Google Git
Sign in
eigen / mirror / HEAD
  1. 9eb8e2a Change array_cwise test name by Charles Schlosser · 1 year, 6 months ago
  2. 725c117 Visitor: fix modulo by zero compiler warning by Charles Schlosser · 1 year, 6 months ago
  3. b8208b3 Specialized loadColData correctly - fix previous BF16 GEMV MR by Chip Kerchner · 1 year, 6 months ago
  4. 2af03fb clean up array_cwise test by Charles Schlosser · 1 year, 6 months ago
  5. fda1373 Fix ColMajor BF16 GEMV for when vector is RowMajor by Chip Kerchner · 1 year, 6 months ago
  6. fdc749d JacobiSVD: set m_nonzeroSingularValues to zero if not finite by Charles Schlosser · 1 year, 6 months ago
  7. 6418ac0 Unroll F32 to BF16 loop - 1.8X faster conversions for LLVM. Use vector pairs for GCC. by Chip Kerchner · 1 year, 6 months ago
  8. 874f594 Add half-`Packet` operations to `StridedLinearBufferCopy`. by Pedro Gonnet · 1 year, 6 months ago
  9. c9a14f4 SSE Packet4ui has pcmp, pmin, pmax by Charles Schlosser · 1 year, 6 months ago
  10. 0b51f76 Revert "Geometry/EulerAngles: make sure that returned solution has canonical ranges" by Rasmus Munk Larsen · 1 year, 6 months ago
  11. 2d0c6ad Revert "Vectorize cast" by Antonio Sánchez · 1 year, 6 months ago
  12. 8999525 AVX2: Packet4ul has pmul, abs2 by Charles Schlosser · 1 year, 6 months ago
  13. eb5ff18 Vectorize cast by Charles Schlosser · 1 year, 6 months ago
  14. 3918768 Fix sparse iterator and tests. by Antonio Sánchez · 1 year, 6 months ago
  15. 7041031 Fix boolean bitwise and warning. by Antonio Sanchez · 1 year, 6 months ago
  16. f6cf5dc Packet4ul does not have Abs2 by Charles Schlosser · 1 year, 6 months ago
  17. 03f646b New VSX version of BF16 GEMV (Power) - up to 6.7X faster by Chip Kerchner · 1 year, 6 months ago
  18. 29c8e3c fix pow for uint32_t, disable pmul<Packet4ul> by Charles Schlosser · 1 year, 6 months ago
  19. 7f06bca Geometry/EulerAngles: make sure that returned solution has canonical ranges by Juraj Oršulić · 1 year, 6 months ago
  20. a347dbb Delete last few occurences of HasHalfPacket. by Rasmus Munk Larsen · 1 year, 6 months ago
  21. b378014 Make sure we return +/-1 above the clamping point for Erf(). by Rasmus Munk Larsen · 1 year, 6 months ago
  22. e2bbf49 Use select ternary op in tensor select evaulator by Charles Schlosser · 1 year, 6 months ago
  23. 2b954be fix typo in sse packetmath by Charles Schlosser · 1 year, 6 months ago
  24. 25685c9 Fix incorrect packet type for unsigned int version of pfirst() in MSVC workaround in PacketMath.h. by Rasmus Munk Larsen · 1 year, 6 months ago
  25. 1e223a9 Add missing 'f' in float literal in SpecialFunctionsImpl.h that triggers implicit conversion warning. by Rasmus Munk Larsen · 1 year, 6 months ago
  26. 3f3ce21 New BF16 pcast functions and move type casting to TypeCasting.h by Chip Kerchner · 1 year, 6 months ago
  27. 17b5b4d Add `Packet4ui`, `Packet8ui`, and `Packet4ul` to the `SSE`/`AVX` `PacketMath.h` headers by Pedro Gonnet · 1 year, 6 months ago
  28. 87300c9 Refactor IndexedView by Charles Schlosser · 1 year, 6 months ago
  29. 1148f0a Add dynamic dispatch to BF16 GEMM (Power) and new VSX version by Chip Kerchner · 1 year, 6 months ago
  30. 3026fc0 Improve accuracy of erf(). by Rasmus Munk Larsen · 1 year, 6 months ago
  31. 554fe02 Enable new AVX512 GEMM kernel by default. by Rasmus Munk Larsen · 1 year, 6 months ago
  32. 0d12fcc Insert from triplets by Charles Schlosser · 1 year, 6 months ago
  33. 990a282 exclude `Eigen/Core` and `Eigen/src/Core` from being ignored due to `core` ignore rule by Rob Conde · 1 year, 6 months ago
  34. b0eded8 DOC: Update documentation for 3.4.x by Rohit Goswami · 1 year, 7 months ago
  35. b0f877f Don't crash on empty tensor contraction. by Rasmus Munk Larsen · 1 year, 7 months ago
  36. 15fbdda ASAN fixes for AVX512 GEMM/TRSM by b-shi · 1 year, 7 months ago
  37. 178ef8c qualify non-const symbolic indexed view with is_lvalue by Charles Schlosser · 1 year, 7 months ago
  38. df1049d Small packet math cleanup. by Rasmus Munk Larsen · 1 year, 7 months ago
  39. 9b48d10 Guard all malloc, realloc and free() fonctions with check_that_malloc_is_allowed() by Antoine Hoarau · 1 year, 7 months ago
  40. c730290 Use the correct truncating intrinsic for double->int casting. by Rasmus Munk Larsen · 1 year, 7 months ago
  41. 766db02 disable raw array indexed view access for 1d arrays by Charles Schlosser · 1 year, 7 months ago
  42. bfbc66e refactor indexedviewmethods, enable non-const ref access with symbolic indices by Charles Schlosser · 1 year, 7 months ago
  43. 1a5dfd7 Fix incorrect casting in AVX512DQ path. by Rasmus Munk Larsen · 1 year, 7 months ago
  44. a086499 Optimize generic_rsqrt_newton_step by Charles Schlosser · 1 year, 7 months ago
  45. b8b8a26 Add more missing vectorized casts for int on x86, and remove redundant unit tests by Rasmus Munk Larsen · 1 year, 7 months ago
  46. 33e206f Remove unused declarations of BLAS/LAPACK routines by unageek · 1 year, 7 months ago
  47. d57a79e Optimize float->bool cast for AVX2, based on Charles Schlosser's comments. by Rasmus Munk Larsen · 1 year, 7 months ago
  48. a5ae832 Fix reversal of arguments to _mm256_set_m128() in pcast<Packet4d, Packet8f>. by Rasmus Munk Larsen · 1 year, 7 months ago
  49. 09945f2 Optimize casting for x86_64. by Rasmus Munk Larsen · 1 year, 7 months ago
  50. 8f9b8e3 Replaced all instances of internal::(U)IntPtr with std::(u)intptr_t. Remove ICC workaround. by Colin Broderick · 1 year, 7 months ago
  51. 2c8011c Fix arm builds. by Antonio Sánchez · 1 year, 7 months ago
  52. fd8f410 Fix 2624 2625 by Charles Schlosser · 1 year, 7 months ago
  53. e887196 Undo cmake pools changes by Chip Kerchner · 1 year, 7 months ago
  54. 81cb6a5 Fix some typos by Jonas Schulze · 1 year, 7 months ago
  55. 555cec1 Fix parsing of command-line arguments when already specified as a cmake list. by Antonio Sánchez · 1 year, 7 months ago
  56. 7db19ba Remove pools if cmake is less than 3.11 by Chip Kerchner · 1 year, 7 months ago
  57. 0488b70 Vectorize tensor.isnan() by using typed predicates. by Rasmus Munk Larsen · 1 year, 7 months ago
  58. f02856c Use EIGEN_NOT_A_MACRO macro (oh the irony!) to avoid build issue in TensorFlow. by Rasmus Munk Larsen · 1 year, 7 months ago
  59. 690ae95 Use C++11 standard features for detecting presence of Inf and NaN by Rasmus Munk Larsen · 1 year, 7 months ago
  60. d71ac6a Fix recent PowerPC warnings and clang warning by Chip Kerchner · 1 year, 7 months ago
  61. d54d228 Limit the number of build jobs to 8 and link jobs to 4 for PowerPC. This should help reduce the OOM build problems. by Chip Kerchner · 1 year, 7 months ago
  62. 23e1541 Put deadcode checks back in from previous change. by Chip Kerchner · 1 year, 7 months ago
  63. 6c58f0f Revert changes that made BF16 GEMM to cause bad register spillage for LLVM (Power) by Chip Kerchner · 1 year, 7 months ago
  64. 8fe6190 Add numext::isnan for AnnoyingOrange^H^H^H^H^H^HScalar. by Rasmus Munk Larsen · 1 year, 7 months ago
  65. 79de101 Handle PropagateFast the same way as PropagateNaN in minmax visitor to by Rasmus Munk Larsen · 1 year, 7 months ago
  66. 9d72412 Add MMA to BF16 GEMV - 5.0-6.3X faster (for Power) by Chip Kerchner · 1 year, 7 months ago
  67. 2067b54 Fix bug in minmax_coeff_visitor for matrix of all NaNs. by Rasmus Munk Larsen · 1 year, 7 months ago
  68. ee0ff0a Fix typo in MathFunctions.h by Rasmus Munk Larsen · 1 year, 7 months ago
  69. 21c49e8 Delete mystery character from Eigen/src/Core/arch/NEON/MathFunctions.h by Rasmus Munk Larsen · 1 year, 8 months ago
  70. 6bb9609 Make new Select implementation backwards compatible. by Rasmus Munk Larsen · 1 year, 8 months ago
  71. 394aabb Fix failing MSVC tests due to compiler bugs. by Antonio Sánchez · 1 year, 8 months ago
  72. d6235d7 Clean up generic packetmath specializations for various backends with the help of a macro. by Rasmus Munk Larsen · 1 year, 8 months ago
  73. e8fdf12 Work around compiler bug in Tridiagonalization.h by Rasmus Munk Larsen · 1 year, 8 months ago
  74. adf26b6 Add newline to end of file. by Rasmus Munk Larsen · 1 year, 8 months ago
  75. 3492d9e s/Lesser/Less/ by Rasmus Munk Larsen · 1 year, 8 months ago
  76. 2419632 Revert change to allFinite(), since the new version does not work for complex numbers. by Rasmus Munk Larsen · 1 year, 8 months ago
  77. b1beba8 Fix LinAlgSVD example code by Zach Davis · 1 year, 8 months ago
  78. 7bf2968 Specify Permutation Index for PartialPivLU and FullPivLU by Charles Schlosser · 1 year, 8 months ago
  79. eb4dbf6 Modify failing cwise test to get it to pass. by Antonio Sánchez · 1 year, 8 months ago
  80. e577f43 Set CMAKE_* cache variables only when Eigen is a top-level project by Timofey Pushkin · 1 year, 8 months ago
  81. 1ce8b25 Vectorize any() / all() by Charles Schlosser · 1 year, 8 months ago
  82. cb8e6d4 Fix 2240, 2620 by Charles Schlosser · 1 year, 8 months ago
  83. d670039 fix tensor comparison test by Charles Schlosser · 1 year, 8 months ago
  84. 2b513ca Added partial linear access for LHS & Output - 30% faster for bfloat16 GEMM MMA (Power) by Chip Kerchner · 1 year, 8 months ago
  85. 0b396c3 Scalarize comps by Charles Schlosser · 1 year, 8 months ago
  86. 3abe124 fix signed shift test by Charles Schlosser · 1 year, 8 months ago
  87. ba7417f Fix gpu conv3d out-of-resources failure. by Antonio Sánchez · 1 year, 8 months ago
  88. 62d5cfe Fix ODR issues with Intel's AVX512 TRSM kernels. by Antonio Sánchez · 1 year, 8 months ago
  89. 826627f vectorize comparisons and select by enabling typed comparisons by Charles Schlosser · 1 year, 8 months ago
  90. 2e9b945 Fix bug that disabled vectorization for coeffMin/coeffMax. by Rasmus Munk Larsen · 1 year, 8 months ago
  91. bc5cdc7 Guard use of long double on GPU device. by Antonio Sánchez · 1 year, 8 months ago
  92. e4598fe Fix compiler versions for certain instructions on Power. by Chip Kerchner · 1 year, 8 months ago
  93. 1c0a6cf Get rid of EIGEN_HAS_AVX512_MATH workaround. by Rasmus Munk Larsen · 1 year, 8 months ago
  94. 00844e3 Fix a number of MSAN failures in SVD tests. by Rasmus Munk Larsen · 1 year, 8 months ago
  95. c3f6706 [SYCL-2020]- null placeholder accessor issue in Reduction SYCL test by Mehdi Goli · 1 year, 8 months ago
  96. 6bcd941 Use pmsub in twoprod. This speeds up pow() on Skylake by ~1%. by Rasmus Munk Larsen · 1 year, 8 months ago
  97. ce62177 Vectorize atanh & add a missing definition and unit test for atan. by Rasmus Munk Larsen · 1 year, 8 months ago
  98. 049a144 Add typed logicals by Charles Schlosser · 1 year, 8 months ago
  99. e797974 Add and enable Packet int divide for Power10. by Chip Kerchner · 1 year, 8 months ago
  100. 5445921 Fix epsilon and dummy_precision values in long double for double doubles. Prevented some algorithms from converging on PPC. by Chip Kerchner · 1 year, 8 months ago