Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | Fix more enum arithmetic. | Rasmus Munk Larsen | 2021-06-15 |
| | |||
* | Fix calls to device functions from host code | Nathan Luehr | 2021-05-11 |
| | |||
* | Fix tensor casts for large packets and casts to/from std::complex | Antonio Sanchez | 2020-06-30 |
| | | | | | | | | | | | | | The original tensor casts were only defined for `SrcCoeffRatio`:`TgtCoeffRatio` 1:1, 1:2, 2:1, 4:1. Here we add the missing 1:N and 8:1. We also add casting `Eigen::half` to/from `std::complex<T>`, which was missing to make it consistent with `Eigen:bfloat16`, and generalize the overload to work for any complex type. Tests were added to `basicstuff`, `packetmath`, and `cxx11_tensor_casts` to test all cast configurations. | ||
* | Remove V2 suffix from TensorBlock | Eugene Zhulenev | 2019-12-10 |
| | |||
* | Do not use std::vector in getResourceRequirements | Eugene Zhulenev | 2019-12-09 |
| | |||
* | Remove legacy block evaluation support | Eugene Zhulenev | 2019-11-12 |
| | |||
* | Block evaluation for TensorGenerator/TensorReverse/TensorShuffling | Eugene Zhulenev | 2019-10-14 |
| | |||
* | Add block evaluation to TensorReshaping/TensorCasting/TensorPadding/TensorSelect | Eugene Zhulenev | 2019-10-02 |
| | |||
* | Tensor block evaluation V2 support for unary/binary/broadcsting | Eugene Zhulenev | 2019-09-24 |
| | |||
* | Add support for asynchronous evaluation of tensor casting expressions. | Rasmus Munk Larsen | 2019-09-19 |
| | |||
* | [SYCL] This PR adds the minimum modifications to the Eigen unsupported ↵ | Mehdi Goli | 2019-06-28 |
| | | | | | | | | | | module required to run it on devices supporting SYCL. * Abstracting the pointer type so that both SYCL memory and pointer can be captured. * Converting SYCL virtual pointer to SYCL device memory in Eigen evaluator class. * Binding SYCL placeholder accessor to command group handler by using bind method in Eigen evaluator node. * Adding SYCL macro for controlling loop unrolling. * Modifying the TensorDeviceSycl.h and SYCL executor method to adopt the above changes. | ||
* | Add PacketConv implementation for non-vectorizable src expressions | Eugene Zhulenev | 2019-02-08 |
| | |||
* | Optimize TensorConversion evaluator: do not convert same type | Eugene Zhulenev | 2019-02-08 |
| | |||
* | Add block evaluationto CwiseUnaryOp and add PreferBlockAccess enum to all ↵ | Eugene Zhulenev | 2018-08-10 |
| | | | | evaluators | ||
* | Enabling per device specialisation of packetsize. | Mehdi Goli | 2018-08-01 |
| | |||
* | Add tiled evaluation support to TensorExecutor | Eugene Zhulenev | 2018-07-25 |
| | |||
* | Code cleanup | Benoit Steiner | 2017-07-10 |
| | |||
* | Merged in mehdi_goli/opencl/DataDependancy (pull request PR-10) | Benoit Steiner | 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 ↵ | Mehdi Goli | 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 ↵ | Benoit Steiner | 2016-05-26 |
| | | | | it involves a cast that isn't vectorized (e.g fp16 to float) | ||
* | Made the static storage class qualifier come first. | Benoit Steiner | 2016-05-25 |
| | |||
* | Eigen cost model part 1. This implements a basic recursive framework to ↵ | Rasmus Munk Larsen | 2016-04-14 |
| | | | | estimate the cost of evaluating tensor expressions. | ||
* | Added missing EIGEN_DEVICE_FUNC to the tensor conversion code. | Benoit Steiner | 2016-04-07 |
| | |||
* | Decoupled the packet type definition from the definition of the tensor ops. ↵ | Benoit Steiner | 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 | Benoit Steiner | 2016-02-21 |
| | |||
* | Optimized casting of tensors in the case where the casting happens to be a no-op | Benoit Steiner | 2016-02-21 |
| | |||
* | Fixed a bug in the tensor type converter | Benoit Steiner | 2016-02-19 |
| | |||
* | Added support for vectorized type casting of int to char. | Benoit Steiner | 2016-02-03 |
| | |||
* | Record whether the underlying tensor storage can be accessed directly during ↵ | Benoit Steiner | 2016-01-19 |
| | | | | the evaluation of an expression. | ||
* | Added more missing EIGEN_DEVICE_FUNC | Benoit Steiner | 2015-11-06 |
| | |||
* | Removed bogus assertion | Benoit Steiner | 2015-10-20 |
| | |||
* | Fixed a bug in the tensor conversion op | Benoit Steiner | 2015-10-20 |
| | |||
* | Many files were missing in previous changeset. | Gael Guennebaud | 2015-07-29 |
| | |||
* | Updated the tensor type casting code as follow: in the case where TgtRatio < ↵ | Benoit Steiner | 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 ↵ | Benoit Steiner | 2015-03-02 |
| | | | | to doubles since alignment can't always be guaranteed. | ||
* | Added support for vectorized type casting of tensors | Benoit Steiner | 2015-02-27 |