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>
Implemented fast size-4 matrix inverse (mimicking Inverse_SSE.h) using NEON intrinsics.
```
Benchmark Time CPU Time Old Time New CPU Old CPU New
--------------------------------------------------------------------------------------------------------
BM_float -0.1285 -0.1275 568 495 572 499
BM_double -0.2265 -0.2254 638 494 641 496
```
* * *
License disclaimer changed to BSD license for MKL_support.h
* * *
Pardiso support fixed, test added.
blas/lapack tests fixed: Scalar parameter was added in Cholesky, product_matrix_vector_triangular remaned to triangular_matrix_vector_product.
* * *
PARDISO test was added physically.
division instead of RCPPS-followed-by-Newton-Raphson. The rationale for that is
that elsewhere in Eigen we dont allow ourselves this approximation (which throws
2 bits of mantissa), so there's no reason we should allow it here.
* renaming, e.g. LU ---> FullPivLU
* split tests framework: more robust, e.g. dont generate empty tests if a number is skipped
* make all remaining tests use that splitting, as needed.
* Fix 4x4 inversion (see stable branch)
* Transform::inverse() and geo_transform test : adapt to new inverse() API, it was also trying to instantiate inverse() for 3x4 matrices.
* CMakeLists: more robust regexp to parse the version number
* misc fixes in unit tests
pivoting for better numerical stability. For now the only application is
determinant.
* New determinant unit-test.
* Disable most of Swap.h for now as it makes LU fail (mysterious).
Anyway Swap needs a big overhaul as proposed on IRC.
* Remnants of old class Inverse removed.
* Some warnings fixed.
(only 30 muls for size 4)
- rework the matrix inversion: now using cofactor technique for size<=3,
so the ugly unrolling is only used for size 4 anymore, and even there
I'm looking to get rid of it.
