6826 Commits

Author	SHA1	Message	Date
Antonio Sánchez	2cf4d18c9c	Disable AVX512 GEMM kernels by default.	2022-07-20 21:22:48 +00:00
Charles Schlosser	a678a3e052	Fix aligned_realloc to call check_that_malloc_is_allowed() if ptr == 0	2022-07-19 20:59:07 +00:00
b-shi	4a56359406	Add option to disable avx512 GEBP kernels	2022-07-18 17:59:09 +00:00
Mathieu Westphal	1092574b26	Fix wrong doxygen group usage	2022-07-12 13:22:46 +02:00
Antonio Sánchez	bb51d9f4fa	Fix ODR violations.	2022-07-09 04:56:36 +00:00
Chip Kerchner	84cf3ff18d	Add pload_partial, pstore_partial (and unaligned versions), pgather_partial, pscatter_partial, loadPacketPartial and storePacketPartial.	2022-06-27 19:18:00 +00:00
Chip Kerchner	c603275dc9	Better performance for Power10 using more load and store vector pairs for GEMV	2022-06-27 18:11:55 +00:00
Antonio Sánchez	bc2ab81634	Eliminate undef warnings when not compiling for AVX512.	2022-06-24 15:10:10 +00:00
Antonio Sánchez	0e083b172e	Use numext::sqrt in Householder.h.	2022-06-21 16:29:59 +00:00
b-shi	37673ca1bc	AVX512 TRSM kernels use alloca if EIGEN_NO_MALLOC requested	2022-06-17 18:05:26 +00:00
Chip Kerchner	4d1c16eab8	Fix tanh and erf to use vectorized version for EIGEN_FAST_MATH in VSX.	2022-06-15 16:06:43 +00:00
Mehdi Goli	7ea823e824	[SYCL-Spec] According to [SYCL-2020 spec](...	2022-06-13 15:52:29 +00:00
Arthur	ba4d7304e2	Document DiagonalBase	2022-06-08 17:46:32 +00:00
Binhao Qin	95463b59bc	Mark index_remap as EIGEN_DEVICE_FUNC in src/Core/Reshaped.h (Fixes #2493)	2022-06-07 20:10:47 +00:00
Shi, Brian	28812d2ebb	AVX512 TRSM Kernels respect EIGEN_NO_MALLOC	2022-06-07 11:28:42 -07:00
Arthur	14aae29470	Provide DiagonalMatrix Product and Initializers	2022-06-06 21:43:22 +00:00
aaraujom	8fbb76a043	Fix build issues with MSVC for AVX512	2022-06-03 14:55:40 +00:00
aaraujom	d49ede4dc4	Add AVX512 s/dgemm optimizations for compute kernel (2nd try)	2022-05-28 02:00:21 +00:00
Arthur	705ae70646	Add R-Bidiagonalization step to BDCSVD	2022-05-27 02:00:24 +00:00
Mario Rincon-Nigro	e99163e732	fix: issue 2481: LDLT produce wrong results with AutoDiffScalar	2022-05-25 15:26:10 +00:00
Chip Kerchner	aa8b7e2c37	Add subMappers to Power GEMM packing - simplifies the address calculations (10% faster)	2022-05-23 15:18:29 +00:00
Guoqiang QI	32a3f9ac33	Improve plogical_shift_* implementations and fix typo in SVE/PacketMath.h	2022-05-23 09:33:49 +00:00
Eisuke Kawashima	ac5c83a3f5	unset executable flag	2022-05-22 22:47:43 +09:00
Antonio Sanchez	481a4a8c31	Fix BDCSVD condition for failing with numerical issue.	2022-05-20 08:18:31 -07:00
Antonio Sánchez	028ab12586	Prevent BDCSVD crash caused by index out of bounds.	2022-05-19 22:29:48 +00:00
Antonio Sánchez	9b9496ad98	Revert "Add AVX512 optimizations for matrix multiply" ... This reverts commit 25db0b4a824ba9a092bbb514fbada51bf9d37a18	2022-05-13 18:50:33 +00:00
aaraujom	25db0b4a82	Add AVX512 optimizations for matrix multiply	2022-05-12 23:41:19 +00:00
Alex_M	2c055f8633	make diagonal matrix cols() and rows() methods constexpr	2022-05-03 10:13:37 +02:00
Chip Kerchner	c2f15edc43	Add load vector_pairs for RHS of GEMM MMA. Improved predux GEMV.	2022-04-25 16:23:01 +00:00
John Mather	9e026e5e28	Removed need to supply the Symmetric flag to UpLo argument for Accelerate LLT and LDLT	2022-04-21 20:02:10 +00:00
Chip Kerchner	44ba7a0da3	Fix compiler bugs for GCC 10 & 11 for Power GEMM	2022-04-20 15:59:00 +00:00
Chip Kerchner	b02c384ef4	Add fused multiply functions for PowerPC - pmsub, pnmadd and pnmsub	2022-04-18 16:16:32 +00:00
Rohit Santhanam	3de96caeaa	Fix HouseholderSequence.h	2022-04-17 02:46:56 +00:00
Antonio Sánchez	f845a8bb1a	Fix cwise NaN propagation for scalar input.	2022-04-16 05:07:44 +00:00
Charles Schlosser	a4bb513b99	Update HouseholderSequence.h	2022-04-15 16:56:17 +00:00
Shi, Brian	fc1d888415	Remove AVX512VL dependency in trsm	2022-04-14 12:44:24 -07:00
Antonio Sánchez	07db964bde	Restrict new AVX512 trsm to AVX512VL, rename files for consistency.	2022-04-14 16:58:32 +00:00
Charles Schlosser	67eeba6e72	Avoidable heap allocation in applyHouseholderToTheLeft	2022-04-13 18:45:36 +00:00
Antonio Sánchez	efb08e0bb5	Revert "Fix ambiguous DiagonalMatrix constructors." ... This reverts commit a81bba962a5fe236e9ded7fd509aa04669559caa	2022-04-12 03:54:31 +00:00
Chip Kerchner	53eec53d2a	Fix Power GEMV order of operations in predux for MMA.	2022-04-11 21:29:05 +00:00
Antonio Sánchez	a81bba962a	Fix ambiguous DiagonalMatrix constructors.	2022-04-11 19:13:25 +00:00
Tobias Schlüter	f3ba220c5d	Remove EIGEN_EMPTY_STRUCT_CTOR	2022-04-08 18:27:26 +00:00
Antonio Sánchez	5ed7a86ae9	Fix MSVC+CUDA issues.	2022-04-08 18:05:32 +00:00
Antonio Sánchez	734ed1efa6	Fix ODR issues in lapacke_helpers.	2022-04-08 15:31:30 +00:00
Antonio Sánchez	2c45a3846e	Fix some max size expressions.	2022-04-06 22:19:57 +00:00
Erik Schultheis	df87d40e34	constexpr reshape helper	2022-04-05 17:32:17 +00:00
Chip Kerchner	403fa33409	Performance improvements in GEMM for Power	2022-04-05 12:18:53 +00:00
Erik Schultheis	e1df3636b2	More constexpr helpers	2022-04-04 18:38:34 +00:00
Erik Schultheis	64909b82bd	static const class members turned into constexpr	2022-04-04 17:33:33 +00:00
William Talbot	2c0ef43b48	Added Scaling function overload for vector rvalue reference	2022-04-04 16:50:09 +00:00