diff options
| author | Harald Welte <laforge@osmocom.org> | 2020-08-02 10:19:32 +0200 |
|---|---|---|
| committer | Harald Welte <laforge@osmocom.org> | 2020-08-02 11:30:31 +0200 |
| commit | 2ba641edaaba0233f5b14ba85f48924f0333512d (patch) | |
| tree | c51dcc9acde0a324a6c48c38d11c4be5f5fff2a1 | |
| parent | 6d21448911514c818da58380d7f1345c78eeaae7 (diff) | |
bits.c: Use faster look-up-table approach for osmo_revbytebits_{buf,u8}
Benchmarking has shown that a look-up table based approach is much
faster than the arithmetic approach we used so far.
This is from a Core i7-6600U:
10 bytes, 1 iterations: flip=379, revb=5491; revb = 1448 %
10 bytes, 10 iterations: flip=728, revb=1517; revb = 208 %
10 bytes, 100 iterations: flip=2952, revb=9305; revb = 315 %
10 bytes, 1000 iterations: flip=26305, revb=90953; revb = 345 %
100 bytes, 1 iterations: flip=468, revb=1093; revb = 233 %
100 bytes, 10 iterations: flip=2634, revb=7418; revb = 281 %
100 bytes, 100 iterations: flip=23666, revb=70718; revb = 298 %
100 bytes, 1000 iterations: flip=237595, revb=900555; revb = 379 %
1024 bytes, 1 iterations: flip=3417, revb=11454; revb = 335 %
1024 bytes, 10 iterations: flip=33579, revb=92353; revb = 275 %
1024 bytes, 100 iterations: flip=555399, revb=1196228; revb = 215 %
1024 bytes, 1000 iterations: flip=3478271, revb=9227966; revb = 265 %
1048576 bytes, 1 iterations: flip=10189583, revb=7022193; revb = 68 %
1048576 bytes, 10 iterations: flip=19693347, revb=54389925; revb = 276 %
1048576 bytes, 100 iterations: flip=151308243, revb=454293151; revb = 300 %
1048576 bytes, 1000 iterations: flip=1390338439, revb=4429862642; revb = 318 %
where 'revb' is the old arithmetic approach, and 'flip' the new
look-up-table approach. In our usual cases of 100..1024 bytes in a
single iteration, the old code takes 233..335% of the look-up table.
Benchmarks on an Atom E6xx also show improvements except in one
situation (a single iteration over one 1MB large buffer).
10 bytes, 1 iterations: flip=416, revb=9184; revb = 2207 %
10 bytes, 10 iterations: flip=1960, revb=4024; revb = 205 %
10 bytes, 100 iterations: flip=13624, revb=32408; revb = 237 %
10 bytes, 1000 iterations: flip=160656, revb=361784; revb = 225 %
100 bytes, 1 iterations: flip=3536, revb=4952; revb = 140 %
100 bytes, 10 iterations: flip=12960, revb=20912; revb = 161 %
100 bytes, 100 iterations: flip=122448, revb=215152; revb = 175 %
100 bytes, 1000 iterations: flip=1204928, revb=1647680; revb = 136 %
1024 bytes, 1 iterations: flip=12944, revb=23128; revb = 178 %
1024 bytes, 10 iterations: flip=126192, revb=239784; revb = 190 %
1024 bytes, 100 iterations: flip=1190184, revb=1491672; revb = 125 %
1024 bytes, 1000 iterations: flip=11865872, revb=15113872; revb = 127 %
1048576 bytes, 1 iterations: flip=16288272, revb=15925888; revb = 97 %
1048576 bytes, 10 iterations: flip=121957000, revb=157883384; revb = 129 %
1048576 bytes, 100 iterations: flip=1219264992, revb=1621265216; revb = 132 %
1048576 bytes, 1000 iterations: flip=12219520648, revb=15960035856; revb = 130 %
Change-Id: I25029fe7e54c92979fb0119992fb8dc167e1536e
| -rw-r--r-- | src/bits.c | 58 |
1 files changed, 32 insertions, 26 deletions
@@ -226,6 +226,35 @@ int osmo_pbit2ubit_ext(ubit_t *out, unsigned int out_ofs, return out_ofs + num_bits; } +/* look-up table for bit-reversal within a byte. Generated using: + int i,k; + for (i = 0 ; i < 256 ; i++) { + uint8_t sample = 0 ; + for (k = 0; k<8; k++) { + if ( i & 1 << k ) sample |= 0x80 >> k; + } + flip_table[i] = sample; + } + */ +static const uint8_t flip_table[256] = { + 0x00, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x10, 0x90, 0x50, 0xd0, 0x30, 0xb0, 0x70, 0xf0, + 0x08, 0x88, 0x48, 0xc8, 0x28, 0xa8, 0x68, 0xe8, 0x18, 0x98, 0x58, 0xd8, 0x38, 0xb8, 0x78, 0xf8, + 0x04, 0x84, 0x44, 0xc4, 0x24, 0xa4, 0x64, 0xe4, 0x14, 0x94, 0x54, 0xd4, 0x34, 0xb4, 0x74, 0xf4, + 0x0c, 0x8c, 0x4c, 0xcc, 0x2c, 0xac, 0x6c, 0xec, 0x1c, 0x9c, 0x5c, 0xdc, 0x3c, 0xbc, 0x7c, 0xfc, + 0x02, 0x82, 0x42, 0xc2, 0x22, 0xa2, 0x62, 0xe2, 0x12, 0x92, 0x52, 0xd2, 0x32, 0xb2, 0x72, 0xf2, + 0x0a, 0x8a, 0x4a, 0xca, 0x2a, 0xaa, 0x6a, 0xea, 0x1a, 0x9a, 0x5a, 0xda, 0x3a, 0xba, 0x7a, 0xfa, + 0x06, 0x86, 0x46, 0xc6, 0x26, 0xa6, 0x66, 0xe6, 0x16, 0x96, 0x56, 0xd6, 0x36, 0xb6, 0x76, 0xf6, + 0x0e, 0x8e, 0x4e, 0xce, 0x2e, 0xae, 0x6e, 0xee, 0x1e, 0x9e, 0x5e, 0xde, 0x3e, 0xbe, 0x7e, 0xfe, + 0x01, 0x81, 0x41, 0xc1, 0x21, 0xa1, 0x61, 0xe1, 0x11, 0x91, 0x51, 0xd1, 0x31, 0xb1, 0x71, 0xf1, + 0x09, 0x89, 0x49, 0xc9, 0x29, 0xa9, 0x69, 0xe9, 0x19, 0x99, 0x59, 0xd9, 0x39, 0xb9, 0x79, 0xf9, + 0x05, 0x85, 0x45, 0xc5, 0x25, 0xa5, 0x65, 0xe5, 0x15, 0x95, 0x55, 0xd5, 0x35, 0xb5, 0x75, 0xf5, + 0x0d, 0x8d, 0x4d, 0xcd, 0x2d, 0xad, 0x6d, 0xed, 0x1d, 0x9d, 0x5d, 0xdd, 0x3d, 0xbd, 0x7d, 0xfd, + 0x03, 0x83, 0x43, 0xc3, 0x23, 0xa3, 0x63, 0xe3, 0x13, 0x93, 0x53, 0xd3, 0x33, 0xb3, 0x73, 0xf3, + 0x0b, 0x8b, 0x4b, 0xcb, 0x2b, 0xab, 0x6b, 0xeb, 0x1b, 0x9b, 0x5b, 0xdb, 0x3b, 0xbb, 0x7b, 0xfb, + 0x07, 0x87, 0x47, 0xc7, 0x27, 0xa7, 0x67, 0xe7, 0x17, 0x97, 0x57, 0xd7, 0x37, 0xb7, 0x77, 0xf7, + 0x0f, 0x8f, 0x4f, 0xcf, 0x2f, 0xaf, 0x6f, 0xef, 0x1f, 0x9f, 0x5f, 0xdf, 0x3f, 0xbf, 0x7f, 0xff, +}; + /*! generalized bit reversal function * \param[in] x the 32bit value to be reversed * \param[in] k the type of reversal requested @@ -265,16 +294,10 @@ uint32_t osmo_revbytebits_32(uint32_t x) /*! reverse the bit order in a byte * \param[in] x 8bit input value * \returns 8bit value where bits order has been reversed - * - * See Chapter 7 "Hackers Delight" */ uint32_t osmo_revbytebits_8(uint8_t x) { - x = (x & 0x55) << 1 | (x & 0xAA) >> 1; - x = (x & 0x33) << 2 | (x & 0xCC) >> 2; - x = (x & 0x0F) << 4 | (x & 0xF0) >> 4; - - return x; + return flip_table[x]; } /*! reverse bit-order of each byte in a buffer @@ -286,26 +309,9 @@ uint32_t osmo_revbytebits_8(uint8_t x) void osmo_revbytebits_buf(uint8_t *buf, int len) { unsigned int i; - unsigned int unaligned_cnt; - int len_remain = len; - unaligned_cnt = ((unsigned long)buf & 3); - for (i = 0; i < unaligned_cnt; i++) { - buf[i] = osmo_revbytebits_8(buf[i]); - len_remain--; - if (len_remain <= 0) - return; - } - - for (i = unaligned_cnt; i + 3 < len; i += 4) { - osmo_store32be(osmo_revbytebits_32(osmo_load32be(buf + i)), buf + i); - len_remain -= 4; - } - - for (i = len - len_remain; i < len; i++) { - buf[i] = osmo_revbytebits_8(buf[i]); - len_remain--; - } + for (i = 0; i < len; i++) + buf[i] = flip_table[buf[i]]; } /*! @} */ |