diff options
author | Jack Lloyd <[email protected]> | 2019-02-21 10:52:20 -0500 |
---|---|---|
committer | Jack Lloyd <[email protected]> | 2019-02-21 10:52:20 -0500 |
commit | a66ca068a2456fc6f96d7f020a1d1556eb56ce83 (patch) | |
tree | 9bd4422489a15795ff9265a7869b96efd8c5f7d6 /src/lib | |
parent | 95249af832950ed6f617cead59a504e47ed57499 (diff) | |
parent | 331551087a341f0fdd758045c3f37d8d96a5d049 (diff) |
Merge GH #1838 Unroll SHA-3
Diffstat (limited to 'src/lib')
-rw-r--r-- | src/lib/hash/sha3/sha3.cpp | 145 | ||||
-rw-r--r-- | src/lib/hash/sha3/sha3_bmi2/sha3_bmi2.cpp | 145 |
2 files changed, 158 insertions, 132 deletions
diff --git a/src/lib/hash/sha3/sha3.cpp b/src/lib/hash/sha3/sha3.cpp index 837768f85..d01d33635 100644 --- a/src/lib/hash/sha3/sha3.cpp +++ b/src/lib/hash/sha3/sha3.cpp @@ -12,6 +12,80 @@ namespace Botan { +namespace { + +inline void SHA3_round(uint64_t T[25], const uint64_t A[25], uint64_t RC) + { + const uint64_t C0 = A[0] ^ A[5] ^ A[10] ^ A[15] ^ A[20]; + const uint64_t C1 = A[1] ^ A[6] ^ A[11] ^ A[16] ^ A[21]; + const uint64_t C2 = A[2] ^ A[7] ^ A[12] ^ A[17] ^ A[22]; + const uint64_t C3 = A[3] ^ A[8] ^ A[13] ^ A[18] ^ A[23]; + const uint64_t C4 = A[4] ^ A[9] ^ A[14] ^ A[19] ^ A[24]; + + const uint64_t D0 = rotl<1>(C0) ^ C3; + const uint64_t D1 = rotl<1>(C1) ^ C4; + const uint64_t D2 = rotl<1>(C2) ^ C0; + const uint64_t D3 = rotl<1>(C3) ^ C1; + const uint64_t D4 = rotl<1>(C4) ^ C2; + + const uint64_t B00 = A[ 0] ^ D1; + const uint64_t B01 = rotl<44>(A[ 6] ^ D2); + const uint64_t B02 = rotl<43>(A[12] ^ D3); + const uint64_t B03 = rotl<21>(A[18] ^ D4); + const uint64_t B04 = rotl<14>(A[24] ^ D0); + T[ 0] = B00 ^ (~B01 & B02) ^ RC; + T[ 1] = B01 ^ (~B02 & B03); + T[ 2] = B02 ^ (~B03 & B04); + T[ 3] = B03 ^ (~B04 & B00); + T[ 4] = B04 ^ (~B00 & B01); + + const uint64_t B05 = rotl<28>(A[ 3] ^ D4); + const uint64_t B06 = rotl<20>(A[ 9] ^ D0); + const uint64_t B07 = rotl< 3>(A[10] ^ D1); + const uint64_t B08 = rotl<45>(A[16] ^ D2); + const uint64_t B09 = rotl<61>(A[22] ^ D3); + T[ 5] = B05 ^ (~B06 & B07); + T[ 6] = B06 ^ (~B07 & B08); + T[ 7] = B07 ^ (~B08 & B09); + T[ 8] = B08 ^ (~B09 & B05); + T[ 9] = B09 ^ (~B05 & B06); + + const uint64_t B10 = rotl< 1>(A[ 1] ^ D2); + const uint64_t B11 = rotl< 6>(A[ 7] ^ D3); + const uint64_t B12 = rotl<25>(A[13] ^ D4); + const uint64_t B13 = rotl< 8>(A[19] ^ D0); + const uint64_t B14 = rotl<18>(A[20] ^ D1); + T[10] = B10 ^ (~B11 & B12); + T[11] = B11 ^ (~B12 & B13); + T[12] = B12 ^ (~B13 & B14); + T[13] = B13 ^ (~B14 & B10); + T[14] = B14 ^ (~B10 & B11); + + const uint64_t B15 = rotl<27>(A[ 4] ^ D0); + const uint64_t B16 = rotl<36>(A[ 5] ^ D1); + const uint64_t B17 = rotl<10>(A[11] ^ D2); + const uint64_t B18 = rotl<15>(A[17] ^ D3); + const uint64_t B19 = rotl<56>(A[23] ^ D4); + T[15] = B15 ^ (~B16 & B17); + T[16] = B16 ^ (~B17 & B18); + T[17] = B17 ^ (~B18 & B19); + T[18] = B18 ^ (~B19 & B15); + T[19] = B19 ^ (~B15 & B16); + + const uint64_t B20 = rotl<62>(A[ 2] ^ D3); + const uint64_t B21 = rotl<55>(A[ 8] ^ D4); + const uint64_t B22 = rotl<39>(A[14] ^ D0); + const uint64_t B23 = rotl<41>(A[15] ^ D1); + const uint64_t B24 = rotl< 2>(A[21] ^ D2); + T[20] = B20 ^ (~B21 & B22); + T[21] = B21 ^ (~B22 & B23); + T[22] = B22 ^ (~B23 & B24); + T[23] = B23 ^ (~B24 & B20); + T[24] = B24 ^ (~B20 & B21); + } + +} + //static void SHA_3::permute(uint64_t A[25]) { @@ -33,73 +107,12 @@ void SHA_3::permute(uint64_t A[25]) 0x8000000000008080, 0x0000000080000001, 0x8000000080008008 }; - for(size_t i = 0; i != 24; ++i) + uint64_t T[25]; + + for(size_t i = 0; i != 24; i += 2) { - const uint64_t C0 = A[0] ^ A[5] ^ A[10] ^ A[15] ^ A[20]; - const uint64_t C1 = A[1] ^ A[6] ^ A[11] ^ A[16] ^ A[21]; - const uint64_t C2 = A[2] ^ A[7] ^ A[12] ^ A[17] ^ A[22]; - const uint64_t C3 = A[3] ^ A[8] ^ A[13] ^ A[18] ^ A[23]; - const uint64_t C4 = A[4] ^ A[9] ^ A[14] ^ A[19] ^ A[24]; - - const uint64_t D0 = rotl<1>(C0) ^ C3; - const uint64_t D1 = rotl<1>(C1) ^ C4; - const uint64_t D2 = rotl<1>(C2) ^ C0; - const uint64_t D3 = rotl<1>(C3) ^ C1; - const uint64_t D4 = rotl<1>(C4) ^ C2; - - const uint64_t B00 = A[ 0] ^ D1; - const uint64_t B10 = rotl< 1>(A[ 1] ^ D2); - const uint64_t B20 = rotl<62>(A[ 2] ^ D3); - const uint64_t B05 = rotl<28>(A[ 3] ^ D4); - const uint64_t B15 = rotl<27>(A[ 4] ^ D0); - const uint64_t B16 = rotl<36>(A[ 5] ^ D1); - const uint64_t B01 = rotl<44>(A[ 6] ^ D2); - const uint64_t B11 = rotl< 6>(A[ 7] ^ D3); - const uint64_t B21 = rotl<55>(A[ 8] ^ D4); - const uint64_t B06 = rotl<20>(A[ 9] ^ D0); - const uint64_t B07 = rotl< 3>(A[10] ^ D1); - const uint64_t B17 = rotl<10>(A[11] ^ D2); - const uint64_t B02 = rotl<43>(A[12] ^ D3); - const uint64_t B12 = rotl<25>(A[13] ^ D4); - const uint64_t B22 = rotl<39>(A[14] ^ D0); - const uint64_t B23 = rotl<41>(A[15] ^ D1); - const uint64_t B08 = rotl<45>(A[16] ^ D2); - const uint64_t B18 = rotl<15>(A[17] ^ D3); - const uint64_t B03 = rotl<21>(A[18] ^ D4); - const uint64_t B13 = rotl< 8>(A[19] ^ D0); - const uint64_t B14 = rotl<18>(A[20] ^ D1); - const uint64_t B24 = rotl< 2>(A[21] ^ D2); - const uint64_t B09 = rotl<61>(A[22] ^ D3); - const uint64_t B19 = rotl<56>(A[23] ^ D4); - const uint64_t B04 = rotl<14>(A[24] ^ D0); - - A[ 0] = B00 ^ (~B01 & B02); - A[ 1] = B01 ^ (~B02 & B03); - A[ 2] = B02 ^ (~B03 & B04); - A[ 3] = B03 ^ (~B04 & B00); - A[ 4] = B04 ^ (~B00 & B01); - A[ 5] = B05 ^ (~B06 & B07); - A[ 6] = B06 ^ (~B07 & B08); - A[ 7] = B07 ^ (~B08 & B09); - A[ 8] = B08 ^ (~B09 & B05); - A[ 9] = B09 ^ (~B05 & B06); - A[10] = B10 ^ (~B11 & B12); - A[11] = B11 ^ (~B12 & B13); - A[12] = B12 ^ (~B13 & B14); - A[13] = B13 ^ (~B14 & B10); - A[14] = B14 ^ (~B10 & B11); - A[15] = B15 ^ (~B16 & B17); - A[16] = B16 ^ (~B17 & B18); - A[17] = B17 ^ (~B18 & B19); - A[18] = B18 ^ (~B19 & B15); - A[19] = B19 ^ (~B15 & B16); - A[20] = B20 ^ (~B21 & B22); - A[21] = B21 ^ (~B22 & B23); - A[22] = B22 ^ (~B23 & B24); - A[23] = B23 ^ (~B24 & B20); - A[24] = B24 ^ (~B20 & B21); - - A[0] ^= RC[i]; + SHA3_round(T, A, RC[i+0]); + SHA3_round(A, T, RC[i+1]); } } diff --git a/src/lib/hash/sha3/sha3_bmi2/sha3_bmi2.cpp b/src/lib/hash/sha3/sha3_bmi2/sha3_bmi2.cpp index f2161b9ba..420a90f9f 100644 --- a/src/lib/hash/sha3/sha3_bmi2/sha3_bmi2.cpp +++ b/src/lib/hash/sha3/sha3_bmi2/sha3_bmi2.cpp @@ -10,6 +10,80 @@ namespace Botan { +namespace { + +inline void SHA3_round(uint64_t T[25], const uint64_t A[25], uint64_t RC) + { + const uint64_t C0 = A[0] ^ A[5] ^ A[10] ^ A[15] ^ A[20]; + const uint64_t C1 = A[1] ^ A[6] ^ A[11] ^ A[16] ^ A[21]; + const uint64_t C2 = A[2] ^ A[7] ^ A[12] ^ A[17] ^ A[22]; + const uint64_t C3 = A[3] ^ A[8] ^ A[13] ^ A[18] ^ A[23]; + const uint64_t C4 = A[4] ^ A[9] ^ A[14] ^ A[19] ^ A[24]; + + const uint64_t D0 = rotl<1>(C0) ^ C3; + const uint64_t D1 = rotl<1>(C1) ^ C4; + const uint64_t D2 = rotl<1>(C2) ^ C0; + const uint64_t D3 = rotl<1>(C3) ^ C1; + const uint64_t D4 = rotl<1>(C4) ^ C2; + + const uint64_t B00 = A[ 0] ^ D1; + const uint64_t B01 = rotl<44>(A[ 6] ^ D2); + const uint64_t B02 = rotl<43>(A[12] ^ D3); + const uint64_t B03 = rotl<21>(A[18] ^ D4); + const uint64_t B04 = rotl<14>(A[24] ^ D0); + T[ 0] = B00 ^ (~B01 & B02) ^ RC; + T[ 1] = B01 ^ (~B02 & B03); + T[ 2] = B02 ^ (~B03 & B04); + T[ 3] = B03 ^ (~B04 & B00); + T[ 4] = B04 ^ (~B00 & B01); + + const uint64_t B05 = rotl<28>(A[ 3] ^ D4); + const uint64_t B06 = rotl<20>(A[ 9] ^ D0); + const uint64_t B07 = rotl< 3>(A[10] ^ D1); + const uint64_t B08 = rotl<45>(A[16] ^ D2); + const uint64_t B09 = rotl<61>(A[22] ^ D3); + T[ 5] = B05 ^ (~B06 & B07); + T[ 6] = B06 ^ (~B07 & B08); + T[ 7] = B07 ^ (~B08 & B09); + T[ 8] = B08 ^ (~B09 & B05); + T[ 9] = B09 ^ (~B05 & B06); + + const uint64_t B10 = rotl< 1>(A[ 1] ^ D2); + const uint64_t B11 = rotl< 6>(A[ 7] ^ D3); + const uint64_t B12 = rotl<25>(A[13] ^ D4); + const uint64_t B13 = rotl< 8>(A[19] ^ D0); + const uint64_t B14 = rotl<18>(A[20] ^ D1); + T[10] = B10 ^ (~B11 & B12); + T[11] = B11 ^ (~B12 & B13); + T[12] = B12 ^ (~B13 & B14); + T[13] = B13 ^ (~B14 & B10); + T[14] = B14 ^ (~B10 & B11); + + const uint64_t B15 = rotl<27>(A[ 4] ^ D0); + const uint64_t B16 = rotl<36>(A[ 5] ^ D1); + const uint64_t B17 = rotl<10>(A[11] ^ D2); + const uint64_t B18 = rotl<15>(A[17] ^ D3); + const uint64_t B19 = rotl<56>(A[23] ^ D4); + T[15] = B15 ^ (~B16 & B17); + T[16] = B16 ^ (~B17 & B18); + T[17] = B17 ^ (~B18 & B19); + T[18] = B18 ^ (~B19 & B15); + T[19] = B19 ^ (~B15 & B16); + + const uint64_t B20 = rotl<62>(A[ 2] ^ D3); + const uint64_t B21 = rotl<55>(A[ 8] ^ D4); + const uint64_t B22 = rotl<39>(A[14] ^ D0); + const uint64_t B23 = rotl<41>(A[15] ^ D1); + const uint64_t B24 = rotl< 2>(A[21] ^ D2); + T[20] = B20 ^ (~B21 & B22); + T[21] = B21 ^ (~B22 & B23); + T[22] = B22 ^ (~B23 & B24); + T[23] = B23 ^ (~B24 & B20); + T[24] = B24 ^ (~B20 & B21); + } + +} + void SHA_3::permute_bmi2(uint64_t A[25]) { static const uint64_t RC[24] = { @@ -23,73 +97,12 @@ void SHA_3::permute_bmi2(uint64_t A[25]) 0x8000000000008080, 0x0000000080000001, 0x8000000080008008 }; - for(size_t i = 0; i != 24; ++i) - { - const uint64_t C0 = A[0] ^ A[5] ^ A[10] ^ A[15] ^ A[20]; - const uint64_t C1 = A[1] ^ A[6] ^ A[11] ^ A[16] ^ A[21]; - const uint64_t C2 = A[2] ^ A[7] ^ A[12] ^ A[17] ^ A[22]; - const uint64_t C3 = A[3] ^ A[8] ^ A[13] ^ A[18] ^ A[23]; - const uint64_t C4 = A[4] ^ A[9] ^ A[14] ^ A[19] ^ A[24]; - - const uint64_t D0 = rotl<1>(C0) ^ C3; - const uint64_t D1 = rotl<1>(C1) ^ C4; - const uint64_t D2 = rotl<1>(C2) ^ C0; - const uint64_t D3 = rotl<1>(C3) ^ C1; - const uint64_t D4 = rotl<1>(C4) ^ C2; - - const uint64_t B00 = A[ 0] ^ D1; - const uint64_t B10 = rotl< 1>(A[ 1] ^ D2); - const uint64_t B20 = rotl<62>(A[ 2] ^ D3); - const uint64_t B05 = rotl<28>(A[ 3] ^ D4); - const uint64_t B15 = rotl<27>(A[ 4] ^ D0); - const uint64_t B16 = rotl<36>(A[ 5] ^ D1); - const uint64_t B01 = rotl<44>(A[ 6] ^ D2); - const uint64_t B11 = rotl< 6>(A[ 7] ^ D3); - const uint64_t B21 = rotl<55>(A[ 8] ^ D4); - const uint64_t B06 = rotl<20>(A[ 9] ^ D0); - const uint64_t B07 = rotl< 3>(A[10] ^ D1); - const uint64_t B17 = rotl<10>(A[11] ^ D2); - const uint64_t B02 = rotl<43>(A[12] ^ D3); - const uint64_t B12 = rotl<25>(A[13] ^ D4); - const uint64_t B22 = rotl<39>(A[14] ^ D0); - const uint64_t B23 = rotl<41>(A[15] ^ D1); - const uint64_t B08 = rotl<45>(A[16] ^ D2); - const uint64_t B18 = rotl<15>(A[17] ^ D3); - const uint64_t B03 = rotl<21>(A[18] ^ D4); - const uint64_t B13 = rotl< 8>(A[19] ^ D0); - const uint64_t B14 = rotl<18>(A[20] ^ D1); - const uint64_t B24 = rotl< 2>(A[21] ^ D2); - const uint64_t B09 = rotl<61>(A[22] ^ D3); - const uint64_t B19 = rotl<56>(A[23] ^ D4); - const uint64_t B04 = rotl<14>(A[24] ^ D0); + uint64_t T[25]; - A[ 0] = B00 ^ (~B01 & B02); - A[ 1] = B01 ^ (~B02 & B03); - A[ 2] = B02 ^ (~B03 & B04); - A[ 3] = B03 ^ (~B04 & B00); - A[ 4] = B04 ^ (~B00 & B01); - A[ 5] = B05 ^ (~B06 & B07); - A[ 6] = B06 ^ (~B07 & B08); - A[ 7] = B07 ^ (~B08 & B09); - A[ 8] = B08 ^ (~B09 & B05); - A[ 9] = B09 ^ (~B05 & B06); - A[10] = B10 ^ (~B11 & B12); - A[11] = B11 ^ (~B12 & B13); - A[12] = B12 ^ (~B13 & B14); - A[13] = B13 ^ (~B14 & B10); - A[14] = B14 ^ (~B10 & B11); - A[15] = B15 ^ (~B16 & B17); - A[16] = B16 ^ (~B17 & B18); - A[17] = B17 ^ (~B18 & B19); - A[18] = B18 ^ (~B19 & B15); - A[19] = B19 ^ (~B15 & B16); - A[20] = B20 ^ (~B21 & B22); - A[21] = B21 ^ (~B22 & B23); - A[22] = B22 ^ (~B23 & B24); - A[23] = B23 ^ (~B24 & B20); - A[24] = B24 ^ (~B20 & B21); - - A[0] ^= RC[i]; + for(size_t i = 0; i != 24; i += 2) + { + SHA3_round(T, A, RC[i+0]); + SHA3_round(A, T, RC[i+1]); } } |