Google Git
Sign in
eigen/mirror/HEAD
  1. 599d71a CI: make REUSE lint failures breaking by Rasmus Munk Larsen · 13 hours ago master
  2. 6f9c2ab CI: add pre-configured smoke test container images to speed up pipelines by Charles Schlosser · 2 days ago
  3. 7e09729 Eigen/GPU [4/5]: Add sparse solvers, FFT, and SpMV (cuDSS, cuFFT, cuSPARSE) by Rasmus Munk Larsen · 2 days ago
  4. 44b3287 Eigen/GPU [3/5]: Add dense cuSOLVER solvers (QR, SVD, EigenSolver) by Rasmus Munk Larsen · 2 days ago
  5. 83184e6 Cleanup: Modernize internal utilities for C++14 by Florian Maurin · 3 days ago
  6. ff72fba Core: drop obsolete feature-detection guards by Florian Maurin · 4 days ago
  7. 90dfbc0 Cleanup: fix include guard comments and names by Florian Maurin · 4 days ago
  8. 4b325d6 Adds support for complex vector API for RISC-V by Chip Kerchner · 5 days ago
  9. ff85966 CI: install xsltproc in before_script, drop apt-get from after_script by Rasmus Munk Larsen · 5 days ago
  10. 9e912de Jacobi: add safe scaling to real-scalar makeGivens by Rasmus Munk Larsen · 5 days ago
  11. c259c74 RVV: add missing SPDX-License-Identifier to PacketMathDecl.h by Rasmus Munk Larsen · 5 days ago
  12. 0efe8f6 RVV: simplify packet math declaration boilerplate by Charles Schlosser · 6 days ago
  13. 2cf9891 blame: ignore clang-format-17 cleanup and SPDX bulk-tag commits by Rasmus Munk Larsen · 6 days ago
  14. b955000 CI/clang-tidy: fix latent issues surfaced when running on many headers by Rasmus Munk Larsen · 6 days ago
  15. 8a3d61c Licensing: SPDX identifiers, REUSE.toml, and checkformat:reuse CI job by Rasmus Munk Larsen · 7 days ago
  16. 2031535 CI: clang-format-17 cleanup of pre-existing drift by Rasmus Munk Larsen · 7 days ago
  17. c930e4e tensor_device: silence -Wclass-memaccess for OffByOneScalar memset by Rasmus Munk Larsen · 7 days ago
  18. d5d3670 CI: fix bench builds (drop Apply/internal::Benchmark*) + relax eigensolver_selfadjoint tolerance by Rasmus Munk Larsen · 7 days ago
  19. 0650965 Rewrite TensorCostModel with principled roofline model by Rasmus Munk Larsen · 7 days ago
  20. dd0790f CI: fix mistyped EIGEN_CI_TEST_LABEL in avx512fp16 jobs by Rasmus Munk Larsen · 7 days ago
  21. b4c12ba TriangularView: alias-aware fallback for structured-diagonal product fast path by Rasmus Munk Larsen · 7 days ago
  22. 1e73632 SelfAdjointEigenSolver: scalar argmin in eigenvalue sort (fixes ARM NEON sort) by Rasmus Munk Larsen · 7 days ago
  23. 9054809 Block-tile and bypass setZero for SelfAdjointView × Diagonal (perf for !2486) by Rasmus Munk Larsen · 7 days ago
  24. 009d382 Lazy structured*diagonal evaluator + SelfAdjointView complex-scalar guard by Rasmus Munk Larsen · 8 days ago
  25. 08e19b5 Eigen/GPU [2/5]: Add library dispatch module (DeviceMatrix, cuBLAS, cuSOLVER) by Rasmus Munk Larsen · 8 days ago
  26. d1c9a64 Use structured diagonal product in SparseInverse by Rasmus Munk Larsen · 8 days ago
  27. 1b27261 Unify triangular and self-adjoint view interfaces by Florian Maurin · 8 days ago
  28. 4d3688f SparseCholesky: skip Scalar-typed AMD prep when OrderingType is AMD by Rasmus Munk Larsen · 8 days ago
  29. 92c7bb7 Core: patanh fast-exit and plog10_float hi+lo accuracy fix by Rasmus Munk Larsen · 8 days ago
  30. 8ce370d AltiVec: honor alpha == 0 short-circuit in GEMV specializations by Rasmus Munk Larsen · 8 days ago
  31. d6f25aa ci: pass compiler vars to google/benchmark cmake invocation by Rasmus Munk Larsen · 8 days ago
  32. efeb543 TensorConcatenation: fix packet() fast-path when concat axis is not innermost by Rasmus Munk Larsen · 8 days ago
  33. 2943e0d Add better error reporting for StorageIndex overflow by Dima-aka-dima · 8 days ago
  34. 7ef0ea4 SparsityPatternRef: bulk-copy fast path for compressed sources by Rasmus Munk Larsen · 8 days ago
  35. a624cf1 AMDOrdering: pattern-only A+A^T merge by Rasmus Munk Larsen · 8 days ago
  36. a25aa64 SparseCore: SparsityPatternRef view; pattern-only AMD ordering & ILUT prep by Rasmus Munk Larsen · 9 days ago
  37. 1d02c1f sparse_vector test: retry initSparse until at least one nonzero by Rasmus Munk Larsen · 9 days ago
  38. 879885e Modernize internal utilities for C++14 by Florian Maurin · 9 days ago
  39. 97bf549 IncompleteLUT: static row matching to handle zero-diagonal matrices (#2626) by Rasmus Munk Larsen · 9 days ago
  40. e0544c9 Speed up small determinant LU fallback by Florian Maurin · 9 days ago
  41. 2b654fe Bug fix in RealQZ: count pushDownZero iterations toward maxIters by Artem Rabetckii · 10 days ago
  42. fef1460 Add block() / getResourceRequirements() to Tensor{Scan,FFT,LayoutSwap,Contraction} by Rasmus Munk Larsen · 11 days ago
  43. 8290a55 Vectorize TensorReverse / TensorRoll packet() inner-slice fast path by Rasmus Munk Larsen · 11 days ago
  44. 8a910e3 Avoid vectorizing tiny fixed-size assignments by Florian Maurin · 13 days ago
  45. 2f3c27c Parallelizer: qualify std::min<int>() to avoid test/main.h macro collision by Rasmus Munk Larsen · 13 days ago
  46. 902713d TensorContraction: add gemv fast paths for all transposed shapes (#1648) by Rasmus Munk Larsen · 14 days ago
  47. 62ac66a Implement blocked tridiagonalization for large matrices by Rasmus Munk Larsen · 14 days ago
  48. ae04638 Clarify top-level license notices by Rasmus Munk Larsen · 14 days ago
  49. c5d31f3 ci: drop CodeRabbit high-level summary, changed-files overview, docstrings precheck by Rasmus Munk Larsen · 14 days ago
  50. cdf9697 SPQR: fix fixed-ordering permutation and complete matrixQ()/matrixR() handling by Florian Maurin · 14 days ago
  51. eca5d71 Fix unsupported EulerAngles gimbal lock conversion by Florian Maurin · 14 days ago
  52. e3270e9 GEMV/GEMM products: runtime L1 detection for two more cache dispatch thresholds by Rasmus Munk Larsen · 2 weeks ago
  53. 50a9b73 Core: skip GEMM/GEMV kernels when alpha == 0 by Rasmus Munk Larsen · 2 weeks ago
  54. 974980e Edit .coderabbit.yaml by Rasmus Munk Larsen · 2 weeks ago
  55. dd7916b ci: trim noise in CodeRabbit walkthrough comment by Rasmus Munk Larsen · 2 weeks ago
  56. f09e444 ci: add CodeRabbit configuration for AI-assisted MR reviews by Rasmus Munk Larsen · 2 weeks ago
  57. c8d5cba Core: clean up remaining nested const storage by Florian Maurin · 2 weeks ago
  58. ad27e61 Geometry module: Optimize AngleAxis, EulerAngles by Rasmus Munk Larsen · 2 weeks ago
  59. 0f90842 TensorConvolution: fix deprecated-enum-enum-conversion warning on gcc-13 by Rasmus Munk Larsen · 2 weeks ago
  60. 76433f6 test: use a public BDCSVD missing-predecessor reproducer by Florian Maurin · 2 weeks ago
  61. f15ef42 GeneralMatrixVector: replace magic 32000 byte cache threshold with detected L1 by Rasmus Munk Larsen · 3 weeks ago
  62. 88936db gemm_pack_rhs: enable vectorized transpose for half-width packets by Rasmus Munk Larsen · 3 weeks ago
  63. dba22e2 Clean up stale TODOs/FIXMEs across Core, SparseCore, QR, SVD, Eigenvalues, and Tensor by Rasmus Munk Larsen · 3 weeks ago
  64. 809f93f BDCSVD: eliminate temporaries flagged by long-standing FIXMEs by Rasmus Munk Larsen · 3 weeks ago
  65. e05a565 SelfAdjointView: add l1Norm() and use it in LLT / LDLT by Rasmus Munk Larsen · 3 weeks ago
  66. 31d9a79 DGMRES: guard against Arnoldi happy breakdown and singular Hessenberg by Rasmus Munk Larsen · 3 weeks ago
  67. f31ff64 test/meta: disambiguate internal::get from new Eigen::get free fns by Rasmus Munk Larsen · 3 weeks ago
  68. 98443d4 TensorMorphing: re-enable BlockAccess for slicing of bool tensors by Rasmus Munk Larsen · 3 weeks ago
  69. f1cccdd TensorConcatenation: real packet() vectorization (~4x speedup) by Rasmus Munk Larsen · 3 weeks ago
  70. be0a5b4 Preserve const coeffRef on mutable CwiseUnaryView by Florian Maurin · 3 weeks ago
  71. 468d2dc AVX ploaddup<Packet4cf>: avoid double* reinterpret by Rasmus Munk Larsen · 3 weeks ago
  72. feabd94 AVX ploaddup<Packet4cf>: delegate to ploaddup<Packet4d> (2 uops vs ~5) by Rasmus Munk Larsen · 3 weeks ago
  73. e9a39b4 DenseBase: collapse minCoeff/maxCoeff overloads via default template arg by Rasmus Munk Larsen · 3 weeks ago
  74. daee26c Drop stale TODO above triangular*homogeneous workaround by Rasmus Munk Larsen · 3 weeks ago
  75. 2c78d14 SparseLU: remove dead/buggy in-loop row-permutation determinant update by Rasmus Munk Larsen · 3 weeks ago
  76. bcc6361 Sweep stale FIXME/TODO comments in Core by Rasmus Munk Larsen · 3 weeks ago
  77. fa91d8f Add mixed dense/skew-symmetric arithmetic operators by Pavel Guzenfeld · 3 weeks ago
  78. de44159 Remove some user-declared destructors by Jeremy Nimmer · 3 weeks ago
  79. 7f27701 Fix Concat evaluator to expose packetSegment for AVX/AVX-512 assignment tail by Rasmus Munk Larsen · 3 weeks ago
  80. bd0c05a CI: drop RelWithDebInfo from avx512fp16 build to fix artifact size by Rasmus Munk Larsen · 3 weeks ago
  81. 4a04380 Fix C++20 enum-enum conversion warnings by Florian Maurin · 3 weeks ago
  82. 3850ca8 Add C++17 structured bindings support for fixed-size Matrix and Array by Pavel Guzenfeld · 3 weeks ago
  83. 5da2b96 Drop cxx11_ prefix from tensor tests and remove stale pre-C++11 comments by Rasmus Munk Larsen · 3 weeks ago
  84. 3ed4fa2 Add hcat/vcat DenseBase concatenation expressions by Pavel Guzenfeld · 3 weeks ago
  85. 2517fb8 Improve GEBP kernel: unified sub-blocking, arch-independent loops, relaxed L1 budget on x86 by Rasmus Munk Larsen · 3 weeks ago
  86. c7d1892 Geometry module: Speed up setFromTwoVectors and AngleAxis * vector by Rasmus Munk Larsen · 3 weeks ago
  87. a77cbf0 BDCSVD: restore perturbCol0 guard by Florian Maurin · 3 weeks ago
  88. abd1bda Optimize UpperBidiagonalization: fix noalias, tune block size and threshold by Rasmus Munk Larsen · 3 weeks ago
  89. 4418f97 Add C++20 contiguous_range tests for Eigen vectors by Pavel Guzenfeld · 3 weeks ago
  90. 86f2c6e SparseRef: fix writable sparse Ref bindings for inner-panel subset views by Florian Maurin · 3 weeks ago
  91. 4c49f07 Introduce `numext::copysign` by onalante-ebay · 3 weeks ago
  92. 2ff14d1 Fix innerVector(s) blocks with fixed-size expressions by Charles Schlosser · 3 weeks ago
  93. 938b921 CI: Remove sanitizer smoketest jobs from MR pipelines by Rasmus Munk Larsen · 3 weeks ago
  94. 2aaea06 Fix left scalar multiplication for TriangularView and SparseSelfAdjointView by Florian Maurin · 3 weeks ago
  95. 6ea5223 Fix SparseLU and SparseQR on row-major and uncompressed sparse inputs by Florian Maurin · 3 weeks ago
  96. cfbffe3 Geometry module: Bug fixes, test coverage, and benchmarks by Rasmus Munk Larsen · 3 weeks ago
  97. 588db79 Apply __launch_bounds__(1024) on CUDA, not just HIP by Rasmus Munk Larsen · 4 weeks ago
  98. d0b2c91 Fix nvcc CUDA test performance: propagate host compiler flags by Rasmus Munk Larsen · 4 weeks ago
  99. 118ea02 CI: Fix Windows ctest retry to only rerun failing tests by Rasmus Munk Larsen · 4 weeks ago
  100. 19ddcbf Revert CI cmake cache skip optimization by Rasmus Munk Larsen · 4 weeks ago