The goal of this MR is to implement a generic SIMD backend (packet ops) for Eigen that uses clang vector extensions instead of platform-dependent intrinsics. Ideally, this should make it possible to build Eigen and achieve reasonable speed on any platform that has a recent clang compiler, without having to write any inline assembly or intrinsics.
Caveats:
* The current implementation is a proof of concept and supports vectorization for float, double, int32_t, and int64_t using fixed-size 512-bit vectors (a somewhat arbitrary choice). I have not done much to tune this for speed yet.
* For now, there is no way to enable this other than setting -DEIGEN_VECTORIZE_GENERIC on the command line.
* This only compiles with newer versions of clang. I have tested that it compiles and all tests pass with clang 19.1.7.
https://clang.llvm.org/docs/LanguageExtensions.html#vectors-and-extended-vectorsCloses#2998 and #2997
See merge request libeigen/eigen!2051
Co-authored-by: Rasmus Munk Larsen <rmlarsen@google.com>
Co-authored-by: Antonio Sánchez <cantonios@google.com>
<!--
Thanks for contributing a merge request!
We recommend that first-time contributors read our [contribution guidelines](https://eigen.tuxfamily.org/index.php?title=Contributing_to_Eigen).
Before submitting the MR, please complete the following checks:
- Create one PR per feature or bugfix,
- Run the test suite to verify your changes.
See our [test guidelines](https://eigen.tuxfamily.org/index.php?title=Tests).
- Add tests to cover the bug addressed or any new feature.
- Document new features. If it is a substantial change, add it to the [Changelog](https://gitlab.com/libeigen/eigen/-/blob/master/CHANGELOG.md).
- Leave the following box checked when submitting: `Allow commits from members who can merge to the target branch`.
This allows us to rebase and merge your change.
Note that we are a team of volunteers; we appreciate your patience during the review process.
-->
### Description
<!--Please explain your changes.-->
Remove deprecated CUDA device properties.
### Reference issue
<!--
You can link to a specific issue using the gitlab syntax #<issue number>.
If the MR fixes an issue, write "Fixes #<issue number>" to have the issue automatically closed on merge.
-->
Fixes#3000.
Closes#3000
See merge request libeigen/eigen!2060
There was only a single code path left in TensorEvaluator using pblend. We can replace that with a call to the more general TernarySelectOp and get rid of pblend entirely from Core.
Closes#2998
See merge request libeigen/eigen!2056
Co-authored-by: Rasmus Munk Larsen <rmlarsen@google.com>
ComplexQZ would try to apply a Jacobi rotation to an empty block, which triggers a warning in static analyzers, since the corresponding `Eigen::Map` object will contain a `nullptr`.
See merge request libeigen/eigen!2043
<!--
Thanks for contributing a merge request! Please name and fully describe your MR as you would for a commit message.
If the MR fixes an issue, please include "Fixes #issue" in the commit message and the MR description.
In addition, we recommend that first-time contributors read our [contribution guidelines](https://eigen.tuxfamily.org/index.php?title=Contributing_to_Eigen) and [git page](https://eigen.tuxfamily.org/index.php?title=Git), which will help you submit a more standardized MR.
Before submitting the MR, you also need to complete the following checks:
- Make one PR per feature/bugfix (don't mix multiple changes into one PR). Avoid committing unrelated changes.
- Rebase before committing
- For code changes, run the test suite (at least the tests that are likely affected by the change).
See our [test guidelines](https://eigen.tuxfamily.org/index.php?title=Tests).
- If possible, add a test (both for bug-fixes as well as new features)
- Make sure new features are documented
Note that we are a team of volunteers; we appreciate your patience during the review process.
Again, thanks for contributing! -->
### Reference issue
<!-- You can link to a specific issue using the gitlab syntax #<issue number> -->
### What does this implement/fix?
<!--Please explain your changes.-->
Currently, we run each test 3 times to account for flaky tests. Sometimes, the test fails so quickly that the random seed is the same for the subsequent test, which fails the exact same way.
This MR uses a nanosecond seed which resolves the issue described above. Now, if the test does not pass on the first attempt but passes on the retries, the gitlab job status will be yellow but still be treated as a pass in the ci/cd pipeline. Hopefully, this means we will get more passes and help us identify room for improvement.
### Additional information
<!--Any additional information you think is important.-->
See merge request libeigen/eigen!2025
Charles Schlosser
Yu You
Rasmus Munk Larsen
Antonio Sánchez
Rasmus Munk Larsen
Ludwig Striet
Damiano Franzò
Guilhem Saurel
Sergiu Deitsch
Artem Bishev
Hs293Go
Tyler Veness