summaryrefslogtreecommitdiff
path: root/benchmarks
Commit message (Collapse)AuthorAgeFilesLines
* BUG: typo, lintingmattip2023-05-111-0/+2
|
* add fast path for str(scalar_int)mattip2023-05-101-0/+10
|
* BUG: Add packaging to benchmark dependenciesChris Sidebottom2023-04-172-2/+4
| | | | After #23010 we now need packaging to run the ufunc benchmarks.
* Merge pull request #23010 from HaoZeke/benchArrayAPISebastian Berg2023-04-148-69/+527
|\ | | | | BENCH: Add coverage for remaining array_api operations
| * BENCH: Rework benchmarksRohit Goswami2023-04-132-77/+81
| |
| * MAINT: Appease linterRohit Goswami2023-03-042-4/+3
| |
| * MAINT: Cleanup with PathRohit Goswami2023-03-041-8/+8
| |
| * BENCH: BugfixRohit Goswami2023-03-041-1/+0
| |
| * BENCH: Rework to test real, roundRohit Goswami2023-03-041-2/+28
| |
| * BENCH: Reduce shapes and types for speedRohit Goswami2023-03-045-22/+23
| |
| * BENCH: Rework whitespaceRohit Goswami2023-03-045-0/+19
| | | | | | | | | | | | Please lets get a linter approved soon... Co-authored-by: Sebastian Berg <sebastian@sipsolutions.net>
| * BENCH: Better usage of np.randomRohit Goswami2023-03-042-3/+4
| | | | | | | | Co-authored-by: Sebastian Berg <sebastian@sipsolutions.net>
| * BENCH: Minor naming changesRohit Goswami2023-03-042-2/+2
| | | | | | | | Co-authored-by: Sebastian Berg <sebastian@sipsolutions.net>
| * BENCH: Use operator where possibleRohit Goswami2023-03-041-9/+6
| | | | | | | | Co-authored-by: Sebastian Berg <sebastian@sipsolutions.net>
| * BENCH: Update to handle bool for DLPackRohit Goswami2023-03-042-2/+6
| |
| * BENCH: Refactor as per review commentsRohit Goswami2023-03-042-7/+9
| | | | | | | | Co-authored-by: Sebastian Berg <sebastian@sipsolutions.net>
| * BENCH: Add manipulation functionsRohit Goswami2023-03-041-0/+104
| |
| * BENCH: Add some documentationRohit Goswami2023-03-041-1/+2
| |
| * BENCH: Add from_dlpackRohit Goswami2023-03-041-0/+19
| |
| * BENCH: Add meshgridRohit Goswami2023-03-041-0/+16
| |
| * BENCH: Add astypeRohit Goswami2023-03-041-0/+17
| |
| * MAINT: Appease linterRohit Goswami2023-03-041-5/+6
| |
| * BENCH: Add transpose() and vdot()Rohit Goswami2023-03-041-0/+22
| |
| * BENCH: Add variants of uniqueRohit Goswami2023-03-041-2/+15
| |
| * BUG,BENCH: Ensure np.nans in np.unique benchmarksRohit Goswami2023-03-041-1/+3
| |
| * BENCH: Add creation functionsRohit Goswami2023-03-041-0/+41
| |
| * MAINT: Fixup BENCH to appease linterRohit Goswami2023-03-043-7/+7
| |
| * BENCH: Add ndarray stats method callsRohit Goswami2023-03-041-10/+36
| |
| * MAINT: Kill unusedRohit Goswami2023-03-041-7/+0
| |
| * BENCH: Add remaining ndarray dunder methodsRohit Goswami2023-03-041-16/+35
| | | | | | | | With the exception of __index__ which is benchmarked anyway
| * MAINT,BENCH: Rework to skip benchmarksRohit Goswami2023-03-041-4/+5
| | | | | | | | Using the slightly less documented NotImplementedError in setup to skip
| * BENCH: Rework numpy stats reductionsRohit Goswami2023-03-041-6/+25
| |
| * MAINT: Minor cleanup of benchmarking toolsRohit Goswami2023-03-041-31/+23
| |
| * BENCH: Add ndarray get,set itemsRohit Goswami2023-03-041-6/+32
| |
| * BENCH: Add 0d ndarray benchmarksRohit Goswami2023-03-041-6/+19
| |
| * BENCH: Refactor and add 0-argument ndarray methodsRohit Goswami2023-03-042-11/+53
| |
| * BENCH: Init benchmarks for 1 arg ndarray methodsRohit Goswami2023-03-041-6/+45
| |
| * BENCH: Add real and round ufuncsRohit Goswami2023-03-041-3/+3
| |
* | DOC: Fix typos & grammer in docstrings and comments (#23503)Pratyay Banerjee2023-03-302-2/+2
|/
* Merge pull request #23153 from seiko2plus/removes_old_cpu_dispatcherCharles Harris2023-02-222-143/+263
|\ | | | | SIMD: Get rid of attribute-based CPU dispatching
| * BENCH: Add new data generatorSayed Adel2023-02-201-0/+109
| | | | | | | | for fairness and to stabilize the benchmark
| * BENCH: cover auto-vectorized ufunc operationsSayed Adel2023-02-201-25/+72
| |
| * BENCH: Clean up ufunc_stridesSayed Adel2023-02-201-139/+103
| |
* | BENCH: Add benchmark for put and types for putmaskSebastian Berg2023-02-201-1/+1
| |
* | MAINT: Further removal of PyArray_Item_INCREF useSebastian Berg2023-02-201-1/+19
| |
* | ENH: Avoid use of item XINCREF and DECREF in fasttakeSebastian Berg2023-02-201-1/+1
|/ | | | | | | | Rather, use the cast function directly when the copy is not trivial (which we know based on it not passing REFCHK, if that passes we assume memcpy is fine). Also uses memcpy, since no overlap is possible here.
* Merge pull request #22315 from r-devulap/avxsortMatti Picus2023-02-151-1/+1
|\ | | | | ENH: Vectorize quicksort for 16-bit and 64-bit dtype using AVX512
| * BENCH: Add float16 to sort benchmarksRaghuveer Devulapalli2023-01-301-1/+1
| |
* | ENH: add indexed loops for maximum, minimum, fmax, fmin (#23177)Matti Picus2023-02-091-2/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | Continuation of the ufunc.at optimizations: add indexed loops for maximum, minimum, fmax, fmin ufuncs and a benchmark for maximum.at (performance increased by ~13x) * BENCH: add np.maximum.at benchmark * remove 'explain_chain' * add a seed to `default_rng() (from review) * MAINT: formatting and change comments, from review
* | Merge pull request #23136 from mattip/indexed-looposSebastian Berg2023-02-071-1/+1
|\ \ | | | | | | ENH: create and use indexed inner loops
View Lorry Controller Status