aboutsummaryrefslogtreecommitdiffhomepage
path: root/unsupported
Commit message (Collapse)AuthorAge
...
| | | * | Creating a pointer type in TensorCustomOp.hGravatar Mehdi Goli2018-08-08
| | |/ / | |/| |
* / | | Fix init order.Gravatar Rasmus Munk Larsen2018-08-07
|/ / /
* | | Silenced a couple of compilation warnings.Gravatar Benoit Steiner2018-08-06
| | |
* | | Fixed compilation errors.Gravatar Benoit Steiner2018-08-06
| | |
* | | Forward declare NoOpOutputKernel as struct rather than class to be ↵Gravatar Rasmus Munk Larsen2018-08-06
| | | | | | | | | | | | consistent with implementation.
| * | Move sigmoid functor to core.Gravatar Rasmus Munk Larsen2018-08-03
|/ /
* | bug #1451: fix numeric_limits<AutoDiffScalar<Der>> with a reference as ↵Gravatar Gael Guennebaud2018-08-04
| | | | | | | | derivative type
| * Replace all using declarations with typedefs in Tensor opsGravatar Eugene Zhulenev2018-08-01
| |
* | Fix initialization order.Gravatar Rasmus Munk Larsen2018-08-03
| |
* | Fixing the compilation error.Gravatar Mehdi Goli2018-08-03
| |
* | Merge with upstream.Gravatar Mehdi Goli2018-08-03
|\ \
* | | Creating separate SYCL required PR for uncontroversial files.Gravatar Mehdi Goli2018-08-03
| | |
| * | Merged in codeplaysoftware/eigen-upstream-pure/constructor_error_clang (pull ↵Gravatar Benoit Steiner2018-08-02
| |\ \ | | | | | | | | | | | | | | | | | | | | request PR-451) Fixing ambigous constructor error for Clang compiler.
| * | | fixing compilation error for cxx11_tensor_trace.cpp error on Microsoft ↵Gravatar Mehdi Goli2018-08-02
|/ / / | | | | | | | | | Visual Studio.
| * / Fixing ambigous constructor error for Clang compiler.Gravatar Mehdi Goli2018-08-02
|/ /
| * Fix typo + get rid of redundant member variables for block sizesGravatar Eugene Zhulenev2018-08-01
| |
* | Merged in paultucker/eigen (pull request PR-431)Gravatar Benoit Steiner2018-08-01
|\ \ | | | | | | | | | | | | | | | Optional ThreadPoolDevice allocator Approved-by: Benoit Steiner <benoit.steiner.goog@gmail.com>
| | * Merged latest changes from upstream/eigenGravatar Eugene Zhulenev2018-08-01
| | |\ | |_|/ |/| |
* | | Merged in codeplaysoftware/eigen-upstream-pure/eigen_variadic_assert (pull ↵Gravatar Benoit Steiner2018-08-01
|\ \ \ | | | | | | | | | | | | | | | | | | | | request PR-447) Adding variadic version of assert which can take a parameter pack as its input.
* \ \ \ Merged in ↵Gravatar Benoit Steiner2018-08-01
|\ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | codeplaysoftware/eigen-upstream-pure/separating_internal_memory_allocation (pull request PR-446) Distinguishing between internal memory allocation/deallocation from explicit user memory allocation/deallocation.
| * | | | Correcting the position of allocate_temp/deallocate_temp in TensorDeviceGpu.hGravatar Mehdi Goli2018-08-01
| | | | |
* | | | | Merged in codeplaysoftware/eigen-upstream-pure/using_PacketType_class (pull ↵Gravatar Benoit Steiner2018-08-01
|\ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | request PR-449) Enabling per device specialisation of packetSize.
| | | * | | Using the suggested modification.Gravatar Mehdi Goli2018-08-01
| | | | | |
| * | | | | Enabling per device specialisation of packetsize.Gravatar Mehdi Goli2018-08-01
| | | | | |
| | | * | | variadic version of assert which can take a parameter pack as its input.Gravatar Mehdi Goli2018-08-01
| | |/ / / | |/| | |
| | * | | Distinguishing between internal memory allocation/deallocation from explicit ↵Gravatar Mehdi Goli2018-08-01
| |/ / / | | | | | | | | | | | | user memory allocation/deallocation.
* / / / Converting ad-hoc inline keyword to EIGEN_STRONG_INLINE MACRO.Gravatar Mehdi Goli2018-08-01
|/ / /
| | * Add block evaluation support to TensorOpsGravatar Eugene Zhulenev2018-07-31
| | |
* | | Merged in yuefengz/eigen (pull request PR-370)Gravatar Benoit Steiner2018-07-31
|\ \ \ | | | | | | | | | | | | Use device's allocate function instead of internal::aligned_malloc.
| | * | Change getAllocator() to allocator() in ThreadPoolDevice.Gravatar Paul Tucker2018-07-31
| | | |
* | | | Merged in ezhulenev/eigen/tiling_3 (pull request PR-438)Gravatar Gael Guennebaud2018-07-31
|\ \ \ \ | | |_|/ | |/| | | | | | Tiled tensor executor
* | | | Speedup trivial tensor broadcasting on GPU by enforcing unaligned loads. See ↵Gravatar Gael Guennebaud2018-07-31
| | | | | | | | | | | | | | | | PR 437.
| * | | Rename Index to StorageIndex + use Eigen::Array and Eigen::Map when possibleGravatar Eugene Zhulenev2018-07-27
| | | |
| * | | Add tiled evaluation support to TensorExecutorGravatar Eugene Zhulenev2018-07-25
| | | |
* | | | Reduce the number of template specializations of classes related to tensor ↵Gravatar Rasmus Munk Larsen2018-07-27
| | | | | | | | | | | | | | | | contraction to reduce binary size.
* | | | fix warnings for doc-eigen-prerequisitesGravatar Christoph Hertzberg2018-07-24
| | | |
* | | | Removed several shadowing types and use global Index typedef everywhereGravatar Christoph Hertzberg2018-07-25
| | | |
* | | | Rename variable which shadows class nameGravatar Christoph Hertzberg2018-07-25
| | | |
* | | | Account for missing change on commit "Remove SimpleThreadPool and..."Gravatar Gustavo Lima Chaves2018-07-23
| | | | | | | | | | | | | | | | | | | | | | | | "... always use {NonBlocking}ThreadPool". It seems the non-blocking implementation was me the default/only one, but a reference to the old name was left unmodified. Fix that.
| * | | TensorBlockIOGravatar Eugene Zhulenev2018-07-23
|/ / /
* | | Initial support of TensorBlockGravatar Eugene Zhulenev2018-07-20
| | |
* | | Move cxx11_tensor_uint128 test under an EIGEN_TEST_CXX11 guardedGravatar Gustavo Lima Chaves2018-07-20
| | | | | | | | | | | | | | | | | | | | | | | | block Builds configured without the -DEIGEN_TEST_CXX11=ON flag would fail right away without this, as this test seems to rely on those language features. The skip under compilation with MSVC was kept.
| | * Add test coverage for ThreadPoolDevice optional allocator.Gravatar Paul Tucker2018-07-19
| | |
* | | PR430: Convert count to the reducer type in MeanReducerGravatar Eugene Zhulenev2018-07-19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Without explicit conversion Tensorflow fails to compile, pset1 template deduction fails. cannot convert '((const Eigen::internal::MeanReducer<Eigen::half>*)this) ->Eigen::internal::MeanReducer<Eigen::half>::packetCount_' (type 'const DenseIndex {aka const long int}') to type 'const type& {aka const Eigen::half&}' return pdiv(vaccum, pset1<Packet>(packetCount_)); Honestly I’m not sure why it works in Eigen tests, because Eigen::half constructor is explicit, and why it stopped working in TF, I didn’t find any relevant changes since previous Eigen upgrade. static_cast<T>(packetCount_) - breaks cxx11_tensor_reductions test for Eigen::half, also quite surprising.
| | * Actually add optional Allocator* arg to ThreadPoolDevice().Gravatar Paul Tucker2018-07-16
| | |
| | * Add optional Allocator argument to ThreadPoolDevice constructor.Gravatar Paul Tucker2018-07-16
| | | | | | | | | | | | | | | | | | When supplied, this allocator will be used in place of internal::aligned_malloc. This permits e.g. use of a NUMA-node specific allocator where the thread-pool is also restricted a single NUMA-node.
* | | bug #1558: fix a corner case in MINRES when both v_new and w_new vanish.Gravatar David Hyde2018-07-08
| | |
* | | Reduce number of allocations in TensorContractionThreadPool.Gravatar Eugene Zhulenev2018-07-16
| | |
* | | bug #1569: fix Tensor<half>::mean() on AVX with respective unit test.Gravatar Gael Guennebaud2018-07-19
| | |
* | | Assert that no output kernel is defined for GPU contractionGravatar Eugene Zhulenev2018-07-18
| | |
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-07 21:20:24 +0000