Skip to content

Instantly share code, notes, and snippets.

@t-mat

t-mat/aesni_generic.hpp

Created February 5, 2026 13:14
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save t-mat/755a7f9f8a03d3debee80e0068f254ba to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save t-mat/755a7f9f8a03d3debee80e0068f254ba to your computer and use it in GitHub Desktop.
Download ZIP
[C++]AES implementation mimicking x86 AES-NI instructions in software
Raw
aesni_generic.hpp
// AES implementation mimicking x86 AES-NI instructions in software
// https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html#text=aes
#ifndef AESNI_GENERIC_HPP_INCLUDED
# define AESNI_GENERIC_HPP_INCLUDED 1
# include <stdint.h>
namespace AesNiGeneric
{
namespace details
{
// ========================================================================
// Internal Helpers
// ========================================================================
// GF(2^8) Multiplication by 2 (xtime)
inline uint8_t mul2(uint8_t p) { return (p << 1) ^ ((p & 0x80) ? 0x1b : 0); }
inline uint8_t mul4(uint8_t p) { return mul2(mul2(p)); }
inline uint8_t mul8(uint8_t p) { return mul2(mul4(p)); }
// GF(2^8) Combined Multiplications for InvMixColumns
inline uint8_t mul9(uint8_t p) { return mul8(p) ^ p; }
inline uint8_t mul11(uint8_t p) { return mul8(p) ^ mul2(p) ^ p; }
inline uint8_t mul13(uint8_t p) { return mul8(p) ^ mul4(p) ^ p; }
inline uint8_t mul14(uint8_t p) { return mul8(p) ^ mul4(p) ^ mul2(p); }
inline void xor_roundkey(uint8_t *d16, const uint8_t *s16, const uint8_t *rk16)
{
for (int i = 0; i < 16; ++i) {
d16[i] = s16[i] ^ rk16[i];
}
}
inline void sbox_cnv(uint8_t v_out[4][4], const uint8_t *s16)
{
// AES Forward S-box
static constexpr uint8_t sbox[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};
for (int i = 0; i < 16; ++i) {
// ShiftRows: Row r shifts left by r
const int a = ((i / 4) + 4 - (i % 4)) % 4;
const int b = i % 4;
v_out[a][b] = sbox[s16[i]];
}
}
inline void inv_sbox_cnv(uint8_t v_out[4][4], const uint8_t *s16)
{
// AES Inverse S-box
static constexpr uint8_t inv_sbox[256] = {
0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38, 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb, //
0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87, 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb, //
0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d, 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e, //
0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2, 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25, //
0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16, 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92, //
0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda, 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84, //
0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a, 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06, //
0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02, 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b, //
0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea, 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73, //
0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85, 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e, //
0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89, 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b, //
0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20, 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4, //
0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31, 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f, //
0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d, 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef, //
0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0, 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61, //
0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26, 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d};
for (int i = 0; i < 16; ++i) {
// InvShiftRows: Row r shifts right by r
const int a = ((i / 4) + (i % 4)) % 4;
const int b = i % 4;
v_out[a][b] = inv_sbox[s16[i]];
}
}
} // namespace details
// ========================================================================
// Public API
// ========================================================================
using namespace details;
inline void aesenc(uint8_t *d16, const uint8_t *s16, const uint8_t *rk16)
{
uint8_t v[4][4];
sbox_cnv(v, s16); // ShiftRows + SubBytes
// MixColumns
for (int i = 0; i < 4; ++i) {
const uint8_t t = v[i][0];
const uint8_t u = v[i][0] ^ v[i][1] ^ v[i][2] ^ v[i][3];
v[i][0] ^= u ^ mul2(v[i][0] ^ v[i][1]);
v[i][1] ^= u ^ mul2(v[i][1] ^ v[i][2]);
v[i][2] ^= u ^ mul2(v[i][2] ^ v[i][3]);
v[i][3] ^= u ^ mul2(v[i][3] ^ t);
}
xor_roundkey(d16, &v[0][0], rk16);
}
inline void aesenclast(uint8_t *d16, const uint8_t *s16, const uint8_t *rk16)
{
uint8_t v[4][4];
sbox_cnv(v, s16); // ShiftRows + SubBytes
xor_roundkey(d16, &v[0][0], rk16);
}
// AES Inverse Mix Columns (equivalent to _mm_aesimc_si128)
// Used for preparing Decryption Round Keys
inline void aesimc(uint8_t *d16, const uint8_t *s16)
{
uint8_t v[4][4];
for (int i = 0; i < 16; ++i) {
v[i / 4][i % 4] = s16[i];
}
uint8_t res[4][4];
for (int i = 0; i < 4; ++i) {
const uint8_t c0 = v[i][0];
const uint8_t c1 = v[i][1];
const uint8_t c2 = v[i][2];
const uint8_t c3 = v[i][3];
res[i][0] = mul14(c0) ^ mul11(c1) ^ mul13(c2) ^ mul9(c3);
res[i][1] = mul9(c0) ^ mul14(c1) ^ mul11(c2) ^ mul13(c3);
res[i][2] = mul13(c0) ^ mul9(c1) ^ mul14(c2) ^ mul11(c3);
res[i][3] = mul11(c0) ^ mul13(c1) ^ mul9(c2) ^ mul14(c3);
}
for (int i = 0; i < 16; ++i) {
d16[i] = res[i / 4][i % 4];
}
}
inline void aesdec(uint8_t *d16, const uint8_t *s16, const uint8_t *rk16)
{
uint8_t v[4][4];
inv_sbox_cnv(v, s16); // InvShiftRows + InvSubBytes
// InvMixColumns
for (int i = 0; i < 4; ++i) {
const uint8_t c0 = v[i][0];
const uint8_t c1 = v[i][1];
const uint8_t c2 = v[i][2];
const uint8_t c3 = v[i][3];
v[i][0] = mul14(c0) ^ mul11(c1) ^ mul13(c2) ^ mul9(c3);
v[i][1] = mul9(c0) ^ mul14(c1) ^ mul11(c2) ^ mul13(c3);
v[i][2] = mul13(c0) ^ mul9(c1) ^ mul14(c2) ^ mul11(c3);
v[i][3] = mul11(c0) ^ mul13(c1) ^ mul9(c2) ^ mul14(c3);
}
xor_roundkey(d16, &v[0][0], rk16);
}
inline void aesdeclast(uint8_t *d16, const uint8_t *s16, const uint8_t *rk16)
{
uint8_t v[4][4];
inv_sbox_cnv(v, s16); // InvShiftRows + InvSubBytes
xor_roundkey(d16, &v[0][0], rk16);
}
} // namespace AesNiGeneric
#endif // AESNI_GENERIC_HPP_INCLUDED
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment