Thomas Helland <thomashellan...@gmail.com> writes: > This should give better cache locality, less memory consumption, > and should also be faster since we avoid a modulo operation. > Also change table size to be power of two. > This gives better performance as we can do bitmasking instead of > modulo operations for fitting the hash in the address space. > By using the algorithm hash = sh + i/2 + i*i/2 > ee are guaranteed that all retries from the quad probing > are distinct, and so should be able to completely fill the table. > This passes the test added to exercise a worst case collision scenario. > --- > src/util/hash_table.c | 101 > +++++++++++++++++++++++++------------------------- > src/util/hash_table.h | 1 - > 2 files changed, 50 insertions(+), 52 deletions(-) > > diff --git a/src/util/hash_table.c b/src/util/hash_table.c > index 3247593..92ffc10 100644 > --- a/src/util/hash_table.c > +++ b/src/util/hash_table.c > @@ -33,7 +33,7 @@ > */ > > /** > - * Implements an open-addressing, linear-reprobing hash table. > + * Implements an open-addressing, quadratic probing hash table. > * > * For more information, see: > * > @@ -51,44 +51,45 @@ > static const uint32_t deleted_key_value; > > /** > - * From Knuth -- a good choice for hash/rehash values is p, p-2 where > - * p and p-2 are both prime. These tables are sized to have an extra 10% > - * free to avoid exponential performance degradation as the hash table fills > + * We chose table sizes that's a power of two. > + * This is computationally less expensive than primes. > + * FNV-1a has good avalanche properties, so collision is not an issue. > + * These tables are sized to have an extra 10% free to avoid > + * exponential performance degradation as the hash table fills > */ > static const struct { > - uint32_t max_entries, size, rehash; > + uint32_t max_entries, size; > } hash_sizes[] = { > - { 2, 5, 3 }, > - { 4, 7, 5 }, > - { 8, 13, 11 }, > - { 16, 19, 17 }, > - { 32, 43, 41 }, > - { 64, 73, 71 }, > - { 128, 151, 149 }, > - { 256, 283, 281 }, > - { 512, 571, 569 }, > - { 1024, 1153, 1151 }, > - { 2048, 2269, 2267 }, > - { 4096, 4519, 4517 }, > - { 8192, 9013, 9011 }, > - { 16384, 18043, 18041 }, > - { 32768, 36109, 36107 }, > - { 65536, 72091, 72089 }, > - { 131072, 144409, 144407 }, > - { 262144, 288361, 288359 }, > - { 524288, 576883, 576881 }, > - { 1048576, 1153459, 1153457 }, > - { 2097152, 2307163, 2307161 }, > - { 4194304, 4613893, 4613891 }, > - { 8388608, 9227641, 9227639 }, > - { 16777216, 18455029, 18455027 }, > - { 33554432, 36911011, 36911009 }, > - { 67108864, 73819861, 73819859 }, > - { 134217728, 147639589, 147639587 }, > - { 268435456, 295279081, 295279079 }, > - { 536870912, 590559793, 590559791 }, > - { 1073741824, 1181116273, 1181116271}, > - { 2147483648ul, 2362232233ul, 2362232231ul} > + { 3, 4 }, > + { 7, 8 }, > + { 14, 16 }, > + { 28, 32 }, > + { 57, 64 }, > + { 115, 128 }, > + { 230, 256 }, > + { 460, 512 }, > + { 921, 1024 }, > + { 1843, 2048 }, > + { 3686, 4096 }, > + { 7372, 8192 }, > + { 14745, 16384 }, > + { 29491, 32768 }, > + { 58982, 65536 }, > + { 117964, 131072 }, > + { 235929, 262144 }, > + { 471859, 524288 }, > + { 943718, 1048576 }, > + { 1887436, 2097152 }, > + { 3774873, 4194304 }, > + { 7549747, 8388608 }, > + { 15099494, 16777216 }, > + { 30198988, 33554432 }, > + { 60397977, 67108864 }, > + { 120795955, 134217728 }, > + { 241591910, 268435456 }, > + { 483183820, 536870912 }, > + { 966367641, 1073741824 }, > + { 1932735283ul, 2147483648ul } > }; > > static int > @@ -123,7 +124,6 @@ _mesa_hash_table_create(void *mem_ctx, > > ht->size_index = 0; > ht->size = hash_sizes[ht->size_index].size; > - ht->rehash = hash_sizes[ht->size_index].rehash; > ht->max_entries = hash_sizes[ht->size_index].max_entries; > ht->key_hash_function = key_hash_function; > ht->key_equals_function = key_equals_function; > @@ -182,12 +182,12 @@ _mesa_hash_table_set_deleted_key(struct hash_table *ht, > const void *deleted_key) > static struct hash_entry * > hash_table_search(struct hash_table *ht, uint32_t hash, const void *key) > { > - uint32_t start_hash_address = hash % ht->size; > + uint32_t start_hash_address = hash & (ht->size - 1); > uint32_t hash_address = start_hash_address; > + // Start at 2, or we will match start_hash_address initially and bail > + uint32_t quad_hash = 2; > > do { > - uint32_t double_hash; > - > struct hash_entry *entry = ht->table + hash_address; > > if (entry_is_free(entry)) { > @@ -198,9 +198,9 @@ hash_table_search(struct hash_table *ht, uint32_t hash, > const void *key) > } > } > > - double_hash = 1 + hash % ht->rehash; > - > - hash_address = (hash_address + double_hash) % ht->size; > + hash_address = (start_hash_address + (quad_hash / 2) + > + ((quad_hash * quad_hash) / 2)) & (ht->size - 1); > + quad_hash++;
I'm assuming you wanted the sequence quoted at: http://en.wikipedia.org/wiki/Quadratic_probing But looking at the iterations of your quad_hash, since you're using integer math: (2 / 2) + (2 * 2) / 2 = 1 + 2 = 3 (3 / 2) + (3 * 3) / 2 = 1 + 4 = 5 (4 / 2) + (4 * 4) / 2 = 2 + 8 = 10 (5 / 2) + (5 * 5) / 2 = 2 + 12 = 14 I think what you wanted as your probe is: uint32_t double_hash = 1; ... hash_address = (start_hash_address + ((quad_hash + quad_hash * quad_hash) >> 1)) & (ht->size - 1) quad_hash++; Then you get: (1 + 1 * 1) / 2 = 3 / 2 = 1 (2 + 2 * 2) / 2 = 6 / 2 = 3 (3 + 3 * 3) / 2 = 12 / 2 = 6 (4 + 4 * 4) / 2 = 20 / 2 = 10
signature.asc
Description: PGP signature
_______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/mesa-dev