Commit message (Collapse) | Author | Age | ||
---|---|---|---|---|
... | ||||
* | Upgraded to the latest version of Eigen that speeds up full reductions on fp16 | 2016-05-12 | ||
| | | | | | by about 3 orders of magnitude as well as some partial reductions by 30% when using cuda 7.5 or above Change: 122191448 | |||
* | Improved support for min and max on 16 bit floats when running on recent cuda | 2016-04-27 | ||
| | | | | | | gpus Updated the check numerics code to make it compatible with fp16 Change: 120980302 | |||
* | Made it possible to compute the cross entropy using 16 bit floats | 2016-04-25 | ||
| | | | | Change: 120739269 | |||
* | Rollback of rollback of cl/120366069: | 2016-04-21 | ||
| | | | | | | | | tensorflow: switch to eigen thread pool This is first step of switching tensorflow to the new non-blocking thread pool in eigen. Change: 120510292 | |||
* | Prevent TensorFlow from crashing when attempting to reduce an empty tensor ↵ | 2016-04-21 | ||
| | | | | | | on GPU Change: 120505517 | |||
* | Fixed a compilation error when targeting cuda 3.0 devices such as the ones | 2016-04-20 | ||
| | | | | | offered by AWS Change: 120369420 | |||
* | Upgraded to the latest version of Eigen that adds support for computing the | 2016-04-14 | ||
| | | | | | sigmoid of fp16 and introduces a condition estimator. Change: 119907721 | |||
* | Added support for trigonometric and transcendental functions of half floats | 2016-04-14 | ||
| | | | | Change: 119850987 | |||
* | Upgraded to the latest version of Eigen that provides significant performance | 2016-04-13 | ||
| | | | | | improvements for fp16 Change: 119771118 | |||
* | Made isinf, isnan, isfinite, ceil and floor work with 16 bit floats. | 2016-04-09 | ||
| | | | | Change: 119458778 | |||
* | Upgraded to the latest version of Eigen that has bug fixes for complex numbers | 2016-04-08 | ||
| | | | | | as well as fp16 Change: 119398881 | |||
* | Upgraded to the latest version of eigen that introduces implementations of ↵ | 2016-04-07 | ||
| | | | | | | | the zeta and polygamma functions, as well as improved support for float16. Change: 119279101 | |||
* | Upgrade to the latest version of Eigen that provides better support for float16 | 2016-04-04 | ||
| | | | | | and fixes the computation of absolute values on gpu. Change: 119001808 | |||
* | Upgraded to the latest version of Eigen | 2016-03-28 | ||
| | | | | Change: 118414762 | |||
* | Upgraded to the latest version of Eigen that provides better support for fp16. | 2016-03-28 | ||
| | | | | | Use Eigen mod functors directly instead of duplicating them. Change: 118362359 | |||
* | Move the NeuralNetwork code out of third_party/eigen3 and into | 2016-03-23 | ||
| | | | | | tensorflow/core/kernel. Change: 117941211 | |||
* | Update Eigen NN headers in staging repo to match public contents. | 2016-03-22 | ||
| | ||||
* | Re-rollback of "TensorFlow: move eigen some NN code from our ↵ | 2016-03-18 | ||
| | | | | | | | third_party/eigen3 copy to being part of TF, add tests." Change: 117608627 | |||
* | Rollforward of "TensorFlow: move eigen some NN code from our ↵ | 2016-03-18 | ||
| | | | | | | | third_party/eigen3 copy to being part of TF, add tests." Change: 117587217 | |||
* | TensorFlow: update eigen to latest change to fix TensorChipping | 2016-03-18 | ||
| | | | | Change: 117570343 | |||
* | Rollback of "TensorFlow: move eigen some NN code from our third_party/eigen3 ↵ | 2016-03-18 | ||
| | | | | | | | copy to being part of TF, add tests." Change: 117519243 | |||
* | TensorFlow: move eigen some NN code from our third_party/eigen3 copy | 2016-03-18 | ||
| | | | | | to being part of TF, add tests. Change: 117509710 | |||
* | TensorFlow: update eigen to latest release that has a fix to too large frame. | 2016-03-18 | ||
| | | | | Change: 117506296 | |||
* | Added basic support for float16 on CPUs and older GPUs. | 2016-03-18 | ||
| | | | | | Also fixed compilation issues with cuda devices that support the compute model 5.3 Change: 117493644 | |||
* | Upgraded to a newer version of Eigen that fixes a compilation error on Android | 2016-03-09 | ||
| | | | | Change: 116831720 | |||
* | Upgraded eigen to make it possible to compile a binary that takes advantage of | 2016-03-09 | ||
| | | | | | both avx instructions and cuda to run as fast as possible. Change: 116775924 | |||
* | Upgraded to a new version of Eigen that adds the ability to pad using values | 2016-03-08 | ||
| | | | | | other than 0 and significantly speeds up a number of computations on GPUs. Change: 116607765 | |||
* | Added the ability to convert between floats and float16 on Kepler and Maxwell | 2016-03-05 | ||
| | | | | | GPUs Change: 116409601 | |||
* | Improved the performance of outer reductions | 2016-03-01 | ||
| | | | | Change: 116063261 | |||
* | Improved the performance of narrow reductions on CUDA | 2016-02-29 | ||
| | | | | Change: 115889721 | |||
* | Upgraded Eigen to fix a compilation error triggered by xcode | 2016-02-22 | ||
| | | | | Change: 115280348 | |||
* | Upgraded to the latest version of eigen, which adds a missing #include | 2016-02-22 | ||
| | | | | Change: 115268843 | |||
* | Added support for half floats to eigen, which is the first step to support half | 2016-02-22 | ||
| | | | | | floats in TensorFlow. The code was tested on Tegra x1. Change: 115253733 | |||
* | TensorFlow: update Eigen to non-broken GPU commit. | 2016-02-12 | ||
| | | | | Change: 114585944 | |||
* | Switch the slow path in matrix_solve_ls to using ↵ | 2016-02-11 | ||
| | | | | | | | Eigen::CompleteOrthogonalDecomposition (COD), which I recently contributed to Eigen in https://bitbucket.org/eigen/eigen/pull-requests/163/implement-complete-orthogonal/diff The advantage of COD over column pivoted QR is that it is able to compute the minimum-norm solution when the matrix is rank-deficient, which is usually the desired behavior and makes it consistent with the fast path. Change: 114483303 | |||
* | TensorFlow: change int -> size_t to silence warning | 2016-02-09 | ||
| | | | | Change: 114243879 | |||
* | Replay of PR #969 for eigen3 | 2016-02-05 | ||
| | | | | Change: 113963788 | |||
* | Upgraded to the latest version of Eigen that brings misc performance and | 2016-02-04 | ||
| | | | | | stability improvements Change: 113791782 | |||
* | Backported several changes from the upstream version of Eigen | 2016-01-29 | ||
| | | | | Change: 113371678 | |||
* | Fix OSS builds. | 2016-01-26 | ||
| | | | | Change: 113114631 | |||
* | Rollback of "Add new matrix_solve_ls op for solving linear least-squares ↵ | 2016-01-26 | ||
| | | | | | | | problems." Doesn't work in OSS Change: 113103348 | |||
* | Running our linter on a lot of files. | 2016-01-24 | ||
| | | | | Change: 112920860 | |||
* | Improved the performance of tensor contractions and spatial convolutions on CPU: | 2016-01-22 | ||
| | | | | | | * Move some checks out of inner loops * Split the mapper in 2: a base mapper, and a sub-mapper. This reduces the number of variables that are contained in the base mapper and helps reduce register spills Change: 112809881 | |||
* | Upgrade to the latest version of eigen which improves the performance of | 2016-01-15 | ||
| | | | | | matrix-vector products and provides various fixes for CUDA. Change: 112298067 | |||
* | Upgraded to the latest version of Eigen, which fixes a compilation error as | 2016-01-11 | ||
| | | | | | well the crash reported in https://github.com/tensorflow/tensorflow/issues/713. Change: 111874622 | |||
* | Rollback of "Pulled the latest version of Eigen, which offers much faster ↵ | 2016-01-08 | ||
| | | | | | | reductions on GPU" Change: 111739152 | |||
* | Added 'logging' import to control_flow_ops which is used in the file but not ↵ | 2016-01-05 | ||
| | | | | | | imported. Change: 110842260 | |||
* | Change: 110415111 | 2015-12-16 | ||
| | ||||
* | Change: 110413131 | 2015-12-16 | ||
| | ||||
* | Switched to the open source version of Eigen | 2015-12-16 | ||
| | | | | Change: 110406666 |