Commit Graph

  • f169c13d8e Replace PPC g++-10 with g++14. Antonio Sánchez 2025-07-02 17:07:44 +00:00
  • 7fa069ef90 tensor documentation Henric Ryden 2025-06-29 03:47:42 +00:00
  • 7c636dd5db Move HIP/CUDA defines to Core. Antonio Sánchez 2025-06-27 16:48:07 +00:00
  • 26616fe5b8 Fix VSX packetmath psin and pcast tests. Antonio Sánchez 2025-06-27 04:08:20 +00:00
  • a395ee162d Fix a collection of random failures encountered when testing with Bazel. Antonio Sánchez 2025-06-26 16:58:24 +00:00
  • 0bce653efc Use QEMU for arm and ppc tests. Antonio Sánchez 2025-06-25 15:22:46 +00:00
  • db8bd5b825 Modify pselect and various masks to use Scalar(1) for true. Antonio Sánchez 2025-06-20 22:40:46 +00:00
  • 6de0515fa6 Create a changelog file. Antonio Sánchez 2025-06-20 21:54:14 +00:00
  • 98fbf6ed77 Decommission aarch64 ampere runner. Antonio Sánchez 2025-06-20 20:33:52 +00:00
  • 81044ec13d Provide macro to explicitly disable alloca Charles Schlosser 2025-06-19 04:23:35 +00:00
  • bcce88c99e Faster emulated half comparisons Charles Schlosser 2025-06-17 17:05:58 +00:00
  • ac6955ebc6 Remove MSVC warnings in FindCoeff.h Filippo Basso 2025-06-17 00:39:02 +00:00
  • 67a898a079 Fix unprotected SIZE in macro. Antonio Sánchez 2025-06-16 22:54:25 +00:00
  • cdf6a1f5ed Add OpenBLAS sbgemm. Antonio Sánchez 2025-06-16 18:23:03 +00:00
  • d228bcdf8f Fix neon compilation bug Charles Schlosser 2025-06-10 21:52:01 +00:00
  • 994f3d107a Fix neon packet math tests, add missing neon intrinsics Charles Schlosser 2025-06-09 17:13:31 +00:00
  • cda19a6255 Make Eigen::Map<const Vector>::operator[] return correct type AnonymousPC 2025-06-07 03:15:18 +08:00
  • d0b490ee09 Optimize maxCoeff and friends Charles Schlosser 2025-06-06 14:55:49 +00:00
  • c458d68fae Fix compile warning about * with bool. Antonio Sánchez 2025-06-05 22:48:57 +00:00
  • 3f00059beb Fix fuzzer range error for scalar parity check. Adam Cogdell 2025-06-05 22:27:35 +00:00
  • 21e89b930c Enable default behavior for pmin<PropagateFast>, predux_min, etc Charles Schlosser 2025-06-02 17:23:37 +00:00
  • 4fdf87bbf5 clean up intel packet reductions Charles Schlosser 2025-05-30 19:18:07 +00:00
  • a7f183cadb Add factory/getters for quat coeffs in both orders Hs293Go 2025-05-24 04:10:50 -04:00
  • d81aa18f4d Explicitly construct the scalar for non-implicitly convertible types Sergiu Deitsch 2025-05-15 17:40:29 +02:00
  • 171bd08ca9 fix 2849 Charles Schlosser 2025-05-15 02:04:50 +00:00
  • db85838ee2 Add DUCC FFT support Damiano Franzò 2025-05-12 17:56:02 +00:00
  • 6f1a143418 Ensure info() implementation across all SolverBase derived types Damiano Franzò 2025-05-02 09:56:48 +02:00
  • f3e7d64f3d Fix: Correct Lapacke bindings for BDCSVD and JacobiSVD to match the updated API Damiano Franzò 2025-05-08 19:06:08 +02:00
  • 434a2fc4a4 Fix obsolete comment in InverseImpl.h. We use PartialPivLU for the general case. Rasmus Munk Larsen 2025-05-08 23:02:10 +00:00
  • ae3aba99db Fix typo in CoreEvaluators.h Rasmus Munk Larsen 2025-05-08 17:43:12 +00:00
  • ee4f86f909 Fix MSAN in vectorized casting evaluator Charles Schlosser 2025-05-08 09:38:35 +00:00
  • 6dbbf0a843 CMake: only create uninstall target when eigen is top level Duy Tran 2025-04-27 17:07:15 -04:00
  • fb2fca90be Avoid unnecessary matrix copy in BDCSVD and JacobiSVD Damiano Franzò 2025-05-01 23:17:21 +00:00
  • d6b23a2256 Fix unused local typedef warning in matrix exponential Tyler Veness 2025-04-29 19:54:15 +00:00
  • 7294434099 Avoid UB in ploaduSegment Rasmus Munk Larsen 2025-04-25 21:13:52 +00:00
  • 2265a5e025 Fix commainitializer noexcept test. Antonio Sánchez 2025-04-23 00:05:02 +00:00
  • 619be0deb6 Replace instances of EIGEN_NOEXCEPT macros Tyler Veness 2025-04-22 00:58:47 +00:00
  • d2dce37767 Optimize slerp() as proposed by Gopinath Vasalamarri. Rasmus Munk Larsen 2025-04-21 14:11:42 -07:00
  • 66d8111ac1 Use a more conservative method to detect non-finite inputs to cbrt. Rasmus Munk Larsen 2025-04-21 20:59:46 +00:00
  • d6689a15d7 Replace instances of EIGEN_CONSTEXPR macro Tyler Veness 2024-11-15 21:11:01 -08:00
  • 33f5f59614 Vectorize cbrt for float and double. Rasmus Munk Larsen 2025-04-17 23:31:20 +00:00
  • 5330960900 Enable packet segment in partial redux Charles Schlosser 2025-04-14 17:44:53 +00:00
  • 6266d430cc packet segment: also check DiagonalWrapper Charles Schlosser 2025-04-12 19:34:11 +00:00
  • e39ad8badc fix constexpr in CoreEvaluators.h Charles Schlosser 2025-04-12 18:54:09 +00:00
  • 7aefb9f4d9 fix memset optimization for std::complex types Charles Schlosser 2025-04-12 16:20:09 +00:00
  • 73ca849a68 fix packetSegment for ArrayWrapper / MatrixWrapper Charles Schlosser 2025-04-12 12:12:48 +00:00
  • 28c3b26d53 masked load/store framework Charles Schlosser 2025-04-12 00:31:10 +00:00
  • cebe09110c Fix a potential deadlock because of Eigen thread pool Eugene Zhulenev 2025-04-11 23:43:14 +00:00
  • 11fd34cc1c Fix the typing of the Tasks in ForkJoin.h William Kong 2025-04-09 17:21:36 +00:00
  • 2cd47d743e Fixe Conversion Warning in Parallelizer Hunter Belanger 2025-04-08 07:39:01 +00:00
  • b860042263 Add postream for ostream-ing packets more reliably. Antonio Sánchez 2025-04-01 22:12:00 +00:00
  • 02d9e1138a Add missing pmadd for Packet16bf. Antonio Sánchez 2025-03-31 04:17:17 +00:00
  • 9cc9209b9b Fix cmake warning and default to j0. Antonio Sánchez 2025-03-29 16:09:40 +00:00
  • e0c99a8dd6 By default, run ctests on all available cores in parallel. Rasmus Munk Larsen 2025-03-27 13:16:44 -07:00
  • 63a40ffb95 Use fma<float> for fma<half> and fma<bfloat16> if native fma is not available on the platform. Rasmus Munk Larsen 2025-03-28 04:26:04 +00:00
  • 44fb6422be All triggering full CI if MR label containts all-tests Antonio Sanchez 2025-03-27 06:53:52 -07:00
  • 3866cbfbe8 Fix test for TensorRef of trace. Rasmus Munk Larsen 2025-03-25 23:01:46 +00:00
  • 6579e36eb4 Allow Tensor trace to be passed to a TensorRef. Antonio Sanchez 2025-03-25 08:26:23 -07:00
  • 8e32cbf7da Reduce flakiness of test for Eigen::half. Antonio Sanchez 2025-03-23 22:31:25 -07:00
  • d935916ac6 Add numext::fma and missing pmadd implementations. Antonio Sánchez 2025-03-23 01:05:53 +00:00
  • 754bd24f5e fix 2828 Charles Schlosser 2025-03-22 17:19:44 +00:00
  • ac2165c11f fix allFinite Charles Schlosser 2025-03-20 16:04:46 +00:00
  • 3143968195 Generalize the Eigen ForkJoin scheduler to use any ThreadPool interface. William Kong 2025-03-19 18:44:03 +00:00
  • 70f2aead9a Use native _Float16 for AVX512FP16 and update vectorization. Antonio Sánchez 2025-03-19 19:55:26 +00:00
  • 0259a52b0e Use more .noalias() Markus Vieth 2025-03-17 19:32:43 +01:00
  • 14f845a1a8 Fix givens rotation. Antonio Sánchez 2025-03-14 17:15:57 +00:00
  • 5e8edd2186 Fix undefined behavior in PPC load. 3.3 Antonio Sanchez 2025-03-13 22:23:45 -07:00
  • 0ac1fc52dd Fix CUDA clang again with new C++11 usages Antonio Sanchez 2025-03-13 20:47:31 -07:00
  • 33b04fe518 CMake: add install-doc target Guilhem Saurel 2024-12-13 21:46:20 +01:00
  • 6aa0143851 Judge unitary-ness relative to scaling. Antonio Sánchez 2024-04-30 22:28:46 +00:00
  • c7f6f8315f Update CUDA testing infra to match master branch. Antonio Sanchez 2025-03-13 21:49:24 +00:00
  • b0448fc6e0 Fix cxx03 testing job configuration Antonio Sanchez 2025-03-13 11:13:35 -07:00
  • 3b8644da50 Better rand to fix MSVC random tests Antonio Sanchez 2025-03-13 08:45:50 -07:00
  • 414c42bfcf Fix cuda clang builds Antonio Sanchez 2025-03-11 19:20:03 -07:00
  • 10e62ccd22 Fix x86 complex vectorized fma Charles Schlosser 2025-03-12 17:06:32 +00:00
  • 952eda443b Fix GPU build failures. Antonio Sanchez 2025-03-09 17:04:41 -07:00
  • 6a4a0b66bd Fix epsilon and dummy_precision values in long double for double doubles. Prevented some algorithms from converging on PPC. Chip Kerchner 2023-02-16 23:35:42 +00:00
  • 079de53fa5 Adjust tolerance of matrix_power test for MSVC. Antonio Sanchez 2022-03-01 23:31:15 +00:00
  • ce950ca2db Patch PPC PacketMath from 3.4. Antonio Sanchez 2025-03-07 20:59:30 -08:00
  • 464c1d0978 Format TensorDeviceThreadPool.h & use if constexpr for c++20. Rasmus Munk Larsen 2025-03-08 01:09:36 +00:00
  • 21223f6bb6 Fix addition of different enum types. Rasmus Munk Larsen 2025-03-07 22:18:00 +00:00
  • 350544eb01 Clean up TensorDeviceThreadPool.h Rasmus Munk Larsen 2025-03-07 18:14:17 +00:00
  • 43810fc1be Fix extra semicolon in DeviceWrapper Kevin 2025-03-07 01:07:23 +00:00
  • d28041ed5a refactor AssignmentFunctors.h, unify with existing scalar_op Charles Schlosser 2025-03-06 01:28:39 +00:00
  • 49bd503308 Fix merge conflict error Antonio Sanchez 2025-03-03 15:21:02 -08:00
  • 5b20d9f326 Fix arm32 float division and related bugs Charles Schlosser 2023-08-29 00:36:07 +00:00
  • 5f8f69020b Remove poor non-convergence checks in NonLinearOptimization. Antonio Sánchez 2022-03-02 19:31:20 +00:00
  • dc9325848a Fix arm32 issues. Antonio Sánchez 2024-01-23 22:04:55 +00:00
  • 9df4c76bb8 Fix emulated builds cmake configuration Antonio Sanchez 2025-03-03 07:26:26 -08:00
  • 0071c2e8a8 Fix more hard-coded magic bounds. Antonio Sánchez 2024-04-29 21:21:11 +00:00
  • 03727bdf55 Slightly adjust error bound for nonlinear tests. Antonio Sánchez 2024-04-25 18:04:49 +00:00
  • 5e39ba6642 Fix emulated tests. Antonio Sánchez 2025-01-31 19:30:42 +00:00
  • d2ce4faa5a Fix cuda 9+ builds Antonio Sanchez 2025-03-02 07:38:47 -08:00
  • 43b7aa2412 Don't check for build type Antonio Sanchez 2025-02-28 22:13:46 -08:00
  • 23b1682723 Fix cuda device warnings Antonio Sanchez 2025-02-28 15:21:23 -08:00
  • 9a86214039 Optimize division operations in TensorVolumePatch.h Gopinath Vasalamarri 2025-02-28 22:34:13 +00:00
  • c53002f5fb Fix failing tests on arm/ppc Antonio Sanchez 2025-02-28 13:15:33 -08:00
  • be5147b090 Fix STL feature detection for c++20. Antonio Sánchez 2025-02-28 19:52:37 +00:00
  • ea37d9e73e Remove private access of std::deque::_M_impl. Antonio Sanchez 2020-12-10 14:59:34 -08:00
  • 179a49684a Fix CMake BOOST warning Antonio Sanchez 2025-02-28 07:33:26 -08:00