CFD/eigen
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
12,304 Commits 2 Branches 88 Tags 112 MiB
master
Commit Graph

7153 Commits

Author SHA1 Message Date
Pedro Gonnet
17b5b4de58 Add Packet4ui, Packet8ui, and Packet4ul to the SSE/AVX PacketMath.h headers 2023-04-17 23:33:59 +00:00
Charles Schlosser
87300c93ca Refactor IndexedView 2023-04-17 12:32:50 +00:00
Chip Kerchner
1148f0a9ec Add dynamic dispatch to BF16 GEMM (Power) and new VSX version 2023-04-14 22:20:42 +00:00
Rasmus Munk Larsen
554fe02ae3 Enable new AVX512 GEMM kernel by default. 2023-04-12 13:39:06 -07:00
Charles Schlosser
0d12fcc34e Insert from triplets 2023-04-12 20:01:48 +00:00
b-shi
15fbddaf9b ASAN fixes for AVX512 GEMM/TRSM 2023-04-04 15:54:24 -07:00
Charles Schlosser
178ef8c97f qualify non-const symbolic indexed view with is_lvalue 2023-04-04 19:06:32 +00:00
Rasmus Munk Larsen
df1049ddf4 Small packet math cleanup. 2023-04-04 16:14:32 +00:00
Antoine Hoarau
9b48d10215 Guard all malloc, realloc and free() fonctions with check_that_malloc_is_allowed() 2023-04-04 04:24:22 +00:00
Rasmus Munk Larsen
c730290fa0 Use the correct truncating intrinsic for double->int casting. 2023-04-03 13:56:41 -07:00
Charles Schlosser
766db02020 disable raw array indexed view access for 1d arrays 2023-03-29 02:39:45 +00:00
Charles Schlosser
bfbc66e078 refactor indexedviewmethods, enable non-const ref access with symbolic indices 2023-03-29 01:35:26 +00:00
Rasmus Munk Larsen
1a5dfd7c0f Fix incorrect casting in AVX512DQ path. 2023-03-27 09:28:06 -07:00
Charles Schlosser
a08649994f Optimize generic_rsqrt_newton_step 2023-03-24 22:42:57 +00:00
Rasmus Munk Larsen
b8b8a26145 Add more missing vectorized casts for int on x86, and remove redundant unit tests 2023-03-24 16:02:00 +00:00
unageek
33e206f714 Remove unused declarations of BLAS/LAPACK routines 2023-03-23 21:54:05 +00:00
Rasmus Munk Larsen
d57a79e512 Optimize float->bool cast for AVX2, based on Charles Schlosser's comments. 2023-03-21 20:59:25 -07:00
Rasmus Munk Larsen
a5ae832773 Fix reversal of arguments to _mm256_set_m128() in pcast<Packet4d, Packet8f>. 2023-03-22 03:21:44 +00:00
Rasmus Munk Larsen
09945f2cc1 Optimize casting for x86_64. 2023-03-21 18:24:16 +00:00
Colin Broderick
8f9b8e3630 Replaced all instances of internal::(U)IntPtr with std::(u)intptr_t. Remove ICC workaround. 2023-03-21 16:50:23 +00:00
Antonio Sánchez
2c8011c2dd Fix arm builds. 2023-03-20 16:59:38 +00:00
Charles Schlosser
fd8f410bbe Fix 2624 2625 2023-03-20 16:30:04 +00:00
Jonas Schulze
81cb6a51d0 Fix some typos 2023-03-16 23:11:43 +00:00
Rasmus Munk Larsen
0488b708b4 Vectorize tensor.isnan() by using typed predicates. 2023-03-16 04:04:22 +00:00
Rasmus Munk Larsen
f02856c640 Use EIGEN_NOT_A_MACRO macro (oh the irony!) to avoid build issue in TensorFlow. 2023-03-15 11:42:57 -07:00
Rasmus Munk Larsen
690ae9502f Use C++11 standard features for detecting presence of Inf and NaN 2023-03-15 16:52:44 +00:00
Chip Kerchner
d71ac6a755 Fix recent PowerPC warnings and clang warning 2023-03-15 16:50:46 +00:00
Chip Kerchner
23e1541863 Put deadcode checks back in from previous change. 2023-03-14 00:57:16 +00:00
Chip Kerchner
6c58f0fe1f Revert changes that made BF16 GEMM to cause bad register spillage for LLVM (Power) 2023-03-13 23:36:06 +00:00
Rasmus Munk Larsen
79de101d23 Handle PropagateFast the same way as PropagateNaN in minmax visitor to 2023-03-13 20:47:11 +00:00
Chip Kerchner
9d72412385 Add MMA to BF16 GEMV - 5.0-6.3X faster (for Power) 2023-03-13 19:37:13 +00:00
Rasmus Munk Larsen
2067b54b13 Fix bug in minmax_coeff_visitor for matrix of all NaNs. 2023-03-13 18:25:22 +00:00
Rasmus Munk Larsen
ee0ff0ab3a Fix typo in MathFunctions.h 2023-03-13 15:50:40 +00:00
Rasmus Munk Larsen
21c49e8f8e Delete mystery character from Eigen/src/Core/arch/NEON/MathFunctions.h 2023-03-10 23:27:24 +00:00
Rasmus Munk Larsen
6bb9609bcb Make new Select implementation backwards compatible. 2023-03-10 23:07:47 +00:00
Antonio Sánchez
394aabb0a3 Fix failing MSVC tests due to compiler bugs. 2023-03-10 22:36:57 +00:00
Rasmus Munk Larsen
d6235d76db Clean up generic packetmath specializations for various backends with the help of a macro. 2023-03-10 22:02:23 +00:00
Rasmus Munk Larsen
e8fdf127c6 Work around compiler bug in Tridiagonalization.h 2023-03-10 21:21:07 +00:00
Rasmus Munk Larsen
adf26b6840 Add newline to end of file. 2023-03-10 16:53:22 +00:00
Rasmus Munk Larsen
3492d9e2e5 s/Lesser/Less/ 2023-03-10 00:28:31 +00:00
Rasmus Munk Larsen
2419632cf5 Revert change to allFinite(), since the new version does not work for complex numbers. 2023-03-09 21:50:43 +00:00
Charles Schlosser
7bf2968fed Specify Permutation Index for PartialPivLU and FullPivLU 2023-03-07 20:28:05 +00:00
Charles Schlosser
1ce8b25825 Vectorize any() / all() 2023-03-06 23:54:02 +00:00
Charles Schlosser
cb8e6d4975 Fix 2240, 2620 2023-03-06 23:11:06 +00:00
Chip Kerchner
2b513ca2a0 Added partial linear access for LHS & Output - 30% faster for bfloat16 GEMM MMA (Power) 2023-03-02 19:22:43 +00:00
Charles Schlosser
0b396c3167 Scalarize comps 2023-03-02 17:06:23 +00:00
Antonio Sánchez
62d5cfe835 Fix ODR issues with Intel's AVX512 TRSM kernels. 2023-02-27 07:54:52 +00:00
Charles Schlosser
826627f653 vectorize comparisons and select by enabling typed comparisons 2023-02-25 20:52:11 +00:00
Rasmus Munk Larsen
2e9b945baf Fix bug that disabled vectorization for coeffMin/coeffMax. 2023-02-25 20:03:54 +00:00
Antonio Sánchez
bc5cdc7a67 Guard use of long double on GPU device. 2023-02-24 21:49:59 +00:00
Chip Kerchner
e4598fedbe Fix compiler versions for certain instructions on Power. 2023-02-23 23:24:41 +00:00
Rasmus Munk Larsen
1c0a6cf228 Get rid of EIGEN_HAS_AVX512_MATH workaround. 2023-02-23 23:16:41 +00:00
Rasmus Munk Larsen
6bcd941ee3 Use pmsub in twoprod. This speeds up pow() on Skylake by ~1%. 2023-02-21 20:09:29 +00:00
Rasmus Munk Larsen
ce62177b5b Vectorize atanh & add a missing definition and unit test for atan. 2023-02-21 03:14:05 +00:00
Charles Schlosser
049a144798 Add typed logicals 2023-02-18 01:23:47 +00:00
Chip Kerchner
e797974689 Add and enable Packet int divide for Power10. 2023-02-17 19:04:18 +00:00
Chip Kerchner
54459214a1 Fix epsilon and dummy_precision values in long double for double doubles. Prevented some algorithms from converging on PPC. 2023-02-16 23:35:42 +00:00
Antonio Sánchez
a16fb889dd Guard complex sqrt on old MSVC compilers. 2023-02-16 19:47:00 +00:00
Charles Schlosser
94b19dc5f2 Add CArg 2023-02-15 21:33:06 +00:00
Charles Schlosser
71a8e60a7a Tweak pasin_float, fix psqrt_complex 2023-02-15 01:01:14 +00:00
Antonio Sánchez
384269937f More NEON packetmath fixes. 2023-02-14 21:45:25 +00:00
Antonio Sánchez
2dfbf1b251 Fix NEON make_packet2f. 2023-02-14 16:52:07 +00:00
Chip Kerchner
4a03409569 Fix problem with array conversions BF16->F32 in Power. 2023-02-13 21:30:45 +00:00
Rasmus Munk Larsen
77b48c440e Fix compiler warnings. 2023-02-10 20:46:23 +00:00
Chip Kerchner
0ecae61568 Disable array BF16 to F32 conversions in Power 2023-02-10 20:06:58 +00:00
Charles Schlosser
c999284bad Print diagonal matrix 2023-02-10 18:07:29 +00:00
Chip Kerchner
fba12e02b3 Fold extra column calculations into an extra MMA accumulator and other bfloat16 MMA GEMM improvements 2023-02-10 17:32:06 +00:00
Chip Kerchner
79cfc74f4d Revert ODR changes and make gemm_extra_cols and gemm_complex_extra_cols EIGEN_ALWAYS_INLINE to avoid external functions. 2023-02-10 17:05:07 +00:00
Alexander Grund
f9659d91f1 Fix ODR violation with gemm_extra_cols on PPC 2023-02-09 22:16:06 +00:00
Charles Schlosser
325e3063d9 Optimize psign 2023-02-09 22:15:26 +00:00
Charles Schlosser
0e490d452d Update file ColPivHouseholderQR_LAPACKE.h 2023-02-09 13:45:56 +00:00
Antonio Sánchez
0a5392d606 Fix MSVC arm build. 2023-02-08 21:46:37 +00:00
Antonio Sánchez
3f7e775715 Add IWYU export pragmas to top-level headers. 2023-02-08 17:40:31 +00:00
Rasmus Munk Larsen
e4f58816d9 Get rid of custom implementation of equal_to and not_equal_no. No longer needed with c+14. 2023-02-07 21:36:44 -08:00
Antonio Sánchez
e256ad1823 Remove LGPL Code and references. 2023-02-08 01:25:06 +00:00
Chip Kerchner
e71f88abce Change in Power eigen_asserts to eigen_internal_asserts since it is putting unnecessary error checking and assertions without NDEBUG. 2023-02-08 00:57:30 +00:00
Gregory Kramida
232b18fa8a Fixes #2602 2023-02-06 22:52:39 +00:00
Antonio Sánchez
f6cc359e10 More EIGEN_DEVICE_FUNC fixes for CUDA 10/11/12. 2023-02-03 19:18:45 +00:00
Charles Schlosser
2a90653395 fix lapacke config 2023-02-03 16:40:08 +00:00
Jeremy Nimmer
13a1f25da9 Revert StlIterators edit from "Fix undefined behavior..." 2023-02-01 20:01:36 +00:00
Charles Schlosser
fd2fd48703 Update file ForwardDeclarations.h 2023-02-01 16:52:20 +00:00
Rasmus Munk Larsen
37b2e97175 Tweak special case handling in atan2. 2023-01-31 17:48:00 -08:00
Jeremy Nimmer
a1cdcdb038 Fix undefined behavior in Block access 2023-02-01 00:40:45 +00:00
Chip Kerchner
4a58f30aa0 Fix pre-POWER8_VECTOR bugs in pcmp_lt and pnegate and reactivate psqrt. 2023-01-31 19:40:24 +00:00
Rasmus Munk Larsen
12ad99ce60 Remove unused variables from GenericPacketMathFunctions.h 2023-01-29 18:10:28 +00:00
Charles Schlosser
6987a200bb Fix stupid sparse bugs with outerSize == 0 2023-01-28 02:03:09 +00:00
Charles Schlosser
0471e61b4c Optimize various mathematical packet ops 2023-01-28 01:34:26 +00:00
Charles Schlosser
1aa6dc2007 Fix sparse warnings 2023-01-27 22:47:42 +00:00
Antonio Sánchez
17ae83a966 Fix bugs exposed by enabling GPU asserts. 2023-01-27 21:43:00 +00:00
Chip Kerchner
ab8725d947 Turn off vectorize version of rsqrt - doesn't match generic version 2023-01-27 18:28:54 +00:00
Charles Schlosser
6d9f662a70 Tweak atan2 2023-01-26 17:38:21 +00:00
Chip Kerchner
6fc9de7d93 Fix slowdown in bfloat16 MMA when rows is not a multiple of 8 or columns is not a multiple of 4. 2023-01-25 18:22:20 +00:00
Charles Schlosser
7f58bc98b1 Refactor sparse 2023-01-23 17:55:50 +00:00
Rasmus Munk Larsen
576448572f More fixes for __GNUC_PATCHLEVEL__. 2023-01-23 17:04:24 +00:00
Rasmus Munk Larsen
164ddf75ab Use __GNUC_PATCHLEVEL__ rather than __GNUC_PATCH__, according to the documentation https://gcc.gnu.org/onlinedocs/cpp/Common-Predefined-Macros.html 2023-01-23 16:56:14 +00:00
Charles Schlosser
5a7ca681d5 Fix sparse insert 2023-01-20 21:32:32 +00:00
Antonio Sánchez
08c961e837 Add custom ODR-safe assert. 2023-01-20 17:38:13 +00:00
Sean McBride
d70b4864d9 issue #2581: review and cleanup of compiler version checks 2023-01-17 18:58:34 +00:00
Mehdi Goli
b523120687 [SYCL-2020 Support] Enabling Intel DPCPP Compiler support to Eigen 2023-01-16 07:04:08 +00:00
tttapa
bae119bb7e Support per-thread is_malloc_allowed() state 2023-01-16 01:34:56 +00:00
Charles Schlosser
fa0bd2c34e improve sparse permutations 2023-01-15 03:21:25 +00:00
Antonio Sánchez
2e61c0c6b4 Add missing EIGEN_DEVICE_FUNC in a few places when called by asserts. 2023-01-15 02:06:17 +00:00
Charles Schlosser
4aca06f63a avoid move assignment in ColPivHouseholderQR 2023-01-15 01:34:10 +00:00
Charles Schlosser
68082b8226 Fix QR, again 2023-01-13 03:23:17 +00:00
Sergey Fedorov
4d05765345 Altivec fixes for Darwin: do not use unsupported VSX insns 2023-01-12 16:33:33 +00:00
Rasmus Munk Larsen
6156797016 Revert "Add template to specify QR permutation index type, Fix ColPivHouseholderQR Lapacke bindings" 
This reverts commit be7791e097
 2023-01-11 18:50:52 +00:00
Charles Schlosser
be7791e097 Add template to specify QR permutation index type, Fix ColPivHouseholderQR Lapacke bindings 2023-01-11 15:57:28 +00:00
Charles Schlosser
9463fc95f4 change insert strategy 2023-01-11 06:24:49 +00:00
Martin Burchell
c54785b071 Fix error: unused parameter 'tmp' [-Werror,-Wunused-parameter] on clang/32-bit arm 2023-01-10 21:15:28 +00:00
Charles Schlosser
81172cbdcb Overhaul Sparse Core 2023-01-07 22:09:42 +00:00
Chip Kerchner
d20fe21ae4 Improve performance for Power10 MMA bfloat16 GEMM 2023-01-06 23:08:37 +00:00
Ryan Senanayake
fe7f527787 Fix guard macros for emulated FP16 operators on GPU 2023-01-06 22:02:51 +00:00
Antonio Sánchez
262194f12c Fix a bunch of minor build and test issues. 2023-01-06 16:37:26 +00:00
Antonio Sánchez
3564668908 Fix overalign check. 2023-01-05 17:10:48 +00:00
Charles Schlosser
f3929ac7ed Fix EIGEN_HAS_CXX17_OVERALIGN for icc 2023-01-03 17:30:10 +00:00
Charles Schlosser
a8bab0d8ae Patch SparseLU 2022-12-31 04:52:36 +00:00
Arthur
311cc0f9cc Enable NEON pcmp, plset, and complex psqrt 2022-12-22 05:38:34 +00:00
Antonio Sánchez
dbf7ae6f9b Fix up C++ version detection macros and cmake tests. 2022-12-20 18:06:03 +00:00
Antonio Sánchez
bb6675caf7 Fix incorrect NEON native fp16 multiplication. 2022-12-19 20:46:44 +00:00
Rasmus Munk Larsen
dd85d26946 Revert "Avoid mixing types in CompressedStorage.h" 2022-12-19 20:09:37 +00:00
Arthur Feeney
c4fb6af24b Enable NEON pabs for unsigned int types 2022-12-19 17:07:36 +00:00
Rasmus Munk Larsen
04e4f0bb24 Add missing colon in SparseMatrix.h. 2022-12-16 21:50:00 +00:00
Rasmus Munk Larsen
3d8a8def8a Avoid mixing types in CompressedStorage.h 2022-12-16 20:11:02 +00:00
Charles Schlosser
4bb2446796 Add operators to CompressedStorageIterator 2022-12-16 16:48:50 +00:00
Alexander Richardson
37de432907 Avoid using std::raise() for divide by zero 2022-12-14 20:06:16 +00:00
Alexander Richardson
62de593c40 Allow std::initializer_list constructors in constexpr expressions 2022-12-14 17:05:37 +00:00
Charles Schlosser
6d3e3678b4 optimize equalspace packetop 2022-12-13 01:22:25 +00:00
Charles Schlosser
2004831941 add EqualSpaced / setEqualSpaced 2022-12-13 00:54:57 +00:00
Melven Roehrig-Zoellner
273f803846 Add BDCSVD_LAPACKE binding 2022-12-09 18:50:12 +00:00
Antonio Sánchez
03c9b4738c Enable direct access for NestByValue. 2022-12-07 18:21:45 +00:00
Chip Kerchner
b59f18b4f7 Increase L2 and L3 cache size for Power10. 2022-12-07 18:20:33 +00:00
Charles Schlosser
44fe539150 add sparse sort inner vectors function 2022-12-01 19:28:56 +00:00
Lianhuang Li
d194167149 Fix the bug using neon instruction fmla for data type half 2022-12-01 17:28:57 +00:00
Pedro Caldeira
31ab62d347 Add support for Power10 (AltiVec) MMA instructions for bfloat16. 2022-11-30 23:33:37 +00:00
Antonio Sánchez
dcb042a87d Fix serialization for non-compressed matrices. 2022-11-30 18:16:47 +00:00
Antonio Sánchez
2260e11eb0 Fix reshape strides when input has non-zero inner stride. 2022-11-29 19:39:29 +00:00
Alexandre Hoffmann
23524ab6fc Changing BiCGSTAB parameters initialization so that it works with custom types 2022-11-29 19:37:46 +00:00
Antonio Sánchez
ab2b26fbc2 Fix sparseLU solver when destination has a non-unit stride. 2022-11-29 19:37:03 +00:00
Antonio Sánchez
e7b1ad0315 Add serialization for sparse matrix and sparse vector. 2022-11-21 19:43:07 +00:00
Charles Schlosser
044f3f6234 Fix bug in handmade_aligned_realloc 2022-11-18 22:35:31 +00:00
Charles Schlosser
02805bd56c Fix AVX2 psignbit 2022-11-16 13:43:11 +00:00
Chip Kerchner
399ce1ed63 Fix duplicate execution code for Power 8 Altivec in pstore_partial. 2022-11-16 13:41:42 +00:00
Gabriele Buondonno
6431dfdb50 Cross product for vectors of size 2. Fixes #1037 2022-11-15 22:39:42 +00:00
Antonio Sánchez
8588d8c74b Correct pnegate for floating-point zero. 2022-11-15 18:07:23 +00:00
Antonio Sanchez
5eacb9e117 Put brackets around unsigned type names. 2022-11-15 09:09:45 -08:00
Antonio Sánchez
37e40dca85 Fix ambiguity in PPC for vec_splats call. 2022-11-14 18:58:16 +00:00
Antonio Sánchez
7dc6db75d4 Fix typo in CholmodSupport 2022-11-08 23:49:56 +00:00
Charles Schlosser
9b6d624eab fix neon 2022-11-08 20:03:01 +00:00
Rasmus Munk Larsen
7e398e9436 Add missing return keyword in psignbit for NEON. 2022-11-04 16:13:09 +00:00
Charles Schlosser
82b152dbe7 Add signbit function 2022-11-04 00:31:20 +00:00