kernox 1.0.1__tar.gz

kernox-1.0.1/LICENSE-APACHE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

kernox-1.0.1/LICENSE-MIT

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Jean-Baptiste Keck
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

kernox-1.0.1/PKG-INFO

@@ -0,0 +1,151 @@
+Metadata-Version: 2.4
+Name: kernox
+Version: 1.0.1
+Summary: Fused symbolic reductions on GPUs (CUDA, ROCm/HIP, SYCL), built on symox
+Author: Jean-Baptiste Keck
+License-Expression: MIT OR Apache-2.0
+Project-URL: Homepage, https://github.com/keckj/kernox
+Project-URL: Documentation, https://keckj.github.io/kernox/
+Project-URL: Source, https://github.com/keckj/kernox
+Project-URL: Issues, https://github.com/keckj/kernox/issues
+Project-URL: Changelog, https://github.com/keckj/kernox/releases
+Project-URL: symox, https://github.com/keckj/symox
+Keywords: gpu,cuda,rocm,sycl,kernel,reduction,pytorch,keops
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Topic :: Scientific/Engineering :: Mathematics
+Classifier: Environment :: GPU :: NVIDIA CUDA
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE-MIT
+License-File: LICENSE-APACHE
+License-File: THIRD_PARTY.md
+Requires-Dist: numpy>=2.3
+Requires-Dist: symox>=0.1.1
+Provides-Extra: cuda
+Requires-Dist: torch>=2.11; extra == "cuda"
+Requires-Dist: nvidia-cuda-nvrtc-cu12>=12.6; extra == "cuda"
+Provides-Extra: rocm
+Requires-Dist: torch>=2.15; extra == "rocm"
+Provides-Extra: xpu
+Requires-Dist: torch>=2.15; extra == "xpu"
+Requires-Dist: intel-sycl-rt>=2026.2.0; extra == "xpu"
+Requires-Dist: intel-cmplr-lib-ur>=2026.2.0; extra == "xpu"
+Provides-Extra: test
+Requires-Dist: pytest>=8.4; extra == "test"
+Dynamic: license-file
+
+# kernox
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/keckj/kernox/v1.0.1/docs/images/kernox-banner.png" alt="kernox logo" width="560">
+</p>
+
+kernox computes pairwise reductions on GPUs (Gaussian kernel sums, nearest
+neighbours, log-sum-exp, softmax-weighted sums, ...) without ever building the
+M×N matrix. You write the formula with symbolic variables indexed by `i` and
+`j`, and kernox turns it into a single fused GPU kernel for NVIDIA (CUDA),
+AMD (ROCm/HIP) or Intel (SYCL) cards. Support for other accelerators may be
+added later.
+
+kernox is a successor to [PyKeOps](https://github.com/getkeops/keops), built on
+the [symox](https://github.com/keckj/symox) symbolic engine. It works with
+PyTorch tensors.
+
+- Documentation: <https://keckj.github.io/kernox/>
+- Getting started: <https://keckj.github.io/kernox/getting-started/>
+
+## Why kernox
+
+- **No M×N matrix.** Memory stays linear in the number of points, so each row
+  can be reduced over millions of points.
+- **Three GPU vendors.** One formula runs on NVIDIA, AMD and Intel GPUs.
+- **Formulas, not strings.** Formulas are Python expressions. Derivatives are
+  computed symbolically and run as fused reductions too.
+- **Predictable numerics.** IEEE arithmetic by default, an explicit opt-in for
+  approximate `exp` and `log`, and an explicit error instead of a silent
+  fallback when something is not supported.
+- **Familiar to PyKeOps users.** The PyKeOps reductions and formula operations
+  are available for PyTorch on GPUs. kernox has no NumPy interface and no CPU
+  backend; the other differences are listed in
+  [Coming from PyKeOps](https://keckj.github.io/kernox/pykeops/).
+
+## Installation
+
+kernox needs Python 3.10 or later, PyTorch and a supported GPU. Install PyTorch
+for your platform first, then kernox from PyPI (symox, its symbolic engine, comes
+with it as a dependency):
+
+```sh
+pip install torch --index-url https://download.pytorch.org/whl/cu126   # NVIDIA
+pip install "kernox[cuda]"
+python -m kernox.diagnostics --check
+```
+
+AMD and Intel instructions, and the details, are in
+[Getting started](https://keckj.github.io/kernox/getting-started/).
+
+## Performance
+
+The goal of kernox is to be **at least as fast as PyKeOps** wherever PyKeOps
+runs, and to bring the same performance to AMD and Intel GPUs, which PyKeOps
+does not support. On NVIDIA GPUs, kernox is already faster than PyKeOps in
+several cases.
+
+LogSumExp reduction, M = N = 10⁵, FP32, on an RTX 2080 Ti; kernox with
+`fast_math=True`, PyKeOps 2.4b in its best configuration (each kernel compiled
+alone in a fresh process); median of two runs:
+
+| Case | kernox | PyKeOps | kernox / PyKeOps |
+| --- | --- | --- | --- |
+| D = 2, dense | 20.1 ms | 21.9 ms | ×0.92 |
+| D = 3, dense | 24.6 ms | 25.8 ms | ×0.95 |
+| D = 2, block-sparse ranges | 8.4 ms | 8.9 ms | ×0.95 |
+| D = 3, block-sparse ranges | 4.2 ms | 4.2 ms | ×1.01 (same within noise) |
+
+These figures cover only the cases listed; they are not a general claim of
+superiority over PyKeOps on every workload or card. A case where kernox is
+slower than PyKeOps is treated as a bug.
+
+## Learn more
+
+- [Getting started](https://keckj.github.io/kernox/getting-started/): installation and a first
+  reduction, step by step.
+- [Concepts](https://keckj.github.io/kernox/concepts/): variables, formulas, reductions, devices and
+  dtypes.
+- How-to guides: [kernel sums](https://keckj.github.io/kernox/guides/kernel-sums/),
+  [nearest neighbours](https://keckj.github.io/kernox/guides/nearest-neighbours/),
+  [log-sum-exp and Sinkhorn](https://keckj.github.io/kernox/guides/logsumexp/),
+  [gradients](https://keckj.github.io/kernox/guides/gradients/),
+  [linear systems](https://keckj.github.io/kernox/guides/linear-systems/) and more.
+- [Coming from PyKeOps](https://keckj.github.io/kernox/pykeops/): a migration guide.
+- [Backends and hardware](https://keckj.github.io/kernox/backends/): what runs where, and the known
+  limitations.
+
+## About the name and logo
+
+symox is *symbolic* plus *ox*: a rusty ox, since symox is written in Rust.
+kernox is *kernels* plus the ox of symox, and also a nod to the redox chemistry
+of copper. The logo goes from orange copper (the ox) to turquoise verdigris
+(the trails and the compute grid), that is, from copper to its oxidation
+patina. And redox contains *reduction*, which is what kernox does: sum, min and
+max, as drawn in the logo.
+
+## License
+
+At your option, [MIT](https://github.com/keckj/kernox/blob/v1.0.1/LICENSE-MIT) or [Apache-2.0](https://github.com/keckj/kernox/blob/v1.0.1/LICENSE-APACHE).
+Provenance of third-party code and algorithms (KeOps, symox):
+[`THIRD_PARTY.md`](https://github.com/keckj/kernox/blob/v1.0.1/THIRD_PARTY.md).
+
+## Projects using kernox
+
+- [remblais](https://github.com/keckj/remblais): a faster GeomLoss (Sinkhorn
+  divergences, kernel norms and optimal transport) on NVIDIA, AMD and Intel
+  GPUs. Documentation: <https://keckj.github.io/remblais/>
+
+## Related projects
+
+- symox, symbolic engine and code generation: <https://github.com/keckj/symox>
+- KeOps / PyKeOps: <https://github.com/getkeops/keops>

kernox-1.0.1/README.md

@@ -0,0 +1,112 @@
+# kernox
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/keckj/kernox/v1.0.1/docs/images/kernox-banner.png" alt="kernox logo" width="560">
+</p>
+
+kernox computes pairwise reductions on GPUs (Gaussian kernel sums, nearest
+neighbours, log-sum-exp, softmax-weighted sums, ...) without ever building the
+M×N matrix. You write the formula with symbolic variables indexed by `i` and
+`j`, and kernox turns it into a single fused GPU kernel for NVIDIA (CUDA),
+AMD (ROCm/HIP) or Intel (SYCL) cards. Support for other accelerators may be
+added later.
+
+kernox is a successor to [PyKeOps](https://github.com/getkeops/keops), built on
+the [symox](https://github.com/keckj/symox) symbolic engine. It works with
+PyTorch tensors.
+
+- Documentation: <https://keckj.github.io/kernox/>
+- Getting started: <https://keckj.github.io/kernox/getting-started/>
+
+## Why kernox
+
+- **No M×N matrix.** Memory stays linear in the number of points, so each row
+  can be reduced over millions of points.
+- **Three GPU vendors.** One formula runs on NVIDIA, AMD and Intel GPUs.
+- **Formulas, not strings.** Formulas are Python expressions. Derivatives are
+  computed symbolically and run as fused reductions too.
+- **Predictable numerics.** IEEE arithmetic by default, an explicit opt-in for
+  approximate `exp` and `log`, and an explicit error instead of a silent
+  fallback when something is not supported.
+- **Familiar to PyKeOps users.** The PyKeOps reductions and formula operations
+  are available for PyTorch on GPUs. kernox has no NumPy interface and no CPU
+  backend; the other differences are listed in
+  [Coming from PyKeOps](https://keckj.github.io/kernox/pykeops/).
+
+## Installation
+
+kernox needs Python 3.10 or later, PyTorch and a supported GPU. Install PyTorch
+for your platform first, then kernox from PyPI (symox, its symbolic engine, comes
+with it as a dependency):
+
+```sh
+pip install torch --index-url https://download.pytorch.org/whl/cu126   # NVIDIA
+pip install "kernox[cuda]"
+python -m kernox.diagnostics --check
+```
+
+AMD and Intel instructions, and the details, are in
+[Getting started](https://keckj.github.io/kernox/getting-started/).
+
+## Performance
+
+The goal of kernox is to be **at least as fast as PyKeOps** wherever PyKeOps
+runs, and to bring the same performance to AMD and Intel GPUs, which PyKeOps
+does not support. On NVIDIA GPUs, kernox is already faster than PyKeOps in
+several cases.
+
+LogSumExp reduction, M = N = 10⁵, FP32, on an RTX 2080 Ti; kernox with
+`fast_math=True`, PyKeOps 2.4b in its best configuration (each kernel compiled
+alone in a fresh process); median of two runs:
+
+| Case | kernox | PyKeOps | kernox / PyKeOps |
+| --- | --- | --- | --- |
+| D = 2, dense | 20.1 ms | 21.9 ms | ×0.92 |
+| D = 3, dense | 24.6 ms | 25.8 ms | ×0.95 |
+| D = 2, block-sparse ranges | 8.4 ms | 8.9 ms | ×0.95 |
+| D = 3, block-sparse ranges | 4.2 ms | 4.2 ms | ×1.01 (same within noise) |
+
+These figures cover only the cases listed; they are not a general claim of
+superiority over PyKeOps on every workload or card. A case where kernox is
+slower than PyKeOps is treated as a bug.
+
+## Learn more
+
+- [Getting started](https://keckj.github.io/kernox/getting-started/): installation and a first
+  reduction, step by step.
+- [Concepts](https://keckj.github.io/kernox/concepts/): variables, formulas, reductions, devices and
+  dtypes.
+- How-to guides: [kernel sums](https://keckj.github.io/kernox/guides/kernel-sums/),
+  [nearest neighbours](https://keckj.github.io/kernox/guides/nearest-neighbours/),
+  [log-sum-exp and Sinkhorn](https://keckj.github.io/kernox/guides/logsumexp/),
+  [gradients](https://keckj.github.io/kernox/guides/gradients/),
+  [linear systems](https://keckj.github.io/kernox/guides/linear-systems/) and more.
+- [Coming from PyKeOps](https://keckj.github.io/kernox/pykeops/): a migration guide.
+- [Backends and hardware](https://keckj.github.io/kernox/backends/): what runs where, and the known
+  limitations.
+
+## About the name and logo
+
+symox is *symbolic* plus *ox*: a rusty ox, since symox is written in Rust.
+kernox is *kernels* plus the ox of symox, and also a nod to the redox chemistry
+of copper. The logo goes from orange copper (the ox) to turquoise verdigris
+(the trails and the compute grid), that is, from copper to its oxidation
+patina. And redox contains *reduction*, which is what kernox does: sum, min and
+max, as drawn in the logo.
+
+## License
+
+At your option, [MIT](https://github.com/keckj/kernox/blob/v1.0.1/LICENSE-MIT) or [Apache-2.0](https://github.com/keckj/kernox/blob/v1.0.1/LICENSE-APACHE).
+Provenance of third-party code and algorithms (KeOps, symox):
+[`THIRD_PARTY.md`](https://github.com/keckj/kernox/blob/v1.0.1/THIRD_PARTY.md).
+
+## Projects using kernox
+
+- [remblais](https://github.com/keckj/remblais): a faster GeomLoss (Sinkhorn
+  divergences, kernel norms and optimal transport) on NVIDIA, AMD and Intel
+  GPUs. Documentation: <https://keckj.github.io/remblais/>
+
+## Related projects
+
+- symox, symbolic engine and code generation: <https://github.com/keckj/symox>
+- KeOps / PyKeOps: <https://github.com/getkeops/keops>

kernox-1.0.1/THIRD_PARTY.md

@@ -0,0 +1,20 @@
+# Third-party code and algorithms
+
+Kernox is dual-licensed under MIT or Apache-2.0, at your option
+([`LICENSE-MIT`](LICENSE-MIT), [`LICENSE-APACHE`](LICENSE-APACHE)). The table
+below lists the code and algorithms taken from third-party projects.
+
+| Kernox file | Source | Revision | License | Nature |
+| --- | --- | --- | --- | --- |
+| `kernox/backends/cuda/_driver.py` | `symox/python/symox/extra/codegen/cuda.py` (keckj/symox) | `2e623e66bb31882e31f6dbfff6f77ae4bd945408` | MIT OR Apache-2.0 | structure of the ctypes Driver/NVRTC binding taken and adapted (CUBIN, occupancy, shared primary context) |
+| `kernox/backends/cuda/_kernel.py` | KeOps `keopscore/keopscore/mapreduce/gpu/GpuReduc1D.py`, `keopscore/keopscore/formulas/reductions/KMin_ArgKMin_Reduction.py` (getkeops/keops) | `ef72bc907df78cd18bff866d3dc7cb6375f11a4d` | MIT | algorithmic scheme (one thread per row i, j tiles in shared memory, blockwise sum, sorted K list); **no line copied**, code rewritten |
+| `kernox/backends/sycl/codegen.py` | KeOps `keopscore/keopscore/mapreduce/gpu/GpuReduc1D.py`, `keopscore/keopscore/formulas/reductions/KMin_ArgKMin_Reduction.py`, `keopscore/keopscore/formulas/reductions/sum_schemes.py` (getkeops/keops) | `ef72bc907df78cd18bff866d3dc7cb6375f11a4d` | MIT | algorithmic scheme (one work-item per row i, j tiles in local memory, blockwise sum, sorted K list); **no line copied**, SYCL code rewritten |
+| `kernox/backends/sycl/_pair_local.py` (temporary) | `symox/python/symox/extra/codegen/sycl.py` (keckj/symox) | `2e623e66bb31882e31f6dbfff6f77ae4bd945408` | MIT OR Apache-2.0 | call to `syclcode_function` (library, no copy) |
+| `tests/conformance/test_keops_port.py` | KeOps `pykeops/pykeops/test/test_torch.py` (`test_generic_syntax_float`, `test_generic_syntax_double`, `test_LazyTensor_sum`, `test_LazyTensor_min`, `test_LazyTensor_min_chunked`), `test_numpy.py` (`test_argkmin`), `test_chunks.py`, `test_finalchunks.py`, `test_lazytensor_clamp.py` (getkeops/keops) | `ef72bc907df78cd18bff866d3dc7cb6375f11a4d` | MIT | formulas, dimensions, sizes and data distributions of the forward tests, rewritten on the Kernox frontend (without autograd, batch or LogSumExp); tolerances replaced by the judgment of the conformance suite; no line copied verbatim |
+| `kernox/ops.py`, `tests/test_ops.py` | KeOps `keopscore/keopscore/formulas/maths/{Round,Mod,ReLU,Step,SinXDivX,XLogX,ClampInt,IfElse,Inv,Normalize,SqDist,WeightedSqNorm,WeightedSqDist,SqNormIso,SqNormDiag,SymSqNorm,OneHot,Elem,Extract,MatVecMult,VecMatMult,TensorProd,TensorDot,Kron,BSpline,SoftDTW_SqDist}.py`, `keopscore/keopscore/utils/math_functions.py`, signatures from `pykeops/pykeops/common/lazy_tensor.py` (getkeops/keops) | `ef72bc907df78cd18bff866d3dc7cb6375f11a4d` | MIT | semantics of the operations (C expressions, order of operations of De Boor, row-major layouts, names and signatures) re-expressed as symox primitives; the NumPy references of the tests (`keops_bspline`, `keops_one_hot`, `keops_round`, `keops_softdtw`) transcribe this C; no line copied |
+| `kernox/linalg.py` | KeOps `pykeops/pykeops/common/operations.py` (`ConjugateGradientSolver`, `_get_atol_rtol`), `pykeops/pykeops/torch/operations.py` (`KernelSolveAutograd`), `pykeops/pykeops/common/lazy_tensor.py` (`solve`, `matvec`, `rmatvec`, `T`) (getkeops/keops) | `ef72bc907df78cd18bff866d3dc7cb6375f11a4d` | MIT | conjugate gradient iteration (criterion `‖r‖ < max(eps‖b‖, eps)`, `maxiter = 10·M`), default value `alpha = 1e-10`, backward pass through the adjoint solve (`Kᵀ = K`); rewritten (symbolic linearity check, VJP for `rmatvec`); no line copied |
+| `kernox/complex.py` | KeOps `keopscore/keopscore/formulas/complex/*.py` (`Real2Complex`, `Imag2Complex`, `ComplexExp1j`, `ComplexReal`, `ComplexImag`, `Conj`, `ComplexSquareAbs`, `ComplexAbs`, `ComplexAngle`, `ComplexExp`, `ComplexAdd`, `ComplexSubtract`, `ComplexMult`, `ComplexRealScal`, `ComplexDivide`, `ComplexSum`), `pykeops/pykeops/common/lazy_tensor.py` (`ComplexGenericLazyTensor`) (getkeops/keops) | `ef72bc907df78cd18bff866d3dc7cb6375f11a4d` | MIT | interleaved representation and definition of each operation (including division via `1/|g|²`, modulus without hypot), promotion and refusal rules; re-expressed as symox primitives; no line copied |
+
+The full licenses are in the original repositories: symox
+(<https://github.com/keckj/symox>, `LICENSE-MIT` and `LICENSE-APACHE`, MIT OR
+Apache-2.0); KeOps (<https://github.com/getkeops/keops>, `licence.txt`, MIT).

kernox-1.0.1/kernox/__init__.py

@@ -0,0 +1,101 @@
+"""kernox: fused symbolic reductions on GPUs.
+
+Documentation: https://keckj.github.io/kernox/. Expressions are symox objects; ``compile`` produces a
+callable that validates its inputs before any native launch.
+"""
+
+from .errors import (
+    BackendUnavailableError,
+    ConstantConversionError,
+    KernoxError,
+    UnsupportedError,
+    ValidationError,
+)
+from .expr import (
+    Formula,
+    Param,
+    ReductionExpr,
+    Vi,
+    Vj,
+    abs,
+    acos,
+    asin,
+    atan,
+    atan2,
+    cat,
+    ceiling,
+    clamp,
+    constant,
+    cos,
+    cosh,
+    eq,
+    exp,
+    floor,
+    log,
+    maximum,
+    minimum,
+    ne,
+    rsqrt,
+    sign,
+    sin,
+    sinh,
+    sqrt,
+    square,
+    tan,
+    tanh,
+    where,
+)
+from .ops import (  # noqa: E402 - also attaches the PyKeOps methods to Formula
+    bspline,
+    clampint,
+    elem,
+    extract,
+    ifelse,
+    inv,
+    kron,
+    matvecmult,
+    mod,
+    normalize,
+    one_hot,
+    relu,
+    round,
+    sinc,
+    sinxdivx,
+    softdtw_sqdist,
+    grad,
+    diff,
+    grad_matrix,
+    divergence,
+    laplacian,
+    trace_operator,
+    sqdist,
+    step,
+    tensordot,
+    tensorprod,
+    vecmatmult,
+    weightedsqdist,
+    weightedsqnorm,
+    xlogx,
+)
+from .complex import ComplexFormula, angle, complex_formula, conj, exp1j, imag, imag2complex, real, real2complex
+from .linalg import LinearOperator, conjugate_gradient
+from .ranges import Ranges, ranges_from_labels
+from .runtime import RangedReduction, Reduction, compile, get_backend, register_backend
+from .tuning import export_wisdom, forget_wisdom, import_wisdom
+from .diagnostics import diagnostics  # noqa: E402 - also `python -m kernox.diagnostics`
+
+__all__ = [
+    "Vi", "Vj", "Param", "Formula", "ReductionExpr", "Reduction", "RangedReduction", "compile",
+    "Ranges", "ranges_from_labels", "LinearOperator", "conjugate_gradient",
+    "ComplexFormula", "real2complex", "imag2complex", "exp1j", "complex_formula", "conj", "angle", "real", "imag",
+    "register_backend", "get_backend", "diagnostics", "export_wisdom", "import_wisdom", "forget_wisdom", "constant", "where", "eq", "ne", "cat",
+    "exp", "log", "sqrt", "rsqrt", "sin", "cos", "tan", "asin", "acos", "atan", "atan2",
+    "sinh", "cosh", "tanh", "abs", "sign", "floor", "ceiling", "square",
+    "minimum", "maximum", "clamp",
+    "relu", "step", "sinxdivx", "sinc", "xlogx", "inv", "round", "mod", "clampint", "ifelse",
+    "normalize", "sqdist", "weightedsqnorm", "weightedsqdist", "one_hot", "elem", "extract",
+    "matvecmult", "vecmatmult", "tensorprod", "tensordot", "kron", "bspline", "softdtw_sqdist",
+    "grad", "diff", "grad_matrix", "divergence", "laplacian", "trace_operator",
+    "KernoxError", "ValidationError", "ConstantConversionError",
+    "BackendUnavailableError", "UnsupportedError",
+]

kernox-1.0.1/kernox/_env.py

@@ -0,0 +1,13 @@
+"""Reading of the ``KERNOX_*`` environment variables.
+
+An empty value is treated as an unset variable.
+"""
+
+from __future__ import annotations
+
+import os
+
+
+def getenv(name: str, default: str | None = None) -> str | None:
+    """Value of ``name`` if it is set and non-empty, otherwise ``default``."""
+    return os.environ.get(name) or default