aboutsummaryrefslogtreecommitdiffhomepage
path: root/unsupported/Eigen
Commit message (Collapse)AuthorAge
* Relax mixing-type constraints for binary coefficient-wise operators:Gravatar Gael Guennebaud2016-06-06
| | | | | | | | | | - Replace internal::scalar_product_traits<A,B> by Eigen::ScalarBinaryOpTraits<A,B,OP> - Remove the "functor_is_product_like" helper (was pretty ugly) - Currently, OP is not used, but it is available to the user for fine grained tuning - Currently, only the following operators have been generalized: *,/,+,-,=,*=,/=,+=,-= - TODO: generalize all other binray operators (comparisons,pow,etc.) - TODO: handle "scalar op array" operators (currently only * is handled) - TODO: move the handling of the "void" scalar type to ScalarBinaryOpTraits
* Add TernaryFunctors and the betainc SpecialFunction.Gravatar Eugene Brevdo2016-06-02
| | | | | | | | | | | | | | | | | | | TernaryFunctors and their executors allow operations on 3-tuples of inputs. API fully implemented for Arrays and Tensors based on binary functors. Ported the cephes betainc function (regularized incomplete beta integral) to Eigen, with support for CPU and GPU, floats, doubles, and half types. Added unit tests in array.cpp and cxx11_tensor_cuda.cu Collapsed revision * Merged helper methods for betainc across floats and doubles. * Added TensorGlobalFunctions with betainc(). Removed betainc() from TensorBase. * Clean up CwiseTernaryOp checks, change igamma_helper to cephes_helper. * betainc: merge incbcf and incbd into incbeta_cfe. and more cleanup. * Update TernaryOp and SpecialFunctions (betainc) based on review comments.
* Use array_prod to compute the number of elements contained in the input ↵Gravatar Benoit Steiner2016-06-04
| | | | tensor expression
* Merged in ibab/eigen (pull request PR-192)Gravatar Benoit Steiner2016-06-03
|\ | | | | | | Add generic scan method
* | Improved the performance of full reductions.Gravatar Benoit Steiner2016-06-03
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | AFTER: BM_fullReduction/10 4541 4543 154017 21.0M items/s BM_fullReduction/64 5191 5193 100000 752.5M items/s BM_fullReduction/512 9588 9588 71361 25.5G items/s BM_fullReduction/4k 244314 244281 2863 64.0G items/s BM_fullReduction/5k 359382 359363 1946 64.8G items/s BEFORE: BM_fullReduction/10 9085 9087 74395 10.5M items/s BM_fullReduction/64 9478 9478 72014 412.1M items/s BM_fullReduction/512 14643 14646 46902 16.7G items/s BM_fullReduction/4k 260338 260384 2678 60.0G items/s BM_fullReduction/5k 385076 385178 1818 60.5G items/s
| * Add generic scan methodGravatar Igor Babuschkin2016-06-03
|/
* Fix MatrixFunctions module.Gravatar Gael Guennebaud2016-06-03
|
* Align the first element of the Waiter struct instead of padding it. This ↵Gravatar Benoit Steiner2016-06-02
| | | | reduces its memory footprint a bit while achieving the goal of preventing false sharing
* Add syntactic sugar to Eigen tensors to allow more natural syntax.Gravatar Rasmus Munk Larsen2016-06-02
| | | | | | | | | Specifically, this enables expressions involving: scalar + tensor scalar * tensor scalar / tensor scalar - tensor
* Add tensor scan opGravatar Igor Babuschkin2016-06-02
| | | | | This is the initial implementation a generic scan operation. Based on this, cumsum and cumprod method have been added to TensorBase.
* Use a single PacketSize variableGravatar Benoit Steiner2016-06-01
|
* Fixed compilation warningGravatar Benoit Steiner2016-06-01
|
* Silenced compilation warning generated by nvcc.Gravatar Benoit Steiner2016-06-01
|
* Added support for mean reductions on fp16Gravatar Benoit Steiner2016-06-01
|
* Only enable optimized reductions of fp16 if the reduction functor supports themGravatar Benoit Steiner2016-05-31
|
* Reimplement clamp as a static function.Gravatar Benoit Steiner2016-05-27
|
* Use NULL instead of nullptr to preserve the compatibility with cxx03Gravatar Benoit Steiner2016-05-27
|
* Added a new operation to enable more powerful tensorindexing.Gravatar Benoit Steiner2016-05-27
|
* Fix compilation when defaulting to row-majorGravatar Gael Guennebaud2016-05-27
|
* Fixed some compilation warningsGravatar Benoit Steiner2016-05-26
|
* Preserve the ability to vectorize the evaluation of an expression even when ↵Gravatar Benoit Steiner2016-05-26
| | | | it involves a cast that isn't vectorized (e.g fp16 to float)
* Resolved merge conflictsGravatar Benoit Steiner2016-05-26
|
* Merged latest reduction improvementsGravatar Benoit Steiner2016-05-26
|\
* | Improved the performance of inner reductions.Gravatar Benoit Steiner2016-05-26
| |
* | Code cleanup.Gravatar Benoit Steiner2016-05-26
| |
* | Made the static storage class qualifier come first.Gravatar Benoit Steiner2016-05-25
| |
* | Deleted unnecessary explicit qualifiers.Gravatar Benoit Steiner2016-05-25
| |
* | Don't mark inline functions as static since it confuses the ICC compilerGravatar Benoit Steiner2016-05-25
| |
* | Marked unused variables as suchGravatar Benoit Steiner2016-05-25
| |
* | Made the IndexPair code compile in non cxx11 modeGravatar Benoit Steiner2016-05-25
| |
* | Made the index pair list code more portable accross various compilersGravatar Benoit Steiner2016-05-25
| |
* | Improved the performance of tensor paddingGravatar Benoit Steiner2016-05-25
| |
* | Added support for statically known lists of pairs of indicesGravatar Benoit Steiner2016-05-25
| |
* | There is no need to make the fp16 full reduction kernel a static function.Gravatar Benoit Steiner2016-05-24
| |
* | Fixed compilation warningGravatar Benoit Steiner2016-05-24
| |
* | Merged in rmlarsen/eigen (pull request PR-188)Gravatar Benoit Steiner2016-05-23
|\ \ | | | | | | | | | Minor cleanups: 1. Get rid of a few unused variables. 2. Get rid of last uses of EIGEN_USE_COST_MODEL.
* | | Silenced several double-promotion warningsGravatar Christoph Hertzberg2016-05-22
| | |
* | | Fix some sign-compare warningsGravatar Christoph Hertzberg2016-05-22
| | |
* | | Make EIGEN_HAS_CONSTEXPR user configurableGravatar Gael Guennebaud2016-05-20
| | |
* | | Make EIGEN_HAS_VARIADIC_TEMPLATES user configurableGravatar Gael Guennebaud2016-05-20
| | |
* | | Make EIGEN_HAS_RVALUE_REFERENCES user configurableGravatar Gael Guennebaud2016-05-20
| | |
* | | Rename EIGEN_HAVE_RVALUE_REFERENCES to EIGEN_HAS_RVALUE_REFERENCESGravatar Gael Guennebaud2016-05-20
| | |
* | | Remove std:: to enable custom scalar types.Gravatar Gael Guennebaud2016-05-19
| | |
| * | Merged eigen/eigen into defaultGravatar Rasmus Larsen2016-05-18
| |\ \
| * \ \ Merge.Gravatar Rasmus Munk Larsen2016-05-18
| |\ \ \
| * | | | Minor cleanups: 1. Get rid of unused variables. 2. Get rid of last uses of ↵Gravatar Rasmus Munk Larsen2016-05-18
| | | | | | | | | | | | | | | | | | | | EIGEN_USE_COST_MODEL.
| | * | | Reduce overhead for small tensors and cheap ops by short-circuiting the ↵Gravatar Rasmus Munk Larsen2016-05-17
| |/ / / | | | | | | | | | | | | const computation and block size calculation in parallelFor.
| | | * Allow vectorized padding on GPU. This helps speed things up a little.Gravatar Benoit Steiner2016-05-17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Before: BM_padding/10 5000000 460 217.03 MFlops/s BM_padding/80 5000000 460 13899.40 MFlops/s BM_padding/640 5000000 461 888421.17 MFlops/s BM_padding/4K 5000000 460 54316322.55 MFlops/s After: BM_padding/10 5000000 454 220.20 MFlops/s BM_padding/80 5000000 455 14039.86 MFlops/s BM_padding/640 5000000 452 904968.83 MFlops/s BM_padding/4K 5000000 411 60750049.21 MFlops/s
* | | | made a fix to the GMRES solver so that it now correctly reports the error ↵Gravatar David Dement2016-05-16
| |/ / |/| | | | | | | | achieved in the solution process
* | | Advertize the packet api of the tensor reducers iff the corresponding packet ↵Gravatar Benoit Steiner2016-05-18
| | | | | | | | | | | | primitives are available.
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-02 20:35:19 +0000