9f,0x9a,0x99,0x88,0x8b,0x8e,0x8d,0x84,0x87,0x82,0x81,
    0x9b,0x98,0x9d,0x9e,0x97,0x94,0x91,0x92,0x83,0x80,0x85,0x86,0x8f,0x8c,0x89,0x8a,
    0xab,0xa8,0xad,0xae,0xa7,0xa4,0xa1,0xa2,0xb3,0xb0,0xb5,0xb6,0xbf,0xbc,0xb9,0xba,
    0xfb,0xf8,0xfd,0xfe,0xf7,0xf4,0xf1,0xf2,0xe3,0xe0,0xe5,0xe6,0xef,0xec,0xe9,0xea,
    0xcb,0xc8,0xcd,0xce,0xc7,0xc4,0xc1,0xc2,0xd3,0xd0,0xd5,0xd6,0xdf,0xdc,0xd9,0xda,
    0x5b,0x58,0x5d,0x5e,0x57,0x54,0x51,0x52,0x43,0x40,0x45,0x46,0x4f,0x4c,0x49,0x4a,
    0x6b,0x68,0x6d,0x6e,0x67,0x64,0x61,0x62,0x73,0x70,0x75,0x76,0x7f,0x7c,0x79,0x7a,
    0x3b,0x38,0x3d,0x3e,0x37,0x34,0x31,0x32,0x23,0x20,0x25,0x26,0x2f,0x2c,0x29,0x2a,
    0x0b,0x08,0x0d,0x0e,0x07,0x04,0x01,0x02,0x13,0x10,0x15,0x16,0x1f,0x1c,0x19,0x1a
};

unsigned char rcon[256] = {
    0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36, 0x6c, 0xd8, 0xab, 0x4d, 0x9a, 
    0x2f, 0x5e, 0xbc, 0x63, 0xc6, 0x97, 0x35, 0x6a, 0xd4, 0xb3, 0x7d, 0xfa, 0xef, 0xc5, 0x91, 0x39, 
    0x72, 0xe4, 0xd3, 0xbd, 0x61, 0xc2, 0x9f, 0x25, 0x4a, 0x94, 0x33, 0x66, 0xcc, 0x83, 0x1d, 0x3a, 
    0x74, 0xe8, 0xcb, 0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36, 0x6c, 0xd8, 
    0xab, 0x4d, 0x9a, 0x2f, 0x5e, 0xbc, 0x63, 0xc6, 0x97, 0x35, 0x6a, 0xd4, 0xb3, 0x7d, 0xfa, 0xef, 
    0xc5, 0x91, 0x39, 0x72, 0xe4, 0xd3, 0xbd, 0x61, 0xc2, 0x9f, 0x25, 0x4a, 0x94, 0x33, 0x66, 0xcc, 
    0x83, 0x1d, 0x3a, 0x74, 0xe8, 0xcb, 0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 
    0x36, 0x6c, 0xd8, 0xab, 0x4d, 0x9a, 0x2f, 0x5e, 0xbc, 0x63, 0xc6, 0x97, 0x35, 0x6a, 0xd4, 0xb3, 
    0x7d, 0xfa, 0xef, 0xc5, 0x91, 0x39, 0x72, 0xe4, 0xd3, 0xbd, 0x61, 0xc2, 0x9f, 0x25, 0x4a, 0x94, 
    0x33, 0x66, 0xcc, 0x83, 0x1d, 0x3a, 0x74, 0xe8, 0xcb, 0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 
    0x40, 0x80, 0x1b, 0x36, 0x6c, 0xd8, 0xab, 0x4d, 0x9a, 0x2f, 0x5e, 0xbc, 0x63, 0xc6, 0x97, 0x35, 
    0x6a, 0xd4, 0xb3, 0x7d, 0xfa, 0xef, 0xc5, 0x91, 0x39, 0x72, 0xe4, 0xd3, 0xbd, 0x61, 0xc2, 0x9f, 
    0x25, 0x4a, 0x94, 0x33, 0x66, 0xcc, 0x83, 0x1d, 0x3a, 0x74, 0xe8, 0xcb, 0x8d, 0x01, 0x02, 0x04, 
    0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36, 0x6c, 0xd8, 0xab, 0x4d, 0x9a, 0x2f, 0x5e, 0xbc, 0x63, 
    0xc6, 0x97, 0x35, 0x6a, 0xd4, 0xb3, 0x7d, 0xfa, 0xef, 0xc5, 0x91, 0x39, 0x72, 0xe4, 0xd3, 0xbd, 
    0x61, 0xc2, 0x9f, 0x25, 0x4a, 0x94, 0x33, 0x66, 0xcc, 0x83, 0x1d, 0x3a, 0x74, 0xe8, 0xcb, 0x8d
};

void print_hex(unsigned char x){
    if(x /16 < 10) cout<<(char)((x/16) + '0');
    else cout<<(char)((x/16 - 10) + 'A');

    if(x % 16 < 10) cout<<(char)((x % 16) + '0');
    else cout<<(char)((x % 16 - 10) + 'A');
}
void key_expansion_core(unsigned char* in, unsigned char i) {
    //Rotate Left:
    unsigned char t;
    t = in[0];
    in[0] = in[1];
    in[1] = in[2];
    in[2] = in[3];
    in[3] = t;

    // S-Box four bytes:
    in[0] = s_box[in[0]]; in[1] = s_box[in[1]];
    in[2] = s_box[in[2]]; in[3] = s_box[in[3]];

    // Rcon:
    in[0] ^= rcon[i];
}

void key_expansion(unsigned char* inputKey, unsigned char* expandedKeys) {
    /*The first 16 bytes of the expanded keys are same as the input key. */
    for(int i=0; i<16; i++){
        expandedKeys[i] = inputKey[i];
    }

    //Variables:
    int bytes_generated = 16; //We have 16 bytes so far i.e. the original key
    int rcon_iteration = 1;
    unsigned char temp[4];

    while(bytes_generated < 176){// 176 because we have to generate 10 more keys for 10 rounds. 16 x 10 + 16 = 176
        //Read 4 bytes for the core
        for(int i=0; i<4; i++){
            temp[i] = expandedKeys[i + bytes_generated - 4];
        }

        // Perform core once for each 16 byte key:
        if(bytes_generated % 16 == 0){
            key_expansion_core(temp, rcon_iteration);
            rcon_iteration++;
        }

        // XOR temp with [bytes_generated -16], and store in expandedKeys
        for(unsigned char a =0; a <4; a++){
            expandedKeys[bytes_generated] = expandedKeys[bytes_generated - 16] ^ temp[a];
            bytes_generated++;
        }
    }
}

void substitute_bytes(unsigned char* state) {
    /* use the substitution box to substitute the element i with the value at index state[i]*/
    for(int i=0; i<16; i++){
        state[i] = s_box[state[i]];
    }
}

void shift_rows(unsigned char* state) {
    unsigned char temp[16];

    temp[0] = state[0];
    temp[1] = state[5];
    temp[2] = state[10];
    temp[3] = state[15];

    temp[4] = state[4];
    temp[5] = state[9];
    temp[6] = state[14];
    temp[7] = state[3];

    temp[8] = state[8];
    temp[9] = state[13];
    temp[10] = state[2];
    temp[11] = state[7];

    temp[12] = state[12];
    temp[13] = state[1];
    temp[14] = state[6];
    temp[15] = state[11];

    /* copy the shifted rows back into state */
    for(int i=0; i<16; i++){
        state[i] = temp[i];
    }
}

void mix_columns(unsigned char* state) {
    unsigned char tmp[16];

    tmp[0] = (unsigned char)(mul2[state[0]] ^ mul3[state[1]] ^ state[2] ^ state[3]);
    tmp[1] = (unsigned char)(state[0] ^ mul2[state[1]] ^ mul3[state[2]] ^ state[3]);
    tmp[2] = (unsigned char)(state[0] ^ state[1] ^ mul2[state[2]] ^ mul3[state[3]]);
    tmp[3] = (unsigned char)(mul3[state[0]] ^ state[1] ^ state[2] ^ mul2[state[3]]);

    tmp[4] = (unsigned char)(mul2[state[4]] ^ mul3[state[5]] ^ state[6] ^ state[7]);
    tmp[5] = (unsigned char)(state[4] ^ mul2[state[5]] ^ mul3[state[6]] ^ state[7]);
    tmp[6] = (unsigned char)(state[4] ^ state[5] ^ mul2[state[6]] ^ mul3[state[7]]);
    tmp[7] = (unsigned char)(mul3[state[4]] ^ state[5] ^ state[6] ^ mul2[state[7]]);

    tmp[8] = (unsigned char)(mul2[state[8]] ^ mul3[state[9]] ^ state[10] ^ state[11]);
    tmp[9] = (unsigned char)(state[8] ^ mul2[state[9]] ^ mul3[state[10]] ^ state[11]);
    tmp[10] = (unsigned char)(state[8] ^ state[9] ^ mul2[state[10]] ^ mul3[state[11]]);
    tmp[11] = (unsigned char)(mul3[state[8]] ^ state[9] ^ state[10] ^ mul2[state[11]]);

    tmp[12] = (unsigned char)(mul2[state[12]] ^ mul3[state[13]] ^ state[14] ^ state[15]);
    tmp[13] = (unsigned char)(state[12] ^ mul2[state[13]] ^ mul3[state[14]] ^ state[15]);
    tmp[14] = (unsigned char)(state[12] ^ state[13] ^ mul2[state[14]] ^ mul3[state[15]]);
    tmp[15] = (unsigned char)(mul3[state[12]] ^ state[13] ^ state[14] ^ mul2[state[15]]);

    for(int i=0; i<16; i++){
        state[i] = tmp[i];
    }

}

void add_round_key(unsigned char* state, unsigned char* roundKey) {
    for(int i=0; i<16; i++){
        state[i] ^= roundKey[i];
    }
}

void aes_encrypt(unsigned char* message, unsigned char* expandedKey) {
    unsigned char state[16];
    for(int i=0; i<16; i++){
        state[i] = message[i];
    }

    int number_of_rounds = 9;

    /* Initial Round */
    add_round_key(state, expandedKey); 

    for(int i=0; i < number_of_rounds; i++){ //repeated rounds
        substitute_bytes(state);
        shift_rows(state);
        mix_columns(state);
        add_round_key(state, expandedKey + 16*i + 16);
    }
    /* Final Round */
    substitute_bytes(state);
    shift_rows(state);
    add_round_key(state, expandedKey + 160);

    for(int i=0; i<16; i++){
        message[i] = state[i];
    }
};