aboutsummaryrefslogtreecommitdiffhomepage
path: root/unsupported/Eigen/CXX11/src/Tensor/TensorConvolution.h
Commit message (Collapse)AuthorAge
* Improved the performance of the tensor convolution code by a factor of about 4.Gravatar Benoit Steiner2014-09-03
|
* Improved the speed of convolutions when running on cuda devicesGravatar Benoit Steiner2014-08-19
|
* Fixed misc typos.Gravatar Benoit Steiner2014-08-13
|
* Added missing apis.Gravatar Benoit Steiner2014-08-13
|
* Updated the convolution and contraction evaluators to follow the new ↵Gravatar Benoit Steiner2014-08-13
| | | | EvalSubExprsIfNeeded apu.
* Silenced a compilation warningGravatar Benoit Steiner2014-06-13
|
* Reworked the expression evaluation mechanism in order to make it possible to ↵Gravatar Benoit Steiner2014-06-13
| | | | | | | | efficiently compute convolutions and contractions in the future: * The scheduling of computation is moved out the the assignment code and into a new TensorExecutor class * The assignment itself is now a regular node on the expression tree * The expression evaluators start by recursively evaluating all their subexpressions if needed
* Fixed a few compilation errors.Gravatar Benoit Steiner2014-06-10
|
* TensorEval are now typed on the device: this will make it possible to use ↵Gravatar Benoit Steiner2014-06-10
| | | | | | partial template specialization to optimize the strategy of each evaluator for each device type. Started work on partial evaluations.
* Improved support for rvalues in tensor expressions.Gravatar Benoit Steiner2014-06-09
|
* Added support for convolution and reshaping of tensors.Gravatar Benoit Steiner2014-06-06