summaryrefslogtreecommitdiff
path: root/numpy
Commit message (Collapse)AuthorAgeFilesLines
* MAINT, DOC: string_ → bytes_ and unicode_ → str_Dimitri Papadopoulos2023-02-1020-129/+130
|
* DOC: unicode → strDimitri Papadopoulos2023-02-101-4/+4
|
* Merge pull request #23181 from mhvk/ufunc-at-complex-add-subtract-multiplyMatti Picus2023-02-105-3/+92
|\ | | | | ENH: enable fast indexed loops for complex add, subtract, multiply
| * ENH: enable fast indexed loops for complex add, subtract, multiplyMarten van Kerkwijk2023-02-095-6/+95
| |
* | ENH: add indexed loops for maximum, minimum, fmax, fmin (#23177)Matti Picus2023-02-095-16/+96
|/ | | | | | | | | | | | | 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
* TST: Comment out spurious print in f2py testSebastian Berg2023-02-091-3/+4
| | | | Matti was wondering where it came from, so lets comment it out.
* BUG/ENH: Fix fast index loops for 1-el array / allow scalar valueMarten van Kerkwijk2023-02-082-2/+16
|
* Merge pull request #23136 from mattip/indexed-looposSebastian Berg2023-02-0716-69/+569
|\ | | | | ENH: create and use indexed inner loops
| * TST, BUG: add a test for unary ufuncs, fix condition for indexed loopsmattip2023-02-074-2/+107
| |
| * ENH: fixes from reviewmattip2023-02-071-12/+4
| |
| * TST: add test (from review)mattip2023-02-071-0/+7
| |
| * BUG: improve check for 1d operands (from review)mattip2023-02-071-1/+4
| |
| * BUG: fixes from review: use iter->nd and adapt to unary ufuncsmattip2023-02-061-6/+11
| |
| * BUG: Deal with casting and non-contig/1-D indicesSebastian Berg2023-02-062-4/+18
| |
| * BUG: Clean up reference handling in `ufunc.at` a little.Sebastian Berg2023-02-061-5/+1
| |
| * MAINT: rework release note, changes from reviewmattip2023-02-055-25/+27
| |
| * MAINT: update EXPERIMENTAL_DTYPE_API_VERSION toomattip2023-02-011-1/+1
| |
| * MAINT: lintingmattip2023-02-011-3/+5
| |
| * MAINT, BUG: fixes from review and testingmattip2023-02-018-81/+177
| |
| * ENH: update and sync the public APImattip2023-01-311-1/+2
| |
| * MAINT: fix lintingmattip2023-01-311-11/+17
| |
| * ENH: use an indexed loop if possible in ufunc_atmattip2023-01-306-16/+63
| |
| * ENH: add indexed lower loops and connect them to ufuncsmattip2023-01-308-18/+219
| |
| * refactor ufunc_at to first get the inner loop, then create the iteratorsmattip2023-01-301-41/+40
| |
| * ENH: add indexed loopsmattip2023-01-302-0/+24
| |
* | Revert type change for random_fJonathan Kohler2023-02-051-1/+1
| |
* | Correct types, add missing functions to c_distributions.pxdJonathan Kohler2023-02-051-4/+10
| | | | | | Correct floating point types on several npyrandom functions exposed for Cython in c_distributions.pyx, add missing float functions
* | Merge pull request #23143 from seberg/dtype-pickleCharles Harris2023-02-023-2/+23
|\ \ | | | | | | ENH: Allow trivial pickling of user DType (classes)
| * | ENH: Allow trivial pickling of user DType (classes)Sebastian Berg2023-02-023-2/+23
| |/ | | | | | | | | | | | | | | | | | | | | This also adds a `_legac` attribute, I am happy to rename it, but I suspect having something like it is useful. Arguably, the best solution would be to give our DTypes a working module+name, but given that we are not there, this seems easy. We could probably check for `__reduce__`, but I am not certain that wouldn't pre-empt successfully already, so this just restores the default for now.
* | Merge pull request #23145 from BvB93/39_typCharles Harris2023-02-0217-624/+117
|\ \ | | | | | | TYP,MAINT: Remove typing-related Python <3.9 leftovers
| * | MAINT: Remove `npt._GenericAlias` in favor of py39 `types.GenericAlias`BvB932023-02-026-440/+6
| | |
| * | MAINT: Make use of the py39 `__class_getitem__` availability in the standard ↵BvB932023-02-025-83/+84
| | | | | | | | | | | | library
| * | MAINT: Remove the python <3.9 guards for `__class_getitem__`BvB932023-02-027-101/+27
| | |
* | | TYP,MAINT: Add a missing explicit `Any` parameter to the `npt.ArrayLike` ↵BvB932023-02-021-1/+1
|/ / | | | | | | definition
* | Merge pull request #23069 from andyfaff/wheelMatti Picus2023-02-016-13/+64
|\ \ | | | | | | BLD: musllinux wheel build
| * | WHL: musllinux wheels [wheel build]Andrew Nelson2023-02-016-13/+64
| | |
* | | Merge pull request #21056 from seiko2plus/replace_raw_arithmfpMatti Picus2023-01-3128-1554/+3133
|\ \ \ | |_|/ |/| | ENH: re-implement SIMD kernels of complex operations
| * | ENH, SIMD: Only dispatch AVX2 for arithmetic operationsSayed Adel2023-01-296-3/+159
| | | | | | | | | | | | no performance gain with AVX512 enabled except for absolute
| * | TST, SIMD: add test cases for the new intrinicsSayed Adel2023-01-292-107/+278
| | |
| * | ENH, SIMD: Implment intrinsic for mask divisionSayed Adel2023-01-292-0/+47
| | |
| * | ENH, SIMD: Implment intrinsic for FMA multiply add(odd) and subtract(even)Sayed Adel2023-01-295-0/+72
| | |
| * | ENH, SIMD: Add special intrinsics for better non-contiguous/partial memory ↵Sayed Adel2023-01-295-66/+1418
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | access for complex load/store summarized as follows: 64-bit contiguous partial load/store over 32-bit lane npyv_load2_till_u32, npyv_load2_till_s32, npyv_load2_till_f32 npyv_load2_tillz_u32, npyv_load2_tillz_s32, npyv_load2_tillz_f32 npyv_store2_till_u32, npyv_store2_till_s32, npyv_store2_till_f32 128-bit contiguous partial load/store over 64-bit lane npyv_load2_till_u64, npyv_load2_till_s64, npyv_load2_till_f64 npyv_load2_tillz_u64, npyv_load2_tillz_s64, npyv_load2_tillz_f64 npyv_store2_till_u64, npyv_store2_till_s64, npyv_store2_till_f64 64-bit non-contiguous load/store over 32-bit stride npyv_loadn2_u32, npyv_loadn2_s32, npyv_loadn2_f32 npyv_storen2_u32, npyv_storen2_s32, npyv_storen2_f32 128-bit non-contiguous load/store over 64-bit stride npyv_loadn2_u64, npyv_loadn2_s64, npyv_loadn2_f64 npyv_storen2_u64, npyv_storen2_s64, npyv_storen2_f64 64-bit non-contiguous partial load/store over 32-bit stride npyv_loadn2_till_u32, npyv_loadn2_till_s32, npyv_loadn2_till_f32 npyv_loadn2_tillz_u32, npyv_loadn2_tillz_s32, npyv_loadn2_tillz_f32 npyv_storen2_till_u32, npyv_storen2_till_s32, npyv_storen2_till_f32 128-bit non-contiguous partial load/store over 64-bit stride npyv_loadn2_till_u64, npyv_loadn2_till_s64, npyv_loadn2_till_f64 npyv_loadn2_tillz_u64, npyv_loadn2_tillz_s64, npyv_loadn2_tillz_f64 npyv_storen2_till_u64, npyv_storen2_till_s64, npyv_storen2_till_f64 2 channels de-interlave/interleave contiguous load/store for all data types npyv_load_##sfx##x2, npyv_store_##sfx##x2
| * | ENH: re-implement SIMD kernels of complex operationsSayed Adel2023-01-292-671/+523
| | | | | | | | | | | | | | | | | | | | | New kernels provides better performance for non-contiguous memory access and don't require 128-bit/64-bit aligment for complex128/complex64 just 64-bit/32-bit, and implmented via universal intrinics.
| * | ENH: Implement intrinsics for shuffle over 128-bit lane and unzipSayed Adel2023-01-298-27/+633
| | | | | | | | | | | | | | | shuffle intrinsics support 32-bit/64-bit vector data types, unzip(deinterleave) intrinsics supports all data types.
| * | ENH: remove raw SIMD of complex operationsSayed Adel2023-01-295-687/+10
| | |
* | | Merge pull request #23111 from seberg/dlpack-boolMatti Picus2023-01-303-19/+147
|\ \ \ | | | | | | | | MAINT: Allow export/import of bools in dlpack
| * | | MAINT: Allow export/import of bools in dlpackSebastian Berg2023-01-273-19/+147
| | | | | | | | | | | | | | | | | | | | Updates the header file and accept as well as export boolean now that the header includes a definition for it.
* | | | Merge pull request #23073 from DWesl/patch-2Matti Picus2023-01-301-0/+20
|\ \ \ \ | | | | | | | | | | CI: Rebase NumPy compiled extension test modules on Cygwin
| * | | | CI: Rebase numpy DLLs in runtests.py.DWesl2023-01-301-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | This assumes NumPy is rebased before tests run, but does not assume the locations are in the database.
| * | | | TST: Rebase F2Py-built extension modules.DWesl2023-01-291-0/+19
| | | | | | | | | | | | | | | | | | | | | | | | | Also adjust CI so they don't immediately collide with NumPy. I forgot to do that last time, which caused problems.
View Lorry Controller Status