eigen

devtools/eigen

Fork 0

mirror of https://gitlab.com/libeigen/eigen.git synced 2026-04-10 11:34:33 +08:00

Commit Graph

Select branches

Hide Pull Requests

2.0

3.0

3.1

3.2

3.3

3.4

5.0

gpu-cg-interop

gpu-dense-solvers

gpu-library-dispatch

gpu-modernize-minimum-versions

gpu-sparse-fft-spmv

master

revert-b1d2ce4c

selfadjoint-eigensolver-audit

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

3.4.0-rc1

3.4.1

5.0.0

5.0.1

actual-start-from-scratch

after-hg-migration

before-3.4

before-evaluators

before-git-migration

before-hg-migration

nightly

starting_new_generickernels

starting_new_packmapcalculator

6156797016 Revert "Add template to specify QR permutation index type, Fix ColPivHouseholderQR Lapacke bindings" Rasmus Munk Larsen 2023-01-11 18:50:52 +00:00
be7791e097 Add template to specify QR permutation index type, Fix ColPivHouseholderQR Lapacke bindings Charles Schlosser 2023-01-11 15:57:28 +00:00
9463fc95f4 change insert strategy Charles Schlosser 2023-01-11 06:24:49 +00:00
c54785b071 Fix error: unused parameter 'tmp' [-Werror,-Wunused-parameter] on clang/32-bit arm Martin Burchell 2023-01-10 21:15:28 +00:00
f47472603b Add missing header for GPU tests. Antonio Sanchez 2023-01-09 11:21:13 -08:00
81172cbdcb Overhaul Sparse Core Charles Schlosser 2023-01-07 22:09:42 +00:00
9255181891 Modified spbenchsolver help message because it could be misunderstood Robin Miquel 2023-01-07 21:35:46 +00:00
d20fe21ae4 Improve performance for Power10 MMA bfloat16 GEMM Chip Kerchner 2023-01-06 23:08:37 +00:00
fe7f527787 Fix guard macros for emulated FP16 operators on GPU Ryan Senanayake 2023-01-06 22:02:51 +00:00
b8422c99cd Update file jacobisvd.cpp Rasmus Munk Larsen 2023-01-06 21:14:17 +00:00
262194f12c Fix a bunch of minor build and test issues. Antonio Sánchez 2023-01-06 16:37:26 +00:00
3564668908 Fix overalign check. Antonio Sánchez 2023-01-05 17:10:48 +00:00
f3929ac7ed Fix EIGEN_HAS_CXX17_OVERALIGN for icc Charles Schlosser 2023-01-03 17:30:10 +00:00
1b33a6374b Fixes git add . doesn't include scripts/buildtests.in LAI Bruce 2023-01-03 17:06:36 +00:00
a8bab0d8ae Patch SparseLU Charles Schlosser 2022-12-31 04:52:36 +00:00
910f6f65d0 Adjust thresholds for bfloat16 product tests that are currently failing. Antonio Sánchez 2022-12-28 19:32:25 +00:00
311cc0f9cc Enable NEON pcmp, plset, and complex psqrt Arthur 2022-12-22 05:38:34 +00:00
dbf7ae6f9b Fix up C++ version detection macros and cmake tests. Antonio Sánchez 2022-12-20 18:06:03 +00:00
bb6675caf7 Fix incorrect NEON native fp16 multiplication. Antonio Sánchez 2022-12-19 20:46:44 +00:00
dd85d26946 Revert "Avoid mixing types in CompressedStorage.h" Rasmus Munk Larsen 2022-12-19 20:09:37 +00:00
c4fb6af24b Enable NEON pabs for unsigned int types Arthur Feeney 2022-12-18 18:30:02 -08:00
400bc5cd5b Add sparse_basic_1 to smoke tests. Rasmus Munk Larsen 2022-12-16 22:03:33 +00:00
04e4f0bb24 Add missing colon in SparseMatrix.h. Rasmus Munk Larsen 2022-12-16 21:50:00 +00:00
3d8a8def8a Avoid mixing types in CompressedStorage.h Rasmus Munk Larsen 2022-12-16 20:11:02 +00:00
4bb2446796 Add operators to CompressedStorageIterator Charles Schlosser 2022-12-16 16:48:50 +00:00
e1aee4ab39 Update test of numext::signbit. Rasmus Munk Larsen 2022-12-15 11:39:32 -08:00
3717854a21 Use numext::signbit instead of std::signbit, which is not defined for bfloat16. Rasmus Munk Larsen 2022-12-15 18:41:46 +00:00
37de432907 Avoid using std::raise() for divide by zero Alexander Richardson 2022-12-14 20:06:16 +00:00
62de593c40 Allow std::initializer_list constructors in constexpr expressions Alexander Richardson 2022-12-14 17:05:37 +00:00
6d3e3678b4 optimize equalspace packetop Charles Schlosser 2022-12-13 01:22:25 +00:00
2004831941 add EqualSpaced / setEqualSpaced Charles Schlosser 2022-12-13 00:54:57 +00:00
273f803846 Add BDCSVD_LAPACKE binding Melven Roehrig-Zoellner 2022-12-09 18:50:12 +00:00
03c9b4738c Enable direct access for NestByValue. Antonio Sánchez 2022-12-07 18:21:45 +00:00
b59f18b4f7 Increase L2 and L3 cache size for Power10. Chip Kerchner 2022-12-07 18:20:33 +00:00
c614b2bbd3 Fix index type for sparse index sorting. Antonio Sánchez 2022-12-06 00:02:31 +00:00
44fe539150 add sparse sort inner vectors function Charles Schlosser 2022-12-01 19:28:56 +00:00
d194167149 Fix the bug using neon instruction fmla for data type half Lianhuang Li 2022-12-01 17:28:57 +00:00
31ab62d347 Add support for Power10 (AltiVec) MMA instructions for bfloat16. Pedro Caldeira 2022-11-30 23:33:37 +00:00
dcb042a87d Fix serialization for non-compressed matrices. Antonio Sánchez 2022-11-30 18:16:47 +00:00
2260e11eb0 Fix reshape strides when input has non-zero inner stride. Antonio Sánchez 2022-11-29 19:39:29 +00:00
23524ab6fc Changing BiCGSTAB parameters initialization so that it works with custom types Alexandre Hoffmann 2022-11-29 19:37:46 +00:00
ab2b26fbc2 Fix sparseLU solver when destination has a non-unit stride. Antonio Sánchez 2022-11-29 19:37:03 +00:00
551eebc8ca Add synchronize method to all devices. Antonio Sánchez 2022-11-29 19:35:02 +00:00
b7551bff92 Fix a bunch of annoying compiler warnings in tests Charles Schlosser 2022-11-21 20:07:19 +00:00
e7b1ad0315 Add serialization for sparse matrix and sparse vector. Antonio Sánchez 2022-11-21 19:43:07 +00:00
044f3f6234 Fix bug in handmade_aligned_realloc Charles Schlosser 2022-11-18 22:35:31 +00:00
6728683938 Small cleanup of IDRS.h Chris 2022-11-16 13:51:23 +00:00
02805bd56c Fix AVX2 psignbit Charles Schlosser 2022-11-16 13:43:11 +00:00
399ce1ed63 Fix duplicate execution code for Power 8 Altivec in pstore_partial. Chip Kerchner 2022-11-16 13:41:42 +00:00
6431dfdb50 Cross product for vectors of size 2. Fixes #1037 Gabriele Buondonno 2022-11-15 22:39:42 +00:00
8588d8c74b Correct pnegate for floating-point zero. Antonio Sánchez 2022-11-15 18:07:23 +00:00
5eacb9e117 Put brackets around unsigned type names. Antonio Sanchez 2022-11-15 09:09:08 -08:00
37e40dca85 Fix ambiguity in PPC for vec_splats call. Antonio Sánchez 2022-11-14 18:58:16 +00:00
7dc6db75d4 Fix typo in CholmodSupport Antonio Sánchez 2022-11-08 23:49:56 +00:00
9b6d624eab fix neon Charles Schlosser 2022-11-08 20:03:01 +00:00
7e398e9436 Add missing return keyword in psignbit for NEON. Rasmus Munk Larsen 2022-11-04 16:13:09 +00:00
82b152dbe7 Add signbit function Charles Schlosser 2022-11-04 00:31:20 +00:00
8f8e36458f Remove recently added sparse assert in SparseMapBase. Antonio Sánchez 2022-11-03 17:29:05 +00:00
01a31b81b2 Remove unused parameter name. Antonio Sanchez 2022-11-01 15:51:25 -07:00
c5b896c5a3 Allow empty matrices to be resized. Antonio Sánchez 2022-10-27 20:33:35 +00:00
886aad1361 Disable patan for double on PPC. Antonio Sánchez 2022-10-27 17:56:08 +00:00
ab407b2b6e Fix handmade_aligned_malloc offset computation. Antonio Sánchez 2022-10-27 17:33:47 +00:00
adb30efb25 Add assert for invalid outerIndexPtr array in SparseMapBase. Antonio Sánchez 2022-10-26 22:51:33 +00:00
c27d1abe46 Fix pragma check for disabling fastmath. Antonio Sánchez 2022-10-26 22:50:57 +00:00
a226371371 Change handmade_aligned_malloc/realloc/free to store a 1 byte offset instead of absolute address Charles Schlosser 2022-10-22 22:51:31 +00:00
bf48d46338 Explicitly state that indices must be sorted. Antonio Sánchez 2022-10-19 18:15:29 +00:00
3bb6a48d8c Fix bug atan2 Rasmus Munk Larsen 2022-10-12 23:49:32 +00:00
14c847dc0e Refactor special values test for pow, and add a similar test for atan2 Rasmus Munk Larsen 2022-10-12 20:12:08 +00:00
462758e8a3 Don't use generic sign function for sign(complex) unless it is vectorizable Rasmus Munk Larsen 2022-10-12 16:03:29 +00:00
c0d6a72611 Use pnegate(pzero(x)) as a generic way to generate -0.0. Some compiler do not handle the literal -0.0 properly in fastmath mode. Rasmus Munk Larsen 2022-10-12 01:57:05 +00:00
7846c7387c Eigen/Sparse: fix warnings -Wunused-but-set-variable Laurent Rineau 2022-10-11 17:37:04 +00:00
3167544873 Handle NaN inputs to atan2. Rasmus Munk Larsen 2022-10-10 19:36:36 -07:00
72db3f0fa5 Remove references to M_PI_2 and M_PI_4. Rasmus Munk Larsen 2022-10-11 00:27:16 +00:00
d6bc062591 Remove reference to EIGEN_HAS_CXX11_MATH. Rasmus Munk Larsen 2022-10-10 23:38:28 +00:00
5ceed0d57f Guard GCC-specific pragmas with "#ifdef EIGEN_COMP_GNUC" Rasmus Munk Larsen 2022-10-10 20:38:53 +00:00
528b68674c [clang-format] Add a few macros to AttributeMacros Alexander Richardson 2022-10-10 16:44:47 +00:00
e95c4a837f Simpler range reduction strategy for atan<float>(). Rasmus Munk Larsen 2022-10-04 18:11:00 +00:00
80efbfdeda Unconditionally enable CXX11 math. Antonio Sánchez 2022-10-04 17:37:47 +00:00
e5794873cb Replace assert with eigen_assert. Antonio Sánchez 2022-10-04 17:11:23 +00:00
7d6a9925cc Fix 4x4 inverse when compiling with -Ofast. Antonio Sánchez 2022-10-04 16:05:49 +00:00
1414a76fa9 Only vectorize atan<double> for Altivec if VSX is available. Rasmus Munk Larsen 2022-10-03 22:06:58 +00:00
c475228b28 Vectorize atan() for double. Rasmus Munk Larsen 2022-10-01 01:49:30 +00:00
1e1848fdb1 Add a vectorized implementation of atan2 to Eigen. Rasmus Munk Larsen 2022-09-28 20:46:49 +00:00
b3bf8d6a13 Try to reduce size of GEBP kernel for non-ARM targets. Rasmus Munk Larsen 2022-09-28 02:37:18 +00:00
13b69fc1b0 Try to reduce compilation time/memory for GEBP kernel using EIGEN_IF_CONSTEXPR Rasmus Munk Larsen 2022-09-23 20:09:42 +00:00
3c4637640b Remove unused typedef. Rasmus Munk Larsen 2022-09-23 19:11:31 +00:00
ed8cda3ce4 Move EIGEN_NEON_GEBP_NR macro to the right place in GeneralBlockPanelKernel.h Rasmus Munk Larsen 2022-09-23 02:24:27 +00:00
e2ea866515 Add a macro to set the nr trait in the BEBP kernel for NEON. Rasmus Munk Larsen 2022-09-22 23:56:34 +00:00
23299632c2 Use 3px8/2px8/1px8/1x8 gebp_kernel on arm64-neon Lianhuang Li 2022-09-21 16:36:40 +00:00
7b2901e2aa Add vectorized integer division for int32 with AVX512, AVX or SSE. Rasmus Munk Larsen 2022-09-21 00:27:23 +00:00
5ffe7b92e0 [ROCm] fixed gpuGetDevice unused message Chao Chen 2022-09-20 21:38:20 +00:00
f913a40678 Revert "Add AVX int32_t pdiv" Rasmus Munk Larsen 2022-09-16 22:48:08 +00:00
273e0c884e Revert "Add constexpr, test for C++14 constexpr." Rasmus Munk Larsen 2022-09-16 21:14:29 +00:00
ea84e7ad63 Add AVX int32_t pdiv Charles Schlosser 2022-09-16 17:06:29 +00:00
dceb779ecd Fix test for pow with mixed integer types. We do not convert the exponent if it is an integer type. Rasmus Munk Larsen 2022-09-12 15:51:27 -07:00
afc014f1b5 Allow mixed types for pow(), as long as the exponent is exactly representable in the base type. Rasmus Munk Larsen 2022-09-12 21:55:30 +00:00
b2c82a9347 Remove bad skew_symmetric_matrix3 test. Antonio Sánchez 2022-09-10 07:08:37 +00:00
e8a2aa24a2 Fix a couple of issues with unary pow(): Rasmus Munk Larsen 2022-09-09 17:21:11 +00:00
07d0759951 [ROCm] Fix for sparse matrix related breakage on ROCm. Rohit Santhanam 2022-09-09 14:41:00 +00:00
fb212c745d Fix g++-6 constexpr and c++20 constexpr build errors. Antonio Sánchez 2022-09-09 03:41:45 +00:00

... 13 14 15 16 17 ...