1/** 2 * Copyright 2013, GitHub, Inc 3 * Copyright 2009-2013, Daniel Lemire, Cliff Moon, 4 * David McIntosh, Robert Becho, Google Inc. and Veronika Zenz 5 * 6 * This program is free software; you can redistribute it and/or 7 * modify it under the terms of the GNU General Public License 8 * as published by the Free Software Foundation; either version 2 9 * of the License, or (at your option) any later version. 10 * 11 * This program is distributed in the hope that it will be useful, 12 * but WITHOUT ANY WARRANTY; without even the implied warranty of 13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 * GNU General Public License for more details. 15 * 16 * You should have received a copy of the GNU General Public License 17 * along with this program; if not, see <http://www.gnu.org/licenses/>. 18 */ 19#ifndef __EWOK_BITMAP_H__ 20#define __EWOK_BITMAP_H__ 21 22struct strbuf; 23typedefuint64_t eword_t; 24#define BITS_IN_EWORD (sizeof(eword_t) * 8) 25 26/** 27 * Do not use __builtin_popcountll. The GCC implementation 28 * is notoriously slow on all platforms. 29 * 30 * See: http://gcc.gnu.org/bugzilla/show_bug.cgi?id=36041 31 */ 32staticinlineuint32_tewah_bit_popcount64(uint64_t x) 33{ 34 x = (x &0x5555555555555555ULL) + ((x >>1) &0x5555555555555555ULL); 35 x = (x &0x3333333333333333ULL) + ((x >>2) &0x3333333333333333ULL); 36 x = (x &0x0F0F0F0F0F0F0F0FULL) + ((x >>4) &0x0F0F0F0F0F0F0F0FULL); 37return(x *0x0101010101010101ULL) >>56; 38} 39 40/* __builtin_ctzll was not available until 3.4.0 */ 41#if defined(__GNUC__) && (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR > 3)) 42#define ewah_bit_ctz64(x) __builtin_ctzll(x) 43#else 44staticinlineintewah_bit_ctz64(uint64_t x) 45{ 46int n =0; 47if((x &0xffffffff) ==0) { x >>=32; n +=32; } 48if((x &0xffff) ==0) { x >>=16; n +=16; } 49if((x &0xff) ==0) { x >>=8; n +=8; } 50if((x &0xf) ==0) { x >>=4; n +=4; } 51if((x &0x3) ==0) { x >>=2; n +=2; } 52if((x &0x1) ==0) { x >>=1; n +=1; } 53return n + !x; 54} 55#endif 56 57struct ewah_bitmap { 58 eword_t *buffer; 59size_t buffer_size; 60size_t alloc_size; 61size_t bit_size; 62 eword_t *rlw; 63}; 64 65typedefvoid(*ewah_callback)(size_t pos,void*); 66 67struct ewah_bitmap *ewah_pool_new(void); 68voidewah_pool_free(struct ewah_bitmap *self); 69 70/** 71 * Allocate a new EWAH Compressed bitmap 72 */ 73struct ewah_bitmap *ewah_new(void); 74 75/** 76 * Clear all the bits in the bitmap. Does not free or resize 77 * memory. 78 */ 79voidewah_clear(struct ewah_bitmap *self); 80 81/** 82 * Free all the memory of the bitmap 83 */ 84voidewah_free(struct ewah_bitmap *self); 85 86intewah_serialize_to(struct ewah_bitmap *self, 87int(*write_fun)(void*out,const void*buf,size_t len), 88void*out); 89intewah_serialize(struct ewah_bitmap *self,int fd); 90intewah_serialize_native(struct ewah_bitmap *self,int fd); 91intewah_serialize_strbuf(struct ewah_bitmap *self,struct strbuf *); 92 93intewah_deserialize(struct ewah_bitmap *self,int fd); 94intewah_read_mmap(struct ewah_bitmap *self,const void*map,size_t len); 95 96uint32_tewah_checksum(struct ewah_bitmap *self); 97 98/** 99 * Logical not (bitwise negation) in-place on the bitmap 100 * 101 * This operation is linear time based on the size of the bitmap. 102 */ 103voidewah_not(struct ewah_bitmap *self); 104 105/** 106 * Call the given callback with the position of every single bit 107 * that has been set on the bitmap. 108 * 109 * This is an efficient operation that does not fully decompress 110 * the bitmap. 111 */ 112voidewah_each_bit(struct ewah_bitmap *self, ewah_callback callback,void*payload); 113 114/** 115 * Set a given bit on the bitmap. 116 * 117 * The bit at position `pos` will be set to true. Because of the 118 * way that the bitmap is compressed, a set bit cannot be unset 119 * later on. 120 * 121 * Furthermore, since the bitmap uses streaming compression, bits 122 * can only set incrementally. 123 * 124 * E.g. 125 * ewah_set(bitmap, 1); // ok 126 * ewah_set(bitmap, 76); // ok 127 * ewah_set(bitmap, 77); // ok 128 * ewah_set(bitmap, 8712800127); // ok 129 * ewah_set(bitmap, 25); // failed, assert raised 130 */ 131voidewah_set(struct ewah_bitmap *self,size_t i); 132 133struct ewah_iterator { 134const eword_t *buffer; 135size_t buffer_size; 136 137size_t pointer; 138 eword_t compressed, literals; 139 eword_t rl, lw; 140int b; 141}; 142 143/** 144 * Initialize a new iterator to run through the bitmap in uncompressed form. 145 * 146 * The iterator can be stack allocated. The underlying bitmap must not be freed 147 * before the iteration is over. 148 * 149 * E.g. 150 * 151 * struct ewah_bitmap *bitmap = ewah_new(); 152 * struct ewah_iterator it; 153 * 154 * ewah_iterator_init(&it, bitmap); 155 */ 156voidewah_iterator_init(struct ewah_iterator *it,struct ewah_bitmap *parent); 157 158/** 159 * Yield every single word in the bitmap in uncompressed form. This is: 160 * yield single words (32-64 bits) where each bit represents an actual 161 * bit from the bitmap. 162 * 163 * Return: true if a word was yield, false if there are no words left 164 */ 165intewah_iterator_next(eword_t *next,struct ewah_iterator *it); 166 167voidewah_or( 168struct ewah_bitmap *ewah_i, 169struct ewah_bitmap *ewah_j, 170struct ewah_bitmap *out); 171 172voidewah_and_not( 173struct ewah_bitmap *ewah_i, 174struct ewah_bitmap *ewah_j, 175struct ewah_bitmap *out); 176 177voidewah_xor( 178struct ewah_bitmap *ewah_i, 179struct ewah_bitmap *ewah_j, 180struct ewah_bitmap *out); 181 182voidewah_and( 183struct ewah_bitmap *ewah_i, 184struct ewah_bitmap *ewah_j, 185struct ewah_bitmap *out); 186 187/** 188 * Direct word access 189 */ 190size_tewah_add_empty_words(struct ewah_bitmap *self,int v,size_t number); 191voidewah_add_dirty_words( 192struct ewah_bitmap *self,const eword_t *buffer,size_t number,int negate); 193size_tewah_add(struct ewah_bitmap *self, eword_t word); 194 195 196/** 197 * Uncompressed, old-school bitmap that can be efficiently compressed 198 * into an `ewah_bitmap`. 199 */ 200struct bitmap { 201 eword_t *words; 202size_t word_alloc; 203}; 204 205struct bitmap *bitmap_new(void); 206voidbitmap_set(struct bitmap *self,size_t pos); 207voidbitmap_clear(struct bitmap *self,size_t pos); 208intbitmap_get(struct bitmap *self,size_t pos); 209voidbitmap_reset(struct bitmap *self); 210voidbitmap_free(struct bitmap *self); 211intbitmap_equals(struct bitmap *self,struct bitmap *other); 212intbitmap_is_subset(struct bitmap *self,struct bitmap *super); 213 214struct ewah_bitmap *bitmap_to_ewah(struct bitmap *bitmap); 215struct bitmap *ewah_to_bitmap(struct ewah_bitmap *ewah); 216 217voidbitmap_and_not(struct bitmap *self,struct bitmap *other); 218voidbitmap_or_ewah(struct bitmap *self,struct ewah_bitmap *other); 219voidbitmap_or(struct bitmap *self,const struct bitmap *other); 220 221voidbitmap_each_bit(struct bitmap *self, ewah_callback callback,void*data); 222size_tbitmap_popcount(struct bitmap *self); 223 224#endif