Commit message (Collapse) | Author | Age | Files | Lines | ||
---|---|---|---|---|---|---|
... | ||||||
* | remove conformance test file (run tests directly instead) | Håvard Pettersen | 2020-12-02 | 2 | -7/+26 | |
| | ||||||
* | clean up tensor conformance testing | Håvard Pettersen | 2020-12-01 | 1 | -19/+0 | |
| | ||||||
* | test dense optimizers with FastValue instead of DefaultTensorEngine | Arne Juul | 2020-11-27 | 12 | -54/+45 | |
| | ||||||
* | Merge branch 'master' into arnej/add-simple-streamed-value | Arne H Juul | 2020-11-25 | 6 | -476/+0 | |
|\ | ||||||
| * | GC unused code | Arne Juul | 2020-11-25 | 6 | -476/+0 | |
| | | | | | | | | | | * remove DefaultValueBuilderFactory * remove PackedMixedTensorBuilderFactory and all packed mixed code. | |||||
* | | run conformance test for StreamedValue also | Arne Juul | 2020-11-23 | 1 | -0/+6 | |
|/ | ||||||
* | Merge pull request #15410 from ↵ | Arne H Juul | 2020-11-21 | 1 | -4/+15 | |
|\ | | | | | | | | | vespa-engine/geirst/mixed-partial-update-remove-test Add partial update remove test with mixed tensor as input. | |||||
| * | Add partial update remove test with mixed tensor as input. | Geir Storli | 2020-11-20 | 1 | -4/+15 | |
| | | ||||||
* | | Merge pull request #15412 from ↵ | Arne H Juul | 2020-11-21 | 1 | -29/+80 | |
|\ \ | | | | | | | | | | | | | vespa-engine/havardpe/improved-benchmarking-fairness Havardpe/improved benchmarking fairness | |||||
| * | | use same loop_cnt when benchmarking if possible | Håvard Pettersen | 2020-11-20 | 1 | -6/+47 | |
| | | | ||||||
| * | | each EvalOp gets its own stash, for more fairness | Håvard Pettersen | 2020-11-20 | 1 | -23/+33 | |
| |/ | ||||||
* / | track CellType move | Arne Juul | 2020-11-20 | 3 | -5/+6 | |
|/ | ||||||
* | combine dimensions and split reduce operations | Håvard Pettersen | 2020-11-19 | 2 | -28/+109 | |
| | ||||||
* | Add support for partial update remove operation where address is not fully ↵ | Geir Storli | 2020-11-17 | 1 | -0/+24 | |
| | | | | specified. | |||||
* | move "keep as-is" optimizers | Arne Juul | 2020-11-12 | 13 | -880/+6 | |
| | | | | | * from eval/tensor/dense to eval/instruction * minimal changes to track move in this commit | |||||
* | move unit test for DenseXWProductFunction | Arne Juul | 2020-11-11 | 2 | -164/+0 | |
| | | | | * and verify with FastValueBuilderFactory also | |||||
* | move dense_xw_product_function to eval/instruction | Arne Juul | 2020-11-11 | 1 | -1/+1 | |
| | ||||||
* | benchmark some forms of join with number | Arne Juul | 2020-11-10 | 1 | -0/+18 | |
| | ||||||
* | untangle factory-based optimization pipeline from DefaultTensorEngine | Håvard Pettersen | 2020-11-03 | 1 | -22/+23 | |
| | ||||||
* | drop BM of PackedMixedTensorBuilderFactory | Arne Juul | 2020-10-26 | 1 | -3/+0 | |
| | ||||||
* | use a run-time flag instead of conditional compilation | Arne Juul | 2020-10-26 | 4 | -27/+15 | |
| | ||||||
* | partial duplicate of micro-bemchmark | Arne Juul | 2020-10-25 | 4 | -7/+27 | |
| | | | | | | | * use conditional compilation to let the installed vespa-tensor-instructions-benchmark run its measurements only for the two most important implementations (old prod and new prod). | |||||
* | Merge pull request #15012 from ↵ | Arne H Juul | 2020-10-22 | 1 | -20/+36 | |
|\ | | | | | | | | | vespa-engine/havardpe/better-dense-plan-for-generic-reduce improve generic dense reduce with more robust cell ordering | |||||
| * | improve generic dense reduce with more robust cell ordering | Håvard Pettersen | 2020-10-22 | 1 | -20/+36 | |
| | | | | | | | | | | | | | | - unroll reduce all loop - extend benchmark with optimized instructions (to catch slow ones) - drop SimpleTensorEngine from benchmark (always very slow) - tweak API on templated aggregators | |||||
* | | rename to vespa-tensor-instructions-benchmark and install it | Arne Juul | 2020-10-22 | 2 | -2/+4 | |
|/ | ||||||
* | be more exact in memory accounting | Arne Juul | 2020-10-21 | 1 | -2/+1 | |
| | | | | | | | | | | | | | * override the delete with size and forward to global delete with actually-allocated size, thereby making it possible for AddressSanitizer to check our accounting * unit test explicitly made a float-cell builder for a double-value, that didn't work out and should not be allowed * put alignment adjustment in a common place * fix off-by-one leftover over-allocation * memory usage stats are no longer estimates, rename correspondingly | |||||
* | drop SimpleValueEngine | Arne Juul | 2020-10-19 | 1 | -6/+0 | |
| | ||||||
* | run conformance test also for SimpleValueEngine | Arne Juul | 2020-10-19 | 1 | -2/+8 | |
| | ||||||
* | added mixed -> partial mixed peek cases | Håvard Pettersen | 2020-10-16 | 1 | -0/+2 | |
| | ||||||
* | added tensor peek benchmark | Håvard Pettersen | 2020-10-16 | 1 | -1/+94 | |
| | ||||||
* | added tensor lambda benchmark | Håvard Pettersen | 2020-10-16 | 1 | -1/+58 | |
| | ||||||
* | added encode/decode benchmark | Håvard Pettersen | 2020-10-16 | 1 | -0/+71 | |
| | ||||||
* | added tensor create benchmark | Håvard Pettersen | 2020-10-16 | 1 | -41/+86 | |
| | ||||||
* | extend map benchmark with number case | Håvard Pettersen | 2020-10-16 | 1 | -1/+6 | |
| | ||||||
* | test via compatibility layer | Arne Juul | 2020-10-15 | 3 | -25/+5 | |
| | ||||||
* | remove DenseTensorView::cellsRef(), just use cells() | Arne Juul | 2020-10-14 | 1 | -1/+1 | |
| | ||||||
* | benchmark GenericMap also | Arne Juul | 2020-10-13 | 1 | -0/+45 | |
| | ||||||
* | allow interpreted function to use new generic operations | Håvard Pettersen | 2020-10-12 | 3 | -62/+36 | |
| | | | | update conformance test to also test with SimpleValue and FastValue | |||||
* | Eliminate noexcept warnings. | Tor Egge | 2020-10-11 | 1 | -6/+6 | |
| | ||||||
* | Merge pull request #14757 from vespa-engine/add-tensor-partial-update-2 | Arne H Juul | 2020-10-09 | 6 | -0/+415 | |
|\ | | | | | Add tensor partial update 2 | |||||
| * | cleanup unit tests after review | Arne Juul | 2020-10-09 | 3 | -19/+7 | |
| | | ||||||
| * | require sparse remove_spec | Arne Juul | 2020-10-08 | 1 | -0/+1 | |
| | | ||||||
| * | test larger mixed, cleanup | Arne Juul | 2020-10-08 | 1 | -3/+1 | |
| | | ||||||
| * | add PartialRemove unit test for bad input | Arne Juul | 2020-10-07 | 1 | -2/+26 | |
| | | ||||||
| * | add PartialAdd unit test for bad input | Arne Juul | 2020-10-07 | 1 | -3/+28 | |
| | | ||||||
| * | add PartialModify unit test for bad input | Arne Juul | 2020-10-07 | 1 | -2/+28 | |
| | | ||||||
| * | add TensorPartialUpdate with add/modify/remove | Arne Juul | 2020-10-07 | 6 | -0/+353 | |
| | | ||||||
* | | Merge pull request #14793 from vespa-engine/havardpe/fork-fast-and-simple-values | Arne H Juul | 2020-10-09 | 1 | -0/+1 | |
|\ \ | | | | | | | Havardpe/fork fast and simple values | |||||
| * | | separate code for simple and fast values | Håvard Pettersen | 2020-10-08 | 1 | -0/+1 | |
| | | | ||||||
* | | | Merge pull request #14769 from vespa-engine/arnej/fix-concat-collapsing | Arne H Juul | 2020-10-08 | 1 | -0/+71 | |
|\ \ \ | |/ / |/| | | Arnej/fix concat collapsing |