12436 Commits

Author SHA1 Message Date
Rasmus Munk Larsen
3cf6bb6f1c Fix a bug in commit 76e8c0455396446f8166c798da5efe879e010bdc: 2023-11-15 21:45:37 +00:00
Charles Schlosser
32165c6f0c Fix Wshorten-64-to-32 warning in gemm parallelizer 2023-11-14 13:51:27 +00:00
Rasmus Munk Larsen
b33dbb5765 Fix implicit narrowing warning in Parallelizer.h. 2023-11-13 21:30:39 +00:00
Antonio Sanchez
3a9635b20c Link pthread for product_threaded test 2023-11-13 11:34:23 -08:00
wk
f78c37f0af traits<Ref>::match: use correct strides 2023-11-11 14:10:56 +00:00
Rasmus Munk Larsen
516d08a490 Fix typo in Parallelizer.h 2023-11-10 20:29:29 +00:00
Rasmus Munk Larsen
76e8c04553 Generalize parallel GEMM implementation in Core to work with ThreadPool in addition to OpenMP. 2023-11-10 17:42:30 +00:00
Antonio Sánchez
4d54c43d6c Fix typo to allow nomalloc test to pass on AVX512. 2023-11-06 18:58:43 +00:00
Antonio Sánchez
a25f02d73e Fix int overflow causing cxx11_tensor_gpu_1 to fail. 2023-11-06 17:10:16 +00:00
Charles Schlosser
6f9ad7da61 fix Wshorten-64-to-32 warnings in div_ceil 2023-10-27 15:52:00 +00:00
Charles Schlosser
1aac9332ce TensorReduction: replace divup with div_ceil 2023-10-25 16:44:34 +00:00
Kyle Macfarlan
5de0f2f89e Fixes #2735: Component-wise cbrt 2023-10-25 03:06:13 +00:00
Antonio Sánchez
48b254a4bc Disable denorm deprecation warnings in MSVC C++23. 2023-10-23 17:56:04 +00:00
Antonio Sánchez
176821f2f7 Avoid building docs if cross-compiling or not top level. 2023-10-23 17:55:01 +00:00
Antonio Sánchez
aa6964bf3a Work around MSVC issue in Block XprType. 2023-10-19 22:02:03 +00:00
Anatoly Borisov
877c2d1e9b fix typo in comment 2023-10-18 12:58:49 +00:00
Antonio Sánchez
0c9526912c Pass div_ceil arguments by value. 2023-10-17 18:46:19 +00:00
Ioannis Assiouras
d9839718aa [ROCm] Replace HIP_PATH with ROCM_PATH for rocm 6.0 2023-10-16 20:56:35 +00:00
Antonio Sánchez
5bdf58b8df Eliminate use of _res. 2023-10-16 19:56:53 +00:00
Rasmus Munk Larsen
a96545777b Consolidate multiple implementations of divup/div_up/div_ceil. 2023-10-10 17:16:59 +00:00
Charles Schlosser
e8515f78ac Fix sparse triangular view iterator 2023-10-05 17:13:37 +00:00
Kevin
6d829e766f Fix extra semicolon in XprHelper 2023-09-14 08:18:28 +00:00
Alejandro Acosta
ba47341a14 [SYCL-2020] Enabling half precision support for SYCL. 2023-09-13 09:12:40 +00:00
François Girinon
92a77a596b Fix call to static functions from device by adding EIGEN_DEVICE_FUNC attribute to run methods 2023-09-13 04:16:52 +00:00
Antonio Sánchez
8f858a4ea8
Export ThreadPool symbols from legacy header. 2023-09-10 20:56:20 +00:00
Chip Kerchner
4e598ad259
New panel modes for GEMM MMA (real & complex). 2023-09-06 20:03:45 +00:00
Daniel Benedí
2c64a655fe Stage will not be ok if pardiso returned error 2023-09-06 14:40:06 +02:00
Charles Schlosser
18018ed013 Unwind Block of Blocks 2023-08-29 17:21:41 +00:00
Charles Schlosser
81b48065ea Fix arm32 float division and related bugs 2023-08-29 00:36:07 +00:00
Antonio Sánchez
2873916f1c Rename plugin headers to .inc. 2023-08-21 16:26:11 +00:00
Antonio Sánchez
6e4d5d4832 Add IWYU private pragmas to internal headers. 2023-08-21 16:25:22 +00:00
Antonio Sánchez
328b5f9085 Add temporary macro to allow unaligned scalar UB. 2023-08-15 15:58:41 +00:00
Charles Schlosser
a798d07659 Fix tensor stridedlinearbuffercopy 2023-08-03 20:36:42 +00:00
Charles Schlosser
8d9f467036 fix boost mp test to refer to new svd tests 2023-08-02 13:38:12 +00:00
Antonio Sánchez
0ae7d7a361 Fix unaligned scalar alignment UB. 2023-08-01 19:39:08 +00:00
cheng wang
66e8f38891 Add architecture definition files for Qualcomm Hexagon Vector Extension (HVX) 2023-08-01 17:47:57 +00:00
Antonio Sánchez
2af700aa40 Fix nullptr dereference in SVD. 2023-08-01 16:33:16 +00:00
Rasmus Munk Larsen
86a43d8c04 Fix clang-tidy warning 2023-07-31 21:26:28 +00:00
Antonio Sánchez
0cef325b07 Fix another UB access. 2023-07-31 19:18:45 +00:00
Charles Schlosser
5527e78a64 Add missing x86 pcasts 2023-07-28 23:41:38 +00:00
Alejandro Acosta
24d15e086f [SYCL-2020] Add test to validate SYCL in Eigen core. 2023-07-28 15:45:08 +00:00
Antonio Sánchez
d4ae542ed1 Fix nullptr dereference issue in triangular product. 2023-07-27 22:10:21 +00:00
Chip Kerchner
7769eb1b2e Fix problems with recent changes and Tensorflow in Power 2023-07-26 16:24:58 +00:00
Yingnan Wu
ba1cb6e45e Fixes #2703 by adding max_digits10 function 2023-07-26 16:02:52 +00:00
Charles Schlosser
9995c3da6f Fix -Wmaybe-uninitialized in SVD 2023-07-25 22:22:17 +00:00
Charles Schlosser
4e9e493b4a Fix -Waggressive-loop-optimizations 2023-07-21 03:47:40 +00:00
Charles Schlosser
6e7abeae69 fix arm build warnings 2023-07-17 20:37:27 +00:00
Charles Schlosser
81fe2d424f Fix more gcc compiler warnings / sort-of bugs 2023-07-14 21:12:45 +00:00
Charles Schlosser
21cd3fe209 Optimize check_rows_cols_for_overflow 2023-07-10 17:40:17 +00:00
Antonio Sánchez
9297aae66f Fix AVX512 nomalloc issues in trsm. 2023-07-10 16:42:13 +00:00