Skip to content

Instantly share code, notes, and snippets.

@emmansun

emmansun/zuc_sbox.go

Last active July 5, 2022 03:40
Show Gist options
  • Save emmansun/15d2fce6659ab97ffaf7ab66e278caee to your computer and use it in GitHub Desktop.
Save emmansun/15d2fce6659ab97ffaf7ab66e278caee to your computer and use it in GitHub Desktop.
Download ZIP
Raw
zuc_sbox.go
package main
import (
"encoding/binary"
"encoding/hex"
"fmt"
)
type __m128i struct {
bytes [16]byte
}
var aes_sbox = [256]byte{
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,
}
var sbox0 = [256]byte{
0x3e, 0x72, 0x5b, 0x47, 0xca, 0xe0, 0x00, 0x33, 0x04, 0xd1, 0x54, 0x98, 0x09, 0xb9, 0x6d, 0xcb,
0x7b, 0x1b, 0xf9, 0x32, 0xaf, 0x9d, 0x6a, 0xa5, 0xb8, 0x2d, 0xfc, 0x1d, 0x08, 0x53, 0x03, 0x90,
0x4d, 0x4e, 0x84, 0x99, 0xe4, 0xce, 0xd9, 0x91, 0xdd, 0xb6, 0x85, 0x48, 0x8b, 0x29, 0x6e, 0xac,
0xcd, 0xc1, 0xf8, 0x1e, 0x73, 0x43, 0x69, 0xc6, 0xb5, 0xbd, 0xfd, 0x39, 0x63, 0x20, 0xd4, 0x38,
0x76, 0x7d, 0xb2, 0xa7, 0xcf, 0xed, 0x57, 0xc5, 0xf3, 0x2c, 0xbb, 0x14, 0x21, 0x06, 0x55, 0x9b,
0xe3, 0xef, 0x5e, 0x31, 0x4f, 0x7f, 0x5a, 0xa4, 0x0d, 0x82, 0x51, 0x49, 0x5f, 0xba, 0x58, 0x1c,
0x4a, 0x16, 0xd5, 0x17, 0xa8, 0x92, 0x24, 0x1f, 0x8c, 0xff, 0xd8, 0xae, 0x2e, 0x01, 0xd3, 0xad,
0x3b, 0x4b, 0xda, 0x46, 0xeb, 0xc9, 0xde, 0x9a, 0x8f, 0x87, 0xd7, 0x3a, 0x80, 0x6f, 0x2f, 0xc8,
0xb1, 0xb4, 0x37, 0xf7, 0x0a, 0x22, 0x13, 0x28, 0x7c, 0xcc, 0x3c, 0x89, 0xc7, 0xc3, 0x96, 0x56,
0x07, 0xbf, 0x7e, 0xf0, 0x0b, 0x2b, 0x97, 0x52, 0x35, 0x41, 0x79, 0x61, 0xa6, 0x4c, 0x10, 0xfe,
0xbc, 0x26, 0x95, 0x88, 0x8a, 0xb0, 0xa3, 0xfb, 0xc0, 0x18, 0x94, 0xf2, 0xe1, 0xe5, 0xe9, 0x5d,
0xd0, 0xdc, 0x11, 0x66, 0x64, 0x5c, 0xec, 0x59, 0x42, 0x75, 0x12, 0xf5, 0x74, 0x9c, 0xaa, 0x23,
0x0e, 0x86, 0xab, 0xbe, 0x2a, 0x02, 0xe7, 0x67, 0xe6, 0x44, 0xa2, 0x6c, 0xc2, 0x93, 0x9f, 0xf1,
0xf6, 0xfa, 0x36, 0xd2, 0x50, 0x68, 0x9e, 0x62, 0x71, 0x15, 0x3d, 0xd6, 0x40, 0xc4, 0xe2, 0x0f,
0x8e, 0x83, 0x77, 0x6b, 0x25, 0x05, 0x3f, 0x0c, 0x30, 0xea, 0x70, 0xb7, 0xa1, 0xe8, 0xa9, 0x65,
0x8d, 0x27, 0x1a, 0xdb, 0x81, 0xb3, 0xa0, 0xf4, 0x45, 0x7a, 0x19, 0xdf, 0xee, 0x78, 0x34, 0x60,
}
var sbox1 = [256]byte{
0x55, 0xc2, 0x63, 0x71, 0x3b, 0xc8, 0x47, 0x86, 0x9f, 0x3c, 0xda, 0x5b, 0x29, 0xaa, 0xfd, 0x77,
0x8c, 0xc5, 0x94, 0x0c, 0xa6, 0x1a, 0x13, 0x00, 0xe3, 0xa8, 0x16, 0x72, 0x40, 0xf9, 0xf8, 0x42,
0x44, 0x26, 0x68, 0x96, 0x81, 0xd9, 0x45, 0x3e, 0x10, 0x76, 0xc6, 0xa7, 0x8b, 0x39, 0x43, 0xe1,
0x3a, 0xb5, 0x56, 0x2a, 0xc0, 0x6d, 0xb3, 0x05, 0x22, 0x66, 0xbf, 0xdc, 0x0b, 0xfa, 0x62, 0x48,
0xdd, 0x20, 0x11, 0x06, 0x36, 0xc9, 0xc1, 0xcf, 0xf6, 0x27, 0x52, 0xbb, 0x69, 0xf5, 0xd4, 0x87,
0x7f, 0x84, 0x4c, 0xd2, 0x9c, 0x57, 0xa4, 0xbc, 0x4f, 0x9a, 0xdf, 0xfe, 0xd6, 0x8d, 0x7a, 0xeb,
0x2b, 0x53, 0xd8, 0x5c, 0xa1, 0x14, 0x17, 0xfb, 0x23, 0xd5, 0x7d, 0x30, 0x67, 0x73, 0x08, 0x09,
0xee, 0xb7, 0x70, 0x3f, 0x61, 0xb2, 0x19, 0x8e, 0x4e, 0xe5, 0x4b, 0x93, 0x8f, 0x5d, 0xdb, 0xa9,
0xad, 0xf1, 0xae, 0x2e, 0xcb, 0x0d, 0xfc, 0xf4, 0x2d, 0x46, 0x6e, 0x1d, 0x97, 0xe8, 0xd1, 0xe9,
0x4d, 0x37, 0xa5, 0x75, 0x5e, 0x83, 0x9e, 0xab, 0x82, 0x9d, 0xb9, 0x1c, 0xe0, 0xcd, 0x49, 0x89,
0x01, 0xb6, 0xbd, 0x58, 0x24, 0xa2, 0x5f, 0x38, 0x78, 0x99, 0x15, 0x90, 0x50, 0xb8, 0x95, 0xe4,
0xd0, 0x91, 0xc7, 0xce, 0xed, 0x0f, 0xb4, 0x6f, 0xa0, 0xcc, 0xf0, 0x02, 0x4a, 0x79, 0xc3, 0xde,
0xa3, 0xef, 0xea, 0x51, 0xe6, 0x6b, 0x18, 0xec, 0x1b, 0x2c, 0x80, 0xf7, 0x74, 0xe7, 0xff, 0x21,
0x5a, 0x6a, 0x54, 0x1e, 0x41, 0x31, 0x92, 0x35, 0xc4, 0x33, 0x07, 0x0a, 0xba, 0x7e, 0x0e, 0x34,
0x88, 0xb1, 0x98, 0x7c, 0xf3, 0x3d, 0x60, 0x6c, 0x7b, 0xca, 0xd3, 0x1f, 0x32, 0x65, 0x04, 0x28,
0x64, 0xbe, 0x85, 0x9b, 0x2f, 0x59, 0x8a, 0xd7, 0xb0, 0x25, 0xac, 0xaf, 0x12, 0x03, 0xe2, 0xf2,
}
var shift_row = set64(0x0B06010C07020D08, 0x030E09040F0A0500)
var shift_row_inv = set64(0x0306090C0F020508, 0x0B0E0104070A0D00)
var Low_nibble_mask = set64(0x0F0F0F0F0F0F0F0F, 0x0F0F0F0F0F0F0F0F)
var High_nibble_mask = set64(0xF0F0F0F0F0F0F0F0, 0xF0F0F0F0F0F0F0F0)
var Top3_bits_of_the_byte = set64(0xe0e0e0e0e0e0e0e0, 0xe0e0e0e0e0e0e0e0)
var Bottom5_bits_of_the_byte = set64(0x1f1f1f1f1f1f1f1f, 0x1f1f1f1f1f1f1f1f)
var P1 = set64(0x090305070C000400, 0x0A020F0F0E000F09)
var P2 = set64(0x0209030F0A0E010B, 0x040C000705060D08)
var P3 = set64(0x0D0C0900050D0303, 0x0F0A0D00060A0602)
var Aes_to_Zuc_mul_low_nibble = set64(0x3938BBBAA7A62524, 0x1D1C9F9E83820100)
var Aes_to_Zuc_mul_high_nibble = set64(0x3DE835E04194499C, 0xA174A97CDD08D500)
var Comb_matrix_mul_low_nibble = set64(0x2D3987935C48F6E2, 0x9A8E3024EBFF4155)
var Comb_matrix_mul_high_nibble = set64(0x3FD0A6497F90E609, 0x638CFA1523CCBA55)
var Comb_matrix_mul_low_nibble_2 = set64(0x786CD2C6091DA3B7, 0xCFDB6571BEAA1400)
var Comb_matrix_mul_low_nibble_aese = set64(0x1F0BB5A16E7AC4D0, 0xA8BC0216D9CD7367)
var Cancel_aes = set64(0x6363636363636363, 0x6363636363636363)
var Const_comb_matrix = set64(0x5555555555555555, 0x5555555555555555)
func set64(hi, lo uint64) (m __m128i) {
binary.LittleEndian.PutUint64(m.bytes[:], lo)
binary.LittleEndian.PutUint64(m.bytes[8:], hi)
return
}
func mm_set_epi32(e0, e1, e2, e3 uint32) (m __m128i) {
binary.LittleEndian.PutUint32(m.bytes[:], e0)
binary.LittleEndian.PutUint32(m.bytes[4:], e1)
binary.LittleEndian.PutUint32(m.bytes[8:], e2)
binary.LittleEndian.PutUint32(m.bytes[12:], e3)
return
}
func mm_and_si128(a, b __m128i) (m __m128i) {
for i := 0; i < 16; i++ {
m.bytes[i] = a.bytes[i] & b.bytes[i]
}
return
}
func mm_or_si128(a, b __m128i) (m __m128i) {
for i := 0; i < 16; i++ {
m.bytes[i] = a.bytes[i] | b.bytes[i]
}
return
}
func mm_andnot_si128(a, b __m128i) (m __m128i) {
for i := 0; i < 16; i++ {
m.bytes[i] = (^a.bytes[i]) & b.bytes[i]
}
return
}
// Shuffle packed 8-bit integers in a according to shuffle control mask in the corresponding 8-bit element of b, and store the results in dst.
func mm_shuffle_epi8(a, b __m128i) (m __m128i) {
for i := 0; i < 16; i++ {
if b.bytes[i]&0x80 == 0x80 {
m.bytes[i] = 0
} else {
idx := b.bytes[i] & 0x0f
m.bytes[i] = a.bytes[idx]
}
}
return
}
func mm_srli_epi32(a __m128i, imm8 byte) (m __m128i) {
e0 := binary.LittleEndian.Uint32(a.bytes[:])
e1 := binary.LittleEndian.Uint32(a.bytes[4:])
e2 := binary.LittleEndian.Uint32(a.bytes[8:])
e3 := binary.LittleEndian.Uint32(a.bytes[12:])
if imm8 > 31 {
e0 = 0
e1 = 0
e2 = 0
e3 = 0
} else {
e0 = e0 >> imm8
e1 = e1 >> imm8
e2 = e2 >> imm8
e3 = e3 >> imm8
}
binary.LittleEndian.PutUint32(m.bytes[:], e0)
binary.LittleEndian.PutUint32(m.bytes[4:], e1)
binary.LittleEndian.PutUint32(m.bytes[8:], e2)
binary.LittleEndian.PutUint32(m.bytes[12:], e3)
return
}
func mm_slli_epi32(a __m128i, imm8 byte) (m __m128i) {
e0 := binary.LittleEndian.Uint32(a.bytes[:])
e1 := binary.LittleEndian.Uint32(a.bytes[4:])
e2 := binary.LittleEndian.Uint32(a.bytes[8:])
e3 := binary.LittleEndian.Uint32(a.bytes[12:])
if imm8 > 31 {
e0 = 0
e1 = 0
e2 = 0
e3 = 0
} else {
e0 = e0 << imm8
e1 = e1 << imm8
e2 = e2 << imm8
e3 = e3 << imm8
}
binary.LittleEndian.PutUint32(m.bytes[:], e0)
binary.LittleEndian.PutUint32(m.bytes[4:], e1)
binary.LittleEndian.PutUint32(m.bytes[8:], e2)
binary.LittleEndian.PutUint32(m.bytes[12:], e3)
return
}
// Instruction: psrlq xmm, imm8
// CPUID Flags: SSE2
func mm_srli_epi64(a __m128i, imm8 byte) (m __m128i) {
lo := binary.LittleEndian.Uint64(a.bytes[:])
hi := binary.LittleEndian.Uint64(a.bytes[8:])
if imm8 > 63 {
lo = 0
hi = 0
} else {
lo = lo >> imm8
hi = hi >> imm8
}
binary.LittleEndian.PutUint64(m.bytes[:], lo)
binary.LittleEndian.PutUint64(m.bytes[8:], hi)
return
}
// Instruction: psllq xmm, imm8
// CPUID Flags: SSE2
func mm_slli_epi64(a __m128i, imm8 byte) (m __m128i) {
lo := binary.LittleEndian.Uint64(a.bytes[:])
hi := binary.LittleEndian.Uint64(a.bytes[8:])
if imm8 > 63 {
lo = 0
hi = 0
} else {
lo = lo << imm8
hi = hi << imm8
}
binary.LittleEndian.PutUint64(m.bytes[:], lo)
binary.LittleEndian.PutUint64(m.bytes[8:], hi)
return
}
func mm_xor(a, b __m128i) (m __m128i) {
for i := 0; i < 16; i++ {
m.bytes[i] = a.bytes[i] ^ b.bytes[i]
}
return
}
func mm_aesenclast_si128(a, rk __m128i) (m __m128i) {
// ShiftRows
s := mm_shuffle_epi8(a, shift_row)
// SubBytes
for i := 0; i < 16; i++ {
s.bytes[i] = aes_sbox[s.bytes[i]]
}
// State XOR RoundKey
s = mm_xor(s, rk)
m.bytes = s.bytes
return m
}
func mm_aese_si128(a, rk __m128i) (m __m128i) {
// State XOR RoundKey
s := mm_xor(a, rk)
// ShiftRows
s = mm_shuffle_epi8(s, shift_row)
// SubBytes
for i := 0; i < 16; i++ {
s.bytes[i] = aes_sbox[s.bytes[i]]
}
m.bytes = s.bytes
return m
}
func computeS0_official(in __m128i) (out __m128i) {
for i := 0; i < 16; i++ {
out.bytes[i] = sbox0[in.bytes[i]]
}
return
}
func computeS0_var(in __m128i) (out __m128i) {
out = mm_and_si128(in, Low_nibble_mask) //x2
xtmp1 := mm_and_si128(in, High_nibble_mask)
xtmp1 = mm_srli_epi64(xtmp1, 4) // x1
p1 := mm_shuffle_epi8(P1, out) // P1[x2]
xtmp2 := mm_xor(xtmp1, p1) // q = x1 ^ P1[x2]
p2 := mm_shuffle_epi8(P2, xtmp2) // P2[q]
xtmp1 = mm_xor(p2, out) // r = x2 ^ P2[q]
p3 := mm_shuffle_epi8(P3, xtmp1) // P3[r]
out = mm_xor(p3, xtmp2) // s=q ^ P3[r]
out = mm_slli_epi64(out, 4)
out = mm_or_si128(out, xtmp1) // (s << 4) | r
xtmp0 := mm_slli_epi32(out, 5)
out = mm_srli_epi32(out, 3)
xtmp0 = mm_and_si128(xtmp0, Top3_bits_of_the_byte)
out = mm_and_si128(out, Bottom5_bits_of_the_byte)
out = mm_or_si128(out, xtmp0)
return
}
func computeS0_var0(in __m128i) (out __m128i) {
for i := 0; i < 16; i++ {
v := in.bytes[i]
q := P1.bytes[v&0xf] ^ (v >> 4)
r := P2.bytes[q] ^ (v & 0xf)
s := P3.bytes[r] ^ q
s = s<<4 | r
tmp0 := (s << 5) & 0xe0
tmp1 := (s >> 3) & 0x1f
out.bytes[i] = tmp0 | tmp1
}
return
}
func computeS1_official(in __m128i) (out __m128i) {
for i := 0; i < 16; i++ {
out.bytes[i] = sbox1[in.bytes[i]]
}
return
}
func computeS1_var0(in __m128i) (out __m128i) {
for i := 0; i < 16; i++ {
v := in.bytes[i]
v = Aes_to_Zuc_mul_low_nibble.bytes[v&0xf] ^ Aes_to_Zuc_mul_high_nibble.bytes[v>>4]
v = aes_sbox[v] ^ 0x63
v = Comb_matrix_mul_low_nibble.bytes[v&0xf] ^ Comb_matrix_mul_high_nibble.bytes[v>>4]
out.bytes[i] = v ^ 0x55
}
return
}
func computeS1_var1(in __m128i) (out __m128i) {
for i := 0; i < 16; i++ {
v := in.bytes[i]
v = Aes_to_Zuc_mul_low_nibble.bytes[v&0xf] ^ Aes_to_Zuc_mul_high_nibble.bytes[v>>4]
v = aes_sbox[v]
v = Comb_matrix_mul_low_nibble.bytes[v&0xf] ^ Comb_matrix_mul_high_nibble.bytes[v>>4]
// out.bytes[i] = v ^ 0x55 ^ 0x67
out.bytes[i] = v ^ 0x32
}
return
}
func computeS1_aesenclast(in __m128i) (out __m128i) {
y := mm_and_si128(in, Low_nibble_mask)
y = mm_shuffle_epi8(Aes_to_Zuc_mul_low_nibble, y)
x := mm_and_si128(in, High_nibble_mask)
x = mm_srli_epi64(x, 4)
x = mm_xor(mm_shuffle_epi8(Aes_to_Zuc_mul_high_nibble, x), y)
x = mm_shuffle_epi8(x, shift_row_inv)
x = mm_aesenclast_si128(x, Cancel_aes)
y = mm_and_si128(x, Low_nibble_mask)
y = mm_shuffle_epi8(Comb_matrix_mul_low_nibble, y)
x = mm_and_si128(x, High_nibble_mask)
x = mm_srli_epi64(x, 4)
x = mm_xor(mm_shuffle_epi8(Comb_matrix_mul_high_nibble, x), y)
x = mm_xor(Const_comb_matrix, x)
return x
}
func computeS1_aesenclast0(in __m128i) (out __m128i) {
y := mm_and_si128(in, Low_nibble_mask)
y = mm_shuffle_epi8(Aes_to_Zuc_mul_low_nibble, y)
x := mm_and_si128(in, High_nibble_mask)
x = mm_srli_epi64(x, 4)
x = mm_xor(mm_shuffle_epi8(Aes_to_Zuc_mul_high_nibble, x), y)
x = mm_shuffle_epi8(x, shift_row_inv)
x = mm_aesenclast_si128(x, Cancel_aes)
y = mm_and_si128(x, Low_nibble_mask)
y = mm_shuffle_epi8(Comb_matrix_mul_low_nibble_2, y)
x = mm_and_si128(x, High_nibble_mask)
x = mm_srli_epi64(x, 4)
x = mm_xor(mm_shuffle_epi8(Comb_matrix_mul_high_nibble, x), y)
return x
}
func computeS1_aesenclast1(in __m128i) (out __m128i) {
y := mm_and_si128(in, Low_nibble_mask)
y = mm_shuffle_epi8(Aes_to_Zuc_mul_low_nibble, y)
x := mm_and_si128(in, High_nibble_mask)
x = mm_srli_epi64(x, 4)
x = mm_xor(mm_shuffle_epi8(Aes_to_Zuc_mul_high_nibble, x), y)
x = mm_shuffle_epi8(x, shift_row_inv)
x = mm_aesenclast_si128(x, set64(0, 0))
y = mm_and_si128(x, Low_nibble_mask)
y = mm_shuffle_epi8(Comb_matrix_mul_low_nibble_aese, y)
x = mm_and_si128(x, High_nibble_mask)
x = mm_srli_epi64(x, 4)
x = mm_xor(mm_shuffle_epi8(Comb_matrix_mul_high_nibble, x), y)
return x
}
func computeS1_aesenclast2(in __m128i) (out __m128i) {
y := mm_and_si128(in, Low_nibble_mask)
y = mm_shuffle_epi8(Aes_to_Zuc_mul_low_nibble, y)
x := mm_and_si128(in, High_nibble_mask)
x = mm_srli_epi64(x, 4)
x = mm_xor(mm_shuffle_epi8(Aes_to_Zuc_mul_high_nibble, x), y)
x = mm_shuffle_epi8(x, shift_row_inv)
x = mm_aesenclast_si128(x, Low_nibble_mask)
y = mm_andnot_si128(x, Low_nibble_mask)
y = mm_shuffle_epi8(Comb_matrix_mul_low_nibble_aese, y)
x = mm_and_si128(x, High_nibble_mask)
x = mm_srli_epi64(x, 4)
x = mm_xor(mm_shuffle_epi8(Comb_matrix_mul_high_nibble, x), y)
return x
}
func computeS1_aese(in __m128i) (out __m128i) {
y := mm_and_si128(in, Low_nibble_mask)
y = mm_shuffle_epi8(Aes_to_Zuc_mul_low_nibble, y)
x := mm_and_si128(in, High_nibble_mask)
x = mm_srli_epi64(x, 4)
x = mm_xor(mm_shuffle_epi8(Aes_to_Zuc_mul_high_nibble, x), y)
x = mm_shuffle_epi8(x, shift_row_inv)
x = mm_aese_si128(x, set64(0, 0))
x = mm_xor(x, Cancel_aes)
y = mm_and_si128(x, Low_nibble_mask)
y = mm_shuffle_epi8(Comb_matrix_mul_low_nibble, y)
x = mm_and_si128(x, High_nibble_mask)
x = mm_srli_epi64(x, 4)
x = mm_xor(mm_shuffle_epi8(Comb_matrix_mul_high_nibble, x), y)
x = mm_xor(Const_comb_matrix, x)
return x
}
func computeS1_aese2(in __m128i) (out __m128i) {
y := mm_and_si128(in, Low_nibble_mask)
y = mm_shuffle_epi8(Aes_to_Zuc_mul_low_nibble, y)
x := mm_and_si128(in, High_nibble_mask)
x = mm_srli_epi64(x, 4)
x = mm_xor(mm_shuffle_epi8(Aes_to_Zuc_mul_high_nibble, x), y)
x = mm_shuffle_epi8(x, shift_row_inv)
x = mm_aese_si128(x, set64(0, 0))
y = mm_and_si128(x, Low_nibble_mask)
y = mm_shuffle_epi8(Comb_matrix_mul_low_nibble_aese, y)
x = mm_and_si128(x, High_nibble_mask)
x = mm_srli_epi64(x, 4)
x = mm_xor(mm_shuffle_epi8(Comb_matrix_mul_high_nibble, x), y)
return x
}
// Generate matrix based on lookup table
func gen_matrix(lookup [256]byte) (m [8]byte) {
c := lookup[0]
m80 := lookup[0x80] ^ c
m40 := lookup[0x40] ^ c
m20 := lookup[0x20] ^ c
m10 := lookup[0x10] ^ c
m08 := lookup[0x08] ^ c
m04 := lookup[0x04] ^ c
m02 := lookup[0x02] ^ c
m01 := lookup[0x01] ^ c
m[0] = (m80 & 0x80) ^ ((m40 & 0x80) >> 1) ^ ((m20 & 0x80) >> 2) ^ ((m10 & 0x80) >> 3) ^ ((m08 & 0x80) >> 4) ^ ((m04 & 0x80) >> 5) ^ ((m02 & 0x80) >> 6) ^ ((m01 & 0x80) >> 7)
m[1] = ((m80 & 0x40) << 1) ^ (m40 & 0x40) ^ ((m20 & 0x40) >> 1) ^ ((m10 & 0x40) >> 2) ^ ((m08 & 0x40) >> 3) ^ ((m04 & 0x40) >> 4) ^ ((m02 & 0x40) >> 5) ^ ((m01 & 0x40) >> 6)
m[2] = ((m80 & 0x20) << 2) ^ ((m40 & 0x20) << 1) ^ (m20 & 0x20) ^ ((m10 & 0x20) >> 1) ^ ((m08 & 0x20) >> 2) ^ ((m04 & 0x20) >> 3) ^ ((m02 & 0x20) >> 4) ^ ((m01 & 0x20) >> 5)
m[3] = ((m80 & 0x10) << 3) ^ ((m40 & 0x10) << 2) ^ ((m20 & 0x10) << 1) ^ (m10 & 0x10) ^ ((m08 & 0x10) >> 1) ^ ((m04 & 0x10) >> 2) ^ ((m02 & 0x10) >> 3) ^ ((m01 & 0x10) >> 4)
m[4] = ((m80 & 0x08) << 4) ^ ((m40 & 0x08) << 3) ^ ((m20 & 0x08) << 2) ^ ((m10 & 0x08) << 1) ^ (m08 & 0x08) ^ ((m04 & 0x08) >> 1) ^ ((m02 & 0x08) >> 2) ^ ((m01 & 0x08) >> 3)
m[5] = ((m80 & 0x04) << 5) ^ ((m40 & 0x04) << 4) ^ ((m20 & 0x04) << 3) ^ ((m10 & 0x04) << 2) ^ ((m08 & 0x04) << 1) ^ (m04 & 0x04) ^ ((m02 & 0x04) >> 1) ^ ((m01 & 0x04) >> 2)
m[6] = ((m80 & 0x02) << 6) ^ ((m40 & 0x02) << 5) ^ ((m20 & 0x02) << 4) ^ ((m10 & 0x02) << 3) ^ ((m08 & 0x02) << 2) ^ ((m04 & 0x02) << 1) ^ (m02 & 0x02) ^ ((m01 & 0x02) >> 1)
m[7] = ((m80 & 0x01) << 7) ^ ((m40 & 0x01) << 6) ^ ((m20 & 0x01) << 5) ^ ((m10 & 0x01) << 4) ^ ((m08 & 0x01) << 2) ^ ((m04 & 0x01) << 2) ^ ((m02 & 0x01) << 1) ^ (m01 & 0x01)
return
}
func main() {
var lookup [256]byte
for i := 0; i < 16; i++ {
for j := 0; j < 16; j++ {
lookup[i*16+j] = Comb_matrix_mul_low_nibble.bytes[j] ^ Comb_matrix_mul_high_nibble.bytes[i]
fmt.Printf("0x%02X, ", lookup[i*16+j])
}
fmt.Println()
}
m := gen_matrix(lookup)
fmt.Printf("%s\n", hex.EncodeToString(m[:]))
// generate Comb_matrix_mul_low_nibble_2, precompute with constant 0x55
for i := 15; i >= 0; i-- {
fmt.Printf("%02X", Comb_matrix_mul_low_nibble.bytes[i]^0x55)
}
fmt.Println()
// generate Comb_matrix_mul_low_nibble_aese, precompute with constant 0x55 ^ 0x67 = 0x32
for i := 15; i >= 0; i-- {
fmt.Printf("%02X", Comb_matrix_mul_low_nibble.bytes[i]^0x32)
}
fmt.Println()
in := set64(0, 0x5ebab467452143df)
official := computeS0_official(in)
varOut := computeS0_var(in)
fmt.Printf("S0: %s %s\n", hex.EncodeToString(official.bytes[:]), hex.EncodeToString(varOut.bytes[:]))
varOut = computeS0_var0(in)
fmt.Printf("S0: %s %s\n", hex.EncodeToString(official.bytes[:]), hex.EncodeToString(varOut.bytes[:]))
official = computeS1_official(in)
varOut = computeS1_var0(in)
fmt.Printf("S1: %s %s\n", hex.EncodeToString(official.bytes[:]), hex.EncodeToString(varOut.bytes[:]))
varOut = computeS1_var1(in)
fmt.Printf("S1: %s %s\n", hex.EncodeToString(official.bytes[:]), hex.EncodeToString(varOut.bytes[:]))
varOut = computeS1_aesenclast(in)
fmt.Printf("S1: %s %s\n", hex.EncodeToString(official.bytes[:]), hex.EncodeToString(varOut.bytes[:]))
varOut = computeS1_aesenclast0(in)
fmt.Printf("S1: %s %s\n", hex.EncodeToString(official.bytes[:]), hex.EncodeToString(varOut.bytes[:]))
varOut = computeS1_aesenclast1(in)
fmt.Printf("S1: %s %s\n", hex.EncodeToString(official.bytes[:]), hex.EncodeToString(varOut.bytes[:]))
varOut = computeS1_aesenclast2(in)
fmt.Printf("S1: %s %s\n", hex.EncodeToString(official.bytes[:]), hex.EncodeToString(varOut.bytes[:]))
varOut = computeS1_aese(in)
fmt.Printf("S1: %s %s\n", hex.EncodeToString(official.bytes[:]), hex.EncodeToString(varOut.bytes[:]))
varOut = computeS1_aese2(in)
fmt.Printf("S1: %s %s\n", hex.EncodeToString(official.bytes[:]), hex.EncodeToString(varOut.bytes[:]))
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment