Commit Graph

Select branches

Hide Pull Requests

3.4.0.dev

master

2.0-beta1

2.0-beta2

2.0-beta3

2.0-beta4

2.0-beta5

2.0-beta6

2.0-rc1

2.0.0

2.0.1

2.0.10

2.0.11

2.0.12

2.0.13

2.0.14

2.0.15

2.0.16

2.0.17

2.0.2

2.0.3

2.0.4

2.0.5

2.0.6

2.0.7

2.0.8

2.0.9

3.0-beta1

3.0-beta2

3.0-beta3

3.0-beta4

3.0-rc1

3.0.0

3.0.1

3.0.2

3.0.3

3.0.4

3.0.5

3.0.6

3.0.7

3.1.0

3.1.0-alpha1

3.1.0-alpha2

3.1.0-beta1

3.1.0-rc1

3.1.0-rc2

3.1.1

3.1.2

3.1.3

3.1.4

3.2-beta1

3.2-rc1

3.2-rc2

3.2.0

3.2.1

3.2.10

3.2.2

3.2.3

3.2.4

3.2.5

3.2.6

3.2.7

3.2.8

3.2.9

3.3-alpha1

3.3-beta1

3.3-beta2

3.3-rc1

3.3-rc2

3.3.0

3.3.1

3.3.2

3.3.3

3.3.4

3.3.5

3.3.6

3.3.7

3.3.8

3.3.8-rc1

3.3.9

3.4-rc1

3.4.0

actual-start-from-scratch

after-hg-migration

before-3.4

before-evaluators

before-git-migration

before-hg-migration

starting_new_generickernels

starting_new_packmapcalculator

Mono Color

• 7d9bb90f15 SVD: fix numerous compiler warnings / failures Charles Schlosser 2023-05-15 16:56:47 +0000
• 2709f4c8fb Use relative path to include EmulateArray.h in CXX11Meta.h, and get rid of redundant meta-programming code, which was moved to Core. Rasmus Munk Larsen 2023-05-09 23:21:35 +0000
• 9a02c977ec Use relative paths to include Meta.h and MaxSizeVector.h in Tensor Rasmus Munk Larsen 2023-05-09 22:07:55 +0000
• 96c42771d6 Make it possible to override the synchonization primitives used by the threadpool using macros. Rasmus Munk Larsen 2023-05-09 19:36:17 +0000
• 1321821e86 Add missing braces in Umeyama.h Rasmus Munk Larsen 2023-05-09 19:10:50 +0000
• 524c329ab2 Work around compiler bug in Umeyama.h. Rasmus Munk Larsen 2023-05-09 18:53:56 +0000
• fbf7189bd5 Fix cuda compilation Charles Schlosser 2023-05-08 16:15:47 +0000
• 0623791930 [SYCL-2020] Enabling USM support for SYCL. SYCL-1.2.1 did not have support for USM. Mehdi Goli 2023-05-05 17:30:36 +0000
• 1698c367a0 Use std::shared_ptr for FFTW/IMKL FFT plan implementation; Fixes #2651 Andrzej Ciarkowski 2023-05-05 16:58:23 +0000
• 1f79a6078f Return NaN in ndtri for values outside valid input range. Antonio Sánchez 2023-05-05 16:27:26 +0000
• 94f57867fe Thread pool Tobias Wood 2023-05-05 16:23:34 +0000
• 9eb8e2afba Change array_cwise test name Charles Schlosser 2023-05-05 03:08:43 +0000
• 725c11719b Visitor: fix modulo by zero compiler warning Charles Schlosser 2023-05-04 18:21:09 +0000
• b8208b363c Specialized loadColData correctly - fix previous BF16 GEMV MR Chip Kerchner 2023-05-04 16:38:17 +0000
• 2af03fb685 clean up array_cwise test Charles Schlosser 2023-05-04 16:02:08 +0000
• fda1373a15 Fix ColMajor BF16 GEMV for when vector is RowMajor Chip Kerchner 2023-05-03 20:12:50 +0000
• fdc749de2a JacobiSVD: set m_nonzeroSingularValues to zero if not finite Charles Schlosser 2023-05-02 17:48:21 +0000
• 6418ac0285 Unroll F32 to BF16 loop - 1.8X faster conversions for LLVM. Use vector pairs for GCC. Chip Kerchner 2023-05-01 16:54:16 +0000
• 874f5947f4 Add half-Packet operations to StridedLinearBufferCopy. Pedro Gonnet 2023-05-01 16:09:31 +0000
• c9a14f48d9 SSE Packet4ui has pcmp, pmin, pmax Charles Schlosser 2023-04-28 20:36:08 +0000
• 0b51f763cb Revert "Geometry/EulerAngles: make sure that returned solution has canonical ranges" Rasmus Munk Larsen 2023-04-27 00:06:23 +0000
• 2d0c6ad873 Revert "Vectorize cast" Antonio Sánchez 2023-04-26 18:03:36 +0000
• 8999525c29 AVX2: Packet4ul has pmul, abs2 Charles Schlosser 2023-04-26 16:22:16 +0000
• eb5ff1861a Vectorize cast Charles Schlosser 2023-04-26 02:50:13 +0000
• 3918768be1 Fix sparse iterator and tests. Antonio Sánchez 2023-04-25 19:05:49 +0000
• 70410310a4 Fix boolean bitwise and warning. Antonio Sanchez 2023-04-25 15:24:49 +0000
• f6cf5dca80 Packet4ul does not have Abs2 Charles Schlosser 2023-04-21 19:48:01 +0000
• 03f646b7e3 New VSX version of BF16 GEMV (Power) - up to 6.7X faster Chip Kerchner 2023-04-21 17:06:59 +0000
• 29c8e3c754 fix pow for uint32_t, disable pmul<Packet4ul> Charles Schlosser 2023-04-21 05:47:56 +0000
• 7f06bcae2c Geometry/EulerAngles: make sure that returned solution has canonical ranges Juraj Oršulić 2023-04-19 19:12:24 +0000
• a347dbbab2 Delete last few occurences of HasHalfPacket. Rasmus Munk Larsen 2023-04-19 10:36:59 -0700
• b378014fef Make sure we return +/-1 above the clamping point for Erf(). Rasmus Munk Larsen 2023-04-18 13:27:47 -0700
• e2bbf496f6 Use select ternary op in tensor select evaulator Charles Schlosser 2023-04-18 20:52:16 +0000
• 2b954be663 fix typo in sse packetmath Charles Schlosser 2023-04-18 18:17:41 +0000
• 25685c90ad Fix incorrect packet type for unsigned int version of pfirst() in MSVC workaround in PacketMath.h. Rasmus Munk Larsen 2023-04-18 17:46:23 +0000
• 1e223a956c Add missing 'f' in float literal in SpecialFunctionsImpl.h that triggers implicit conversion warning. Rasmus Munk Larsen 2023-04-18 17:33:29 +0000
• 3f3ce214e6 New BF16 pcast functions and move type casting to TypeCasting.h Chip Kerchner 2023-04-18 02:38:38 +0000
• 17b5b4de58 Add Packet4ui, Packet8ui, and Packet4ul to the SSE/AVX PacketMath.h headers Pedro Gonnet 2023-04-17 23:33:59 +0000
• 87300c93ca Refactor IndexedView Charles Schlosser 2023-04-17 12:32:50 +0000
• 1148f0a9ec Add dynamic dispatch to BF16 GEMM (Power) and new VSX version Chip Kerchner 2023-04-14 22:20:42 +0000
• 3026fc0d3c Improve accuracy of erf(). Rasmus Munk Larsen 2023-04-14 16:57:56 +0000
• 554fe02ae3 Enable new AVX512 GEMM kernel by default. Rasmus Munk Larsen 2023-04-12 13:39:06 -0700
• 0d12fcc34e Insert from triplets Charles Schlosser 2023-04-12 20:01:48 +0000
• 990a282fc4 exclude Eigen/Core and Eigen/src/Core from being ignored due to core ignore rule Rob Conde 2023-04-12 10:36:08 -0400
• b0eded878d DOC: Update documentation for 3.4.x Rohit Goswami 2023-04-06 19:20:41 +0000
• b0f877f8e0 Don't crash on empty tensor contraction. Rasmus Munk Larsen 2023-04-05 17:06:14 +0000
• 15fbddaf9b ASAN fixes for AVX512 GEMM/TRSM b-shi 2023-03-31 12:58:07 -0700
• 178ef8c97f qualify non-const symbolic indexed view with is_lvalue Charles Schlosser 2023-04-04 19:06:32 +0000
• df1049ddf4 Small packet math cleanup. Rasmus Munk Larsen 2023-04-04 16:14:32 +0000
• 9b48d10215 Guard all malloc, realloc and free() fonctions with check_that_malloc_is_allowed() Antoine Hoarau 2023-04-04 04:24:22 +0000
• c730290fa0 Use the correct truncating intrinsic for double->int casting. Rasmus Munk Larsen 2023-04-03 13:56:41 -0700
• 766db02020 disable raw array indexed view access for 1d arrays Charles Schlosser 2023-03-29 02:39:45 +0000
• bfbc66e078 refactor indexedviewmethods, enable non-const ref access with symbolic indices Charles Schlosser 2023-03-29 01:35:26 +0000
• 1a5dfd7c0f Fix incorrect casting in AVX512DQ path. Rasmus Munk Larsen 2023-03-27 09:28:06 -0700
• a08649994f Optimize generic_rsqrt_newton_step Charles Schlosser 2023-03-24 22:42:57 +0000
• b8b8a26145 Add more missing vectorized casts for int on x86, and remove redundant unit tests Rasmus Munk Larsen 2023-03-24 16:02:00 +0000
• 33e206f714 Remove unused declarations of BLAS/LAPACK routines unageek 2023-03-23 21:54:05 +0000
• d57a79e512 Optimize float->bool cast for AVX2, based on Charles Schlosser's comments. Rasmus Munk Larsen 2023-03-21 20:59:25 -0700
• a5ae832773 Fix reversal of arguments to _mm256_set_m128() in pcast<Packet4d, Packet8f>. Rasmus Munk Larsen 2023-03-22 03:21:44 +0000
• 09945f2cc1 Optimize casting for x86_64. Rasmus Munk Larsen 2023-03-21 18:24:16 +0000
• 8f9b8e3630 Replaced all instances of internal::(U)IntPtr with std::(u)intptr_t. Remove ICC workaround. Colin Broderick 2023-03-21 16:50:23 +0000
• 2c8011c2dd Fix arm builds. Antonio Sánchez 2023-03-20 16:59:38 +0000
• fd8f410bbe Fix 2624 2625 Charles Schlosser 2023-03-20 16:30:04 +0000
• e887196d9d Undo cmake pools changes Chip Kerchner 2023-03-17 16:06:26 +0000
• 81cb6a51d0 Fix some typos Jonas Schulze 2023-03-16 23:11:43 +0000
• 555cec17ed Fix parsing of command-line arguments when already specified as a cmake list. Antonio Sánchez 2023-03-16 22:47:38 +0000
• 7db19baabe Remove pools if cmake is less than 3.11 Chip Kerchner 2023-03-16 16:54:45 +0000
• 0488b708b4 Vectorize tensor.isnan() by using typed predicates. Rasmus Munk Larsen 2023-03-16 04:04:22 +0000
• f02856c640 Use EIGEN_NOT_A_MACRO macro (oh the irony!) to avoid build issue in TensorFlow. Rasmus Munk Larsen 2023-03-15 11:42:57 -0700
• 690ae9502f Use C++11 standard features for detecting presence of Inf and NaN Rasmus Munk Larsen 2023-03-15 16:52:44 +0000
• d71ac6a755 Fix recent PowerPC warnings and clang warning Chip Kerchner 2023-03-15 16:50:46 +0000
• d54d228b49 Limit the number of build jobs to 8 and link jobs to 4 for PowerPC. This should help reduce the OOM build problems. Chip Kerchner 2023-03-15 16:29:41 +0000
• 23e1541863 Put deadcode checks back in from previous change. Chip Kerchner 2023-03-14 00:57:16 +0000
• 6c58f0fe1f Revert changes that made BF16 GEMM to cause bad register spillage for LLVM (Power) Chip Kerchner 2023-03-13 23:36:06 +0000
• 8fe6190001 Add numext::isnan for AnnoyingOrange^H^H^H^H^H^HScalar. Rasmus Munk Larsen 2023-03-13 21:19:35 +0000
• 79de101d23 Handle PropagateFast the same way as PropagateNaN in minmax visitor to Rasmus Munk Larsen 2023-03-13 20:47:11 +0000
• 9d72412385 Add MMA to BF16 GEMV - 5.0-6.3X faster (for Power) Chip Kerchner 2023-03-13 19:37:13 +0000
• 2067b54b13 Fix bug in minmax_coeff_visitor for matrix of all NaNs. Rasmus Munk Larsen 2023-03-13 18:25:22 +0000
• ee0ff0ab3a Fix typo in MathFunctions.h Rasmus Munk Larsen 2023-03-13 15:50:40 +0000
• 21c49e8f8e Delete mystery character from Eigen/src/Core/arch/NEON/MathFunctions.h Rasmus Munk Larsen 2023-03-10 23:27:24 +0000
• 6bb9609bcb Make new Select implementation backwards compatible. Rasmus Munk Larsen 2023-03-10 23:07:47 +0000
• 394aabb0a3 Fix failing MSVC tests due to compiler bugs. Antonio Sánchez 2023-03-10 22:36:57 +0000
• d6235d76db Clean up generic packetmath specializations for various backends with the help of a macro. Rasmus Munk Larsen 2023-03-10 22:02:23 +0000
• e8fdf127c6 Work around compiler bug in Tridiagonalization.h Rasmus Munk Larsen 2023-03-10 21:21:07 +0000
• adf26b6840 Add newline to end of file. Rasmus Munk Larsen 2023-03-10 16:53:22 +0000
• 3492d9e2e5 s/Lesser/Less/ Rasmus Munk Larsen 2023-03-10 00:28:31 +0000
• 2419632cf5 Revert change to allFinite(), since the new version does not work for complex numbers. Rasmus Munk Larsen 2023-03-09 21:50:43 +0000
• b1beba8a3e Fix LinAlgSVD example code Zach Davis 2023-03-08 17:04:59 +0000
• 7bf2968fed Specify Permutation Index for PartialPivLU and FullPivLU Charles Schlosser 2023-03-07 20:28:05 +0000
• eb4dbf6135 Modify failing cwise test to get it to pass. Antonio Sánchez 2023-03-07 19:47:42 +0000
• e577f43ab2 Set CMAKE_* cache variables only when Eigen is a top-level project Timofey Pushkin 2023-03-07 14:39:45 +0000
• 1ce8b25825 Vectorize any() / all() Charles Schlosser 2023-03-06 23:54:02 +0000
• cb8e6d4975 Fix 2240, 2620 Charles Schlosser 2023-03-06 23:11:06 +0000
• d670039309 fix tensor comparison test Charles Schlosser 2023-03-06 13:11:14 +0000
• 2b513ca2a0 Added partial linear access for LHS & Output - 30% faster for bfloat16 GEMM MMA (Power) Chip Kerchner 2023-03-02 19:22:43 +0000
• 0b396c3167 Scalarize comps Charles Schlosser 2023-03-02 17:06:23 +0000
• 3abe12472e fix signed shift test Charles Schlosser 2023-03-01 14:31:13 +0000
• ba7417f146 Fix gpu conv3d out-of-resources failure. Antonio Sánchez 2023-02-28 21:25:00 +0000
• 62d5cfe835 Fix ODR issues with Intel's AVX512 TRSM kernels. Antonio Sánchez 2023-02-27 07:54:52 +0000
• 826627f653 vectorize comparisons and select by enabling typed comparisons Charles Schlosser 2023-02-25 20:52:11 +0000