aboutsummaryrefslogtreecommitdiffstats
path: root/searchlib
Commit message (Collapse)AuthorAgeFilesLines
* remove parameter count from interpreted functionsHåvard Pettersen2020-04-031-1/+1
|
* count reachables for statisticsArne Juul2020-04-012-3/+38
|
* use snake_caseArne Juul2020-04-012-7/+7
|
* add some simple statistics when exploring stateArne Juul2020-04-013-0/+28
|
* Merge pull request #12779 from ↵Geir Storli2020-03-319-77/+217
|\ | | | | | | | | vespa-engine/geirst/nearest-neighbor-index-saving-and-loading Nearest neighbor index saving and loading
| * Test that hnsw index is integrated in dense tensor attribute.Geir Storli2020-03-311-11/+49
| |
| * Implement saving and loading of nearest neighbor index.Geir Storli2020-03-319-66/+168
| |
* | - Add testing of enumerated weighted sets.Henning Baldersheim2020-03-312-14/+19
|/ | | | | - Add testing that query can use floating point numbers for the weight. - Stay with the type feature_t for query. Do not assume th ethe weight type used in the attribute.
* Merge pull request #12765 from vespa-engine/geirst/attribute-loading-cleanupGeir Storli2020-03-3016-162/+141
|\ | | | | Attribute loading cleanup
| * Use const reference to attribute vector.Geir Storli2020-03-302-19/+19
| |
| * Remove opening of udat file which is never used.Geir Storli2020-03-304-41/+10
| | | | | | | | All loading of udat file is using LoadUtils::loadUDAT() instead.
| * Move functions used to open / load attribute vector data files to separate ↵Geir Storli2020-03-3015-129/+139
| | | | | | | | class.
* | Merge pull request #12753 from vespa-engine/toregge/handle-newer-gtest-versionTor Egge2020-03-303-5/+5
|\ \ | |/ |/| Handle newer gtest versions where the legacy API is deprecated.
| * Reduce code duplication in test code.Tor Egge2020-03-303-25/+5
| |
| * Handle newer gtest versions where the legacy API is deprecated.Tor Egge2020-03-293-0/+20
| |
* | Merge pull request #12733 from vespa-engine/arnej/add-hnsw-index-save-and-loadGeir Storli2020-03-3016-154/+553
|\ \ | |/ |/| Add save and load of HNSW index
| * review follow-up:Arne Juul2020-03-279-38/+55
| | | | | | | | | | | | * add documentation comments * style fixes * return bool from load() for error handling
| * Add save and load of HNSW indexArne Juul2020-03-2614-150/+532
| | | | | | | | | | | | | | | | * split graph data out into a simpler struct * implement HnswIndexSaver * implement HnswIndexLoader * add unit test checking that saving and loading works as expected
* | Extend attribute save targets to support custom file writers.Geir Storli2020-03-2711-30/+304
| | | | | | | | This is a preparation for saving and loading nearest neighbor index in the tensor attribute code.
* | adaptive sequenced executor (experimental)Håvard Pettersen2020-03-266-18/+768
|/
* Merge pull request #12713 from ↵Arne H Juul2020-03-255-4/+67
|\ | | | | | | | | vespa-engine/geirst/nearest-neighbor-index-saver-skeleton Add skeleton for nearest neighbor index saver.
| * Add skeleton for nearest neighbor index saver.Geir Storli2020-03-255-4/+67
| |
* | Unify the metrics for queuesize similar to what we have for the spi queues.Henning Baldersheim2020-03-251-1/+1
|/
* Merge pull request #12691 from ↵Geir Storli2020-03-2414-11/+114
|\ | | | | | | | | vespa-engine/geirst/tensor-attribute-in-state-explorer Expose information from tensor attribute and hnsw index in state expl…
| * Expose information from tensor attribute and hnsw index in state explorer ↵Geir Storli2020-03-2414-11/+114
| | | | | | | | for attribute.
* | Merge pull request #12690 from vespa-engine/havardpe/rank-setup-stack-usageHåvard Pettersen2020-03-241-9/+35
|\ \ | | | | | | rank setup stack usage
| * | rank setup stack usageHåvard Pettersen2020-03-241-9/+35
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | With large models comes large stack usage. - compile in separate thread for deterministic stack size (verify rank setup vs. proton config setup) - warn about stack usage when over 128K (note that recursive decent parsing of rank expressions comes on top of the usage reported by the blueprint resolver)
* | | Merge pull request #12671 from vespa-engine/arnej/configurable-distance-metricsArne H Juul2020-03-2422-87/+534
|\ \ \ | |/ / |/| | Arnej/configurable distance metrics
| * | update copyright headersArne Juul2020-03-242-2/+2
| | |
| * | extend unit testArne Juul2020-03-241-0/+4
| | |
| * | add documentation commentArne Juul2020-03-241-0/+4
| | |
| * | constify DistanceFunctionArne Juul2020-03-249-13/+13
| | |
| * | add reference and refactorArne Juul2020-03-241-7/+10
| | |
| * | remove debug printingArne Juul2020-03-241-2/+0
| | |
| * | unit test distance functionsArne Juul2020-03-244-1/+208
| | |
| * | output distance in metersArne Juul2020-03-241-7/+12
| | |
| * | simplify iteratorArne Juul2020-03-231-27/+8
| | | | | | | | | | | | | | | * now distance function handles cell type, so iterator does not need to be templated on that.
| * | track API changesArne Juul2020-03-231-7/+18
| | | | | | | | | | | | * also, NNS iterators no longer handles different cell types
| * | check that query tensor is converted correctlyArne Juul2020-03-231-6/+10
| | |
| * | use distance function from index if availableArne Juul2020-03-236-34/+87
| | | | | | | | | | | | | | | | | | | | | * convert query tensor to same cell type as attribute * use DistanceFunction to calculate abstract distances for NNS * use DistanceFunction to convert abstract distances to rawscore * if no index is available, use a fallback DistanceFunction
| * | use external factory for distance functionArne Juul2020-03-231-11/+5
| | |
| * | track API changesArne Juul2020-03-231-1/+4
| | |
| * | extend API with distance_function accessArne Juul2020-03-232-0/+3
| | |
| * | add distance metric to HnswIndexParamsArne Juul2020-03-231-1/+15
| | |
| * | split out DistanceFunction factoryArne Juul2020-03-233-0/+57
| | |
| * | more distance functionsArne Juul2020-03-232-0/+106
| |/ | | | | | | | | | | * extend DistanceFunction API * add Angular metric * add GeoDegrees metric
* / Avoid expensive systemcall. We already track the writeposition in byteSize.Henning Baldersheim2020-03-231-2/+4
|/
* Include limits header file when needed.Tor Egge2020-03-212-0/+2
|
* Revert "Revert "Since the most important aspect our use of hash maps/sets is ↵Henning Baldersheim2020-03-201-2/+2
| | | | for spee…""
* Revert "Since the most important aspect our use of hash maps/sets is for ↵Harald Musum2020-03-201-2/+2
| | | | spee…"