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

Mono Color

• 02db1228ed Add constructor for long types. Ville Kallioniemi 2016-01-26 23:41:01 -07:00
• 412bb5a631 Remove redundant test. Gael Guennebaud 2016-01-26 23:35:30 +01:00
• 0f8d26c6a9 Doc: add flip* and arrayfun MatLab equivalent. Gael Guennebaud 2016-01-26 23:34:48 +01:00
• cfa21f8123 Remove dead code. Gael Guennebaud 2016-01-26 23:33:15 +01:00
• 6850eab33b Re-enable blocking on rows in non-l3 blocking mode. Gael Guennebaud 2016-01-26 23:32:48 +01:00
• aa8c6a251e Make sure that micro-panel-size is smaller than blocking sizes (otherwise we might get a buffer overflow) Gael Guennebaud 2016-01-26 23:31:48 +01:00
• 5b0a9ee003 Make sure that block sizes are smaller than input matrix sizes. Gael Guennebaud 2016-01-26 23:30:24 +01:00
• 639b1d864a bug #1152: Fix data race in static initialization of blas Benoit Jacob 2016-01-26 11:44:16 -05:00
• 44d4674955 bug #1153: Don't rely on __GXX_EXPERIMENTAL_CXX0X__ to detect C++11 support Christoph Hertzberg 2016-01-26 16:45:33 +01:00
• 5eb2790be0 Fixed minor typo in SplineFitting. Hauke Heibel 2016-01-25 22:17:52 +01:00
• 8328caa618 bug #51: add block preallocation mechanism to selfadjoit*matrix product. Gael Guennebaud 2016-01-25 22:06:42 +01:00
• 2f9e6314b1 update BLAS interface to general_matrix_matrix_triangular_product Gael Guennebaud 2016-01-25 21:56:05 +01:00
• e58827d2ed bug #51: make general_matrix_matrix_triangular_product use L3-blocking helper so that general symmetric rank-updates and general-matrix-to-triangular products do not trigger dynamic memory allocation for fixed size matrices. Gael Guennebaud 2016-01-25 17:16:33 +01:00
• c10021c00a bug #1144: clarify the doc about aliasing in case of resizing and matrix product. Gael Guennebaud 2016-01-25 15:50:55 +01:00
• b114e6fd3b Improve documentation. Gael Guennebaud 2016-01-25 11:56:25 +01:00
• 869b4443ac Add SparseVector::conservativeResize() method. Gael Guennebaud 2016-01-25 11:55:39 +01:00
• e3a15a03a4 Don't explicitely evaluate the subexpression from TensorForcedEval::evalSubExprIfNeeded, as it will be done when executing the EvalTo subexpression Benoit Steiner 2016-01-24 23:04:50 -08:00
• bd207ce11e Added missing EIGEN_DEVICE_FUNC qualifier Benoit Steiner 2016-01-24 20:36:05 -08:00
• acf6f7af6b Merged in larsmans/eigen (pull request PR-156) Gael Guennebaud 2016-01-24 22:28:49 +01:00
• cc482e32f1 Method is called visit, not visitor Lars Buitinck 2016-01-24 15:50:59 +01:00
• 19e437daf0 Copyedit documentation: typos, spelling Lars Buitinck 2016-01-24 15:50:36 +01:00
• 1cf85bd875 bug #977: add stableNormalize[d] methods: they are analogues to normalize[d] but with carefull handling of under/over-flow Gael Guennebaud 2016-01-23 22:40:11 +01:00
• 369d6d1ae3 Add link to reference paper. Gael Guennebaud 2016-01-23 22:16:03 +01:00
• 0caa4b1531 bug #1150: make IncompleteCholesky more robust by iteratively increase the shift until the factorization succeed (with at most 10 attempts). Gael Guennebaud 2016-01-23 22:13:54 +01:00
• cb4e53ff7f Merged in ville-k/eigen/tensorflow_fix (pull request PR-153) Benoit Steiner 2016-01-22 19:11:31 -08:00
• 9f94e030c1 Re-add executable flags to minimize changeset. Ville Kallioniemi 2016-01-22 20:08:45 -07:00
• 3aeeca32af Leverage the new blocking code in the tensor contraction code. Benoit Steiner 2016-01-22 16:36:30 -08:00
• 4beb447e27 Created a mechanism to enable contraction mappers to determine the best blocking strategy. Benoit Steiner 2016-01-22 14:37:26 -08:00
• 5358c38589 bug #1095: add Cholmod*::logDeterminant/determinant (from patch of Joshua Pritikin) Gael Guennebaud 2016-01-22 16:05:29 +01:00
• 6a44ccb58b Backout changeset 690bc950f7 Gael Guennebaud 2016-01-22 15:03:53 +01:00
• 06971223ef Unify std::numeric_limits and device::numeric_limits within numext namespace Gael Guennebaud 2016-01-22 15:02:21 +01:00
• 9b6c72958a Update to latest default branch Ville Kallioniemi 2016-01-21 23:08:54 -07:00
• 73aec9219b Make use of 32 bit ints explicit and remove executable bit from headers. Ville Kallioniemi 2016-01-21 23:00:32 -07:00
• 7b68cf2e0f Pulled latest updates from trunk Benoit Steiner 2016-01-21 17:17:56 -08:00
• c33479324c Fixed a constness bug Benoit Steiner 2016-01-21 17:08:11 -08:00
• ee37eb4eed bug #977: avoid division by 0 in normalize() and normalized(). Gael Guennebaud 2016-01-21 20:43:42 +01:00
• 7cae8918c0 Fix compilation on old gcc+AVX Gael Guennebaud 2016-01-21 20:30:32 +01:00
• 8dca9f97e3 Add numext::sqrt function to enable custom optimized implementation. Gael Guennebaud 2016-01-21 20:18:51 +01:00
• 34340458cb bug #1151: remove useless critical section Gael Guennebaud 2016-01-21 14:29:45 +01:00
• 690bc950f7 fix clang warnings Jan Prach 2016-01-20 19:35:59 -08:00
• f2a842294f Pulled latest updates from the trunk Benoit Steiner 2016-01-20 18:12:53 -08:00
• 7ce932edd3 Small cleanup and small fix to the contraction of row major tensors Benoit Steiner 2016-01-20 18:12:08 -08:00
• 62f7e77711 add upper|lower case in incomplete_cholesky unit test Gael Guennebaud 2016-01-21 00:02:59 +01:00
• 47076bf00e Reduce the register pressure exerted by the tensor mappers whenever possible. This improves the performance of the contraction of a matrix with a vector by about 35%. Benoit Steiner 2016-01-20 14:51:48 -08:00
• ebd3388ee6 Pulled latest updates from trunk Benoit Steiner 2016-01-20 13:56:43 -08:00
• ed8ade9c65 bug #1149: fix Pastix*::*parm() Gael Guennebaud 2016-01-20 19:01:24 +01:00
• 4c5e96aab6 bug #1148: silent Pastix by default Gael Guennebaud 2016-01-20 18:56:17 +01:00
• db237d0c75 bug #1145: fix PastixSupport LLT/LDLT wrappers (missing resize prior to calls to selfAdjointView) Gael Guennebaud 2016-01-20 18:49:01 +01:00
• 0b7169d1f7 bug #1147: fix compilation of PastixSupport Gael Guennebaud 2016-01-20 18:15:59 +01:00
• 234a1094b7 Add static assertion to y(), z(), w() accessors Gael Guennebaud 2016-01-20 09:18:44 +01:00
• 915e7667cd Remove executable bit from header files Ville Kallioniemi 2016-01-19 21:17:29 -07:00
• 2832175a68 Use explicitly 32 bit integer types in constructors. Ville Kallioniemi 2016-01-19 20:12:17 -07:00
• df79c00901 Improved the formatting of the code Benoit Steiner 2016-01-19 17:24:08 -08:00
• 6d472d8375 Moved the contraction mapping code to its own file to make the code more manageable. Benoit Steiner 2016-01-19 17:22:05 -08:00
• b3b722905f Improved code indentation Benoit Steiner 2016-01-19 17:09:47 -08:00
• 5b7713dd33 Record whether the underlying tensor storage can be accessed directly during the evaluation of an expression. Benoit Steiner 2016-01-19 17:05:10 -08:00
• 63fb66f53a Add ctor for long Ville Kallioniemi 2016-01-17 21:25:36 -07:00
• 6a75e7e0d5 Digamma cleanup Eugene Brevdo 2016-01-15 16:32:21 -08:00
• 34057cff23 Fixed a race condition that could affect some reductions on CUDA devices. Benoit Steiner 2016-01-15 15:11:56 -08:00
• 0461f0153e Made it possible to compare tensor dimensions inside a CUDA kernel. Benoit Steiner 2016-01-15 11:22:16 -08:00
• aed4cb1269 Use warp shuffles instead of shared memory access to speedup the inner reduction kernel. Benoit Steiner 2016-01-14 21:45:14 -08:00
• c1a42c2d0d Don't disable the AVX implementations of plset when compiling with AVX512 enabled Benoit Steiner 2016-01-14 17:21:39 -08:00
• 0366478df8 Added alignment requirement to the AVX512 packet traits. Benoit Steiner 2016-01-14 17:02:39 -08:00
• 3cfd16f3af Fixed the signature of the plset primitives for AVX512 Benoit Steiner 2016-01-14 16:58:01 -08:00
• 67f44365ea Fixed the AVX512 signature of the ptranspose primitives Benoit Steiner 2016-01-14 16:51:11 -08:00
• a282eb1363 pscatter/pgather use Index instead of int to specify the stride Benoit Steiner 2016-01-14 16:39:39 -08:00
• 7832485575 Deleted unnecessary commas and semicolons Benoit Steiner 2016-01-14 16:36:29 -08:00
• 8fe2532e70 Fixed a boundary condition bug in the outer reduction kernel Benoit Steiner 2016-01-14 09:29:48 -08:00
• 9f013a9d86 Properly record the rank of reduced tensors in the tensor traits. Benoit Steiner 2016-01-13 14:24:37 -08:00
• 79b69b7444 Trigger the optimized matrix vector path more conservatively. Benoit Steiner 2016-01-12 15:21:09 -08:00
• d920d57f38 Improved the performance of the contraction of a 2d tensor with a 1d tensor by a factor of 3 or more. This helps speedup LSTM neural networks. Benoit Steiner 2016-01-12 11:32:27 -08:00
• bd7d901da9 Reverted a previous change that tripped nvcc when compiling in debug mode. Benoit Steiner 2016-01-11 17:49:44 -08:00
• bbdabbb379 Made the blas utils usable from within a cuda kernel Benoit Steiner 2016-01-11 17:26:56 -08:00
• c5e6900400 Silenced a few compilation warnings. Benoit Steiner 2016-01-11 17:06:39 -08:00
• f894736d61 Updated the tensor traits: the alignment is not part of the Flags enum anymore Benoit Steiner 2016-01-11 16:42:18 -08:00
• 4f7714d72c Enabled the use of fixed dimensions from within a cuda kernel. Benoit Steiner 2016-01-11 16:01:00 -08:00
• 01c55d37e6 Deleted unused variable. Benoit Steiner 2016-01-11 15:53:19 -08:00
• 0504c56ea7 Silenced a nvcc compilation warning Benoit Steiner 2016-01-11 15:49:21 -08:00
• b523771a24 Silenced several compilation warnings triggered by nvcc. Benoit Steiner 2016-01-11 14:25:43 -08:00
• 2c3b13eded Merged in jeremy_barnes/eigen/shader-model-3.0 (pull request PR-152) Benoit Steiner 2016-01-11 11:43:37 -08:00
• 2ccb1c8634 Fixed a bug in the dispatch of optimized reduction kernels. Benoit Steiner 2016-01-11 10:36:37 -08:00
• 780623261e Re-enabled the optimized reduction CUDA code. Benoit Steiner 2016-01-11 09:07:14 -08:00
• 91678f489a Cleaned up double-defined macro from last commit Jeremy Barnes 2016-01-10 22:44:45 -05:00
• 403a7cb6c3 Alternative way of forcing instantiation of device kernels without causing warnings or requiring device to device kernel invocations. Jeremy Barnes 2016-01-10 22:39:13 -05:00
• b557662e58 merge Gael Guennebaud 2016-01-09 08:37:01 +01:00
• 8b9dc9f0df bug #1144: fix regression in x=y+A*x (aliasing), and move evaluator_traits::AssumeAliasing to evaluator_assume_aliasing. Gael Guennebaud 2016-01-09 08:30:38 +01:00
• e76904af1b Simplified the dispatch code. Benoit Steiner 2016-01-08 16:50:57 -08:00
• d726e864ac Made it possible to use array of size 0 on CUDA devices Benoit Steiner 2016-01-08 16:38:14 -08:00
• 3358dfd5dd Reworked the dispatch of optimized cuda reduction kernels to workaround a nvcc bug that prevented the code from compiling in optimized mode in some cases Benoit Steiner 2016-01-08 16:28:53 -08:00
• 53749ff415 Prevent nvcc from miscompiling the cuda metakernel. Unfortunately this reintroduces some compulation warnings but it's much better than having to deal with random assertion failures. Benoit Steiner 2016-01-08 13:53:40 -08:00
• f9d71a1729 extend matlab conversion table Gael Guennebaud 2016-01-08 22:24:45 +01:00
• 6639b7d6e8 Removed a couple of partial specialization that confuse nvcc and result in errors such as this: error: more than one partial specialization matches the template argument list of class "Eigen::internal::get<3, Eigen::internal::numeric_list<std::size_t, 1UL, 1UL, 1UL, 1UL>>" "Eigen::internal::get<n, Eigen::internal::numeric_list<T, a, as...>>" "Eigen::internal::get<n, Eigen::internal::numeric_list<T, as...>>" Benoit Steiner 2016-01-07 18:45:19 -08:00
• 0cb2ca5de2 Fixed a typo. Benoit Steiner 2016-01-06 18:50:28 -08:00
• 213459d818 Optimized the performance of broadcasting of scalars. Benoit Steiner 2016-01-06 18:47:45 -08:00
• ee738321aa rm remaining debug code Gael Guennebaud 2016-01-06 14:49:40 +01:00
• 54bf582303 bug #1143: Work-around gcc bug Christoph Hertzberg 2016-01-06 11:59:24 +01:00
• 99093c0fe0 Added support for AVX512 to the build files Benoit Steiner 2016-01-05 10:02:49 -08:00
• cfff40b1d4 Improved the performance of reductions on CUDA devices Benoit Steiner 2016-01-04 17:25:00 -08:00
• 515dee0baf Added a 'divup' util to compute the floor of the quotient of two integers Benoit Steiner 2016-01-04 16:29:26 -08:00
• 715f6f049f Improve inline documentation of SparseCompressedBase and its derived classes Gael Guennebaud 2016-01-03 21:56:30 +01:00