hiae 0.2.0

//! Portable fallback implementation of AES operations using lookup tables.

/// AES S-box lookup table.
#[cfg(not(any(
    all(
        target_arch = "aarch64",
        target_feature = "neon",
        target_feature = "aes"
    ),
    all(target_arch = "x86_64", target_feature = "aes")
)))]
const SBOX: [u8; 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,
];

/// Precomputed multiplication by 2 in GF(2^8).
#[cfg(not(any(
    all(
        target_arch = "aarch64",
        target_feature = "neon",
        target_feature = "aes"
    ),
    all(target_arch = "x86_64", target_feature = "aes")
)))]
const MUL2: [u8; 256] = [
    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,
];

/// Precomputed multiplication by 3 in GF(2^8).
#[cfg(not(any(
    all(
        target_arch = "aarch64",
        target_feature = "neon",
        target_feature = "aes"
    ),
    all(target_arch = "x86_64", target_feature = "aes")
)))]
const MUL3: [u8; 256] = [
    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,
];

/// Convert 16 bytes to 4x4 AES state matrix (column-major order).
#[cfg(not(any(
    all(
        target_arch = "aarch64",
        target_feature = "neon",
        target_feature = "aes"
    ),
    all(target_arch = "x86_64", target_feature = "aes")
)))]
#[inline]
fn bytes_to_state(data: &[u8; 16]) -> [[u8; 4]; 4] {
    let mut state = [[0u8; 4]; 4];
    for i in 0..16 {
        state[i % 4][i / 4] = data[i];
    }
    state
}

/// Convert 4x4 AES state matrix to 16 bytes (column-major order).
#[cfg(not(any(
    all(
        target_arch = "aarch64",
        target_feature = "neon",
        target_feature = "aes"
    ),
    all(target_arch = "x86_64", target_feature = "aes")
)))]
#[inline]
fn state_to_bytes(state: &[[u8; 4]; 4]) -> [u8; 16] {
    let mut result = [0u8; 16];
    for i in 0..16 {
        result[i] = state[i % 4][i / 4];
    }
    result
}

/// Apply AES SubBytes transformation.
#[cfg(not(any(
    all(
        target_arch = "aarch64",
        target_feature = "neon",
        target_feature = "aes"
    ),
    all(target_arch = "x86_64", target_feature = "aes")
)))]
#[inline]
fn sub_bytes(state: &mut [[u8; 4]; 4]) {
    for row in state.iter_mut() {
        for byte in row.iter_mut() {
            *byte = SBOX[*byte as usize];
        }
    }
}

/// Apply AES ShiftRows transformation.
#[cfg(not(any(
    all(
        target_arch = "aarch64",
        target_feature = "neon",
        target_feature = "aes"
    ),
    all(target_arch = "x86_64", target_feature = "aes")
)))]
#[inline]
fn shift_rows(state: &mut [[u8; 4]; 4]) {
    // Row 0: no shift
    // Row 1: shift left by 1
    let temp = state[1][0];
    state[1][0] = state[1][1];
    state[1][1] = state[1][2];
    state[1][2] = state[1][3];
    state[1][3] = temp;

    // Row 2: shift left by 2
    let temp1 = state[2][0];
    let temp2 = state[2][1];
    state[2][0] = state[2][2];
    state[2][1] = state[2][3];
    state[2][2] = temp1;
    state[2][3] = temp2;

    // Row 3: shift left by 3 (same as shift right by 1)
    let temp = state[3][3];
    state[3][3] = state[3][2];
    state[3][2] = state[3][1];
    state[3][1] = state[3][0];
    state[3][0] = temp;
}

/// Apply AES MixColumns transformation with unrolled loop for better performance.
#[cfg(not(any(
    all(
        target_arch = "aarch64",
        target_feature = "neon",
        target_feature = "aes"
    ),
    all(target_arch = "x86_64", target_feature = "aes")
)))]
#[inline]
fn mix_columns(state: &mut [[u8; 4]; 4]) {
    // Unroll the loop for better compiler optimization

    // Column 0
    let s0 = state[0][0];
    let s1 = state[1][0];
    let s2 = state[2][0];
    let s3 = state[3][0];
    state[0][0] = MUL2[s0 as usize] ^ MUL3[s1 as usize] ^ s2 ^ s3;
    state[1][0] = s0 ^ MUL2[s1 as usize] ^ MUL3[s2 as usize] ^ s3;
    state[2][0] = s0 ^ s1 ^ MUL2[s2 as usize] ^ MUL3[s3 as usize];
    state[3][0] = MUL3[s0 as usize] ^ s1 ^ s2 ^ MUL2[s3 as usize];

    // Column 1
    let s0 = state[0][1];
    let s1 = state[1][1];
    let s2 = state[2][1];
    let s3 = state[3][1];
    state[0][1] = MUL2[s0 as usize] ^ MUL3[s1 as usize] ^ s2 ^ s3;
    state[1][1] = s0 ^ MUL2[s1 as usize] ^ MUL3[s2 as usize] ^ s3;
    state[2][1] = s0 ^ s1 ^ MUL2[s2 as usize] ^ MUL3[s3 as usize];
    state[3][1] = MUL3[s0 as usize] ^ s1 ^ s2 ^ MUL2[s3 as usize];

    // Column 2
    let s0 = state[0][2];
    let s1 = state[1][2];
    let s2 = state[2][2];
    let s3 = state[3][2];
    state[0][2] = MUL2[s0 as usize] ^ MUL3[s1 as usize] ^ s2 ^ s3;
    state[1][2] = s0 ^ MUL2[s1 as usize] ^ MUL3[s2 as usize] ^ s3;
    state[2][2] = s0 ^ s1 ^ MUL2[s2 as usize] ^ MUL3[s3 as usize];
    state[3][2] = MUL3[s0 as usize] ^ s1 ^ s2 ^ MUL2[s3 as usize];

    // Column 3
    let s0 = state[0][3];
    let s1 = state[1][3];
    let s2 = state[2][3];
    let s3 = state[3][3];
    state[0][3] = MUL2[s0 as usize] ^ MUL3[s1 as usize] ^ s2 ^ s3;
    state[1][3] = s0 ^ MUL2[s1 as usize] ^ MUL3[s2 as usize] ^ s3;
    state[2][3] = s0 ^ s1 ^ MUL2[s2 as usize] ^ MUL3[s3 as usize];
    state[3][3] = MUL3[s0 as usize] ^ s1 ^ s2 ^ MUL2[s3 as usize];
}

/// Portable AESL implementation using lookup tables.
#[cfg(not(any(
    all(
        target_arch = "aarch64",
        target_feature = "neon",
        target_feature = "aes"
    ),
    all(target_arch = "x86_64", target_feature = "aes")
)))]
#[inline]
pub fn aesl(block: &[u8; 16]) -> [u8; 16] {
    let mut state = bytes_to_state(block);
    sub_bytes(&mut state);
    shift_rows(&mut state);
    mix_columns(&mut state);
    state_to_bytes(&state)
}

/// Portable reduction XOR for 16 blocks with optimized loop unrolling.
#[cfg(not(any(
    all(target_arch = "aarch64", target_feature = "neon"),
    all(target_arch = "x86_64", target_feature = "sse2")
)))]
#[inline]
pub fn xor_reduce_blocks(blocks: &[[u8; 16]; 16]) -> [u8; 16] {
    let mut result = blocks[0];

    // Process blocks in batches of 4 for better cache efficiency
    // This helps the compiler generate more efficient code
    for chunk in blocks[1..].chunks_exact(4) {
        for i in 0..16 {
            result[i] ^= chunk[0][i] ^ chunk[1][i] ^ chunk[2][i] ^ chunk[3][i];
        }
    }

    // Handle remaining blocks (should be 3 or fewer)
    for block in blocks[1..].chunks_exact(4).remainder() {
        for i in 0..16 {
            result[i] ^= block[i];
        }
    }

    result
}

#[cfg(test)]
mod tests {
    #[test]
    fn test_aesl_spec_vector() {
        // Test vector from the specification
        let input = [
            0x00, 0x11, 0x22, 0x33, 0x44, 0x55, 0x66, 0x77, 0x88, 0x99, 0xaa, 0xbb, 0xcc, 0xdd,
            0xee, 0xff,
        ];
        let expected = [
            0x63, 0x79, 0xe6, 0xd9, 0xf4, 0x67, 0xfb, 0x76, 0xad, 0x06, 0x3c, 0xf4, 0xd2, 0xeb,
            0x8a, 0xa3,
        ];

        let result = crate::intrinsics::aesl(&input);
        assert_eq!(result, expected);
    }
}