Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | Add block evaluationto CwiseUnaryOp and add PreferBlockAccess enum to all ↵ | 2018-08-10 | |
| | | | | evaluators | ||
* | Enabling per device specialisation of packetsize. | 2018-08-01 | |
| | |||
* | Add tiled evaluation support to TensorExecutor | 2018-07-25 | |
| | |||
* | Code cleanup | 2017-07-10 | |
| | |||
* | Merged in mehdi_goli/opencl/DataDependancy (pull request PR-10) | 2017-06-28 | |
| | | | | | | | | | | DataDependancy * Wrapping data type to the pointer class for sycl in non-terminal nodes; not having that breaks Tensorflow Conv2d code. * Applying Ronnan's Comments. * Applying benoit's comments | ||
* | Adding Tensor ReverseOp; TensorStriding; TensorConversionOp; Modifying ↵ | 2017-01-16 | |
| | | | | Tensor Contractsycl to be located in any place in the expression tree. | ||
* | Preserve the ability to vectorize the evaluation of an expression even when ↵ | 2016-05-26 | |
| | | | | it involves a cast that isn't vectorized (e.g fp16 to float) | ||
* | Made the static storage class qualifier come first. | 2016-05-25 | |
| | |||
* | Eigen cost model part 1. This implements a basic recursive framework to ↵ | 2016-04-14 | |
| | | | | estimate the cost of evaluating tensor expressions. | ||
* | Added missing EIGEN_DEVICE_FUNC to the tensor conversion code. | 2016-04-07 | |
| | |||
* | Decoupled the packet type definition from the definition of the tensor ops. ↵ | 2016-03-08 | |
| | | | | All the vectorization is now defined in the tensor evaluators. This will make it possible to relialably support devices with different packet types in the same compilation unit. | ||
* | Fixed compilation warning generated by clang | 2016-02-21 | |
| | |||
* | Optimized casting of tensors in the case where the casting happens to be a no-op | 2016-02-21 | |
| | |||
* | Fixed a bug in the tensor type converter | 2016-02-19 | |
| | |||
* | Added support for vectorized type casting of int to char. | 2016-02-03 | |
| | |||
* | Record whether the underlying tensor storage can be accessed directly during ↵ | 2016-01-19 | |
| | | | | the evaluation of an expression. | ||
* | Added more missing EIGEN_DEVICE_FUNC | 2015-11-06 | |
| | |||
* | Removed bogus assertion | 2015-10-20 | |
| | |||
* | Fixed a bug in the tensor conversion op | 2015-10-20 | |
| | |||
* | Many files were missing in previous changeset. | 2015-07-29 | |
| | |||
* | Updated the tensor type casting code as follow: in the case where TgtRatio < ↵ | 2015-03-02 | |
| | | | | SrcRatio, disable the vectorization of the source expression unless is has direct-access. | ||
* | Disabled the use of aligned memory loads when converting a tensor from float ↵ | 2015-03-02 | |
| | | | | to doubles since alignment can't always be guaranteed. | ||
* | Added support for vectorized type casting of tensors | 2015-02-27 | |