aboutsummaryrefslogtreecommitdiffhomepage
Commit message (Collapse)AuthorAge
* Marked unused variables as suchGravatar Benoit Steiner2016-05-25
|
* Specify the rounding mode in the correct locationGravatar Benoit Steiner2016-05-25
|
* Updated the README file for the tensor benchmarksGravatar Benoit Steiner2016-05-25
|
* Explicitly specify the rounding mode when converting floats to fp16Gravatar Benoit Steiner2016-05-25
|
* Made the IndexPair code compile in non cxx11 modeGravatar Benoit Steiner2016-05-25
|
* Made the index pair list code more portable accross various compilersGravatar Benoit Steiner2016-05-25
|
* Improved the performance of tensor paddingGravatar Benoit Steiner2016-05-25
|
* Added support for statically known lists of pairs of indicesGravatar Benoit Steiner2016-05-25
|
* Disable the use of MMX instructions on x86_64 since too many compilers only ↵Gravatar Benoit Steiner2016-05-25
| | | | support them in 32bit mode
* Use numext:: instead of std:: functions.Gravatar Benoit Steiner2016-05-25
|
* Fix typo in dont_over_optimizeGravatar Gael Guennebaud2016-05-25
|
* Fix warning.Gravatar Gael Guennebaud2016-05-25
|
* Fix compilation with ICC.Gravatar Gael Guennebaud2016-05-25
|
* Fix static/inline order.Gravatar Gael Guennebaud2016-05-25
|
* There is no need to make the fp16 full reduction kernel a static function.Gravatar Benoit Steiner2016-05-24
|
* Fixed compilation warningGravatar Benoit Steiner2016-05-24
|
* Cleaned up the fp16 code a little moreGravatar Benoit Steiner2016-05-24
|
* Pulled latest updates from trunkGravatar Benoit Steiner2016-05-24
|\
* | Cleaned up the fp16 codeGravatar Benoit Steiner2016-05-24
| |
| * update doc wrt to unaligned vectorizationGravatar Gael Guennebaud2016-05-24
| |
| * Document EIGEN_UNALIGNED_VECTORIZE.Gravatar Gael Guennebaud2016-05-24
| |
| * Workaround clang/llvm bug in code generation.Gravatar Gael Guennebaud2016-05-24
| |
| * bug #256: enable vectorization with unaligned loads/stores.Gravatar Gael Guennebaud2016-05-24
| | | | | | | | | | This concerns all architectures and all sizes. This new behavior can be disabled by defining EIGEN_UNALIGNED_VECTORIZE=0
| * Block<> should not disable vectorization based on inner-size, this is the ↵Gravatar Gael Guennebaud2016-05-24
| | | | | | | | responsibilty of the assignment logic.
| * Clean propagation of Dest/Src alignments.Gravatar Gael Guennebaud2016-05-24
|/
* Remove now-unused protate PacketMath funcGravatar Benoit Jacob2016-05-24
|
* Remove the rotating kernel. It was only useful on some ARM CPUs (Qualcomm ↵Gravatar Benoit Jacob2016-05-24
| | | | Krait) that are not as ubiquitous today as they were when I introduced it.
* Don't attempt to use MMX instructions with visualstudio since they're only ↵Gravatar Benoit Steiner2016-05-24
| | | | partially supported.
* Worked around missing clang intrinsicGravatar Benoit Steiner2016-05-24
|
* Use the generic ploadquad intrinsics since it does the jobGravatar Benoit Steiner2016-05-24
|
* Worked around missing clang intrinsicsGravatar Benoit Steiner2016-05-24
|
* Added missing EIGEN_DEVICE_FUNC qualifierGravatar Benoit Steiner2016-05-23
|
* Include mmintrin.h to make it possible to use mmx instructions when needed. ↵Gravatar Benoit Steiner2016-05-23
| | | | For example, this will enable the definition of a half packet for the Packet4f type.
* Use the Index type instead of integers to specify the strides in ↵Gravatar Benoit Steiner2016-05-23
| | | | pgather/pscatter
* Added missing alignment in the fp16 packet traitsGravatar Benoit Steiner2016-05-23
|
* ptranspose is not a template.Gravatar Benoit Steiner2016-05-23
|
* Avoid unnecessary float to double conversionsGravatar Benoit Steiner2016-05-23
|
* Avoid unnecessary float to double conversion.Gravatar Benoit Steiner2016-05-23
|
* Started to vectorize the processing of 16bit floats on CPU.Gravatar Benoit Steiner2016-05-23
|
* Don't optimize the processing of the last rows of a matrix matrix product in ↵Gravatar Benoit Steiner2016-05-23
| | | | cases that violate the assumptions made by the optimized code path.
* Fixed a typo in the array.cpp testGravatar Benoit Steiner2016-05-23
|
* Merged in rmlarsen/eigen (pull request PR-188)Gravatar Benoit Steiner2016-05-23
|\ | | | | | | Minor cleanups: 1. Get rid of a few unused variables. 2. Get rid of last uses of EIGEN_USE_COST_MODEL.
* | Replace multiple constructors of half-type by a generic/templated ↵Gravatar Christoph Hertzberg2016-05-23
| | | | | | | | constructor. This fixes an incompatibility with long double, exposed by the previous commit.
* | Silenced several double-promotion warningsGravatar Christoph Hertzberg2016-05-22
| |
* | fixed macro nameGravatar Christoph Hertzberg2016-05-22
| |
* | Fix some sign-compare warningsGravatar Christoph Hertzberg2016-05-22
| |
* | Identify clang++ even if it is not named llvm-clang++Gravatar Christoph Hertzberg2016-05-22
| |
* | Document EIGEN_MAX_CPP_VER and user controllable compiler features.Gravatar Gael Guennebaud2016-05-20
| |
* | Make EIGEN_HAS_CONSTEXPR user configurableGravatar Gael Guennebaud2016-05-20
| |
* | Make EIGEN_HAS_VARIADIC_TEMPLATES user configurableGravatar Gael Guennebaud2016-05-20
| |
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-02 04:04:36 +0000