Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | Fix calls to device functions from host code | Nathan Luehr | 2021-05-11 |
| | |||
* | Inherit alignment trait from argument in TensorBroadcasting to avoid ↵ | Rasmus Munk Larsen | 2020-07-28 |
| | | | | segfault when the argument is unaligned. | ||
* | Tensor block evaluation cost model | Eugene Zhulenev | 2019-12-18 |
| | |||
* | 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 |
| | |||
* | Cleanup Tensor block destination and materialized block storage allocation | Eugene Zhulenev | 2019-10-16 |
| | |||
* | TensorBroadcasting support for random/uniform blocks | Eugene Zhulenev | 2019-10-16 |
| | |||
* | 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 |
| | |||
* | evalSubExprsIfNeededAsync + async TensorContractionThreadPool | Eugene Zhulenev | 2019-08-30 |
| | |||
* | [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. | ||
* | Support reshaping with static shapes and dimensions conversion in tensor ↵ | Eugene Zhulenev | 2018-09-14 |
| | | | | broadcasting | ||
* | Fix compilation of tiled evaluation code with c++03 | Eugene Zhulenev | 2018-09-11 |
| | |||
* | Merge with upstream eigen/default | Eugene Zhulenev | 2018-08-27 |
|\ | |||
| * | Fix some trivial C++11 vs C++03 compatibility warnings | Christoph Hertzberg | 2018-08-25 |
| | | |||
* | | Add block evaluationto CwiseUnaryOp and add PreferBlockAccess enum to all ↵ | Eugene Zhulenev | 2018-08-10 |
| | | | | | | | | evaluators | ||
* | | Replace all using declarations with typedefs in Tensor ops | Eugene Zhulenev | 2018-08-01 |
| | | |||
* | | Fix typo + get rid of redundant member variables for block sizes | Eugene Zhulenev | 2018-08-01 |
| | | |||
* | | Merged latest changes from upstream/eigen | Eugene Zhulenev | 2018-08-01 |
|\| | |||
| * | Enabling per device specialisation of packetsize. | Mehdi Goli | 2018-08-01 |
| | | |||
* | | Add block evaluation support to TensorOps | Eugene Zhulenev | 2018-07-31 |
| | | |||
| * | Merged in ezhulenev/eigen/tiling_3 (pull request PR-438) | Gael Guennebaud | 2018-07-31 |
| |\ | |/ |/| | | | Tiled tensor executor | ||
| * | Speedup trivial tensor broadcasting on GPU by enforcing unaligned loads. See ↵ | Gael Guennebaud | 2018-07-31 |
| | | | | | | | | PR 437. | ||
* | | Rename Index to StorageIndex + use Eigen::Array and Eigen::Map when possible | Eugene Zhulenev | 2018-07-27 |
| | | |||
* | | Add tiled evaluation support to TensorExecutor | Eugene Zhulenev | 2018-07-25 |
|/ | |||
* | Get rid of alias for m_broadcast. | Rasmus Munk Larsen | 2018-07-13 |
| | |||
* | Optimize the case where broadcasting is a no-op. | Rasmus Munk Larsen | 2018-07-13 |
| | |||
* | bug #1567: add optimized path for tensor broadcasting and 'Channel First' shape | Gael Guennebaud | 2018-07-09 |
| | |||
* | Performance improvements to tensor broadcast operation | Vamsi Sripathi | 2018-05-23 |
| | | | | | | 1. Added new packet functions using SIMD for NByOne, OneByN cases 2. Modified existing packet functions to reduce index calculations when input stride is non-SIMD 3. Added 4 test cases to cover the new packet functions | ||
* | 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 | ||
* | Size indices are signed. | Benoit Steiner | 2017-02-16 |
| | |||
* | Partial OpenCL support via SYCL compatible with ComputeCpp CE. | Luke Iwanski | 2016-09-19 |
| | |||
* | Enable the use of the packet api to evaluate tensor broadcasts. This speed ↵ | Benoit Steiner | 2016-05-17 |
| | | | | | | | | | | | | | | | things up quite a bit: Before" M_broadcasting/10 500000 3690 27.10 MFlops/s BM_broadcasting/80 500000 4014 1594.24 MFlops/s BM_broadcasting/640 100000 14770 27731.35 MFlops/s BM_broadcasting/4K 5000 632711 39512.48 MFlops/s After: BM_broadcasting/10 500000 4287 23.33 MFlops/s BM_broadcasting/80 500000 4455 1436.41 MFlops/s BM_broadcasting/640 200000 10195 40173.01 MFlops/s BM_broadcasting/4K 5000 423746 58997.57 MFlops/s | ||
* | Fixed syntax error | Benoit Steiner | 2016-05-16 |
| | |||
* | Fixed compilation errors triggered by old versions of gcc | Benoit Steiner | 2016-05-12 |
| | |||
* | 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. | ||
* | 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. | ||
* | Record whether the underlying tensor storage can be accessed directly during ↵ | Benoit Steiner | 2016-01-19 |
| | | | | the evaluation of an expression. | ||
* | Fixed a typo. | Benoit Steiner | 2016-01-06 |
| | |||
* | Optimized the performance of broadcasting of scalars. | Benoit Steiner | 2016-01-06 |
| | |||
* | Simplified more of the IndexList code. | Benoit Steiner | 2015-11-12 |
| | |||
* | Added static assertions to avoid misuses of padding, broadcasting and ↵ | Benoit Steiner | 2015-11-06 |
| | | | | concatenation ops. | ||
* | Many files were missing in previous changeset. | Gael Guennebaud | 2015-07-29 |
| | |||
* | Fixed several compilation warnings reported by clang | Benoit Steiner | 2015-02-25 |
| | |||
* | Silcenced a few compilation warnings | Benoit Steiner | 2015-02-10 |
| | |||
* | Improved support for RowMajor tensors | Benoit Steiner | 2015-01-14 |
| | | | | Misc fixes and API cleanups. | ||
* | Fixed compilation errors with clang. | Benoit Steiner | 2014-11-13 |
| | | | | H: Enter commit message. Lines beginning with 'HG:' are removed. | ||
* | Optimized broadcasting | Benoit Steiner | 2014-11-12 |
| |